Upload app.py with huggingface_hub

app.py

@@ -0,0 +1,47 @@
+from flask import Flask,jsonify
+
+# Initialize Flask app
+superKart_Sales_forecast = Flask("SuperKart Sales Forecast")
+
+# Load the serialized model
+try:
+    loaded_model = joblib.load('tuned_random_forest_model.pkl')
+    print("Model loaded successfully!")
+except Exception as e:
+    print(f"Error loading model: {e}")
+    loaded_model = None # Set model to None if loading fails
+
+
+@superKart_Sales_forecast.route('/predict', methods=['POST'])
+def predict():
+    if loaded_model is None:
+        return jsonify({'error': 'Model not loaded'}), 500
+
+    try:
+        # Get data from the request
+        data = request.get_json(force=True)
+        # Convert the incoming data to a pandas DataFrame
+        # Assuming the incoming data is a list of dictionaries, where each dictionary is a row
+        # The columns should match the features used during training (excluding the target)
+        input_df = pd.DataFrame(data)
+
+        # Ensure the columns are in the same order as the training data
+        # You might need to store the order of columns from X_train during training
+        # For now, assuming input_df columns match X_train columns
+        # A more robust solution would involve saving and loading the column order
+        # For demonstration, let's assume the column order is consistent
+
+        # Make predictions
+        predictions = loaded_model.predict(input_df)
+
+        # Convert predictions to a list and return as JSON
+        return jsonify(predictions.tolist())
+
+    except Exception as e:
+        return jsonify({'error': str(e)}), 400
+
+# To run the Flask superKart_Sales_forecast (for local testing)
+#if __name__ == '__main__':
+#     # This will run the server locally on port 5000
+#     # In a production environment, you would use a production-ready server like Gunicorn or uWSGI
+#      superKart_Sales_forecast.run(debug=True, host='0.0.0.0', port=5000)