{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "f1822fc3-a9ee-4cea-8096-6ced40479730",
   "metadata": {},
   "source": [
    "# Classification"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "58097093-edaa-43e0-9cba-8e5ffac261ca",
   "metadata": {},
   "source": [
    "<img src=\"https://www.hindustantimes.com/ht-img/img/2025/06/03/550x309/rainy_season_1748849555787_1748914696054.jpg\" width=750>"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3d4cbf3c-1fc4-45d3-9dbc-54a4ef021c03",
   "metadata": {},
   "source": [
    "### Dataset Download  \n",
    "You can download the CSV file here:  \n",
    "[https://www.kaggle.com/competitions/playground-series-s5e3/data)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "074deefc-4f22-42c1-a9da-f2cd10ebb926",
   "metadata": {},
   "source": [
    "### Introduction\n",
    "The goal of this project is to predict whether it will rain using daily weather data.\n",
    "This is a binary classification problem, and the model predicts the probability of rainfall."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "04707f5f-fbaf-40d0-84bf-eaae40761beb",
   "metadata": {},
   "source": [
    "### Import Libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 101,
   "id": "9f2245ee-bd9e-4dc8-b0fb-6b6aa2f2e67b",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import numpy as np\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.metrics import accuracy_score, confusion_matrix, classification_report\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from lightgbm import LGBMClassifier\n",
    "from catboost import CatBoostClassifier\n",
    "from xgboost import XGBClassifier\n",
    "from sklearn.naive_bayes import GaussianNB\n",
    "from sklearn.naive_bayes import BernoulliNB\n",
    "from sklearn.metrics import roc_auc_score\n",
    "from sklearn.metrics import roc_curve,auc\n",
    "import joblib\n",
    "import warnings\n",
    "warnings.filterwarnings('ignore')\n",
    "pd.set_option('display.max_columns',100)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cbb71464-c774-4b61-97e0-1fca53e0da3f",
   "metadata": {},
   "source": [
    "### Load Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "351cb1cd-65ff-473a-bce2-ca6e94ed19b1",
   "metadata": {},
   "outputs": [],
   "source": [
    "df1=pd.read_csv('train.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "adca0a24-7cd9-48d6-a57e-f1121d79fff2",
   "metadata": {},
   "outputs": [],
   "source": [
    "df2=pd.read_csv('test.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "9c0b706e-543b-439a-b2f0-49bfad02b621",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>day</th>\n",
       "      <th>pressure</th>\n",
       "      <th>maxtemp</th>\n",
       "      <th>temparature</th>\n",
       "      <th>mintemp</th>\n",
       "      <th>dewpoint</th>\n",
       "      <th>humidity</th>\n",
       "      <th>cloud</th>\n",
       "      <th>sunshine</th>\n",
       "      <th>winddirection</th>\n",
       "      <th>windspeed</th>\n",
       "      <th>rainfall</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1017.4</td>\n",
       "      <td>21.2</td>\n",
       "      <td>20.6</td>\n",
       "      <td>19.9</td>\n",
       "      <td>19.4</td>\n",
       "      <td>87.0</td>\n",
       "      <td>88.0</td>\n",
       "      <td>1.1</td>\n",
       "      <td>60.0</td>\n",
       "      <td>17.2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>1019.5</td>\n",
       "      <td>16.2</td>\n",
       "      <td>16.9</td>\n",
       "      <td>15.8</td>\n",
       "      <td>15.4</td>\n",
       "      <td>95.0</td>\n",
       "      <td>91.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>21.9</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>1024.1</td>\n",
       "      <td>19.4</td>\n",
       "      <td>16.1</td>\n",
       "      <td>14.6</td>\n",
       "      <td>9.3</td>\n",
       "      <td>75.0</td>\n",
       "      <td>47.0</td>\n",
       "      <td>8.3</td>\n",
       "      <td>70.0</td>\n",
       "      <td>18.1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>1013.4</td>\n",
       "      <td>18.1</td>\n",
       "      <td>17.8</td>\n",
       "      <td>16.9</td>\n",
       "      <td>16.8</td>\n",
       "      <td>95.0</td>\n",
       "      <td>95.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>60.0</td>\n",
       "      <td>35.6</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>1021.8</td>\n",
       "      <td>21.3</td>\n",
       "      <td>18.4</td>\n",
       "      <td>15.2</td>\n",
       "      <td>9.6</td>\n",
       "      <td>52.0</td>\n",
       "      <td>45.0</td>\n",
       "      <td>3.6</td>\n",
       "      <td>40.0</td>\n",
       "      <td>24.8</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   id  day  pressure  maxtemp  temparature  mintemp  dewpoint  humidity  \\\n",
       "0   0    1    1017.4     21.2         20.6     19.9      19.4      87.0   \n",
       "1   1    2    1019.5     16.2         16.9     15.8      15.4      95.0   \n",
       "2   2    3    1024.1     19.4         16.1     14.6       9.3      75.0   \n",
       "3   3    4    1013.4     18.1         17.8     16.9      16.8      95.0   \n",
       "4   4    5    1021.8     21.3         18.4     15.2       9.6      52.0   \n",
       "\n",
       "   cloud  sunshine  winddirection  windspeed  rainfall  \n",
       "0   88.0       1.1           60.0       17.2         1  \n",
       "1   91.0       0.0           50.0       21.9         1  \n",
       "2   47.0       8.3           70.0       18.1         1  \n",
       "3   95.0       0.0           60.0       35.6         1  \n",
       "4   45.0       3.6           40.0       24.8         0  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "7552d292-ffdb-48aa-af90-96ce3384268f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>day</th>\n",
       "      <th>pressure</th>\n",
       "      <th>maxtemp</th>\n",
       "      <th>temparature</th>\n",
       "      <th>mintemp</th>\n",
       "      <th>dewpoint</th>\n",
       "      <th>humidity</th>\n",
       "      <th>cloud</th>\n",
       "      <th>sunshine</th>\n",
       "      <th>winddirection</th>\n",
       "      <th>windspeed</th>\n",
       "      <th>rainfall</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2185</th>\n",
       "      <td>2185</td>\n",
       "      <td>361</td>\n",
       "      <td>1014.6</td>\n",
       "      <td>23.2</td>\n",
       "      <td>20.6</td>\n",
       "      <td>19.1</td>\n",
       "      <td>19.9</td>\n",
       "      <td>97.0</td>\n",
       "      <td>88.0</td>\n",
       "      <td>0.1</td>\n",
       "      <td>40.0</td>\n",
       "      <td>22.1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2186</th>\n",
       "      <td>2186</td>\n",
       "      <td>362</td>\n",
       "      <td>1012.4</td>\n",
       "      <td>17.2</td>\n",
       "      <td>17.3</td>\n",
       "      <td>16.3</td>\n",
       "      <td>15.3</td>\n",
       "      <td>91.0</td>\n",
       "      <td>88.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>35.3</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2187</th>\n",
       "      <td>2187</td>\n",
       "      <td>363</td>\n",
       "      <td>1013.3</td>\n",
       "      <td>19.0</td>\n",
       "      <td>16.3</td>\n",
       "      <td>14.3</td>\n",
       "      <td>12.6</td>\n",
       "      <td>79.0</td>\n",
       "      <td>79.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>40.0</td>\n",
       "      <td>32.9</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2188</th>\n",
       "      <td>2188</td>\n",
       "      <td>364</td>\n",
       "      <td>1022.3</td>\n",
       "      <td>16.4</td>\n",
       "      <td>15.2</td>\n",
       "      <td>13.8</td>\n",
       "      <td>14.7</td>\n",
       "      <td>92.0</td>\n",
       "      <td>93.0</td>\n",
       "      <td>0.1</td>\n",
       "      <td>40.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2189</th>\n",
       "      <td>2189</td>\n",
       "      <td>365</td>\n",
       "      <td>1013.8</td>\n",
       "      <td>21.2</td>\n",
       "      <td>19.1</td>\n",
       "      <td>18.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>89.0</td>\n",
       "      <td>88.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>70.0</td>\n",
       "      <td>48.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        id  day  pressure  maxtemp  temparature  mintemp  dewpoint  humidity  \\\n",
       "2185  2185  361    1014.6     23.2         20.6     19.1      19.9      97.0   \n",
       "2186  2186  362    1012.4     17.2         17.3     16.3      15.3      91.0   \n",
       "2187  2187  363    1013.3     19.0         16.3     14.3      12.6      79.0   \n",
       "2188  2188  364    1022.3     16.4         15.2     13.8      14.7      92.0   \n",
       "2189  2189  365    1013.8     21.2         19.1     18.0      18.0      89.0   \n",
       "\n",
       "      cloud  sunshine  winddirection  windspeed  rainfall  \n",
       "2185   88.0       0.1           40.0       22.1         1  \n",
       "2186   88.0       0.0           50.0       35.3         1  \n",
       "2187   79.0       5.0           40.0       32.9         1  \n",
       "2188   93.0       0.1           40.0       18.0         1  \n",
       "2189   88.0       1.0           70.0       48.0         1  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "d2d023ba-8019-4a91-83b1-d140d6e32d67",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>day</th>\n",
       "      <th>pressure</th>\n",
       "      <th>maxtemp</th>\n",
       "      <th>temparature</th>\n",
       "      <th>mintemp</th>\n",
       "      <th>dewpoint</th>\n",
       "      <th>humidity</th>\n",
       "      <th>cloud</th>\n",
       "      <th>sunshine</th>\n",
       "      <th>winddirection</th>\n",
       "      <th>windspeed</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2190</td>\n",
       "      <td>1</td>\n",
       "      <td>1019.5</td>\n",
       "      <td>17.5</td>\n",
       "      <td>15.8</td>\n",
       "      <td>12.7</td>\n",
       "      <td>14.9</td>\n",
       "      <td>96.0</td>\n",
       "      <td>99.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>24.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2191</td>\n",
       "      <td>2</td>\n",
       "      <td>1016.5</td>\n",
       "      <td>17.5</td>\n",
       "      <td>16.5</td>\n",
       "      <td>15.8</td>\n",
       "      <td>15.1</td>\n",
       "      <td>97.0</td>\n",
       "      <td>99.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>35.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2192</td>\n",
       "      <td>3</td>\n",
       "      <td>1023.9</td>\n",
       "      <td>11.2</td>\n",
       "      <td>10.4</td>\n",
       "      <td>9.4</td>\n",
       "      <td>8.9</td>\n",
       "      <td>86.0</td>\n",
       "      <td>96.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>40.0</td>\n",
       "      <td>16.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2193</td>\n",
       "      <td>4</td>\n",
       "      <td>1022.9</td>\n",
       "      <td>20.6</td>\n",
       "      <td>17.3</td>\n",
       "      <td>15.2</td>\n",
       "      <td>9.5</td>\n",
       "      <td>75.0</td>\n",
       "      <td>45.0</td>\n",
       "      <td>7.1</td>\n",
       "      <td>20.0</td>\n",
       "      <td>50.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2194</td>\n",
       "      <td>5</td>\n",
       "      <td>1022.2</td>\n",
       "      <td>16.1</td>\n",
       "      <td>13.8</td>\n",
       "      <td>6.4</td>\n",
       "      <td>4.3</td>\n",
       "      <td>68.0</td>\n",
       "      <td>49.0</td>\n",
       "      <td>9.2</td>\n",
       "      <td>20.0</td>\n",
       "      <td>19.4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     id  day  pressure  maxtemp  temparature  mintemp  dewpoint  humidity  \\\n",
       "0  2190    1    1019.5     17.5         15.8     12.7      14.9      96.0   \n",
       "1  2191    2    1016.5     17.5         16.5     15.8      15.1      97.0   \n",
       "2  2192    3    1023.9     11.2         10.4      9.4       8.9      86.0   \n",
       "3  2193    4    1022.9     20.6         17.3     15.2       9.5      75.0   \n",
       "4  2194    5    1022.2     16.1         13.8      6.4       4.3      68.0   \n",
       "\n",
       "   cloud  sunshine  winddirection  windspeed  \n",
       "0   99.0       0.0           50.0       24.3  \n",
       "1   99.0       0.0           50.0       35.3  \n",
       "2   96.0       0.0           40.0       16.9  \n",
       "3   45.0       7.1           20.0       50.6  \n",
       "4   49.0       9.2           20.0       19.4  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df2.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "73169afb-21e3-4767-9925-0cb4f9598c66",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>day</th>\n",
       "      <th>pressure</th>\n",
       "      <th>maxtemp</th>\n",
       "      <th>temparature</th>\n",
       "      <th>mintemp</th>\n",
       "      <th>dewpoint</th>\n",
       "      <th>humidity</th>\n",
       "      <th>cloud</th>\n",
       "      <th>sunshine</th>\n",
       "      <th>winddirection</th>\n",
       "      <th>windspeed</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>725</th>\n",
       "      <td>2915</td>\n",
       "      <td>361</td>\n",
       "      <td>1020.8</td>\n",
       "      <td>18.2</td>\n",
       "      <td>17.6</td>\n",
       "      <td>16.1</td>\n",
       "      <td>13.7</td>\n",
       "      <td>96.0</td>\n",
       "      <td>95.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>20.0</td>\n",
       "      <td>34.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>726</th>\n",
       "      <td>2916</td>\n",
       "      <td>362</td>\n",
       "      <td>1011.7</td>\n",
       "      <td>23.2</td>\n",
       "      <td>18.1</td>\n",
       "      <td>16.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>78.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>1.6</td>\n",
       "      <td>40.0</td>\n",
       "      <td>25.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>727</th>\n",
       "      <td>2917</td>\n",
       "      <td>363</td>\n",
       "      <td>1022.7</td>\n",
       "      <td>21.0</td>\n",
       "      <td>18.5</td>\n",
       "      <td>17.0</td>\n",
       "      <td>15.5</td>\n",
       "      <td>92.0</td>\n",
       "      <td>96.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>21.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>728</th>\n",
       "      <td>2918</td>\n",
       "      <td>364</td>\n",
       "      <td>1014.4</td>\n",
       "      <td>21.0</td>\n",
       "      <td>20.0</td>\n",
       "      <td>19.7</td>\n",
       "      <td>19.8</td>\n",
       "      <td>94.0</td>\n",
       "      <td>93.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>39.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>729</th>\n",
       "      <td>2919</td>\n",
       "      <td>365</td>\n",
       "      <td>1020.9</td>\n",
       "      <td>22.2</td>\n",
       "      <td>18.8</td>\n",
       "      <td>17.0</td>\n",
       "      <td>13.3</td>\n",
       "      <td>79.0</td>\n",
       "      <td>89.0</td>\n",
       "      <td>0.2</td>\n",
       "      <td>60.0</td>\n",
       "      <td>50.6</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       id  day  pressure  maxtemp  temparature  mintemp  dewpoint  humidity  \\\n",
       "725  2915  361    1020.8     18.2         17.6     16.1      13.7      96.0   \n",
       "726  2916  362    1011.7     23.2         18.1     16.0      16.0      78.0   \n",
       "727  2917  363    1022.7     21.0         18.5     17.0      15.5      92.0   \n",
       "728  2918  364    1014.4     21.0         20.0     19.7      19.8      94.0   \n",
       "729  2919  365    1020.9     22.2         18.8     17.0      13.3      79.0   \n",
       "\n",
       "     cloud  sunshine  winddirection  windspeed  \n",
       "725   95.0       0.0           20.0       34.3  \n",
       "726   80.0       1.6           40.0       25.2  \n",
       "727   96.0       0.0           50.0       21.9  \n",
       "728   93.0       0.0           50.0       39.5  \n",
       "729   89.0       0.2           60.0       50.6  "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df2.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "c958d2fd-b39a-4a81-91db-d01d84435794",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(2190, 13)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "0f33a15d-b47c-448b-9db5-689cf03a7b88",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(730, 12)"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df2.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "2dd14ac2-2357-4011-b55e-565a85fb5f44",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 2190 entries, 0 to 2189\n",
      "Data columns (total 13 columns):\n",
      " #   Column         Non-Null Count  Dtype  \n",
      "---  ------         --------------  -----  \n",
      " 0   id             2190 non-null   int64  \n",
      " 1   day            2190 non-null   int64  \n",
      " 2   pressure       2190 non-null   float64\n",
      " 3   maxtemp        2190 non-null   float64\n",
      " 4   temparature    2190 non-null   float64\n",
      " 5   mintemp        2190 non-null   float64\n",
      " 6   dewpoint       2190 non-null   float64\n",
      " 7   humidity       2190 non-null   float64\n",
      " 8   cloud          2190 non-null   float64\n",
      " 9   sunshine       2190 non-null   float64\n",
      " 10  winddirection  2190 non-null   float64\n",
      " 11  windspeed      2190 non-null   float64\n",
      " 12  rainfall       2190 non-null   int64  \n",
      "dtypes: float64(10), int64(3)\n",
      "memory usage: 222.6 KB\n"
     ]
    }
   ],
   "source": [
    "df1.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "23fbf628-be15-45ab-9df4-ff5b94d34107",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 730 entries, 0 to 729\n",
      "Data columns (total 12 columns):\n",
      " #   Column         Non-Null Count  Dtype  \n",
      "---  ------         --------------  -----  \n",
      " 0   id             730 non-null    int64  \n",
      " 1   day            730 non-null    int64  \n",
      " 2   pressure       730 non-null    float64\n",
      " 3   maxtemp        730 non-null    float64\n",
      " 4   temparature    730 non-null    float64\n",
      " 5   mintemp        730 non-null    float64\n",
      " 6   dewpoint       730 non-null    float64\n",
      " 7   humidity       730 non-null    float64\n",
      " 8   cloud          730 non-null    float64\n",
      " 9   sunshine       730 non-null    float64\n",
      " 10  winddirection  729 non-null    float64\n",
      " 11  windspeed      730 non-null    float64\n",
      "dtypes: float64(10), int64(2)\n",
      "memory usage: 68.6 KB\n"
     ]
    }
   ],
   "source": [
    "df2.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "fa1e3ec5-b8d8-4056-ae6b-ff8db9a393e4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "id               0\n",
       "day              0\n",
       "pressure         0\n",
       "maxtemp          0\n",
       "temparature      0\n",
       "mintemp          0\n",
       "dewpoint         0\n",
       "humidity         0\n",
       "cloud            0\n",
       "sunshine         0\n",
       "winddirection    0\n",
       "windspeed        0\n",
       "rainfall         0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "46c8a0be-c098-418a-907e-704ad0fffa0a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "id               0\n",
       "day              0\n",
       "pressure         0\n",
       "maxtemp          0\n",
       "temparature      0\n",
       "mintemp          0\n",
       "dewpoint         0\n",
       "humidity         0\n",
       "cloud            0\n",
       "sunshine         0\n",
       "winddirection    1\n",
       "windspeed        0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df2.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "54557dd2-7a9c-42e7-b356-327300cf2224",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x800 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(12,8))\n",
    "sns.heatmap(df1.corr(numeric_only=True)[['rainfall']].sort_values('rainfall', ascending=False),annot=True, cmap='coolwarm')\n",
    "plt.title('Correlation with rainfall')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "9c4ef0a1-7703-4910-aae9-9dee6edae488",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.kdeplot(data=df1,x='humidity',hue='rainfall',fill=True,common_norm=False);"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a6bcff29-a9c8-4a57-b34d-411d868e59c1",
   "metadata": {},
   "source": [
    "The KDE plot shows that rainy days are associated with clearly higher humidity values, with a noticeable right-shift of the distribution compared to non-rainy days, indicating strong predictive potential."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "73927b25-b1dc-4eba-aa47-c2a7eed8b914",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "rainfall\n",
       "1    0.753425\n",
       "0    0.246575\n",
       "Name: proportion, dtype: float64"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1['rainfall'].value_counts(normalize=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "006dfece-bb09-45d2-b011-79c09412e2d5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 500x400 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(5,4))\n",
    "sns.countplot(x='rainfall', data=df1)\n",
    "plt.title('Target Distribution')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "88e1692a-a276-402c-905a-97acb9025db2",
   "metadata": {},
   "source": [
    "The target variable is imbalanced, with approximately 75% rainy days and 25% non-rainy days, making ROC-AUC an appropriate evaluation metric."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "26cc4f58-25d2-4c72-acaa-69a9e57e8427",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>id</th>\n",
       "      <td>2190.0</td>\n",
       "      <td>1094.500000</td>\n",
