Update app.py

app.py

@@ -8,10 +8,11 @@ from flask_cors import CORS
 app = Flask("Engineering College General Predictor")
 CORS(app)
 
-# Load trained model & helpers
-pipeline = joblib.load('pipeline.pkl')
-target_encoder = joblib.load('target_encoder.pkl')
-choice_code_map = pd.read_csv('choice_code_map.csv',index_col='Choice Code')
+# 🔷 Load trained model & helpers from backend_files/
+pipeline = joblib.load('xgb_best_model.joblib')
+target_encoder = joblib.load('label_encoder.joblib')
+feature_columns = joblib.load('feature_columns.joblib')
+choice_code_map = pd.read_csv('choice_code_map.csv', index_col='Choice Code')
 
 # Home route
 @app.get('/')
@@ -33,12 +34,15 @@ def predict():
 
         # Build DataFrame
         sample_df = pd.DataFrame([{
-        'Category': data['Category'],
-        'Rank': data['Rank'],
-        'Percentage': data['Percentage'],   
-        'Course Name': data['Course Name']
+            'Category': data['Category'],
+            'Rank': data['Rank'],
+            'Percentage': data['Percentage'],   
+            'Course Name': data['Course Name']
         }])
 
+        # 🔷 Ensure column order matches training
+        sample_df = sample_df[feature_columns]
+
         # Predict probabilities
         proba = pipeline.predict_proba(sample_df)[0]
 
@@ -70,4 +74,4 @@ def predict():
 
 # Run server
 if __name__ == '__main__':
-    app.run(debug=False, host='0.0.0.0', port=7860)
+    app.run(debug=False, host='0.0.0.0', port=7860)