Download app.py from BujjiProjectPrep/SalesForecastModelBackend: direct link, hf CLI and curl.
- Browser
- Download file 2.43 kB
-
https://huggingface.co/spaces/BujjiProjectPrep/SalesForecastModelBackend/resolve/main/app.py
- Command line
-
hf download hf://spaces/BujjiProjectPrep/SalesForecastModelBackend/app.py
-
curl -L -o app.py https://huggingface.co/spaces/BujjiProjectPrep/SalesForecastModelBackend/resolve/main/app.py
2.43 kB
| import joblib | |
| import pandas as pd | |
| from flask import Flask, request, jsonify | |
| # Initialize the Flask application | |
| superkart_sales_api = Flask("SuperKart Sales Forecast API") | |
| model = joblib.load("sales_forecast_model_v1_0.joblib") | |
| EXPECTED_FEATURES = [ | |
| "Product_Weight", | |
| "Product_Allocated_Area", | |
| "Product_MRP", | |
| "Store_Age", | |
| "Product_Sugar_Content", | |
| "Product_Type", | |
| "Store_Size", | |
| "Store_Location_City_Type", | |
| "Store_Type", | |
| ] | |
| # Define a route for the home page (GET request) | |
| def home(): | |
| """ | |
| Handles GET requests to the root URL ('/'). | |
| Returns a simple welcome message and the expected schema. | |
| """ | |
| return "Welcome to the SuperKart Sales Forecast API!" | |
| # Define an endpoint for single sales prediction (POST request) | |
| def predict_sales(): | |
| """ | |
| Handles POST requests to the '/v1/sales' endpoint. | |
| Expects a JSON payload with SuperKart product & store features and | |
| returns the predicted Product_Store_Sales_Total as JSON. | |
| Example payload: | |
| { | |
| "Product_Weight": 12.5, | |
| "Product_Allocated_Area": 0.06, | |
| "Product_MRP": 150, | |
| "Store_Age": 16, | |
| "Product_Sugar_Content": "Regular", | |
| "Product_Type": "Snack Foods", | |
| "Store_Size": "Medium", | |
| "Store_Location_City_Type": "Tier 2", | |
| "Store_Type": "Supermarket Type 2" | |
| } | |
| """ | |
| try: | |
| payload = request.get_json() | |
| # Basic validation: ensure all required features are present | |
| missing = [f for f in EXPECTED_FEATURES if f not in payload] | |
| if missing: | |
| return jsonify({ | |
| "error": "Missing required feature(s).", | |
| "missing": missing, | |
| "expected_features": EXPECTED_FEATURES | |
| }), 400 | |
| # Build a single-row DataFrame in the expected feature order | |
| sample = {f: payload[f] for f in EXPECTED_FEATURES} | |
| input_df = pd.DataFrame([sample]) | |
| # Predict sales (model outputs actual sales; no log transform) | |
| pred = model.predict(input_df)[0] | |
| pred = round(float(pred), 2) | |
| return jsonify({"Predicted Product_Store_Sales_Total": pred}) | |
| except Exception as e: | |
| return jsonify({"error": str(e)}), 500 | |
| # Run the Flask application in debug mode if this script is executed directly | |
| if __name__ == "__main__": | |
| superkart_sales_api.run(debug=True) | |