       "      <td>632.342866</td>\n",
       "      <td>0.0</td>\n",
       "      <td>547.250</td>\n",
       "      <td>1094.50</td>\n",
       "      <td>1641.750</td>\n",
       "      <td>2189.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>day</th>\n",
       "      <td>2190.0</td>\n",
       "      <td>179.948402</td>\n",
       "      <td>105.203592</td>\n",
       "      <td>1.0</td>\n",
       "      <td>89.000</td>\n",
       "      <td>178.50</td>\n",
       "      <td>270.000</td>\n",
       "      <td>365.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>pressure</th>\n",
       "      <td>2190.0</td>\n",
       "      <td>1013.602146</td>\n",
       "      <td>5.655366</td>\n",
       "      <td>999.0</td>\n",
       "      <td>1008.600</td>\n",
       "      <td>1013.00</td>\n",
       "      <td>1017.775</td>\n",
       "      <td>1034.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>maxtemp</th>\n",
       "      <td>2190.0</td>\n",
       "      <td>26.365799</td>\n",
       "      <td>5.654330</td>\n",
       "      <td>10.4</td>\n",
       "      <td>21.300</td>\n",
       "      <td>27.80</td>\n",
       "      <td>31.200</td>\n",
       "      <td>36.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>temparature</th>\n",
       "      <td>2190.0</td>\n",
       "      <td>23.953059</td>\n",
       "      <td>5.222410</td>\n",
       "      <td>7.4</td>\n",
       "      <td>19.300</td>\n",
       "      <td>25.50</td>\n",
       "      <td>28.400</td>\n",
       "      <td>31.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mintemp</th>\n",
       "      <td>2190.0</td>\n",
       "      <td>22.170091</td>\n",
       "      <td>5.059120</td>\n",
       "      <td>4.0</td>\n",
       "      <td>17.700</td>\n",
       "      <td>23.85</td>\n",
       "      <td>26.400</td>\n",
       "      <td>29.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>dewpoint</th>\n",
       "      <td>2190.0</td>\n",
       "      <td>20.454566</td>\n",
       "      <td>5.288406</td>\n",
       "      <td>-0.3</td>\n",
       "      <td>16.800</td>\n",
       "      <td>22.15</td>\n",
       "      <td>25.000</td>\n",
       "      <td>26.7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>humidity</th>\n",
       "      <td>2190.0</td>\n",
       "      <td>82.036530</td>\n",
       "      <td>7.800654</td>\n",
       "      <td>39.0</td>\n",
       "      <td>77.000</td>\n",
       "      <td>82.00</td>\n",
       "      <td>88.000</td>\n",
       "      <td>98.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>cloud</th>\n",
       "      <td>2190.0</td>\n",
       "      <td>75.721918</td>\n",
       "      <td>18.026498</td>\n",
       "      <td>2.0</td>\n",
       "      <td>69.000</td>\n",
       "      <td>83.00</td>\n",
       "      <td>88.000</td>\n",
       "      <td>100.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>sunshine</th>\n",
       "      <td>2190.0</td>\n",
       "      <td>3.744429</td>\n",
       "      <td>3.626327</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.400</td>\n",
       "      <td>2.40</td>\n",
       "      <td>6.800</td>\n",
       "      <td>12.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>winddirection</th>\n",
       "      <td>2190.0</td>\n",
       "      <td>104.863151</td>\n",
       "      <td>80.002416</td>\n",
       "      <td>10.0</td>\n",
       "      <td>40.000</td>\n",
       "      <td>70.00</td>\n",
       "      <td>200.000</td>\n",
       "      <td>300.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>windspeed</th>\n",
       "      <td>2190.0</td>\n",
       "      <td>21.804703</td>\n",
       "      <td>9.898659</td>\n",
       "      <td>4.4</td>\n",
       "      <td>14.125</td>\n",
       "      <td>20.50</td>\n",
       "      <td>27.900</td>\n",
       "      <td>59.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>rainfall</th>\n",
       "      <td>2190.0</td>\n",
       "      <td>0.753425</td>\n",
       "      <td>0.431116</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.000</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.000</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                count         mean         std    min       25%      50%  \\\n",
       "id             2190.0  1094.500000  632.342866    0.0   547.250  1094.50   \n",
       "day            2190.0   179.948402  105.203592    1.0    89.000   178.50   \n",
       "pressure       2190.0  1013.602146    5.655366  999.0  1008.600  1013.00   \n",
       "maxtemp        2190.0    26.365799    5.654330   10.4    21.300    27.80   \n",
       "temparature    2190.0    23.953059    5.222410    7.4    19.300    25.50   \n",
       "mintemp        2190.0    22.170091    5.059120    4.0    17.700    23.85   \n",
       "dewpoint       2190.0    20.454566    5.288406   -0.3    16.800    22.15   \n",
       "humidity       2190.0    82.036530    7.800654   39.0    77.000    82.00   \n",
       "cloud          2190.0    75.721918   18.026498    2.0    69.000    83.00   \n",
       "sunshine       2190.0     3.744429    3.626327    0.0     0.400     2.40   \n",
       "winddirection  2190.0   104.863151   80.002416   10.0    40.000    70.00   \n",
       "windspeed      2190.0    21.804703    9.898659    4.4    14.125    20.50   \n",
       "rainfall       2190.0     0.753425    0.431116    0.0     1.000     1.00   \n",
       "\n",
       "                    75%     max  \n",
       "id             1641.750  2189.0  \n",
       "day             270.000   365.0  \n",
       "pressure       1017.775  1034.6  \n",
       "maxtemp          31.200    36.0  \n",
       "temparature      28.400    31.5  \n",
       "mintemp          26.400    29.8  \n",
       "dewpoint         25.000    26.7  \n",
       "humidity         88.000    98.0  \n",
       "cloud            88.000   100.0  \n",
       "sunshine          6.800    12.1  \n",
       "winddirection   200.000   300.0  \n",
       "windspeed        27.900    59.5  \n",
       "rainfall          1.000     1.0  "
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1.describe().T"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "81347dea-1eef-4142-bf4c-297f8eee6a76",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.boxplot(data=df1,x='rainfall',y='humidity')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "caa73444-5f46-4025-acae-2c89175d5025",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>id</th>\n",
       "      <td>730.0</td>\n",
       "      <td>2554.500000</td>\n",
       "      <td>210.877136</td>\n",
       "      <td>2190.0</td>\n",
       "      <td>2372.250</td>\n",
       "      <td>2554.50</td>\n",
       "      <td>2736.750</td>\n",
       "      <td>2919.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>day</th>\n",
       "      <td>730.0</td>\n",
       "      <td>183.000000</td>\n",
       "      <td>105.438271</td>\n",
       "      <td>1.0</td>\n",
       "      <td>92.000</td>\n",
       "      <td>183.00</td>\n",
       "      <td>274.000</td>\n",
       "      <td>365.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>pressure</th>\n",
       "      <td>730.0</td>\n",
       "      <td>1013.503014</td>\n",
       "      <td>5.505871</td>\n",
       "      <td>1000.0</td>\n",
       "      <td>1008.725</td>\n",
       "      <td>1012.70</td>\n",
       "      <td>1017.600</td>\n",
       "      <td>1032.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>maxtemp</th>\n",
       "      <td>730.0</td>\n",
       "      <td>26.372466</td>\n",
       "      <td>5.672521</td>\n",
       "      <td>7.4</td>\n",
       "      <td>21.600</td>\n",
       "      <td>27.80</td>\n",
       "      <td>31.000</td>\n",
       "      <td>35.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>temparature</th>\n",
       "      <td>730.0</td>\n",
       "      <td>23.963288</td>\n",
       "      <td>5.278098</td>\n",
       "      <td>5.9</td>\n",
       "      <td>19.825</td>\n",
       "      <td>25.65</td>\n",
       "      <td>28.375</td>\n",
       "      <td>31.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mintemp</th>\n",
       "      <td>730.0</td>\n",
       "      <td>22.110274</td>\n",
       "      <td>5.170744</td>\n",
       "      <td>4.2</td>\n",
       "      <td>17.825</td>\n",
       "      <td>23.90</td>\n",
       "      <td>26.400</td>\n",
       "      <td>29.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>dewpoint</th>\n",
       "      <td>730.0</td>\n",
       "      <td>20.460137</td>\n",
       "      <td>5.391169</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>16.800</td>\n",
       "      <td>22.30</td>\n",
       "      <td>25.000</td>\n",
       "      <td>26.7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>humidity</th>\n",
       "      <td>730.0</td>\n",
       "      <td>82.669863</td>\n",
       "      <td>7.818714</td>\n",
       "      <td>39.0</td>\n",
       "      <td>77.250</td>\n",
       "      <td>82.00</td>\n",
       "      <td>89.000</td>\n",
       "      <td>98.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>cloud</th>\n",
       "      <td>730.0</td>\n",
       "      <td>76.360274</td>\n",
       "      <td>17.934121</td>\n",
       "      <td>0.0</td>\n",
       "      <td>69.000</td>\n",
       "      <td>83.00</td>\n",
       "      <td>88.000</td>\n",
       "      <td>100.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>sunshine</th>\n",
       "      <td>730.0</td>\n",
       "      <td>3.664384</td>\n",
       "      <td>3.639272</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.325</td>\n",
       "      <td>2.20</td>\n",
       "      <td>6.675</td>\n",
       "      <td>11.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>winddirection</th>\n",
       "      <td>729.0</td>\n",
       "      <td>103.923182</td>\n",
       "      <td>81.695458</td>\n",
       "      <td>10.0</td>\n",
       "      <td>40.000</td>\n",
       "      <td>70.00</td>\n",
       "      <td>200.000</td>\n",
       "      <td>300.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>windspeed</th>\n",
       "      <td>730.0</td>\n",
       "      <td>22.484247</td>\n",
       "      <td>9.954779</td>\n",
       "      <td>4.5</td>\n",
       "      <td>14.500</td>\n",
       "      <td>21.30</td>\n",
       "      <td>28.400</td>\n",
       "      <td>59.5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               count         mean         std     min       25%      50%  \\\n",
       "id             730.0  2554.500000  210.877136  2190.0  2372.250  2554.50   \n",
       "day            730.0   183.000000  105.438271     1.0    92.000   183.00   \n",
       "pressure       730.0  1013.503014    5.505871  1000.0  1008.725  1012.70   \n",
       "maxtemp        730.0    26.372466    5.672521     7.4    21.600    27.80   \n",
       "temparature    730.0    23.963288    5.278098     5.9    19.825    25.65   \n",
       "mintemp        730.0    22.110274    5.170744     4.2    17.825    23.90   \n",
       "dewpoint       730.0    20.460137    5.391169    -0.0    16.800    22.30   \n",
       "humidity       730.0    82.669863    7.818714    39.0    77.250    82.00   \n",
       "cloud          730.0    76.360274   17.934121     0.0    69.000    83.00   \n",
       "sunshine       730.0     3.664384    3.639272     0.0     0.325     2.20   \n",
       "winddirection  729.0   103.923182   81.695458    10.0    40.000    70.00   \n",
       "windspeed      730.0    22.484247    9.954779     4.5    14.500    21.30   \n",
       "\n",
       "                    75%     max  \n",
       "id             2736.750  2919.0  \n",
       "day             274.000   365.0  \n",
       "pressure       1017.600  1032.2  \n",
       "maxtemp          31.000    35.8  \n",
       "temparature      28.375    31.8  \n",
       "mintemp          26.400    29.1  \n",
       "dewpoint         25.000    26.7  \n",
       "humidity         89.000    98.0  \n",
       "cloud            88.000   100.0  \n",
       "sunshine          6.675    11.8  \n",
       "winddirection   200.000   300.0  \n",
       "windspeed        28.400    59.5  "
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df2.describe().T"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0519fa14-897b-4e88-b089-1c9313e678db",
   "metadata": {},
   "source": [
    "### Feature Engineering"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "992bf85e-47f4-42bb-a046-6b96d24b66d0",
   "metadata": {},
   "outputs": [],
   "source": [
    "median=df1['winddirection'].median()\n",
    "df2['winddirection']=df2['winddirection'].fillna(median)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "0da1fcaf-1d6e-43fa-a229-e34eebbb6ea4",
   "metadata": {},
   "outputs": [],
   "source": [
    "def add_features(df):\n",
    "\n",
    "    # Temperature variability\n",
    "    df['temp_range']=df['maxtemp'] - df['mintemp']\n",
    "    # Air saturation level\n",
    "    df['humidity_gap'] = df['humidity'] - df['dewpoint']\n",
    "    # Sunshine vs. Cloud\n",
    "    df['sunshine_ratio']=df['sunshine'] / (df['cloud'] + 1)\n",
    "    # Wind intensity\n",
    "    df['wind_energy']=df['windspeed'] * df['winddirection']\n",
    "    # Saisonale Features\n",
    "    df['sin_day']=np.sin(2 * np.pi * df['day'] / 365)\n",
    "    df['cos_day']=np.cos(2 * np.pi * df['day'] / 365)\n",
    "\n",
    "    return df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "e5991e8f-3114-4b39-8c25-725d971365e0",
   "metadata": {},
   "outputs": [],
   "source": [
    "df1=add_features(df1)\n",
    "df2=add_features(df2)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "010ac0c4-4571-4b5b-bb2d-4c4bfbdadf5c",
   "metadata": {},
   "source": [
    "### Modelling"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "aeb1a3ad-ae09-411d-84d8-1e700c276498",
   "metadata": {},
   "outputs": [],
   "source": [
    "x=df1.drop(['rainfall','id'],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "e84b71a3-9081-438c-afd4-6ff58b267d1a",
   "metadata": {},
   "outputs": [],
   "source": [
    "y=df1[['rainfall']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "bb924891-7388-4009-a66c-d7fc6064280e",
   "metadata": {},
   "outputs": [],
   "source": [
    "x_train,x_val, y_train, y_val=train_test_split(x,y, test_size=.20, random_state=42, stratify=y)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c2b3dbc2-2a54-426c-91f6-23b713313cfd",
   "metadata": {},
   "source": [
    "### 1th LogisticRegression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "163ed19c-2526-480b-b089-04d67a93563f",
   "metadata": {},
   "outputs": [],
   "source": [
    "lr=LogisticRegression(max_iter=1000,class_weight='balanced',n_jobs=-1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "7d0e78e1-8a96-4cff-8a5d-78d862e7723a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-1 {\n",
       "  /* Definition of color scheme common for light and dark mode */\n",
       "  --sklearn-color-text: #000;\n",
       "  --sklearn-color-text-muted: #666;\n",
       "  --sklearn-color-line: gray;\n",
       "  /* Definition of color scheme for unfitted estimators */\n",
       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
       "  --sklearn-color-unfitted-level-3: chocolate;\n",
       "  /* Definition of color scheme for fitted estimators */\n",
       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
       "\n",
       "  /* Specific color for light theme */\n",
       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-icon: #696969;\n",
       "\n",
       "  @media (prefers-color-scheme: dark) {\n",
       "    /* Redefinition of color scheme for dark theme */\n",
       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-icon: #878787;\n",
       "  }\n",
       "}\n",
       "\n",
       "#sk-container-id-1 {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 pre {\n",
       "  padding: 0;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 input.sk-hidden--visually {\n",
       "  border: 0;\n",
       "  clip: rect(1px 1px 1px 1px);\n",
       "  clip: rect(1px, 1px, 1px, 1px);\n",
       "  height: 1px;\n",
       "  margin: -1px;\n",
       "  overflow: hidden;\n",
       "  padding: 0;\n",
       "  position: absolute;\n",
       "  width: 1px;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-dashed-wrapped {\n",
       "  border: 1px dashed var(--sklearn-color-line);\n",
       "  margin: 0 0.4em 0.5em 0.4em;\n",
       "  box-sizing: border-box;\n",
       "  padding-bottom: 0.4em;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-container {\n",
       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
       "     so we also need the `!important` here to be able to override the\n",
       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
       "  display: inline-block !important;\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-text-repr-fallback {\n",
       "  display: none;\n",
       "}\n",
       "\n",
       "div.sk-parallel-item,\n",
       "div.sk-serial,\n",
       "div.sk-item {\n",
       "  /* draw centered vertical line to link estimators */\n",
       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
       "  background-size: 2px 100%;\n",
       "  background-repeat: no-repeat;\n",
       "  background-position: center center;\n",
       "}\n",
       "\n",
       "/* Parallel-specific style estimator block */\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item::after {\n",
       "  content: \"\";\n",
       "  width: 100%;\n",
       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
       "  flex-grow: 1;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel {\n",
       "  display: flex;\n",
       "  align-items: stretch;\n",
       "  justify-content: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
       "  align-self: flex-end;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
       "  align-self: flex-start;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
       "  width: 0;\n",
       "}\n",
       "\n",
       "/* Serial-specific style estimator block */\n",
       "\n",
       "#sk-container-id-1 div.sk-serial {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "  align-items: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  padding-right: 1em;\n",
       "  padding-left: 1em;\n",
       "}\n",
       "\n",
       "\n",
       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
       "clickable and can be expanded/collapsed.\n",
       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
       "*/\n",
       "\n",
       "/* Pipeline and ColumnTransformer style (default) */\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable {\n",
       "  /* Default theme specific background. It is overwritten whether we have a\n",
       "  specific estimator or a Pipeline/ColumnTransformer */\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "/* Toggleable label */\n",
       "#sk-container-id-1 label.sk-toggleable__label {\n",
       "  cursor: pointer;\n",
       "  display: flex;\n",
       "  width: 100%;\n",
       "  margin-bottom: 0;\n",
       "  padding: 0.5em;\n",
       "  box-sizing: border-box;\n",
       "  text-align: center;\n",
       "  align-items: start;\n",
       "  justify-content: space-between;\n",
       "  gap: 0.5em;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 label.sk-toggleable__label .caption {\n",
       "  font-size: 0.6rem;\n",
       "  font-weight: lighter;\n",
       "  color: var(--sklearn-color-text-muted);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
       "  /* Arrow on the left of the label */\n",
       "  content: \"▸\";\n",
       "  float: left;\n",
       "  margin-right: 0.25em;\n",
       "  color: var(--sklearn-color-icon);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "/* Toggleable content - dropdown */\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable__content {\n",
       "  display: none;\n",
       "  text-align: left;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable__content pre {\n",
       "  margin: 0.2em;\n",
       "  border-radius: 0.25em;\n",
       "  color: var(--sklearn-color-text);\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
       "  /* Expand drop-down */\n",
       "  display: block;\n",
       "  width: 100%;\n",
       "  overflow: visible;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
       "  content: \"▾\";\n",
       "}\n",
       "\n",
       "/* Pipeline/ColumnTransformer-specific style */\n",
       "\n",
       "#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator-specific style */\n",
       "\n",
       "/* Colorize estimator box */\n",
       "#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
       "#sk-container-id-1 div.sk-label label {\n",
       "  /* The background is the default theme color */\n",
       "  color: var(--sklearn-color-text-on-default-background);\n",
       "}\n",
       "\n",
       "/* On hover, darken the color of the background */\n",
       "#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "/* Label box, darken color on hover, fitted */\n",
       "#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator label */\n",
       "\n",
       "#sk-container-id-1 div.sk-label label {\n",
       "  font-family: monospace;\n",
       "  font-weight: bold;\n",
       "  display: inline-block;\n",
       "  line-height: 1.2em;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-label-container {\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "/* Estimator-specific */\n",
       "#sk-container-id-1 div.sk-estimator {\n",
       "  font-family: monospace;\n",
       "  border: 1px dotted var(--sklearn-color-border-box);\n",
       "  border-radius: 0.25em;\n",
       "  box-sizing: border-box;\n",
       "  margin-bottom: 0.5em;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-estimator.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "/* on hover */\n",
       "#sk-container-id-1 div.sk-estimator:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
       "\n",
       "/* Common style for \"i\" and \"?\" */\n",
       "\n",
       ".sk-estimator-doc-link,\n",
       "a:link.sk-estimator-doc-link,\n",
       "a:visited.sk-estimator-doc-link {\n",
       "  float: right;\n",
