Upload folder using huggingface_hub

Dockerfile

@@ -2,4 +2,5 @@ FROM python:3.9-slim
 WORKDIR /app
 COPY . .
 RUN pip install --no-cache-dir -r requirements.txt
+# Important: app:app refers to app.py and the Flask instance named 'app'
 CMD ["gunicorn", "-w", "4", "-b", "0.0.0.0:7860", "app:app"]

Extraalearn.joblib

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24baf43ea0f346143f13d01b29bdfdb621b557660f1395a07cfc80ae2b7bc708
-size 143796
+oid sha256:ac845d7fb46e64e4860caffd4e491dba9a6c3bdd652d55e1d2c0ae7a4a4fed98
+size 143810

app.py

@@ -3,12 +3,13 @@ import joblib
 import pandas as pd
 from flask import Flask, request, jsonify
 
-# Initialize Flask app
+# Create the Flask app
 app = Flask(__name__)
 
 # Load the model
 model = joblib.load('Extraalearn.joblib')
 
+# Define the expected feature columns from training (excluding 'status')
 EXPECTED_FEATURES = [
     'age', 'website_visits', 'time_spent_on_website', 'page_views_per_visit',
     'current_occupation_Student', 'current_occupation_Unemployed',
@@ -21,33 +22,51 @@ EXPECTED_FEATURES = [
 
 @app.get('/')
 def home():
-    return 'ExtraaLearn Lead Conversion API is Running'
+    return 'ExtraaLearn API is Running'
 
 @app.post('/v1/predict')
-def predict():
+def predict_conversion_probability(): # Renamed endpoint for clarity
     try:
         data = request.get_json()
-        p = {}
-        p['age'] = float(data.get('age', 0))
-        p['website_visits'] = float(data.get('website_visits', 0))
-        p['time_spent_on_website'] = float(data.get('time_spent_on_website', 0))
-        p['page_views_per_visit'] = float(data.get('page_views_per_visit', 0))
-        p['current_occupation_Student'] = 1 if data.get('current_occupation') == 'Student' else 0
-        p['current_occupation_Unemployed'] = 1 if data.get('current_occupation') == 'Unemployed' else 0
-        p['first_interaction_Website'] = 1 if data.get('first_interaction') == 'Website' else 0
-        p['profile_completed_Low'] = 1 if data.get('profile_completed') == 'Low' else 0
-        p['profile_completed_Medium'] = 1 if data.get('profile_completed') == 'Medium' else 0
-        p['last_activity_Phone Activity'] = 1 if data.get('last_activity') == 'Phone Activity' else 0
-        p['last_activity_Website Activity'] = 1 if data.get('last_activity') == 'Website Activity' else 0
-        p['print_media_type1_Yes'] = 1 if data.get('print_media_type1') == 'Yes' else 0
-        p['print_media_type2_Yes'] = 1 if data.get('print_media_type2') == 'Yes' else 0
-        p['digital_media_Yes'] = 1 if data.get('digital_media') == 'Yes' else 0
-        p['educational_channels_Yes'] = 1 if data.get('educational_channels') == 'Yes' else 0
-        p['referral_Yes'] = 1 if data.get('referral') == 'Yes' else 0
-
-        df_final = pd.DataFrame([p])[EXPECTED_FEATURES]
-        prediction_proba = model.predict_proba(df_final)[:, 1].tolist()[0]
-        return jsonify({'Conversion_Probability': float(prediction_proba)})
+
+        # Create a dictionary to hold the processed features
+        processed_data = {}
+
+        # 1. Map Numerical Features
+        processed_data['age'] = float(data.get('age', 0))
+        processed_data['website_visits'] = float(data.get('website_visits', 0))
+        processed_data['time_spent_on_website'] = float(data.get('time_spent_on_website', 0))
+        processed_data['page_views_per_visit'] = float(data.get('page_views_per_visit', 0))
+
+        # 2. Map Categorical Features (One-Hot Encoding logic)
+        # Note: 'Professional', 'Mobile App', 'High', 'Email Activity', and 'No' are the baselines (drop_first)
+
+        occ = data.get('current_occupation', '')
+        processed_data['current_occupation_Student'] = 1 if occ == 'Student' else 0
+        processed_data['current_occupation_Unemployed'] = 1 if occ == 'Unemployed' else 0
+
+        processed_data['first_interaction_Website'] = 1 if data.get('first_interaction', '') == 'Website' else 0
+
+        prof = data.get('profile_completed', '')
+        processed_data['profile_completed_Low'] = 1 if prof == 'Low' else 0
+        processed_data['profile_completed_Medium'] = 1 if prof == 'Medium' else 0
+
+        last = data.get('last_activity', '')
+        processed_data['last_activity_Phone Activity'] = 1 if last == 'Phone Activity' else 0
+        processed_data['last_activity_Website Activity'] = 1 if last == 'Website Activity' else 0
+
+        processed_data['print_media_type1_Yes'] = 1 if data.get('print_media_type1', '') == 'Yes' else 0
+        processed_data['print_media_type2_Yes'] = 1 if data.get('print_media_type2', '') == 'Yes' else 0
+        processed_data['digital_media_Yes'] = 1 if data.get('digital_media', '') == 'Yes' else 0
+        processed_data['educational_channels_Yes'] = 1 if data.get('educational_channels', '') == 'Yes' else 0
+        processed_data['referral_Yes'] = 1 if data.get('referral', '') == 'Yes' else 0
+
+        # Convert dictionary to DataFrame with the exact training order
+        df_final = pd.DataFrame([processed_data])[EXPECTED_FEATURES]
+
+        # Predict probability of conversion (positive class is 1)
+        prediction_proba = model.predict_proba(df_final)[:, 1].tolist()[0] # Use predict_proba
+        return jsonify({'Conversion_Probability': float(prediction_proba)}) # Changed key to Conversion_Probability
     except Exception as e:
         return jsonify({'error': str(e)}), 400
 

requirements.txt

@@ -4,6 +4,10 @@ scikit-learn==1.6.1
 seaborn==0.13.2
 joblib==1.4.2
 xgboost==2.1.4
+joblib==1.4.2
+Werkzeug==2.2.2
 flask==2.2.2
 gunicorn==20.1.0
 requests==2.32.3
+uvicorn[standard]
+streamlit==1.43.2