Update app.py

app.py

@@ -1,62 +1,66 @@
-# Import necessary libraries
 import os
 import joblib
 import pandas as pd
 from flask import Flask, request, jsonify
 
 # Initialize Flask app
-superkart_api = Flask("SuperKart")
+app = Flask("SuperKart")
 
-# Global model variable (lazy loading)
+MODEL_PATH = "superkart_model.joblib"
 model = None
-MODEL_PATH = "superkart_model_v1_0.joblib"
 
 
 def load_model():
-    """
-    Load the model only once when first needed.
-    Prevents Hugging Face startup crashes.
-    """
     global model
     if model is None:
         if not os.path.exists(MODEL_PATH):
-            raise FileNotFoundError(f"Model file not found: {MODEL_PATH}")
+            raise FileNotFoundError(f"Model not found: {MODEL_PATH}")
         model = joblib.load(MODEL_PATH)
 
 
-# Health check endpoint (IMPORTANT for Hugging Face Spaces)
-@superkart_api.get("/")
-def home():
-    return "SuperKart API is running"
+# Health check (required by Hugging Face Spaces)
+@app.route("/", methods=["GET"])
+def health():
+    return "SuperKart Backend is running"
 
 
-# Prediction endpoint
-@superkart_api.post("/v1/predict")
-def predict_sales():
+# Prediction endpoint (MATCHES STREAMLIT)
+@app.route("/predict", methods=["POST"])
+def predict():
     try:
         load_model()
 
         data = request.get_json(force=True)
 
-        # Enforce correct feature schema
-        sample = {
-            "Product_Weight": data["Product_Weight"],
-            "Product_Sugar_Content": data["Product_Sugar_Content"],
-            "Product_Allocated_Area": data["Product_Allocated_Area"],
-            "Product_MRP": data["Product_MRP"],
-            "Store_Size": data["Store_Size"],
-            "Store_Location_City_Type": data["Store_Location_City_Type"],
-            "Store_Type": data["Store_Type"],
-            "Product_Id_char": data["Product_Id_char"],
-            "Store_Age_Years": data["Store_Age_Years"],
-            "Product_Type_Category": data["Product_Type_Category"],
-        }
+        # Convert incoming list-based JSON to DataFrame
+        df = pd.DataFrame(data)
 
-        input_df = pd.DataFrame([sample])
+        # -------------------------------
+        # FEATURE ENGINEERING (IMPORTANT)
+        # -------------------------------
 
-        prediction = model.predict(input_df)[0]
+        # Store_Age_Years = 2025 - Store_Establishment_Year
+        if "Store_Establishment_Year" in df.columns:
+            df["Store_Age_Years"] = 2025 - df["Store_Establishment_Year"]
+            df.drop(columns=["Store_Establishment_Year"], inplace=True)
 
-        return jsonify({"Sales": float(prediction)})
+        # Product_Id_char (dummy but required by model)
+        if "Product_Id_char" not in df.columns:
+            df["Product_Id_char"] = "A"
+
+        # Product_Type_Category (same as Product_Type)
+        if "Product_Type" in df.columns:
+            df["Product_Type_Category"] = df["Product_Type"]
+            df.drop(columns=["Product_Type"], inplace=True)
+
+        # -------------------------------
+        # PREDICTION
+        # -------------------------------
+        prediction = model.predict(df)
+
+        return jsonify({
+            "predictions": prediction.tolist()
+        })
 
     except KeyError as e:
         return jsonify({"error": f"Missing field: {str(e)}"}), 400
@@ -64,6 +68,6 @@ def predict_sales():
         return jsonify({"error": str(e)}), 500
 
 
-# Run app (Hugging Face requires port 7860)
+# Run on Hugging Face required port
 if __name__ == "__main__":
-    superkart_api.run(host="0.0.0.0", port=7860)
+    app.run(host="0.0.0.0", port=7860)