       "  font-size: smaller;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1em;\n",
       "  height: 1em;\n",
       "  width: 1em;\n",
       "  text-decoration: none !important;\n",
       "  margin-left: 0.5em;\n",
       "  text-align: center;\n",
       "  /* unfitted */\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted,\n",
       "a:link.sk-estimator-doc-link.fitted,\n",
       "a:visited.sk-estimator-doc-link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "/* Span, style for the box shown on hovering the info icon */\n",
       ".sk-estimator-doc-link span {\n",
       "  display: none;\n",
       "  z-index: 9999;\n",
       "  position: relative;\n",
       "  font-weight: normal;\n",
       "  right: .2ex;\n",
       "  padding: .5ex;\n",
       "  margin: .5ex;\n",
       "  width: min-content;\n",
       "  min-width: 20ex;\n",
       "  max-width: 50ex;\n",
       "  color: var(--sklearn-color-text);\n",
       "  box-shadow: 2pt 2pt 4pt #999;\n",
       "  /* unfitted */\n",
       "  background: var(--sklearn-color-unfitted-level-0);\n",
       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted span {\n",
       "  /* fitted */\n",
       "  background: var(--sklearn-color-fitted-level-0);\n",
       "  border: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link:hover span {\n",
       "  display: block;\n",
       "}\n",
       "\n",
       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
       "\n",
       "#sk-container-id-1 a.estimator_doc_link {\n",
       "  float: right;\n",
       "  font-size: 1rem;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1rem;\n",
       "  height: 1rem;\n",
       "  width: 1rem;\n",
       "  text-decoration: none;\n",
       "  /* unfitted */\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 a.estimator_doc_link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "#sk-container-id-1 a.estimator_doc_link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "\n",
       ".estimator-table summary {\n",
       "    padding: .5rem;\n",
       "    font-family: monospace;\n",
       "    cursor: pointer;\n",
       "}\n",
       "\n",
       ".estimator-table details[open] {\n",
       "    padding-left: 0.1rem;\n",
       "    padding-right: 0.1rem;\n",
       "    padding-bottom: 0.3rem;\n",
       "}\n",
       "\n",
       ".estimator-table .parameters-table {\n",
       "    margin-left: auto !important;\n",
       "    margin-right: auto !important;\n",
       "}\n",
       "\n",
       ".estimator-table .parameters-table tr:nth-child(odd) {\n",
       "    background-color: #fff;\n",
       "}\n",
       "\n",
       ".estimator-table .parameters-table tr:nth-child(even) {\n",
       "    background-color: #f6f6f6;\n",
       "}\n",
       "\n",
       ".estimator-table .parameters-table tr:hover {\n",
       "    background-color: #e0e0e0;\n",
       "}\n",
       "\n",
       ".estimator-table table td {\n",
       "    border: 1px solid rgba(106, 105, 104, 0.232);\n",
       "}\n",
       "\n",
       ".user-set td {\n",
       "    color:rgb(255, 94, 0);\n",
       "    text-align: left;\n",
       "}\n",
       "\n",
       ".user-set td.value pre {\n",
       "    color:rgb(255, 94, 0) !important;\n",
       "    background-color: transparent !important;\n",
       "}\n",
       "\n",
       ".default td {\n",
       "    color: black;\n",
       "    text-align: left;\n",
       "}\n",
       "\n",
       ".user-set td i,\n",
       ".default td i {\n",
       "    color: black;\n",
       "}\n",
       "\n",
       ".copy-paste-icon {\n",
       "    background-image: url(data:image/svg+xml;base64,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);\n",
       "    background-repeat: no-repeat;\n",
       "    background-size: 14px 14px;\n",
       "    background-position: 0;\n",
       "    display: inline-block;\n",
       "    width: 14px;\n",
       "    height: 14px;\n",
       "    cursor: pointer;\n",
       "}\n",
       "</style><body><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LogisticRegression(class_weight=&#x27;balanced&#x27;, max_iter=1000, n_jobs=-1)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>LogisticRegression</div></div><div><a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.7/modules/generated/sklearn.linear_model.LogisticRegression.html\">?<span>Documentation for LogisticRegression</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></div></label><div class=\"sk-toggleable__content fitted\" data-param-prefix=\"\">\n",
       "        <div class=\"estimator-table\">\n",
       "            <details>\n",
       "                <summary>Parameters</summary>\n",
       "                <table class=\"parameters-table\">\n",
       "                  <tbody>\n",
       "                    \n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('penalty',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">penalty&nbsp;</td>\n",
       "            <td class=\"value\">&#x27;l2&#x27;</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('dual',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">dual&nbsp;</td>\n",
       "            <td class=\"value\">False</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('tol',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">tol&nbsp;</td>\n",
       "            <td class=\"value\">0.0001</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('C',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">C&nbsp;</td>\n",
       "            <td class=\"value\">1.0</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('fit_intercept',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">fit_intercept&nbsp;</td>\n",
       "            <td class=\"value\">True</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('intercept_scaling',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">intercept_scaling&nbsp;</td>\n",
       "            <td class=\"value\">1</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('class_weight',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">class_weight&nbsp;</td>\n",
       "            <td class=\"value\">&#x27;balanced&#x27;</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('random_state',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">random_state&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('solver',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">solver&nbsp;</td>\n",
       "            <td class=\"value\">&#x27;lbfgs&#x27;</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('max_iter',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">max_iter&nbsp;</td>\n",
       "            <td class=\"value\">1000</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('multi_class',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">multi_class&nbsp;</td>\n",
       "            <td class=\"value\">&#x27;deprecated&#x27;</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('verbose',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">verbose&nbsp;</td>\n",
       "            <td class=\"value\">0</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('warm_start',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">warm_start&nbsp;</td>\n",
       "            <td class=\"value\">False</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('n_jobs',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">n_jobs&nbsp;</td>\n",
       "            <td class=\"value\">-1</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('l1_ratio',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">l1_ratio&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "                  </tbody>\n",
       "                </table>\n",
       "            </details>\n",
       "        </div>\n",
       "    </div></div></div></div></div><script>function copyToClipboard(text, element) {\n",
       "    // Get the parameter prefix from the closest toggleable content\n",
       "    const toggleableContent = element.closest('.sk-toggleable__content');\n",
       "    const paramPrefix = toggleableContent ? toggleableContent.dataset.paramPrefix : '';\n",
       "    const fullParamName = paramPrefix ? `${paramPrefix}${text}` : text;\n",
       "\n",
       "    const originalStyle = element.style;\n",
       "    const computedStyle = window.getComputedStyle(element);\n",
       "    const originalWidth = computedStyle.width;\n",
       "    const originalHTML = element.innerHTML.replace('Copied!', '');\n",
       "\n",
       "    navigator.clipboard.writeText(fullParamName)\n",
       "        .then(() => {\n",
       "            element.style.width = originalWidth;\n",
       "            element.style.color = 'green';\n",
       "            element.innerHTML = \"Copied!\";\n",
       "\n",
       "            setTimeout(() => {\n",
       "                element.innerHTML = originalHTML;\n",
       "                element.style = originalStyle;\n",
       "            }, 2000);\n",
       "        })\n",
       "        .catch(err => {\n",
       "            console.error('Failed to copy:', err);\n",
       "            element.style.color = 'red';\n",
       "            element.innerHTML = \"Failed!\";\n",
       "            setTimeout(() => {\n",
       "                element.innerHTML = originalHTML;\n",
       "                element.style = originalStyle;\n",
       "            }, 2000);\n",
       "        });\n",
       "    return false;\n",
       "}\n",
       "\n",
       "document.querySelectorAll('.fa-regular.fa-copy').forEach(function(element) {\n",
       "    const toggleableContent = element.closest('.sk-toggleable__content');\n",
       "    const paramPrefix = toggleableContent ? toggleableContent.dataset.paramPrefix : '';\n",
       "    const paramName = element.parentElement.nextElementSibling.textContent.trim();\n",
       "    const fullParamName = paramPrefix ? `${paramPrefix}${paramName}` : paramName;\n",
       "\n",
       "    element.setAttribute('title', fullParamName);\n",
       "});\n",
       "</script></body>"
      ],
      "text/plain": [
       "LogisticRegression(class_weight='balanced', max_iter=1000, n_jobs=-1)"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lr.fit(x_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "fbb53f48-2a20-4b1e-8d36-3d1137d06947",
   "metadata": {},
   "outputs": [],
   "source": [
    "lrtahmin=lr.predict(x_val)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "2f365622-e02d-4842-8a33-3798bc3cd028",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_val_proba=lr.predict_proba(x_val)[:, 1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "d02db6f4-8f05-41f4-8065-a78f7de30432",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "ROC AUC: 0.8804\n"
     ]
    }
   ],
   "source": [
    "roc_auc=roc_auc_score(y_val, y_val_proba)\n",
    "print(f\"ROC AUC: {roc_auc:.4f}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "864c7b94-e7cf-455f-b5aa-557a5a20a646",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.8425\n"
     ]
    }
   ],
   "source": [
    "acc=accuracy_score(y_val, lrtahmin)\n",
    "print(f\"Accuracy: {acc:.4f}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "fa6a703b-a982-4246-b7ae-13e9e91cf922",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 81,  27],\n",
       "       [ 42, 288]])"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "confusion_matrix(y_val, lrtahmin)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "65cf7610-858b-4176-bace-88a435b82a67",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Classification Report:\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.66      0.75      0.70       108\n",
      "           1       0.91      0.87      0.89       330\n",
      "\n",
      "    accuracy                           0.84       438\n",
      "   macro avg       0.79      0.81      0.80       438\n",
      "weighted avg       0.85      0.84      0.85       438\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(\"\\nClassification Report:\")\n",
    "print(classification_report(y_val, lrtahmin))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "05bba194-cad2-48c5-b4e8-8d13e400efad",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 600x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fpr, tpr, thresholds=roc_curve(y_val, y_val_proba)\n",
    "roc_auc=auc(fpr, tpr)\n",
    "\n",
    "plt.figure(figsize=(6,5))\n",
    "plt.plot(fpr, tpr, label=f'Logistic Regression (AUC = {roc_auc:.3f})')\n",
    "plt.plot([0, 1], [0, 1], 'k--', label='Random Classifier')\n",
    "\n",
    "plt.xlabel('False Positive Rate')\n",
    "plt.ylabel('True Positive Rate')\n",
    "plt.title('ROC Curve')\n",
    "plt.legend(loc='lower right')\n",
    "plt.grid(alpha=0.3)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "27f8acd4-038d-4744-8a5c-b7f7522d9abb",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "cm=confusion_matrix(y_val, lrtahmin).astype(int)\n",
    "\n",
    "sns.heatmap(cm, annot=True, fmt='d')\n",
    "plt.show();"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "7ca4a2df-8974-4ad8-a014-57ad0e1e091e",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.ensemble import AdaBoostClassifier\n",
    "from sklearn.ensemble import GradientBoostingClassifier\n",
    "from sklearn.naive_bayes import MultinomialNB\n",
    "from sklearn.naive_bayes import BernoulliNB\n",
    "\n",
    "from sklearn.metrics import accuracy_score, precision_score, recall_score\n",
    "from sklearn.metrics import f1_score, confusion_matrix, classification_report\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "b = BernoulliNB()\n",
    "l = LogisticRegression()\n",
    "d = DecisionTreeClassifier()\n",
    "r = RandomForestClassifier()\n",
    "gb= GradientBoostingClassifier()\n",
    "kn= KNeighborsClassifier()\n",
    "ab= AdaBoostClassifier()\n",
    "\n",
    "def algo_test(x, y):\n",
    "    modeller=[ b, l, d, r, gb, kn, ab]\n",
    "    isimler=[\"BernoulliNB\", \"LogisticRegression\", \"DecisionTreeClassifier\", \n",
    "             \"RandomForestClassifier\", \"GradientBoostingClassifier\", \"KNeighborsClassifier\",\n",
    "             \"AdaBoostClassifier\"]\n",
    "\n",
    "    x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=.3, random_state = 42)\n",
    "    \n",
    "    accuracy = []\n",
    "    precision = []\n",
    "    recall = []\n",
    "    f1 = []\n",
    "    mdl=[]\n",
    "\n",
    "    print(\"Veriler hazır modeller deneniyor\")\n",
    "    for model in modeller:\n",
    "        print(model, \" modeli eğitiliyor!..\")\n",
    "        model=model.fit(x_train,y_train)\n",
    "        tahmin=model.predict(x_test)\n",
    "        mdl.append(model)\n",
    "        accuracy.append(accuracy_score(y_test, tahmin))\n",
    "        precision.append(precision_score(y_test, tahmin, average=\"micro\"))\n",
    "        recall.append(recall_score(y_test, tahmin, average=\"micro\"))\n",
    "        f1.append(f1_score(y_test, tahmin, average=\"micro\"))\n",
    "        print(confusion_matrix(y_test, tahmin))\n",
    "\n",
    "    print(\"Eğitim tamamlandı.\")\n",
    "    \n",
    "    metrics=pd.DataFrame(columns=[\"Accuracy\", \"Precision\", \"Recall\", \"F1\", \"Model\"], index=isimler)\n",
    "    metrics[\"Accuracy\"] = accuracy\n",
    "    metrics[\"Precision\"] = precision  \n",
    "    metrics[\"Recall\"] = recall\n",
    "    metrics[\"F1\"] = f1\n",
    "    metrics[\"Model\"]=mdl\n",
    "\n",
    "    metrics.sort_values(\"F1\", ascending=False, inplace=True)\n",
    "\n",
    "    print(\"En başarılı model: \", metrics.iloc[0].name)\n",
    "    model=metrics.iloc[0,-1]\n",
    "    tahmin=model.predict(np.array(x_test) if model==kn else x_test)\n",
    "    print(\"Confusion Matrix:\")\n",
    "    print(confusion_matrix(y_test, tahmin))\n",
    "    print(\"classification Report:\")\n",
    "    print(classification_report(y_test, tahmin))\n",
    "    print(\"Diğer Modeller:\")\n",
    "    \n",
    "    return metrics.drop(\"Model\", axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "55a49924-6776-4c8b-878f-0551171be667",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Veriler hazır modeller deneniyor\n",
      "BernoulliNB()  modeli eğitiliyor!..\n",
      "[[  0 167]\n",
      " [  0 490]]\n",
      "LogisticRegression()  modeli eğitiliyor!..\n",
      "[[105  62]\n",
      " [ 30 460]]\n",
      "DecisionTreeClassifier()  modeli eğitiliyor!..\n",
      "[[ 94  73]\n",
      " [ 56 434]]\n",
      "RandomForestClassifier()  modeli eğitiliyor!..\n",
      "[[102  65]\n",
      " [ 36 454]]\n",
      "GradientBoostingClassifier()  modeli eğitiliyor!..\n",
      "[[ 98  69]\n",
      " [ 33 457]]\n",
      "KNeighborsClassifier()  modeli eğitiliyor!..\n",
      "[[ 51 116]\n",
      " [ 30 460]]\n",
      "AdaBoostClassifier()  modeli eğitiliyor!..\n",
      "[[111  56]\n",
      " [ 46 444]]\n",
      "Eğitim tamamlandı.\n",
      "En başarılı model:  LogisticRegression\n",
      "Confusion Matrix:\n",
      "[[105  62]\n",
      " [ 30 460]]\n",
      "classification Report:\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.78      0.63      0.70       167\n",
      "           1       0.88      0.94      0.91       490\n",
      "\n",
      "    accuracy                           0.86       657\n",
      "   macro avg       0.83      0.78      0.80       657\n",
      "weighted avg       0.85      0.86      0.85       657\n",
      "\n",
      "Diğer Modeller:\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Accuracy</th>\n",
       "      <th>Precision</th>\n",
       "      <th>Recall</th>\n",
       "      <th>F1</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>LogisticRegression</th>\n",
       "      <td>0.859970</td>\n",
       "      <td>0.859970</td>\n",
       "      <td>0.859970</td>\n",
       "      <td>0.859970</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>RandomForestClassifier</th>\n",
       "      <td>0.846271</td>\n",
       "      <td>0.846271</td>\n",
       "      <td>0.846271</td>\n",
       "      <td>0.846271</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>GradientBoostingClassifier</th>\n",
       "      <td>0.844749</td>\n",
       "      <td>0.844749</td>\n",
       "      <td>0.844749</td>\n",
       "      <td>0.844749</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>AdaBoostClassifier</th>\n",
       "      <td>0.844749</td>\n",
       "      <td>0.844749</td>\n",
       "      <td>0.844749</td>\n",
       "      <td>0.844749</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>DecisionTreeClassifier</th>\n",
       "      <td>0.803653</td>\n",
       "      <td>0.803653</td>\n",
       "      <td>0.803653</td>\n",
       "      <td>0.803653</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>KNeighborsClassifier</th>\n",
       "      <td>0.777778</td>\n",
       "      <td>0.777778</td>\n",
       "      <td>0.777778</td>\n",
       "      <td>0.777778</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>BernoulliNB</th>\n",
       "      <td>0.745814</td>\n",
       "      <td>0.745814</td>\n",
       "      <td>0.745814</td>\n",
       "      <td>0.745814</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                            Accuracy  Precision    Recall        F1\n",
       "LogisticRegression          0.859970   0.859970  0.859970  0.859970\n",
       "RandomForestClassifier      0.846271   0.846271  0.846271  0.846271\n",
       "GradientBoostingClassifier  0.844749   0.844749  0.844749  0.844749\n",
       "AdaBoostClassifier          0.844749   0.844749  0.844749  0.844749\n",
       "DecisionTreeClassifier      0.803653   0.803653  0.803653  0.803653\n",
       "KNeighborsClassifier        0.777778   0.777778  0.777778  0.777778\n",
       "BernoulliNB                 0.745814   0.745814  0.745814  0.745814"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "algo_test(x,y)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b48abc85-0a88-4398-8bfa-7245324ca082",
   "metadata": {},
   "source": [
    "### 2th XGBClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "id": "da821a02-f3ab-4698-9106-7b2762e88eb4",
   "metadata": {},
   "outputs": [],
   "source": [
    "xg=XGBClassifier(\n",
    "    n_estimators=2000,\n",
    "    learning_rate=0.03,\n",
    "    max_depth=4,\n",
    "    min_child_weight=5,\n",
    "    subsample=0.8,\n",
    "    colsample_bytree=0.8,\n",
    "    reg_alpha=0.0,\n",
    "    reg_lambda=1.0,\n",
    "    gamma=0.0,\n",
    "    objective='binary:logistic',\n",
    "    eval_metric='auc',\n",
    "    tree_method='hist',\n",
    "    random_state=42,\n",
    "    n_jobs=-1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "id": "9e1c16c9-dd3b-4465-8b81-b22d9125ebdd",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-3 {\n",
       "  /* Definition of color scheme common for light and dark mode */\n",
       "  --sklearn-color-text: #000;\n",
       "  --sklearn-color-text-muted: #666;\n",
       "  --sklearn-color-line: gray;\n",
       "  /* Definition of color scheme for unfitted estimators */\n",
       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
       "  --sklearn-color-unfitted-level-3: chocolate;\n",
       "  /* Definition of color scheme for fitted estimators */\n",
       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
       "\n",
       "  /* Specific color for light theme */\n",
       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-icon: #696969;\n",
       "\n",
       "  @media (prefers-color-scheme: dark) {\n",
       "    /* Redefinition of color scheme for dark theme */\n",
       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-icon: #878787;\n",
       "  }\n",
       "}\n",
       "\n",
       "#sk-container-id-3 {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 pre {\n",
       "  padding: 0;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 input.sk-hidden--visually {\n",
       "  border: 0;\n",
       "  clip: rect(1px 1px 1px 1px);\n",
       "  clip: rect(1px, 1px, 1px, 1px);\n",
       "  height: 1px;\n",
       "  margin: -1px;\n",
       "  overflow: hidden;\n",
       "  padding: 0;\n",
       "  position: absolute;\n",
       "  width: 1px;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-dashed-wrapped {\n",
