Upload app.py with huggingface_hub

app.py

@@ -0,0 +1,121 @@
+
+from flask import Flask, request, jsonify
+import joblib
+import pandas as pd
+from datetime import datetime
+
+app = Flask(__name__)
+
+print("Starting SuperKart API...")
+
+# Load complete pipeline
+try:
+    pipeline = joblib.load('superkart_complete_pipeline.joblib')
+    print("Complete pipeline loaded successfully")
+except Exception as e:
+    print(f"Error loading pipeline: {e}")
+    pipeline = None
+
+@app.route('/')
+def home():
+    return jsonify({
+        "message": "SuperKart Sales Prediction API",
+        "status": "active",
+        "model_loaded": pipeline is not None,
+        "endpoints": {
+            "predict": "/predict",
+            "health": "/health"
+        }
+    })
+
+@app.route('/health')
+def health():
+    return jsonify({
+        "status": "healthy",
+        "model_loaded": pipeline is not None,
+        "timestamp": datetime.now().isoformat()
+    })
+
+@app.route('/predict', methods=['POST'])
+def predict():
+    try:
+        if pipeline is None:
+            return jsonify({
+                "error": "Pipeline not loaded",
+                "status": "error"
+            }), 500
+            
+        data = request.get_json()
+        if not data:
+            return jsonify({
+                "error": "No input data provided",
+                "status": "error"
+            }), 400
+        
+        # Dynamic feature engineering in backend
+        current_year = datetime.now().year
+        
+        # Calculate Store_Age dynamically
+        if 'Store_Establishment_Year' in data:
+            data['Store_Age'] = current_year - data['Store_Establishment_Year']
+        
+        # Extract Product_Category_Code from Product_Id
+        if 'Product_Id' in data:
+            data['Product_Category_Code'] = data['Product_Id'][:2]
+            # Remove Product_Id as it's not needed for model input
+            data.pop('Product_Id')
+        
+        # Required fields for model input (including derived features)
+        required_fields = [
+            'Product_Weight', 'Product_Sugar_Content', 'Product_Allocated_Area',
+            'Product_Type', 'Product_MRP', 'Store_Establishment_Year',
+            'Store_Size', 'Store_Location_City_Type', 'Store_Type'
+        ]
+        
+        missing_fields = [field for field in required_fields if field not in data]
+        if missing_fields:
+            return jsonify({
+                "error": f"Missing required fields: {missing_fields}",
+                "status": "error"
+            }), 400
+        
+        # Create DataFrame for prediction (using only base features for model)
+        model_features = [
+            'Product_Weight', 'Product_Sugar_Content', 'Product_Allocated_Area',
+            'Product_Type', 'Product_MRP', 'Store_Establishment_Year',
+            'Store_Size', 'Store_Location_City_Type', 'Store_Type'
+        ]
+        
+        input_dict = {k: data[k] for k in model_features if k in data}
+        input_df = pd.DataFrame([input_dict])
+        
+        print(f"Input data: {input_dict}")
+        
+        # Make prediction using complete pipeline
+        prediction = pipeline.predict(input_df)
+        
+        print(f"Prediction: ${prediction[0]:.2f}")
+        
+        return jsonify({
+            "prediction": float(prediction[0]),
+            "status": "success",
+            "derived_features": {
+                "store_age": data.get('Store_Age'),
+                "product_category_code": data.get('Product_Category_Code')
+            },
+            "input_summary": {
+                "product_type": data.get('Product_Type'),
+                "store_type": data.get('Store_Type'),
+                "mrp": data.get('Product_MRP')
+            }
+        })
+        
+    except Exception as e:
+        print(f"Prediction error: {str(e)}")
+        return jsonify({
+            "error": str(e),
+            "status": "error"
+        }), 500
+
+if __name__ == '__main__':
+    app.run(host='0.0.0.0', port=7860, debug=False)