app.py

import streamlit as st
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, classification_report, confusion_matrix

# Custom Streamlit styling - Dark mode version
st.markdown(
    """
    <style>
    body {
        background-color: #1E1E1E;
        color: #FFFFFF;
        font-family: 'Arial', sans-serif;
    }
    .stButton>button {
        background-color: #4A90E2;
        color: #FFFFFF;
        border-radius: 15px;
        padding: 12px 24px;
        font-size: 16px;
        font-weight: bold;
    }
    # .stSlider>div>div>div {
    #     background-color: #4A90E2;
    }
    .title {
        color: #64FFDA;
        text-shadow: 1px 1px #FF4C4C;
    }
    # .stSlider label, .stSlider>div>div>span {
    #     color: #FFFFFF !important;
    }
    </style>
    """,
    unsafe_allow_html=True
)

# Load the League of Legends dataset
st.title("🎮 League of Legends Game Win Predictor")
st.markdown("<h2 class='title'>Predict whether the Blue Team will dominate the game! 💥</h2>", unsafe_allow_html=True)

# Load dataset directly
file_path = 'high_diamond_ranked_10min.csv'
df = pd.read_csv(file_path)
st.write("### 📊 Dataset Preview")
st.dataframe(df.head())

# Select relevant columns
df = df[['blueFirstBlood', 'blueKills', 'blueDeaths', 'blueAssists', 'blueTotalGold', 'blueTotalExperience', 'blueDragons', 'blueHeralds', 'blueTowersDestroyed', 'blueWins']]
df = df.dropna()

# Define features and target
X = df.drop('blueWins', axis=1)
y = df['blueWins']

# Split data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Scale data
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

# Train Logistic Regression Model
model = LogisticRegression(random_state=42)
model.fit(X_train, y_train)
y_pred = model.predict(X_test)

# Display model performance
accuracy = accuracy_score(y_test, y_pred)
st.write("### 🔥 Model Performance")
st.write(f"**✅ Model Accuracy:** {accuracy:.2f}")

# Visualizing performance
st.write("### 📊 Performance Breakdown")
conf_matrix = confusion_matrix(y_test, y_pred)
st.write("Confusion Matrix:")
fig, ax = plt.subplots()
sns.heatmap(conf_matrix, annot=True, fmt='d', cmap='coolwarm', ax=ax)
st.pyplot(fig)

# Feature Importance Visualization
st.write("### 🔍 Feature Importance")
feature_importance = abs(model.coef_[0])
features = X.columns
fig, ax = plt.subplots()
ax.barh(features, feature_importance, color='#4A90E2')
ax.set_title("Feature Importance for Blue Team Win Prediction")
ax.set_xlabel("Importance")
st.pyplot(fig)

# Prediction section
st.write("### 🎮 Predict Game Outcome")
st.markdown("Adjust the stats below to simulate a match scenario!")

first_blood = st.selectbox("Did Blue Team Get First Blood?", [0, 1])
kills = st.slider("Blue Team Kills", min_value=0, max_value=50, value=5)
deaths = st.slider("Blue Team Deaths", min_value=0, max_value=50, value=5)
assists = st.slider("Blue Team Assists", min_value=0, max_value=50, value=10)
total_gold = st.slider("Blue Team Total Gold", min_value=10000, max_value=100000, value=50000)
total_exp = st.slider("Blue Team Total Experience", min_value=10000, max_value=100000, value=50000)
dragons = st.slider("Blue Team Dragons Taken", min_value=0, max_value=5, value=1)
heralds = st.slider("Blue Team Heralds Taken", min_value=0, max_value=2, value=0)
towers = st.slider("Blue Team Towers Destroyed", min_value=0, max_value=11, value=2)

if st.button("✨ Predict Win"):
    input_data = scaler.transform([[first_blood, kills, deaths, assists, total_gold, total_exp, dragons, heralds, towers]])
    prediction = model.predict(input_data)[0]
    prediction_proba = model.predict_proba(input_data)[0]

    st.subheader("🔮 Prediction Result")
    result_text = "🏅 Blue Team is likely to WIN! 🎉" if prediction == 1 else "⚔️ Blue Team is likely to LOSE. 😞"
    st.success(result_text) if prediction == 1 else st.error(result_text)
    st.write(f"Confidence: {prediction_proba[prediction]:.2f}")

    # Win/Loss Bar Chart
    st.write("### 📊 Win Probability Breakdown")
    fig, ax = plt.subplots()
    ax.bar(["Win", "Lose"], [prediction_proba[1], prediction_proba[0]], color=["#64FFDA", "#FF4C4C"])
    ax.set_ylim(0, 1)
    ax.set_ylabel("Probability")
    ax.set_title("Blue Team Win/Loss Probability")
    st.pyplot(fig)