       "  border: 1px dashed var(--sklearn-color-line);\n",
       "  margin: 0 0.4em 0.5em 0.4em;\n",
       "  box-sizing: border-box;\n",
       "  padding-bottom: 0.4em;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-container {\n",
       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
       "     so we also need the `!important` here to be able to override the\n",
       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
       "  display: inline-block !important;\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-text-repr-fallback {\n",
       "  display: none;\n",
       "}\n",
       "\n",
       "div.sk-parallel-item,\n",
       "div.sk-serial,\n",
       "div.sk-item {\n",
       "  /* draw centered vertical line to link estimators */\n",
       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
       "  background-size: 2px 100%;\n",
       "  background-repeat: no-repeat;\n",
       "  background-position: center center;\n",
       "}\n",
       "\n",
       "/* Parallel-specific style estimator block */\n",
       "\n",
       "#sk-container-id-3 div.sk-parallel-item::after {\n",
       "  content: \"\";\n",
       "  width: 100%;\n",
       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
       "  flex-grow: 1;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-parallel {\n",
       "  display: flex;\n",
       "  align-items: stretch;\n",
       "  justify-content: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-parallel-item {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-parallel-item:first-child::after {\n",
       "  align-self: flex-end;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-parallel-item:last-child::after {\n",
       "  align-self: flex-start;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-parallel-item:only-child::after {\n",
       "  width: 0;\n",
       "}\n",
       "\n",
       "/* Serial-specific style estimator block */\n",
       "\n",
       "#sk-container-id-3 div.sk-serial {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "  align-items: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  padding-right: 1em;\n",
       "  padding-left: 1em;\n",
       "}\n",
       "\n",
       "\n",
       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
       "clickable and can be expanded/collapsed.\n",
       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
       "*/\n",
       "\n",
       "/* Pipeline and ColumnTransformer style (default) */\n",
       "\n",
       "#sk-container-id-3 div.sk-toggleable {\n",
       "  /* Default theme specific background. It is overwritten whether we have a\n",
       "  specific estimator or a Pipeline/ColumnTransformer */\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "/* Toggleable label */\n",
       "#sk-container-id-3 label.sk-toggleable__label {\n",
       "  cursor: pointer;\n",
       "  display: flex;\n",
       "  width: 100%;\n",
       "  margin-bottom: 0;\n",
       "  padding: 0.5em;\n",
       "  box-sizing: border-box;\n",
       "  text-align: center;\n",
       "  align-items: start;\n",
       "  justify-content: space-between;\n",
       "  gap: 0.5em;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 label.sk-toggleable__label .caption {\n",
       "  font-size: 0.6rem;\n",
       "  font-weight: lighter;\n",
       "  color: var(--sklearn-color-text-muted);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 label.sk-toggleable__label-arrow:before {\n",
       "  /* Arrow on the left of the label */\n",
       "  content: \"▸\";\n",
       "  float: left;\n",
       "  margin-right: 0.25em;\n",
       "  color: var(--sklearn-color-icon);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 label.sk-toggleable__label-arrow:hover:before {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "/* Toggleable content - dropdown */\n",
       "\n",
       "#sk-container-id-3 div.sk-toggleable__content {\n",
       "  display: none;\n",
       "  text-align: left;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-toggleable__content.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-toggleable__content pre {\n",
       "  margin: 0.2em;\n",
       "  border-radius: 0.25em;\n",
       "  color: var(--sklearn-color-text);\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-toggleable__content.fitted pre {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
       "  /* Expand drop-down */\n",
       "  display: block;\n",
       "  width: 100%;\n",
       "  overflow: visible;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
       "  content: \"▾\";\n",
       "}\n",
       "\n",
       "/* Pipeline/ColumnTransformer-specific style */\n",
       "\n",
       "#sk-container-id-3 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator-specific style */\n",
       "\n",
       "/* Colorize estimator box */\n",
       "#sk-container-id-3 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-label label.sk-toggleable__label,\n",
       "#sk-container-id-3 div.sk-label label {\n",
       "  /* The background is the default theme color */\n",
       "  color: var(--sklearn-color-text-on-default-background);\n",
       "}\n",
       "\n",
       "/* On hover, darken the color of the background */\n",
       "#sk-container-id-3 div.sk-label:hover label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "/* Label box, darken color on hover, fitted */\n",
       "#sk-container-id-3 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator label */\n",
       "\n",
       "#sk-container-id-3 div.sk-label label {\n",
       "  font-family: monospace;\n",
       "  font-weight: bold;\n",
       "  display: inline-block;\n",
       "  line-height: 1.2em;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-label-container {\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "/* Estimator-specific */\n",
       "#sk-container-id-3 div.sk-estimator {\n",
       "  font-family: monospace;\n",
       "  border: 1px dotted var(--sklearn-color-border-box);\n",
       "  border-radius: 0.25em;\n",
       "  box-sizing: border-box;\n",
       "  margin-bottom: 0.5em;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-estimator.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "/* on hover */\n",
       "#sk-container-id-3 div.sk-estimator:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-estimator.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
       "\n",
       "/* Common style for \"i\" and \"?\" */\n",
       "\n",
       ".sk-estimator-doc-link,\n",
       "a:link.sk-estimator-doc-link,\n",
       "a:visited.sk-estimator-doc-link {\n",
       "  float: right;\n",
       "  font-size: smaller;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1em;\n",
       "  height: 1em;\n",
       "  width: 1em;\n",
       "  text-decoration: none !important;\n",
       "  margin-left: 0.5em;\n",
       "  text-align: center;\n",
       "  /* unfitted */\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted,\n",
       "a:link.sk-estimator-doc-link.fitted,\n",
       "a:visited.sk-estimator-doc-link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "/* Span, style for the box shown on hovering the info icon */\n",
       ".sk-estimator-doc-link span {\n",
       "  display: none;\n",
       "  z-index: 9999;\n",
       "  position: relative;\n",
       "  font-weight: normal;\n",
       "  right: .2ex;\n",
       "  padding: .5ex;\n",
       "  margin: .5ex;\n",
       "  width: min-content;\n",
       "  min-width: 20ex;\n",
       "  max-width: 50ex;\n",
       "  color: var(--sklearn-color-text);\n",
       "  box-shadow: 2pt 2pt 4pt #999;\n",
       "  /* unfitted */\n",
       "  background: var(--sklearn-color-unfitted-level-0);\n",
       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted span {\n",
       "  /* fitted */\n",
       "  background: var(--sklearn-color-fitted-level-0);\n",
       "  border: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link:hover span {\n",
       "  display: block;\n",
       "}\n",
       "\n",
       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
       "\n",
       "#sk-container-id-3 a.estimator_doc_link {\n",
       "  float: right;\n",
       "  font-size: 1rem;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1rem;\n",
       "  height: 1rem;\n",
       "  width: 1rem;\n",
       "  text-decoration: none;\n",
       "  /* unfitted */\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 a.estimator_doc_link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "#sk-container-id-3 a.estimator_doc_link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 a.estimator_doc_link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "\n",
       ".estimator-table summary {\n",
       "    padding: .5rem;\n",
       "    font-family: monospace;\n",
       "    cursor: pointer;\n",
       "}\n",
       "\n",
       ".estimator-table details[open] {\n",
       "    padding-left: 0.1rem;\n",
       "    padding-right: 0.1rem;\n",
       "    padding-bottom: 0.3rem;\n",
       "}\n",
       "\n",
       ".estimator-table .parameters-table {\n",
       "    margin-left: auto !important;\n",
       "    margin-right: auto !important;\n",
       "}\n",
       "\n",
       ".estimator-table .parameters-table tr:nth-child(odd) {\n",
       "    background-color: #fff;\n",
       "}\n",
       "\n",
       ".estimator-table .parameters-table tr:nth-child(even) {\n",
       "    background-color: #f6f6f6;\n",
       "}\n",
       "\n",
       ".estimator-table .parameters-table tr:hover {\n",
       "    background-color: #e0e0e0;\n",
       "}\n",
       "\n",
       ".estimator-table table td {\n",
       "    border: 1px solid rgba(106, 105, 104, 0.232);\n",
       "}\n",
       "\n",
       ".user-set td {\n",
       "    color:rgb(255, 94, 0);\n",
       "    text-align: left;\n",
       "}\n",
       "\n",
       ".user-set td.value pre {\n",
       "    color:rgb(255, 94, 0) !important;\n",
       "    background-color: transparent !important;\n",
       "}\n",
       "\n",
       ".default td {\n",
       "    color: black;\n",
       "    text-align: left;\n",
       "}\n",
       "\n",
       ".user-set td i,\n",
       ".default td i {\n",
       "    color: black;\n",
       "}\n",
       "\n",
       ".copy-paste-icon {\n",
       "    background-image: url(data:image/svg+xml;base64,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);\n",
       "    background-repeat: no-repeat;\n",
       "    background-size: 14px 14px;\n",
       "    background-position: 0;\n",
       "    display: inline-block;\n",
       "    width: 14px;\n",
       "    height: 14px;\n",
       "    cursor: pointer;\n",
       "}\n",
       "</style><body><div id=\"sk-container-id-3\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
       "              colsample_bylevel=None, colsample_bynode=None,\n",
       "              colsample_bytree=0.8, device=None, early_stopping_rounds=None,\n",
       "              enable_categorical=False, eval_metric=&#x27;auc&#x27;, feature_types=None,\n",
       "              feature_weights=None, gamma=0.0, grow_policy=None,\n",
       "              importance_type=None, interaction_constraints=None,\n",
       "              learning_rate=0.03, max_bin=None, max_cat_threshold=None,\n",
       "              max_cat_to_onehot=None, max_delta_step=None, max_depth=4,\n",
       "              max_leaves=None, min_child_weight=5, missing=nan,\n",
       "              monotone_constraints=None, multi_strategy=None, n_estimators=2000,\n",
       "              n_jobs=-1, num_parallel_tree=None, ...)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" checked><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>XGBClassifier</div></div><div><a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://xgboost.readthedocs.io/en/release_3.1.0/python/python_api.html#xgboost.XGBClassifier\">?<span>Documentation for XGBClassifier</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></div></label><div class=\"sk-toggleable__content fitted\" data-param-prefix=\"\">\n",
       "        <div class=\"estimator-table\">\n",
       "            <details>\n",
       "                <summary>Parameters</summary>\n",
       "                <table class=\"parameters-table\">\n",
       "                  <tbody>\n",
       "                    \n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('objective',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">objective&nbsp;</td>\n",
       "            <td class=\"value\">&#x27;binary:logistic&#x27;</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('base_score',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">base_score&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('booster',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">booster&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('callbacks',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">callbacks&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('colsample_bylevel',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">colsample_bylevel&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('colsample_bynode',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">colsample_bynode&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('colsample_bytree',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">colsample_bytree&nbsp;</td>\n",
       "            <td class=\"value\">0.8</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('device',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">device&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('early_stopping_rounds',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">early_stopping_rounds&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('enable_categorical',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">enable_categorical&nbsp;</td>\n",
       "            <td class=\"value\">False</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('eval_metric',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">eval_metric&nbsp;</td>\n",
       "            <td class=\"value\">&#x27;auc&#x27;</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('feature_types',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">feature_types&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('feature_weights',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">feature_weights&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('gamma',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">gamma&nbsp;</td>\n",
       "            <td class=\"value\">0.0</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('grow_policy',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">grow_policy&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('importance_type',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">importance_type&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('interaction_constraints',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">interaction_constraints&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('learning_rate',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">learning_rate&nbsp;</td>\n",
       "            <td class=\"value\">0.03</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('max_bin',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">max_bin&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('max_cat_threshold',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">max_cat_threshold&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('max_cat_to_onehot',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">max_cat_to_onehot&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('max_delta_step',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">max_delta_step&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('max_depth',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">max_depth&nbsp;</td>\n",
       "            <td class=\"value\">4</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('max_leaves',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">max_leaves&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('min_child_weight',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">min_child_weight&nbsp;</td>\n",
       "            <td class=\"value\">5</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('missing',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">missing&nbsp;</td>\n",
       "            <td class=\"value\">nan</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('monotone_constraints',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">monotone_constraints&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('multi_strategy',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">multi_strategy&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('n_estimators',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">n_estimators&nbsp;</td>\n",
       "            <td class=\"value\">2000</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('n_jobs',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">n_jobs&nbsp;</td>\n",
       "            <td class=\"value\">-1</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('num_parallel_tree',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">num_parallel_tree&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('random_state',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">random_state&nbsp;</td>\n",
       "            <td class=\"value\">42</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('reg_alpha',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">reg_alpha&nbsp;</td>\n",
       "            <td class=\"value\">0.0</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('reg_lambda',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">reg_lambda&nbsp;</td>\n",
       "            <td class=\"value\">1.0</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('sampling_method',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">sampling_method&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('scale_pos_weight',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">scale_pos_weight&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('subsample',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">subsample&nbsp;</td>\n",
       "            <td class=\"value\">0.8</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('tree_method',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">tree_method&nbsp;</td>\n",
       "            <td class=\"value\">&#x27;hist&#x27;</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('validate_parameters',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">validate_parameters&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('verbosity',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">verbosity&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "                  </tbody>\n",
       "                </table>\n",
       "            </details>\n",
       "        </div>\n",
       "    </div></div></div></div></div><script>function copyToClipboard(text, element) {\n",
       "    // Get the parameter prefix from the closest toggleable content\n",
       "    const toggleableContent = element.closest('.sk-toggleable__content');\n",
       "    const paramPrefix = toggleableContent ? toggleableContent.dataset.paramPrefix : '';\n",
       "    const fullParamName = paramPrefix ? `${paramPrefix}${text}` : text;\n",
       "\n",
       "    const originalStyle = element.style;\n",
       "    const computedStyle = window.getComputedStyle(element);\n",
       "    const originalWidth = computedStyle.width;\n",
       "    const originalHTML = element.innerHTML.replace('Copied!', '');\n",
       "\n",
       "    navigator.clipboard.writeText(fullParamName)\n",
       "        .then(() => {\n",
       "            element.style.width = originalWidth;\n",
       "            element.style.color = 'green';\n",
       "            element.innerHTML = \"Copied!\";\n",
       "\n",
       "            setTimeout(() => {\n",
       "                element.innerHTML = originalHTML;\n",
       "                element.style = originalStyle;\n",
       "            }, 2000);\n",
       "        })\n",
       "        .catch(err => {\n",
       "            console.error('Failed to copy:', err);\n",
       "            element.style.color = 'red';\n",
       "            element.innerHTML = \"Failed!\";\n",
       "            setTimeout(() => {\n",
       "                element.innerHTML = originalHTML;\n",
       "                element.style = originalStyle;\n",
       "            }, 2000);\n",
       "        });\n",
       "    return false;\n",
       "}\n",
       "\n",
       "document.querySelectorAll('.fa-regular.fa-copy').forEach(function(element) {\n",
       "    const toggleableContent = element.closest('.sk-toggleable__content');\n",
       "    const paramPrefix = toggleableContent ? toggleableContent.dataset.paramPrefix : '';\n",
       "    const paramName = element.parentElement.nextElementSibling.textContent.trim();\n",
       "    const fullParamName = paramPrefix ? `${paramPrefix}${paramName}` : paramName;\n",
       "\n",
       "    element.setAttribute('title', fullParamName);\n",
       "});\n",
       "</script></body>"
      ],
      "text/plain": [
       "XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
       "              colsample_bylevel=None, colsample_bynode=None,\n",
       "              colsample_bytree=0.8, device=None, early_stopping_rounds=None,\n",
       "              enable_categorical=False, eval_metric='auc', feature_types=None,\n",
       "              feature_weights=None, gamma=0.0, grow_policy=None,\n",
       "              importance_type=None, interaction_constraints=None,\n",
       "              learning_rate=0.03, max_bin=None, max_cat_threshold=None,\n",
       "              max_cat_to_onehot=None, max_delta_step=None, max_depth=4,\n",
       "              max_leaves=None, min_child_weight=5, missing=nan,\n",
       "              monotone_constraints=None, multi_strategy=None, n_estimators=2000,\n",
       "              n_jobs=-1, num_parallel_tree=None, ...)"
