Update app.py

app.py

@@ -3,12 +3,14 @@ import joblib
 import numpy as np
 import json
 import math
+import xgboost as xgb
 
-app = Flask(__name__)  # Corrected from _name_ to __name__
+app = Flask(__name__)
 
 # Load models
-xgb = joblib.load("xgb_model.pkl")
 rf = joblib.load("rf_model.pkl")
+xgb_model = xgb.Booster()
+xgb_model.load_model("xgb_model.json")  # Load the XGBoost model from JSON
 
 # Load tile catalog and sizes
 with open("tile_catalog.json", "r", encoding="utf-8") as f:
@@ -46,8 +48,8 @@ def recommend():
         features = prepare_features(data)
         
         # Get predictions from both models
-        xgb_pred = xgb.predict_proba(features)[0][1]
-        rf_pred = rf.predict_proba(features)[0][1]
+        xgb_pred = xgb_model.predict(xgb.DMatrix(features))[0]  # XGBoost prediction
+        rf_pred = rf.predict_proba(features)[0][1]  # Random Forest prediction
         combined_score = (xgb_pred + rf_pred) / 2
         
         # Filter products based on criteria
@@ -170,5 +172,5 @@ def calculate_requirements(area, coverage):
         ]
     }
 
-if __name__ == '__main__':  # Corrected from _name_ to __name__
+if __name__ == '__main__':
     app.run(host='0.0.0.0', port=5000, debug=True)