Upload folder using huggingface_hub

app.py

@@ -3,13 +3,23 @@ import joblib
 import pandas as pd
 from flask import Flask, request, jsonify
 
-# Create the Flask app - the name 'app' is standard for Gunicorn
+# Create the Flask app
 app = Flask(__name__)
 
-# Load the model from the local directory inside the container
-# Note: backend_files contains Extraalearn.joblib, so in the container it's just 'Extraalearn.joblib'
+# 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',
+    'first_interaction_Website', 'profile_completed_Low',
+    'profile_completed_Medium', 'last_activity_Phone Activity',
+    'last_activity_Website Activity', 'print_media_type1_Yes',
+    'print_media_type2_Yes', 'digital_media_Yes',
+    'educational_channels_Yes', 'referral_Yes'
+]
+
 @app.get('/')
 def home():
     return 'ExtraaLearn API is Running'
@@ -18,8 +28,25 @@ def home():
 def predict_sales():
     try:
         data = request.get_json()
-        input_data = pd.DataFrame([data])
-        prediction = model.predict(input_data).tolist()[0]
+        # Convert input to DataFrame
+        df_input = pd.DataFrame([data])
+        
+        # Apply One-Hot Encoding to match training preprocessing
+        categorical_cols = ['current_occupation', 'first_interaction', 'profile_completed', 
+                           'last_activity', 'print_media_type1', 'print_media_type2', 
+                           'digital_media', 'educational_channels', 'referral']
+        
+        df_encoded = pd.get_dummies(df_input, columns=categorical_cols, dtype=int)
+        
+        # Ensure all columns from training are present (add missing as 0)
+        for col in EXPECTED_FEATURES:
+            if col not in df_encoded.columns:
+                df_encoded[col] = 0
+        
+        # Reorder columns to match training set exactly
+        df_encoded = df_encoded[EXPECTED_FEATURES]
+        
+        prediction = model.predict(df_encoded).tolist()[0]
         return jsonify({'Sales': float(prediction)})
     except Exception as e:
         return jsonify({'error': str(e)}), 400