      ]
     },
     "execution_count": 60,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "xg.fit(x_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "id": "650fbb69-2f4d-4db9-8b14-63bb9bc69699",
   "metadata": {},
   "outputs": [],
   "source": [
    "xgtahmin=xg.predict(x_val)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "id": "a43ecfc2-121e-4ff6-a994-6c2a4c69b937",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_proba_xg=xg.predict_proba(x_val)[:, 1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "id": "cc3addd2-d923-4ba3-bfe7-3d2dfa9b7c60",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "ROC AUC: 0.8516\n"
     ]
    }
   ],
   "source": [
    "roc_auc=roc_auc_score(y_val, y_proba_xg)\n",
    "print(f\"ROC AUC: {roc_auc:.4f}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "id": "5ec53cd7-59f0-46f1-9505-09696959cc21",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.8447\n"
     ]
    }
   ],
   "source": [
    "acc=accuracy_score(y_val, xgtahmin)\n",
    "print(f\"Accuracy: {acc:.4f}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "id": "83b835e6-a07a-40ac-9fe0-9560ab76977b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 68,  40],\n",
       "       [ 28, 302]])"
      ]
     },
     "execution_count": 65,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "confusion_matrix(y_val, xgtahmin)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "id": "d4fcfa0e-d954-42f7-9c75-5c78c51003d3",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Classification Report:\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.71      0.63      0.67       108\n",
      "           1       0.88      0.92      0.90       330\n",
      "\n",
      "    accuracy                           0.84       438\n",
      "   macro avg       0.80      0.77      0.78       438\n",
      "weighted avg       0.84      0.84      0.84       438\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(\"\\nClassification Report:\")\n",
    "print(classification_report(y_val, xgtahmin))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "id": "0d7e9cad-31fa-4a8b-934c-7316b79f2309",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 600x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fpr, tpr, thresholds=roc_curve(y_val, y_proba_xg)\n",
    "roc_auc=auc(fpr, tpr)\n",
    "\n",
    "plt.figure(figsize=(6,5))\n",
    "plt.plot(fpr, tpr, label=f'Logistic Regression (AUC = {roc_auc:.3f})')\n",
    "plt.plot([0, 1], [0, 1], 'k--', label='Random Classifier')\n",
    "\n",
    "plt.xlabel('False Positive Rate')\n",
    "plt.ylabel('True Positive Rate')\n",
    "plt.title('ROC Curve')\n",
    "plt.legend(loc='lower right')\n",
    "plt.grid(alpha=0.3)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a27b8c65-0324-4ca5-bae6-703cf7de84ee",
   "metadata": {},
   "source": [
    "### 3th CatBoostClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "id": "2a0326f3-8553-4aad-9223-aa5af132e9a2",
   "metadata": {},
   "outputs": [],
   "source": [
    "cb=CatBoostClassifier(iterations=5000,\n",
    "    learning_rate=0.03,\n",
    "    depth=6,\n",
    "    l2_leaf_reg=3.0,\n",
    "    loss_function='Logloss',\n",
    "    eval_metric='AUC',\n",
    "    random_seed=42,\n",
    "    verbose=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "id": "6d1fa588-92b0-4aed-900a-7e0b9f5be5ed",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<catboost.core.CatBoostClassifier at 0x26010c5ba10>"
      ]
     },
     "execution_count": 70,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cb.fit(x_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "id": "7c21ab0f-cbcf-4098-9be2-26903e438ac3",
   "metadata": {},
   "outputs": [],
   "source": [
    "cbtahmin=cb.predict(x_val)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "id": "ffce99fe-beec-485b-a135-669d1d2904ee",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_proba_cb=cb.predict_proba(x_val)[:, 1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "id": "e7632ffc-123c-4359-ae7f-61c8f0d2f323",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "ROC AUC: 0.8616\n"
     ]
    }
   ],
   "source": [
    "roc_auc=roc_auc_score(y_val, y_proba_cb)\n",
    "print(f\"ROC AUC: {roc_auc:.4f}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "id": "e8e60398-6688-4512-aabd-eb00b3581639",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.8402\n"
     ]
    }
   ],
   "source": [
    "acc=accuracy_score(y_val, cbtahmin)\n",
    "print(f\"Accuracy: {acc:.4f}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "id": "61593263-dbb2-44de-91de-79b5aa784845",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 63,  45],\n",
       "       [ 25, 305]])"
      ]
     },
     "execution_count": 75,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "confusion_matrix(y_val, cbtahmin)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "id": "ffc1374c-1c59-4c61-8b28-90f53a5304f0",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Classification Report:\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.72      0.58      0.64       108\n",
      "           1       0.87      0.92      0.90       330\n",
      "\n",
      "    accuracy                           0.84       438\n",
      "   macro avg       0.79      0.75      0.77       438\n",
      "weighted avg       0.83      0.84      0.83       438\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(\"\\nClassification Report:\")\n",
    "print(classification_report(y_val, cbtahmin))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "id": "be85fd8c-65da-4eba-a16d-fac9369564aa",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 600x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fpr, tpr, thresholds=roc_curve(y_val, y_proba_cb)\n",
    "roc_auc=auc(fpr, tpr)\n",
    "\n",
    "plt.figure(figsize=(6,5))\n",
    "plt.plot(fpr, tpr, label=f'Logistic Regression (AUC = {roc_auc:.3f})')\n",
    "plt.plot([0, 1], [0, 1], 'k--', label='Random Classifier')\n",
    "\n",
    "plt.xlabel('False Positive Rate')\n",
    "plt.ylabel('True Positive Rate')\n",
    "plt.title('ROC Curve')\n",
    "plt.legend(loc='lower right')\n",
    "plt.grid(alpha=0.3)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d2e52575-e401-45e3-86cd-ed104e4b205e",
   "metadata": {},
   "source": [
    "### 4th LGBMClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "id": "7fdbb1fa-3f18-493c-a08a-c27d8df761b4",
   "metadata": {},
   "outputs": [],
   "source": [
    "lg=LGBMClassifier(\n",
    "    n_estimators=5000,\n",
    "    learning_rate=0.03,\n",
    "    num_leaves=31,\n",
    "    max_depth=-1,\n",
    "    min_child_samples=20,\n",
    "    subsample=0.8,\n",
    "    colsample_bytree=0.8,\n",
    "    reg_alpha=0.0,\n",
    "    reg_lambda=0.0,\n",
    "    random_state=42,\n",
    "    n_jobs=-1\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "id": "81c24bff-ea26-4586-958e-fdf1e2076c34",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[LightGBM] [Info] Number of positive: 1320, number of negative: 432\n",
      "[LightGBM] [Info] Auto-choosing col-wise multi-threading, the overhead of testing was 0.000695 seconds.\n",
      "You can set `force_col_wise=true` to remove the overhead.\n",
      "[LightGBM] [Info] Total Bins 2967\n",
      "[LightGBM] [Info] Number of data points in the train set: 1752, number of used features: 17\n",
      "[LightGBM] [Info] [binary:BoostFromScore]: pavg=0.753425 -> initscore=1.116961\n",
      "[LightGBM] [Info] Start training from score 1.116961\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
      "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-4 {\n",
       "  /* Definition of color scheme common for light and dark mode */\n",
       "  --sklearn-color-text: #000;\n",
       "  --sklearn-color-text-muted: #666;\n",
       "  --sklearn-color-line: gray;\n",
       "  /* Definition of color scheme for unfitted estimators */\n",
       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
       "  --sklearn-color-unfitted-level-3: chocolate;\n",
       "  /* Definition of color scheme for fitted estimators */\n",
       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
       "\n",
       "  /* Specific color for light theme */\n",
       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-icon: #696969;\n",
       "\n",
       "  @media (prefers-color-scheme: dark) {\n",
       "    /* Redefinition of color scheme for dark theme */\n",
       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-icon: #878787;\n",
       "  }\n",
       "}\n",
       "\n",
       "#sk-container-id-4 {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 pre {\n",
       "  padding: 0;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 input.sk-hidden--visually {\n",
       "  border: 0;\n",
       "  clip: rect(1px 1px 1px 1px);\n",
       "  clip: rect(1px, 1px, 1px, 1px);\n",
       "  height: 1px;\n",
       "  margin: -1px;\n",
       "  overflow: hidden;\n",
       "  padding: 0;\n",
       "  position: absolute;\n",
       "  width: 1px;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-dashed-wrapped {\n",
       "  border: 1px dashed var(--sklearn-color-line);\n",
       "  margin: 0 0.4em 0.5em 0.4em;\n",
       "  box-sizing: border-box;\n",
       "  padding-bottom: 0.4em;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-container {\n",
       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
       "     so we also need the `!important` here to be able to override the\n",
       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
       "  display: inline-block !important;\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-text-repr-fallback {\n",
       "  display: none;\n",
       "}\n",
       "\n",
       "div.sk-parallel-item,\n",
       "div.sk-serial,\n",
       "div.sk-item {\n",
       "  /* draw centered vertical line to link estimators */\n",
       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
       "  background-size: 2px 100%;\n",
       "  background-repeat: no-repeat;\n",
       "  background-position: center center;\n",
       "}\n",
       "\n",
       "/* Parallel-specific style estimator block */\n",
       "\n",
       "#sk-container-id-4 div.sk-parallel-item::after {\n",
       "  content: \"\";\n",
       "  width: 100%;\n",
       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
       "  flex-grow: 1;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-parallel {\n",
       "  display: flex;\n",
       "  align-items: stretch;\n",
       "  justify-content: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-parallel-item {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-parallel-item:first-child::after {\n",
       "  align-self: flex-end;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-parallel-item:last-child::after {\n",
       "  align-self: flex-start;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-parallel-item:only-child::after {\n",
       "  width: 0;\n",
       "}\n",
       "\n",
       "/* Serial-specific style estimator block */\n",
       "\n",
       "#sk-container-id-4 div.sk-serial {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "  align-items: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  padding-right: 1em;\n",
       "  padding-left: 1em;\n",
       "}\n",
       "\n",
       "\n",
       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
       "clickable and can be expanded/collapsed.\n",
       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
       "*/\n",
       "\n",
       "/* Pipeline and ColumnTransformer style (default) */\n",
       "\n",
       "#sk-container-id-4 div.sk-toggleable {\n",
       "  /* Default theme specific background. It is overwritten whether we have a\n",
       "  specific estimator or a Pipeline/ColumnTransformer */\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "/* Toggleable label */\n",
       "#sk-container-id-4 label.sk-toggleable__label {\n",
       "  cursor: pointer;\n",
       "  display: flex;\n",
       "  width: 100%;\n",
       "  margin-bottom: 0;\n",
       "  padding: 0.5em;\n",
       "  box-sizing: border-box;\n",
       "  text-align: center;\n",
       "  align-items: start;\n",
       "  justify-content: space-between;\n",
       "  gap: 0.5em;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 label.sk-toggleable__label .caption {\n",
       "  font-size: 0.6rem;\n",
       "  font-weight: lighter;\n",
       "  color: var(--sklearn-color-text-muted);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 label.sk-toggleable__label-arrow:before {\n",
       "  /* Arrow on the left of the label */\n",
       "  content: \"▸\";\n",
       "  float: left;\n",
       "  margin-right: 0.25em;\n",
       "  color: var(--sklearn-color-icon);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 label.sk-toggleable__label-arrow:hover:before {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "/* Toggleable content - dropdown */\n",
       "\n",
       "#sk-container-id-4 div.sk-toggleable__content {\n",
       "  display: none;\n",
       "  text-align: left;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-toggleable__content.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-toggleable__content pre {\n",
       "  margin: 0.2em;\n",
       "  border-radius: 0.25em;\n",
       "  color: var(--sklearn-color-text);\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-toggleable__content.fitted pre {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
       "  /* Expand drop-down */\n",
       "  display: block;\n",
       "  width: 100%;\n",
       "  overflow: visible;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
       "  content: \"▾\";\n",
       "}\n",
       "\n",
       "/* Pipeline/ColumnTransformer-specific style */\n",
       "\n",
       "#sk-container-id-4 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator-specific style */\n",
       "\n",
       "/* Colorize estimator box */\n",
       "#sk-container-id-4 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-label label.sk-toggleable__label,\n",
       "#sk-container-id-4 div.sk-label label {\n",
       "  /* The background is the default theme color */\n",
       "  color: var(--sklearn-color-text-on-default-background);\n",
       "}\n",
       "\n",
       "/* On hover, darken the color of the background */\n",
       "#sk-container-id-4 div.sk-label:hover label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "/* Label box, darken color on hover, fitted */\n",
       "#sk-container-id-4 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator label */\n",
       "\n",
       "#sk-container-id-4 div.sk-label label {\n",
       "  font-family: monospace;\n",
       "  font-weight: bold;\n",
       "  display: inline-block;\n",
       "  line-height: 1.2em;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-label-container {\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "/* Estimator-specific */\n",
       "#sk-container-id-4 div.sk-estimator {\n",
       "  font-family: monospace;\n",
       "  border: 1px dotted var(--sklearn-color-border-box);\n",
       "  border-radius: 0.25em;\n",
       "  box-sizing: border-box;\n",
       "  margin-bottom: 0.5em;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-estimator.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "/* on hover */\n",
       "#sk-container-id-4 div.sk-estimator:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-estimator.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
       "\n",
       "/* Common style for \"i\" and \"?\" */\n",
       "\n",
       ".sk-estimator-doc-link,\n",
       "a:link.sk-estimator-doc-link,\n",
       "a:visited.sk-estimator-doc-link {\n",
       "  float: right;\n",
       "  font-size: smaller;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1em;\n",
       "  height: 1em;\n",
       "  width: 1em;\n",
       "  text-decoration: none !important;\n",
       "  margin-left: 0.5em;\n",
       "  text-align: center;\n",
       "  /* unfitted */\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted,\n",
       "a:link.sk-estimator-doc-link.fitted,\n",
       "a:visited.sk-estimator-doc-link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "/* Span, style for the box shown on hovering the info icon */\n",
       ".sk-estimator-doc-link span {\n",
       "  display: none;\n",
       "  z-index: 9999;\n",
       "  position: relative;\n",
       "  font-weight: normal;\n",
       "  right: .2ex;\n",
       "  padding: .5ex;\n",
       "  margin: .5ex;\n",
       "  width: min-content;\n",
       "  min-width: 20ex;\n",
       "  max-width: 50ex;\n",
       "  color: var(--sklearn-color-text);\n",
       "  box-shadow: 2pt 2pt 4pt #999;\n",
       "  /* unfitted */\n",
       "  background: var(--sklearn-color-unfitted-level-0);\n",
       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted span {\n",
       "  /* fitted */\n",
       "  background: var(--sklearn-color-fitted-level-0);\n",
       "  border: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link:hover span {\n",
       "  display: block;\n",
       "}\n",
       "\n",
       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
       "\n",
       "#sk-container-id-4 a.estimator_doc_link {\n",
       "  float: right;\n",
       "  font-size: 1rem;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1rem;\n",
       "  height: 1rem;\n",
       "  width: 1rem;\n",
       "  text-decoration: none;\n",
       "  /* unfitted */\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 a.estimator_doc_link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "#sk-container-id-4 a.estimator_doc_link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 a.estimator_doc_link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "\n",
       ".estimator-table summary {\n",
       "    padding: .5rem;\n",
       "    font-family: monospace;\n",
       "    cursor: pointer;\n",
       "}\n",
       "\n",
       ".estimator-table details[open] {\n",
       "    padding-left: 0.1rem;\n",
       "    padding-right: 0.1rem;\n",
       "    padding-bottom: 0.3rem;\n",
       "}\n",
       "\n",
       ".estimator-table .parameters-table {\n",
       "    margin-left: auto !important;\n",
       "    margin-right: auto !important;\n",
       "}\n",
       "\n",
       ".estimator-table .parameters-table tr:nth-child(odd) {\n",
       "    background-color: #fff;\n",
       "}\n",
       "\n",
       ".estimator-table .parameters-table tr:nth-child(even) {\n",
       "    background-color: #f6f6f6;\n",
       "}\n",
       "\n",
       ".estimator-table .parameters-table tr:hover {\n",
       "    background-color: #e0e0e0;\n",
       "}\n",
       "\n",
       ".estimator-table table td {\n",
       "    border: 1px solid rgba(106, 105, 104, 0.232);\n",
       "}\n",
       "\n",
       ".user-set td {\n",
       "    color:rgb(255, 94, 0);\n",
       "    text-align: left;\n",
       "}\n",
       "\n",
       ".user-set td.value pre {\n",
       "    color:rgb(255, 94, 0) !important;\n",
       "    background-color: transparent !important;\n",
       "}\n",
       "\n",
       ".default td {\n",
       "    color: black;\n",
       "    text-align: left;\n",
       "}\n",
       "\n",
       ".user-set td i,\n",
       ".default td i {\n",
       "    color: black;\n",
       "}\n",
       "\n",
       ".copy-paste-icon {\n",
       "    background-image: url(data:image/svg+xml;base64,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);\n",
       "    background-repeat: no-repeat;\n",
       "    background-size: 14px 14px;\n",
       "    background-position: 0;\n",
       "    display: inline-block;\n",
       "    width: 14px;\n",
       "    height: 14px;\n",
       "    cursor: pointer;\n",
       "}\n",
       "</style><body><div id=\"sk-container-id-4\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LGBMClassifier(colsample_bytree=0.8, learning_rate=0.03, n_estimators=5000,\n",
       "               n_jobs=-1, random_state=42, subsample=0.8)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-4\" type=\"checkbox\" checked><label for=\"sk-estimator-id-4\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>LGBMClassifier</div></div><div><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></div></label><div class=\"sk-toggleable__content fitted\" data-param-prefix=\"\">\n",
       "        <div class=\"estimator-table\">\n",
       "            <details>\n",
       "                <summary>Parameters</summary>\n",
       "                <table class=\"parameters-table\">\n",
       "                  <tbody>\n",
       "                    \n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('boosting_type',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">boosting_type&nbsp;</td>\n",
       "            <td class=\"value\">&#x27;gbdt&#x27;</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('num_leaves',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">num_leaves&nbsp;</td>\n",
       "            <td class=\"value\">31</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('max_depth',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">max_depth&nbsp;</td>\n",
       "            <td class=\"value\">-1</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('learning_rate',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">learning_rate&nbsp;</td>\n",
       "            <td class=\"value\">0.03</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('n_estimators',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">n_estimators&nbsp;</td>\n",
       "            <td class=\"value\">5000</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('subsample_for_bin',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">subsample_for_bin&nbsp;</td>\n",
       "            <td class=\"value\">200000</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('objective',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">objective&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('class_weight',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">class_weight&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('min_split_gain',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">min_split_gain&nbsp;</td>\n",
       "            <td class=\"value\">0.0</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('min_child_weight',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">min_child_weight&nbsp;</td>\n",
       "            <td class=\"value\">0.001</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('min_child_samples',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">min_child_samples&nbsp;</td>\n",
       "            <td class=\"value\">20</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('subsample',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">subsample&nbsp;</td>\n",
       "            <td class=\"value\">0.8</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('subsample_freq',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">subsample_freq&nbsp;</td>\n",
       "            <td class=\"value\">0</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('colsample_bytree',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">colsample_bytree&nbsp;</td>\n",
       "            <td class=\"value\">0.8</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('reg_alpha',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">reg_alpha&nbsp;</td>\n",
       "            <td class=\"value\">0.0</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('reg_lambda',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">reg_lambda&nbsp;</td>\n",
       "            <td class=\"value\">0.0</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('random_state',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">random_state&nbsp;</td>\n",
       "            <td class=\"value\">42</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('n_jobs',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">n_jobs&nbsp;</td>\n",
       "            <td class=\"value\">-1</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('importance_type',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">importance_type&nbsp;</td>\n",
       "            <td class=\"value\">&#x27;split&#x27;</td>\n",
       "        </tr>\n",
       "    \n",
       "                  </tbody>\n",
       "                </table>\n",
       "            </details>\n",
       "        </div>\n",
       "    </div></div></div></div></div><script>function copyToClipboard(text, element) {\n",
       "    // Get the parameter prefix from the closest toggleable content\n",
       "    const toggleableContent = element.closest('.sk-toggleable__content');\n",
       "    const paramPrefix = toggleableContent ? toggleableContent.dataset.paramPrefix : '';\n",
       "    const fullParamName = paramPrefix ? `${paramPrefix}${text}` : text;\n",
       "\n",
       "    const originalStyle = element.style;\n",
       "    const computedStyle = window.getComputedStyle(element);\n",
       "    const originalWidth = computedStyle.width;\n",
       "    const originalHTML = element.innerHTML.replace('Copied!', '');\n",
       "\n",
       "    navigator.clipboard.writeText(fullParamName)\n",
       "        .then(() => {\n",
       "            element.style.width = originalWidth;\n",
       "            element.style.color = 'green';\n",
       "            element.innerHTML = \"Copied!\";\n",
       "\n",
       "            setTimeout(() => {\n",
       "                element.innerHTML = originalHTML;\n",
       "                element.style = originalStyle;\n",
       "            }, 2000);\n",
       "        })\n",
       "        .catch(err => {\n",
       "            console.error('Failed to copy:', err);\n",
       "            element.style.color = 'red';\n",
       "            element.innerHTML = \"Failed!\";\n",
       "            setTimeout(() => {\n",
       "                element.innerHTML = originalHTML;\n",
       "                element.style = originalStyle;\n",
       "            }, 2000);\n",
       "        });\n",
       "    return false;\n",
       "}\n",
       "\n",
       "document.querySelectorAll('.fa-regular.fa-copy').forEach(function(element) {\n",
       "    const toggleableContent = element.closest('.sk-toggleable__content');\n",
       "    const paramPrefix = toggleableContent ? toggleableContent.dataset.paramPrefix : '';\n",
       "    const paramName = element.parentElement.nextElementSibling.textContent.trim();\n",
       "    const fullParamName = paramPrefix ? `${paramPrefix}${paramName}` : paramName;\n",
       "\n",
       "    element.setAttribute('title', fullParamName);\n",
       "});\n",
       "</script></body>"
      ],
      "text/plain": [
       "LGBMClassifier(colsample_bytree=0.8, learning_rate=0.03, n_estimators=5000,\n",
       "               n_jobs=-1, random_state=42, subsample=0.8)"
      ]
     },
     "execution_count": 84,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lg.fit(x_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "id": "d7ebe36f-d2ce-4658-ad9c-fc00dbc7cac3",
   "metadata": {},
   "outputs": [],
   "source": [
    "lgtahmin=lg.predict(x_val)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "id": "ecc02a36-c4e4-4917-b4d9-c2a4e50e102a",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_proba_lg=lg.predict_proba(x_val)[:, 1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "id": "e7811f7b-f3f7-4401-94c4-14ba0baa624e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "ROC AUC: 0.8535\n"
     ]
    }
   ],
   "source": [
    "roc_auc=roc_auc_score(y_val, y_proba_lg)\n",
    "print(f\"ROC AUC: {roc_auc:.4f}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "id": "7851b96e-0885-4704-a358-476ceeb50453",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.8470\n"
     ]
    }
   ],
   "source": [
    "acc=accuracy_score(y_val, lgtahmin)\n",
    "print(f\"Accuracy: {acc:.4f}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "id": "5eed7bc9-a72b-42e0-8f42-b7b863e72e13",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 65,  43],\n",
       "       [ 24, 306]])"
      ]
     },
     "execution_count": 89,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "confusion_matrix(y_val, lgtahmin)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "id": "95f034ca-0fde-4fa5-b95b-2b96f243c5e2",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Classification Report:\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.73      0.60      0.66       108\n",
      "           1       0.88      0.93      0.90       330\n",
      "\n",
      "    accuracy                           0.85       438\n",
      "   macro avg       0.80      0.76      0.78       438\n",
      "weighted avg       0.84      0.85      0.84       438\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(\"\\nClassification Report:\")\n",
    "print(classification_report(y_val, lgtahmin))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "id": "9bca057b-0a5e-4523-ad02-57377cf0cc80",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 600x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fpr, tpr, thresholds=roc_curve(y_val, y_proba_lg)\n",
    "roc_auc=auc(fpr, tpr)\n",
    "\n",
    "plt.figure(figsize=(6,5))\n",
    "plt.plot(fpr, tpr, label=f'Logistic Regression (AUC = {roc_auc:.3f})')\n",
    "plt.plot([0, 1], [0, 1], 'k--', label='Random Classifier')\n",
    "\n",
    "plt.xlabel('False Positive Rate')\n",
    "plt.ylabel('True Positive Rate')\n",
    "plt.title('ROC Curve')\n",
    "plt.legend(loc='lower right')\n",
    "plt.grid(alpha=0.3)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cf52efa8-ea58-4576-950e-674c4fd249b3",
   "metadata": {},
   "source": [
    "### 5th AdaBoostClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "id": "c7b669e3-01ea-4095-b391-7b89834d3dcd",
   "metadata": {},
   "outputs": [],
   "source": [
    "ab=AdaBoostClassifier(estimator=DecisionTreeClassifier(max_depth=2, random_state=42),n_estimators=400,learning_rate=0.05,random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "id": "7078e457-49b8-4b2e-9147-d93987eefc4c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-5 {\n",
       "  /* Definition of color scheme common for light and dark mode */\n",
       "  --sklearn-color-text: #000;\n",
       "  --sklearn-color-text-muted: #666;\n",
       "  --sklearn-color-line: gray;\n",
       "  /* Definition of color scheme for unfitted estimators */\n",
       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
       "  --sklearn-color-unfitted-level-3: chocolate;\n",
       "  /* Definition of color scheme for fitted estimators */\n",
       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
       "\n",
       "  /* Specific color for light theme */\n",
       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-icon: #696969;\n",
       "\n",
       "  @media (prefers-color-scheme: dark) {\n",
       "    /* Redefinition of color scheme for dark theme */\n",
       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-icon: #878787;\n",
       "  }\n",
       "}\n",
       "\n",
       "#sk-container-id-5 {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "#sk-container-id-5 pre {\n",
       "  padding: 0;\n",
       "}\n",
       "\n",
       "#sk-container-id-5 input.sk-hidden--visually {\n",
       "  border: 0;\n",
       "  clip: rect(1px 1px 1px 1px);\n",
       "  clip: rect(1px, 1px, 1px, 1px);\n",
       "  height: 1px;\n",
       "  margin: -1px;\n",
       "  overflow: hidden;\n",
       "  padding: 0;\n",
       "  position: absolute;\n",
       "  width: 1px;\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-dashed-wrapped {\n",
       "  border: 1px dashed var(--sklearn-color-line);\n",
       "  margin: 0 0.4em 0.5em 0.4em;\n",
       "  box-sizing: border-box;\n",
       "  padding-bottom: 0.4em;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-container {\n",
       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
       "     so we also need the `!important` here to be able to override the\n",
       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
       "  display: inline-block !important;\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-text-repr-fallback {\n",
       "  display: none;\n",
       "}\n",
       "\n",
       "div.sk-parallel-item,\n",
       "div.sk-serial,\n",
       "div.sk-item {\n",
       "  /* draw centered vertical line to link estimators */\n",
       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
       "  background-size: 2px 100%;\n",
       "  background-repeat: no-repeat;\n",
       "  background-position: center center;\n",
       "}\n",
       "\n",
       "/* Parallel-specific style estimator block */\n",
       "\n",
       "#sk-container-id-5 div.sk-parallel-item::after {\n",
       "  content: \"\";\n",
       "  width: 100%;\n",
       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
       "  flex-grow: 1;\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-parallel {\n",
       "  display: flex;\n",
       "  align-items: stretch;\n",
       "  justify-content: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-parallel-item {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-parallel-item:first-child::after {\n",
       "  align-self: flex-end;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-parallel-item:last-child::after {\n",
       "  align-self: flex-start;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-parallel-item:only-child::after {\n",
       "  width: 0;\n",
       "}\n",
       "\n",
       "/* Serial-specific style estimator block */\n",
       "\n",
       "#sk-container-id-5 div.sk-serial {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "  align-items: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  padding-right: 1em;\n",
       "  padding-left: 1em;\n",
       "}\n",
       "\n",
       "\n",
       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
       "clickable and can be expanded/collapsed.\n",
       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
       "*/\n",
       "\n",
       "/* Pipeline and ColumnTransformer style (default) */\n",
       "\n",
       "#sk-container-id-5 div.sk-toggleable {\n",
       "  /* Default theme specific background. It is overwritten whether we have a\n",
       "  specific estimator or a Pipeline/ColumnTransformer */\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "/* Toggleable label */\n",
       "#sk-container-id-5 label.sk-toggleable__label {\n",
       "  cursor: pointer;\n",
       "  display: flex;\n",
       "  width: 100%;\n",
       "  margin-bottom: 0;\n",
       "  padding: 0.5em;\n",
       "  box-sizing: border-box;\n",
       "  text-align: center;\n",
       "  align-items: start;\n",
       "  justify-content: space-between;\n",
       "  gap: 0.5em;\n",
       "}\n",
       "\n",
       "#sk-container-id-5 label.sk-toggleable__label .caption {\n",
       "  font-size: 0.6rem;\n",
       "  font-weight: lighter;\n",
       "  color: var(--sklearn-color-text-muted);\n",
       "}\n",
       "\n",
       "#sk-container-id-5 label.sk-toggleable__label-arrow:before {\n",
       "  /* Arrow on the left of the label */\n",
       "  content: \"▸\";\n",
       "  float: left;\n",
       "  margin-right: 0.25em;\n",
       "  color: var(--sklearn-color-icon);\n",
       "}\n",
       "\n",
       "#sk-container-id-5 label.sk-toggleable__label-arrow:hover:before {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "/* Toggleable content - dropdown */\n",
       "\n",
       "#sk-container-id-5 div.sk-toggleable__content {\n",
       "  display: none;\n",
       "  text-align: left;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-toggleable__content.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-toggleable__content pre {\n",
       "  margin: 0.2em;\n",
       "  border-radius: 0.25em;\n",
       "  color: var(--sklearn-color-text);\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-toggleable__content.fitted pre {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-5 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
       "  /* Expand drop-down */\n",
       "  display: block;\n",
       "  width: 100%;\n",
       "  overflow: visible;\n",
       "}\n",
       "\n",
       "#sk-container-id-5 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
       "  content: \"▾\";\n",
       "}\n",
       "\n",
       "/* Pipeline/ColumnTransformer-specific style */\n",
       "\n",
       "#sk-container-id-5 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator-specific style */\n",
       "\n",
       "/* Colorize estimator box */\n",
       "#sk-container-id-5 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-label label.sk-toggleable__label,\n",
       "#sk-container-id-5 div.sk-label label {\n",
       "  /* The background is the default theme color */\n",
       "  color: var(--sklearn-color-text-on-default-background);\n",
       "}\n",
       "\n",
       "/* On hover, darken the color of the background */\n",
       "#sk-container-id-5 div.sk-label:hover label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "/* Label box, darken color on hover, fitted */\n",
       "#sk-container-id-5 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator label */\n",
       "\n",
       "#sk-container-id-5 div.sk-label label {\n",
       "  font-family: monospace;\n",
       "  font-weight: bold;\n",
       "  display: inline-block;\n",
       "  line-height: 1.2em;\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-label-container {\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "/* Estimator-specific */\n",
       "#sk-container-id-5 div.sk-estimator {\n",
       "  font-family: monospace;\n",
       "  border: 1px dotted var(--sklearn-color-border-box);\n",
       "  border-radius: 0.25em;\n",
       "  box-sizing: border-box;\n",
       "  margin-bottom: 0.5em;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-estimator.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "/* on hover */\n",
       "#sk-container-id-5 div.sk-estimator:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-estimator.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
       "\n",
       "/* Common style for \"i\" and \"?\" */\n",
       "\n",
       ".sk-estimator-doc-link,\n",
       "a:link.sk-estimator-doc-link,\n",
       "a:visited.sk-estimator-doc-link {\n",
       "  float: right;\n",
       "  font-size: smaller;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1em;\n",
       "  height: 1em;\n",
       "  width: 1em;\n",
       "  text-decoration: none !important;\n",
       "  margin-left: 0.5em;\n",
       "  text-align: center;\n",
       "  /* unfitted */\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted,\n",
       "a:link.sk-estimator-doc-link.fitted,\n",
       "a:visited.sk-estimator-doc-link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "/* Span, style for the box shown on hovering the info icon */\n",
       ".sk-estimator-doc-link span {\n",
       "  display: none;\n",
       "  z-index: 9999;\n",
       "  position: relative;\n",
       "  font-weight: normal;\n",
       "  right: .2ex;\n",
       "  padding: .5ex;\n",
       "  margin: .5ex;\n",
       "  width: min-content;\n",
       "  min-width: 20ex;\n",
       "  max-width: 50ex;\n",
       "  color: var(--sklearn-color-text);\n",
       "  box-shadow: 2pt 2pt 4pt #999;\n",
       "  /* unfitted */\n",
       "  background: var(--sklearn-color-unfitted-level-0);\n",
       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted span {\n",
       "  /* fitted */\n",
       "  background: var(--sklearn-color-fitted-level-0);\n",
       "  border: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link:hover span {\n",
       "  display: block;\n",
       "}\n",
       "\n",
       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
       "\n",
       "#sk-container-id-5 a.estimator_doc_link {\n",
       "  float: right;\n",
       "  font-size: 1rem;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1rem;\n",
       "  height: 1rem;\n",
       "  width: 1rem;\n",
       "  text-decoration: none;\n",
       "  /* unfitted */\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "}\n",
       "\n",
       "#sk-container-id-5 a.estimator_doc_link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "#sk-container-id-5 a.estimator_doc_link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "#sk-container-id-5 a.estimator_doc_link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "\n",
       ".estimator-table summary {\n",
       "    padding: .5rem;\n",
       "    font-family: monospace;\n",
       "    cursor: pointer;\n",
       "}\n",
       "\n",
       ".estimator-table details[open] {\n",
       "    padding-left: 0.1rem;\n",
       "    padding-right: 0.1rem;\n",
       "    padding-bottom: 0.3rem;\n",
       "}\n",
       "\n",
       ".estimator-table .parameters-table {\n",
       "    margin-left: auto !important;\n",
       "    margin-right: auto !important;\n",
       "}\n",
       "\n",
       ".estimator-table .parameters-table tr:nth-child(odd) {\n",
       "    background-color: #fff;\n",
       "}\n",
       "\n",
       ".estimator-table .parameters-table tr:nth-child(even) {\n",
       "    background-color: #f6f6f6;\n",
       "}\n",
       "\n",
       ".estimator-table .parameters-table tr:hover {\n",
       "    background-color: #e0e0e0;\n",
       "}\n",
       "\n",
       ".estimator-table table td {\n",
       "    border: 1px solid rgba(106, 105, 104, 0.232);\n",
       "}\n",
       "\n",
       ".user-set td {\n",
       "    color:rgb(255, 94, 0);\n",
       "    text-align: left;\n",
       "}\n",
       "\n",
       ".user-set td.value pre {\n",
       "    color:rgb(255, 94, 0) !important;\n",
       "    background-color: transparent !important;\n",
       "}\n",
       "\n",
       ".default td {\n",
       "    color: black;\n",
       "    text-align: left;\n",
       "}\n",
       "\n",
       ".user-set td i,\n",
       ".default td i {\n",
       "    color: black;\n",
       "}\n",
       "\n",
       ".copy-paste-icon {\n",
       "    background-image: url(data:image/svg+xml;base64,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);\n",
       "    background-repeat: no-repeat;\n",
       "    background-size: 14px 14px;\n",
       "    background-position: 0;\n",
       "    display: inline-block;\n",
       "    width: 14px;\n",
       "    height: 14px;\n",
       "    cursor: pointer;\n",
       "}\n",
       "</style><body><div id=\"sk-container-id-5\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>AdaBoostClassifier(estimator=DecisionTreeClassifier(max_depth=2,\n",
       "                                                    random_state=42),\n",
       "                   learning_rate=0.05, n_estimators=400, random_state=42)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-5\" type=\"checkbox\" ><label for=\"sk-estimator-id-5\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>AdaBoostClassifier</div></div><div><a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.7/modules/generated/sklearn.ensemble.AdaBoostClassifier.html\">?<span>Documentation for AdaBoostClassifier</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></div></label><div class=\"sk-toggleable__content fitted\" data-param-prefix=\"\">\n",
       "        <div class=\"estimator-table\">\n",
       "            <details>\n",
       "                <summary>Parameters</summary>\n",
       "                <table class=\"parameters-table\">\n",
       "                  <tbody>\n",
       "                    \n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('estimator',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">estimator&nbsp;</td>\n",
       "            <td class=\"value\">DecisionTreeC...ndom_state=42)</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('n_estimators',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">n_estimators&nbsp;</td>\n",
       "            <td class=\"value\">400</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('learning_rate',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">learning_rate&nbsp;</td>\n",
       "            <td class=\"value\">0.05</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('algorithm',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">algorithm&nbsp;</td>\n",
       "            <td class=\"value\">&#x27;deprecated&#x27;</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('random_state',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">random_state&nbsp;</td>\n",
       "            <td class=\"value\">42</td>\n",
       "        </tr>\n",
       "    \n",
       "                  </tbody>\n",
       "                </table>\n",
       "            </details>\n",
       "        </div>\n",
       "    </div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-6\" type=\"checkbox\" ><label for=\"sk-estimator-id-6\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>estimator: DecisionTreeClassifier</div></div></label><div class=\"sk-toggleable__content fitted\" data-param-prefix=\"estimator__\"><pre>DecisionTreeClassifier(max_depth=2, random_state=42)</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-7\" type=\"checkbox\" ><label for=\"sk-estimator-id-7\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>DecisionTreeClassifier</div></div><div><a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.7/modules/generated/sklearn.tree.DecisionTreeClassifier.html\">?<span>Documentation for DecisionTreeClassifier</span></a></div></label><div class=\"sk-toggleable__content fitted\" data-param-prefix=\"estimator__\">\n",
       "        <div class=\"estimator-table\">\n",
       "            <details>\n",
       "                <summary>Parameters</summary>\n",
       "                <table class=\"parameters-table\">\n",
       "                  <tbody>\n",
       "                    \n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('criterion',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">criterion&nbsp;</td>\n",
       "            <td class=\"value\">&#x27;gini&#x27;</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('splitter',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">splitter&nbsp;</td>\n",
       "            <td class=\"value\">&#x27;best&#x27;</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('max_depth',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">max_depth&nbsp;</td>\n",
       "            <td class=\"value\">2</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('min_samples_split',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">min_samples_split&nbsp;</td>\n",
       "            <td class=\"value\">2</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('min_samples_leaf',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">min_samples_leaf&nbsp;</td>\n",
       "            <td class=\"value\">1</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('min_weight_fraction_leaf',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">min_weight_fraction_leaf&nbsp;</td>\n",
       "            <td class=\"value\">0.0</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('max_features',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">max_features&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('random_state',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">random_state&nbsp;</td>\n",
       "            <td class=\"value\">42</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('max_leaf_nodes',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">max_leaf_nodes&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('min_impurity_decrease',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">min_impurity_decrease&nbsp;</td>\n",
       "            <td class=\"value\">0.0</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('class_weight',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">class_weight&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('ccp_alpha',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">ccp_alpha&nbsp;</td>\n",
       "            <td class=\"value\">0.0</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('monotonic_cst',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">monotonic_cst&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "                  </tbody>\n",
       "                </table>\n",
       "            </details>\n",
       "        </div>\n",
       "    </div></div></div></div></div></div></div></div></div></div><script>function copyToClipboard(text, element) {\n",
       "    // Get the parameter prefix from the closest toggleable content\n",
       "    const toggleableContent = element.closest('.sk-toggleable__content');\n",
       "    const paramPrefix = toggleableContent ? toggleableContent.dataset.paramPrefix : '';\n",
       "    const fullParamName = paramPrefix ? `${paramPrefix}${text}` : text;\n",
       "\n",
       "    const originalStyle = element.style;\n",
       "    const computedStyle = window.getComputedStyle(element);\n",
       "    const originalWidth = computedStyle.width;\n",
       "    const originalHTML = element.innerHTML.replace('Copied!', '');\n",
       "\n",
       "    navigator.clipboard.writeText(fullParamName)\n",
       "        .then(() => {\n",
       "            element.style.width = originalWidth;\n",
       "            element.style.color = 'green';\n",
       "            element.innerHTML = \"Copied!\";\n",
       "\n",
       "            setTimeout(() => {\n",
       "                element.innerHTML = originalHTML;\n",
       "                element.style = originalStyle;\n",
       "            }, 2000);\n",
       "        })\n",
       "        .catch(err => {\n",
       "            console.error('Failed to copy:', err);\n",
       "            element.style.color = 'red';\n",
       "            element.innerHTML = \"Failed!\";\n",
       "            setTimeout(() => {\n",
       "                element.innerHTML = originalHTML;\n",
       "                element.style = originalStyle;\n",
       "            }, 2000);\n",
       "        });\n",
       "    return false;\n",
       "}\n",
       "\n",
       "document.querySelectorAll('.fa-regular.fa-copy').forEach(function(element) {\n",
       "    const toggleableContent = element.closest('.sk-toggleable__content');\n",
       "    const paramPrefix = toggleableContent ? toggleableContent.dataset.paramPrefix : '';\n",
       "    const paramName = element.parentElement.nextElementSibling.textContent.trim();\n",
       "    const fullParamName = paramPrefix ? `${paramPrefix}${paramName}` : paramName;\n",
       "\n",
       "    element.setAttribute('title', fullParamName);\n",
       "});\n",
       "</script></body>"
      ],
      "text/plain": [
       "AdaBoostClassifier(estimator=DecisionTreeClassifier(max_depth=2,\n",
       "                                                    random_state=42),\n",
       "                   learning_rate=0.05, n_estimators=400, random_state=42)"
      ]
     },
     "execution_count": 93,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ab.fit(x_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "id": "3a71443e-172e-4b98-a311-0cf72a5980c7",
   "metadata": {},
   "outputs": [],
   "source": [
    "abtahmin=ab.predict(x_val)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "id": "efc1a13f-b3b4-45e2-a5e1-4e3cb63ec26f",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_proba_ab=ab.predict_proba(x_val)[:, 1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "id": "380d15a0-9ee4-4241-a94d-d41072ac0c39",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "ROC AUC: 0.8743\n"
     ]
    }
   ],
   "source": [
    "roc_auc=roc_auc_score(y_val, y_proba_ab)\n",
    "print(f\"ROC AUC: {roc_auc:.4f}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "id": "d5f59412-62af-4cb4-a898-bc797f007e87",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.8767\n"
     ]
    }
   ],
   "source": [
    "acc=accuracy_score(y_val, abtahmin)\n",
    "print(f\"Accuracy: {acc:.4f}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 98,
   "id": "9f120140-27a9-461b-b00f-210c84cb90b0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 71,  37],\n",
       "       [ 17, 313]])"
      ]
     },
     "execution_count": 98,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "confusion_matrix(y_val, abtahmin)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "id": "e1b49c46-57b0-49cd-9586-c7f6d0b4d296",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Classification Report:\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.81      0.66      0.72       108\n",
      "           1       0.89      0.95      0.92       330\n",
      "\n",
      "    accuracy                           0.88       438\n",
      "   macro avg       0.85      0.80      0.82       438\n",
      "weighted avg       0.87      0.88      0.87       438\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(\"\\nClassification Report:\")\n",
    "print(classification_report(y_val, abtahmin))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "id": "c107239d-5ea0-4ca2-8887-eb735cf1b7d4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 600x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fpr, tpr, thresholds=roc_curve(y_val, y_proba_ab)\n",
    "roc_auc=auc(fpr, tpr)\n",
    "\n",
    "plt.figure(figsize=(6,5))\n",
    "plt.plot(fpr, tpr, label=f'Logistic Regression (AUC = {roc_auc:.3f})')\n",
    "plt.plot([0, 1], [0, 1], 'k--', label='Random Classifier')\n",
    "\n",
    "plt.xlabel('False Positive Rate')\n",
    "plt.ylabel('True Positive Rate')\n",
    "plt.title('ROC Curve')\n",
    "plt.legend(loc='lower right')\n",
    "plt.grid(alpha=0.3)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f1252f44-96ca-4f2e-b2ac-2977c2aa6d89",
   "metadata": {},
   "source": [
    "### Test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 109,
   "id": "9c2d1c71-be6a-4060-9be9-9a6ddd00fbdf",
   "metadata": {},
   "outputs": [],
   "source": [
    "sub=pd.read_csv('sample_submission.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 110,
   "id": "fb3933eb-c1b2-40e5-a54b-ae84cdfa7e32",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>rainfall</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2190</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2191</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2192</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2193</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2194</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     id  rainfall\n",
       "0  2190         0\n",
       "1  2191         0\n",
       "2  2192         0\n",
       "3  2193         0\n",
       "4  2194         0"
      ]
     },
     "execution_count": 110,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sub.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 124,
   "id": "98053c2c-c3d3-4218-a1f8-c91dd2a1c10e",
   "metadata": {},
   "outputs": [],
   "source": [
    "x_test=df2.drop(['id'],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 125,
   "id": "d0fb5206-4da9-4928-b2d6-1fee3e4caa4e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>day</th>\n",
       "      <th>pressure</th>\n",
       "      <th>maxtemp</th>\n",
       "      <th>temparature</th>\n",
       "      <th>mintemp</th>\n",
       "      <th>dewpoint</th>\n",
       "      <th>humidity</th>\n",
       "      <th>cloud</th>\n",
       "      <th>sunshine</th>\n",
       "      <th>winddirection</th>\n",
       "      <th>windspeed</th>\n",
       "      <th>temp_range</th>\n",
       "      <th>humidity_gap</th>\n",
       "      <th>sunshine_ratio</th>\n",
       "      <th>wind_energy</th>\n",
       "      <th>sin_day</th>\n",
       "      <th>cos_day</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>1019.5</td>\n",
       "      <td>17.5</td>\n",
       "      <td>15.8</td>\n",
       "      <td>12.7</td>\n",
       "      <td>14.9</td>\n",
       "      <td>96.0</td>\n",
       "      <td>99.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>24.3</td>\n",
       "      <td>4.8</td>\n",
       "      <td>81.1</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1215.0</td>\n",
       "      <td>0.017213</td>\n",
       "      <td>0.999852</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1016.5</td>\n",
       "      <td>17.5</td>\n",
       "      <td>16.5</td>\n",
       "      <td>15.8</td>\n",
       "      <td>15.1</td>\n",
       "      <td>97.0</td>\n",
       "      <td>99.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>35.3</td>\n",
       "      <td>1.7</td>\n",
       "      <td>81.9</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1765.0</td>\n",
       "      <td>0.034422</td>\n",
       "      <td>0.999407</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>1023.9</td>\n",
       "      <td>11.2</td>\n",
       "      <td>10.4</td>\n",
       "      <td>9.4</td>\n",
       "      <td>8.9</td>\n",
       "      <td>86.0</td>\n",
       "      <td>96.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>40.0</td>\n",
       "      <td>16.9</td>\n",
       "      <td>1.8</td>\n",
       "      <td>77.1</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>676.0</td>\n",
       "      <td>0.051620</td>\n",
       "      <td>0.998667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1022.9</td>\n",
       "      <td>20.6</td>\n",
       "      <td>17.3</td>\n",
       "      <td>15.2</td>\n",
       "      <td>9.5</td>\n",
       "      <td>75.0</td>\n",
       "      <td>45.0</td>\n",
       "      <td>7.1</td>\n",
       "      <td>20.0</td>\n",
       "      <td>50.6</td>\n",
       "      <td>5.4</td>\n",
       "      <td>65.5</td>\n",
       "      <td>0.154348</td>\n",
       "      <td>1012.0</td>\n",
       "      <td>0.068802</td>\n",
       "      <td>0.997630</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>1022.2</td>\n",
       "      <td>16.1</td>\n",
       "      <td>13.8</td>\n",
       "      <td>6.4</td>\n",
       "      <td>4.3</td>\n",
       "      <td>68.0</td>\n",
       "      <td>49.0</td>\n",
       "      <td>9.2</td>\n",
       "      <td>20.0</td>\n",
       "      <td>19.4</td>\n",
       "      <td>9.7</td>\n",
       "      <td>63.7</td>\n",
       "      <td>0.184000</td>\n",
       "      <td>388.0</td>\n",
       "      <td>0.085965</td>\n",
       "      <td>0.996298</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   day  pressure  maxtemp  temparature  mintemp  dewpoint  humidity  cloud  \\\n",
       "0    1    1019.5     17.5         15.8     12.7      14.9      96.0   99.0   \n",
       "1    2    1016.5     17.5         16.5     15.8      15.1      97.0   99.0   \n",
       "2    3    1023.9     11.2         10.4      9.4       8.9      86.0   96.0   \n",
       "3    4    1022.9     20.6         17.3     15.2       9.5      75.0   45.0   \n",
       "4    5    1022.2     16.1         13.8      6.4       4.3      68.0   49.0   \n",
       "\n",
       "   sunshine  winddirection  windspeed  temp_range  humidity_gap  \\\n",
       "0       0.0           50.0       24.3         4.8          81.1   \n",
       "1       0.0           50.0       35.3         1.7          81.9   \n",
       "2       0.0           40.0       16.9         1.8          77.1   \n",
       "3       7.1           20.0       50.6         5.4          65.5   \n",
       "4       9.2           20.0       19.4         9.7          63.7   \n",
       "\n",
       "   sunshine_ratio  wind_energy   sin_day   cos_day  \n",
       "0        0.000000       1215.0  0.017213  0.999852  \n",
       "1        0.000000       1765.0  0.034422  0.999407  \n",
       "2        0.000000        676.0  0.051620  0.998667  \n",
       "3        0.154348       1012.0  0.068802  0.997630  \n",
       "4        0.184000        388.0  0.085965  0.996298  "
      ]
     },
     "execution_count": 125,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_test.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 126,
   "id": "2362f929-857b-4f76-bd9d-09f232d112fa",
   "metadata": {},
   "outputs": [],
   "source": [
    "final_lr=LogisticRegression(max_iter=1000,class_weight='balanced',n_jobs=-1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 127,
   "id": "026ea9fa-7357-4bee-9d58-58a81034887d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-10 {\n",
       "  /* Definition of color scheme common for light and dark mode */\n",
       "  --sklearn-color-text: #000;\n",
       "  --sklearn-color-text-muted: #666;\n",
       "  --sklearn-color-line: gray;\n",
       "  /* Definition of color scheme for unfitted estimators */\n",
       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
       "  --sklearn-color-unfitted-level-3: chocolate;\n",
       "  /* Definition of color scheme for fitted estimators */\n",
       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
       "\n",
       "  /* Specific color for light theme */\n",
       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-icon: #696969;\n",
       "\n",
       "  @media (prefers-color-scheme: dark) {\n",
       "    /* Redefinition of color scheme for dark theme */\n",
       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-icon: #878787;\n",
       "  }\n",
       "}\n",
       "\n",
       "#sk-container-id-10 {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "#sk-container-id-10 pre {\n",
       "  padding: 0;\n",
       "}\n",
       "\n",
       "#sk-container-id-10 input.sk-hidden--visually {\n",
       "  border: 0;\n",
       "  clip: rect(1px 1px 1px 1px);\n",
       "  clip: rect(1px, 1px, 1px, 1px);\n",
       "  height: 1px;\n",
       "  margin: -1px;\n",
       "  overflow: hidden;\n",
       "  padding: 0;\n",
       "  position: absolute;\n",
       "  width: 1px;\n",
       "}\n",
       "\n",
       "#sk-container-id-10 div.sk-dashed-wrapped {\n",
       "  border: 1px dashed var(--sklearn-color-line);\n",
       "  margin: 0 0.4em 0.5em 0.4em;\n",
       "  box-sizing: border-box;\n",
       "  padding-bottom: 0.4em;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "#sk-container-id-10 div.sk-container {\n",
       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
       "     so we also need the `!important` here to be able to override the\n",
       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
       "  display: inline-block !important;\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-10 div.sk-text-repr-fallback {\n",
       "  display: none;\n",
       "}\n",
       "\n",
       "div.sk-parallel-item,\n",
       "div.sk-serial,\n",
       "div.sk-item {\n",
       "  /* draw centered vertical line to link estimators */\n",
       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
       "  background-size: 2px 100%;\n",
       "  background-repeat: no-repeat;\n",
       "  background-position: center center;\n",
       "}\n",
       "\n",
       "/* Parallel-specific style estimator block */\n",
       "\n",
       "#sk-container-id-10 div.sk-parallel-item::after {\n",
       "  content: \"\";\n",
       "  width: 100%;\n",
       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
       "  flex-grow: 1;\n",
       "}\n",
       "\n",
       "#sk-container-id-10 div.sk-parallel {\n",
       "  display: flex;\n",
       "  align-items: stretch;\n",
       "  justify-content: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-10 div.sk-parallel-item {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "}\n",
       "\n",
       "#sk-container-id-10 div.sk-parallel-item:first-child::after {\n",
       "  align-self: flex-end;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-10 div.sk-parallel-item:last-child::after {\n",
       "  align-self: flex-start;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-10 div.sk-parallel-item:only-child::after {\n",
       "  width: 0;\n",
       "}\n",
       "\n",
       "/* Serial-specific style estimator block */\n",
       "\n",
       "#sk-container-id-10 div.sk-serial {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "  align-items: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  padding-right: 1em;\n",
       "  padding-left: 1em;\n",
       "}\n",
       "\n",
       "\n",
       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
       "clickable and can be expanded/collapsed.\n",
       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
       "*/\n",
       "\n",
       "/* Pipeline and ColumnTransformer style (default) */\n",
       "\n",
       "#sk-container-id-10 div.sk-toggleable {\n",
       "  /* Default theme specific background. It is overwritten whether we have a\n",
       "  specific estimator or a Pipeline/ColumnTransformer */\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "/* Toggleable label */\n",
       "#sk-container-id-10 label.sk-toggleable__label {\n",
       "  cursor: pointer;\n",
       "  display: flex;\n",
       "  width: 100%;\n",
       "  margin-bottom: 0;\n",
       "  padding: 0.5em;\n",
       "  box-sizing: border-box;\n",
       "  text-align: center;\n",
       "  align-items: start;\n",
       "  justify-content: space-between;\n",
       "  gap: 0.5em;\n",
       "}\n",
       "\n",
       "#sk-container-id-10 label.sk-toggleable__label .caption {\n",
       "  font-size: 0.6rem;\n",
       "  font-weight: lighter;\n",
       "  color: var(--sklearn-color-text-muted);\n",
       "}\n",
       "\n",
       "#sk-container-id-10 label.sk-toggleable__label-arrow:before {\n",
       "  /* Arrow on the left of the label */\n",
       "  content: \"▸\";\n",
       "  float: left;\n",
       "  margin-right: 0.25em;\n",
       "  color: var(--sklearn-color-icon);\n",
       "}\n",
       "\n",
       "#sk-container-id-10 label.sk-toggleable__label-arrow:hover:before {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "/* Toggleable content - dropdown */\n",
       "\n",
       "#sk-container-id-10 div.sk-toggleable__content {\n",
       "  display: none;\n",
       "  text-align: left;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-10 div.sk-toggleable__content.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-10 div.sk-toggleable__content pre {\n",
       "  margin: 0.2em;\n",
       "  border-radius: 0.25em;\n",
       "  color: var(--sklearn-color-text);\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-10 div.sk-toggleable__content.fitted pre {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-10 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
       "  /* Expand drop-down */\n",
       "  display: block;\n",
       "  width: 100%;\n",
       "  overflow: visible;\n",
       "}\n",
       "\n",
       "#sk-container-id-10 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
       "  content: \"▾\";\n",
       "}\n",
       "\n",
       "/* Pipeline/ColumnTransformer-specific style */\n",
       "\n",
       "#sk-container-id-10 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-10 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator-specific style */\n",
       "\n",
       "/* Colorize estimator box */\n",
       "#sk-container-id-10 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-10 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-10 div.sk-label label.sk-toggleable__label,\n",
       "#sk-container-id-10 div.sk-label label {\n",
       "  /* The background is the default theme color */\n",
       "  color: var(--sklearn-color-text-on-default-background);\n",
       "}\n",
       "\n",
       "/* On hover, darken the color of the background */\n",
       "#sk-container-id-10 div.sk-label:hover label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "/* Label box, darken color on hover, fitted */\n",
       "#sk-container-id-10 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator label */\n",
       "\n",
       "#sk-container-id-10 div.sk-label label {\n",
       "  font-family: monospace;\n",
       "  font-weight: bold;\n",
       "  display: inline-block;\n",
       "  line-height: 1.2em;\n",
       "}\n",
       "\n",
       "#sk-container-id-10 div.sk-label-container {\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "/* Estimator-specific */\n",
       "#sk-container-id-10 div.sk-estimator {\n",
       "  font-family: monospace;\n",
       "  border: 1px dotted var(--sklearn-color-border-box);\n",
       "  border-radius: 0.25em;\n",
       "  box-sizing: border-box;\n",
       "  margin-bottom: 0.5em;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-10 div.sk-estimator.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "/* on hover */\n",
       "#sk-container-id-10 div.sk-estimator:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-10 div.sk-estimator.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
       "\n",
       "/* Common style for \"i\" and \"?\" */\n",
       "\n",
       ".sk-estimator-doc-link,\n",
       "a:link.sk-estimator-doc-link,\n",
       "a:visited.sk-estimator-doc-link {\n",
       "  float: right;\n",
       "  font-size: smaller;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1em;\n",
       "  height: 1em;\n",
       "  width: 1em;\n",
       "  text-decoration: none !important;\n",
       "  margin-left: 0.5em;\n",
       "  text-align: center;\n",
       "  /* unfitted */\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted,\n",
       "a:link.sk-estimator-doc-link.fitted,\n",
       "a:visited.sk-estimator-doc-link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "/* Span, style for the box shown on hovering the info icon */\n",
       ".sk-estimator-doc-link span {\n",
       "  display: none;\n",
       "  z-index: 9999;\n",
       "  position: relative;\n",
       "  font-weight: normal;\n",
       "  right: .2ex;\n",
       "  padding: .5ex;\n",
       "  margin: .5ex;\n",
       "  width: min-content;\n",
       "  min-width: 20ex;\n",
       "  max-width: 50ex;\n",
       "  color: var(--sklearn-color-text);\n",
       "  box-shadow: 2pt 2pt 4pt #999;\n",
       "  /* unfitted */\n",
       "  background: var(--sklearn-color-unfitted-level-0);\n",
       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted span {\n",
       "  /* fitted */\n",
       "  background: var(--sklearn-color-fitted-level-0);\n",
       "  border: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link:hover span {\n",
       "  display: block;\n",
       "}\n",
       "\n",
       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
       "\n",
       "#sk-container-id-10 a.estimator_doc_link {\n",
       "  float: right;\n",
       "  font-size: 1rem;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1rem;\n",
       "  height: 1rem;\n",
       "  width: 1rem;\n",
       "  text-decoration: none;\n",
       "  /* unfitted */\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "}\n",
       "\n",
       "#sk-container-id-10 a.estimator_doc_link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "#sk-container-id-10 a.estimator_doc_link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "#sk-container-id-10 a.estimator_doc_link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "\n",
       ".estimator-table summary {\n",
       "    padding: .5rem;\n",
       "    font-family: monospace;\n",
       "    cursor: pointer;\n",
       "}\n",
       "\n",
       ".estimator-table details[open] {\n",
       "    padding-left: 0.1rem;\n",
       "    padding-right: 0.1rem;\n",
       "    padding-bottom: 0.3rem;\n",
       "}\n",
       "\n",
       ".estimator-table .parameters-table {\n",
       "    margin-left: auto !important;\n",
       "    margin-right: auto !important;\n",
       "}\n",
       "\n",
       ".estimator-table .parameters-table tr:nth-child(odd) {\n",
       "    background-color: #fff;\n",
       "}\n",
       "\n",
       ".estimator-table .parameters-table tr:nth-child(even) {\n",
       "    background-color: #f6f6f6;\n",
       "}\n",
       "\n",
       ".estimator-table .parameters-table tr:hover {\n",
       "    background-color: #e0e0e0;\n",
       "}\n",
       "\n",
       ".estimator-table table td {\n",
       "    border: 1px solid rgba(106, 105, 104, 0.232);\n",
       "}\n",
       "\n",
       ".user-set td {\n",
       "    color:rgb(255, 94, 0);\n",
       "    text-align: left;\n",
       "}\n",
       "\n",
       ".user-set td.value pre {\n",
       "    color:rgb(255, 94, 0) !important;\n",
       "    background-color: transparent !important;\n",
       "}\n",
       "\n",
       ".default td {\n",
       "    color: black;\n",
       "    text-align: left;\n",
       "}\n",
       "\n",
       ".user-set td i,\n",
       ".default td i {\n",
       "    color: black;\n",
       "}\n",
       "\n",
       ".copy-paste-icon {\n",
       "    background-image: url(data:image/svg+xml;base64,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);\n",
       "    background-repeat: no-repeat;\n",
       "    background-size: 14px 14px;\n",
       "    background-position: 0;\n",
       "    display: inline-block;\n",
       "    width: 14px;\n",
       "    height: 14px;\n",
       "    cursor: pointer;\n",
       "}\n",
       "</style><body><div id=\"sk-container-id-10\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LogisticRegression(class_weight=&#x27;balanced&#x27;, max_iter=1000, n_jobs=-1)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-12\" type=\"checkbox\" checked><label for=\"sk-estimator-id-12\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>LogisticRegression</div></div><div><a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.7/modules/generated/sklearn.linear_model.LogisticRegression.html\">?<span>Documentation for LogisticRegression</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></div></label><div class=\"sk-toggleable__content fitted\" data-param-prefix=\"\">\n",
       "        <div class=\"estimator-table\">\n",
       "            <details>\n",
       "                <summary>Parameters</summary>\n",
       "                <table class=\"parameters-table\">\n",
       "                  <tbody>\n",
       "                    \n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('penalty',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">penalty&nbsp;</td>\n",
       "            <td class=\"value\">&#x27;l2&#x27;</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('dual',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">dual&nbsp;</td>\n",
       "            <td class=\"value\">False</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('tol',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">tol&nbsp;</td>\n",
       "            <td class=\"value\">0.0001</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('C',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">C&nbsp;</td>\n",
       "            <td class=\"value\">1.0</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('fit_intercept',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">fit_intercept&nbsp;</td>\n",
       "            <td class=\"value\">True</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('intercept_scaling',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">intercept_scaling&nbsp;</td>\n",
       "            <td class=\"value\">1</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('class_weight',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">class_weight&nbsp;</td>\n",
       "            <td class=\"value\">&#x27;balanced&#x27;</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('random_state',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">random_state&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('solver',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">solver&nbsp;</td>\n",
       "            <td class=\"value\">&#x27;lbfgs&#x27;</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('max_iter',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">max_iter&nbsp;</td>\n",
       "            <td class=\"value\">1000</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('multi_class',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">multi_class&nbsp;</td>\n",
       "            <td class=\"value\">&#x27;deprecated&#x27;</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('verbose',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">verbose&nbsp;</td>\n",
       "            <td class=\"value\">0</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('warm_start',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">warm_start&nbsp;</td>\n",
       "            <td class=\"value\">False</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('n_jobs',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">n_jobs&nbsp;</td>\n",
       "            <td class=\"value\">-1</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('l1_ratio',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">l1_ratio&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "                  </tbody>\n",
       "                </table>\n",
       "            </details>\n",
       "        </div>\n",
       "    </div></div></div></div></div><script>function copyToClipboard(text, element) {\n",
       "    // Get the parameter prefix from the closest toggleable content\n",
       "    const toggleableContent = element.closest('.sk-toggleable__content');\n",
       "    const paramPrefix = toggleableContent ? toggleableContent.dataset.paramPrefix : '';\n",
       "    const fullParamName = paramPrefix ? `${paramPrefix}${text}` : text;\n",
       "\n",
       "    const originalStyle = element.style;\n",
       "    const computedStyle = window.getComputedStyle(element);\n",
       "    const originalWidth = computedStyle.width;\n",
       "    const originalHTML = element.innerHTML.replace('Copied!', '');\n",
       "\n",
       "    navigator.clipboard.writeText(fullParamName)\n",
       "        .then(() => {\n",
       "            element.style.width = originalWidth;\n",
       "            element.style.color = 'green';\n",
       "            element.innerHTML = \"Copied!\";\n",
       "\n",
       "            setTimeout(() => {\n",
       "                element.innerHTML = originalHTML;\n",
       "                element.style = originalStyle;\n",
       "            }, 2000);\n",
       "        })\n",
       "        .catch(err => {\n",
       "            console.error('Failed to copy:', err);\n",
       "            element.style.color = 'red';\n",
       "            element.innerHTML = \"Failed!\";\n",
       "            setTimeout(() => {\n",
       "                element.innerHTML = originalHTML;\n",
       "                element.style = originalStyle;\n",
       "            }, 2000);\n",
       "        });\n",
       "    return false;\n",
       "}\n",
       "\n",
       "document.querySelectorAll('.fa-regular.fa-copy').forEach(function(element) {\n",
       "    const toggleableContent = element.closest('.sk-toggleable__content');\n",
       "    const paramPrefix = toggleableContent ? toggleableContent.dataset.paramPrefix : '';\n",
       "    const paramName = element.parentElement.nextElementSibling.textContent.trim();\n",
       "    const fullParamName = paramPrefix ? `${paramPrefix}${paramName}` : paramName;\n",
       "\n",
       "    element.setAttribute('title', fullParamName);\n",
       "});\n",
       "</script></body>"
      ],
      "text/plain": [
       "LogisticRegression(class_weight='balanced', max_iter=1000, n_jobs=-1)"
      ]
     },
     "execution_count": 127,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "final_lr.fit(x, y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 128,
   "id": "18eb6a1f-cf96-4314-9ebd-cfc8e142f8c6",
   "metadata": {},
   "outputs": [],
   "source": [
    "test_proba=final_lr.predict_proba(x_test)[:, 1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 129,
   "id": "ad338f35-473c-4552-88de-790bb4851222",
   "metadata": {},
   "outputs": [],
   "source": [
    "submission=pd.DataFrame({'id': df2['id'],'rainfall': test_proba})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 130,
   "id": "0c7f40c8-76c1-45b4-a1b2-52f07f353f13",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "     id  rainfall\n",
      "0  2190  0.958098\n",
      "1  2191  0.951503\n",
      "2  2192  0.843682\n",
      "3  2193  0.028115\n",
      "4  2194  0.020298\n"
     ]
    }
   ],
   "source": [
    "print(submission.head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 131,
   "id": "d80d2f11-d226-4e02-8c75-7498d72d3125",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(730, 2)\n"
     ]
    }
   ],
   "source": [
    "print(submission.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 132,
   "id": "039ccaa5-23d3-488d-8ee6-b40e42d01609",
   "metadata": {},
   "outputs": [],
   "source": [
    "submission.to_csv('submission.csv',index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 136,
   "id": "bbbf2947-cafb-4928-a1f3-83e05ccabc27",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['lr_final_model.pkl']"
      ]
     },
     "execution_count": 136,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "joblib.dump(final_lr, 'lr_final_model.pkl')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 137,
   "id": "1b7029b8-0e5d-46cb-a6ca-f6027f2ba314",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['feature_names.pkl']"
      ]
     },
     "execution_count": 137,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "joblib.dump(x_train.columns.tolist(),'feature_names.pkl')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ec26707b-79af-4f69-b5ec-38d7ed478721",
   "metadata": {},
   "source": [
    "### Conclusion\n",
    "Several classification models were tested and compared using the ROC-AUC metric.\n",
    "Logistic Regression achieved the best performance with a ROC-AUC score of 0.88, showing that the relationship between the features and rainfall is largely linear.\n",
    "The results indicate that the selected features provide strong and meaningful information for predicting rainfall."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [conda env:base] *",
   "language": "python",
   "name": "conda-base-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.13.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}