Download app.py from bhumitps/md-be: direct link, hf CLI and curl.
- Browser
- Download file 1.44 kB
-
https://huggingface.co/spaces/bhumitps/md-be/resolve/main/app.py
- Command line
-
hf download hf://spaces/bhumitps/md-be/app.py
-
curl -L -o app.py https://huggingface.co/spaces/bhumitps/md-be/resolve/main/app.py
1.44 kB
| import os | |
| from flask import Flask, request, jsonify | |
| import joblib | |
| import pandas as pd | |
| # Create a Flask application instance | |
| app = Flask(__name__) | |
| # Define model path | |
| MODEL_DIR = "model_artifacts" | |
| MODEL_FILENAME = "best_sales_forecast_model.joblib" | |
| MODEL_PATH = os.path.join(MODEL_DIR, MODEL_FILENAME) | |
| # Load model at startup | |
| try: | |
| model = joblib.load(MODEL_PATH) | |
| print(" Model loaded successfully!") | |
| except Exception as e: | |
| print(f" Error loading model: {e}") | |
| model = None | |
| # Health check route | |
| def index(): | |
| return jsonify({"status": "Backend is running!"}) | |
| # Prediction route | |
| def predict(): | |
| if model is None: | |
| return jsonify({"error": "Model not loaded"}), 500 | |
| try: | |
| # Get request JSON | |
| data = request.get_json(force=True) | |
| if not data: | |
| return jsonify({"error": "No input data provided"}), 400 | |
| # Convert to DataFrame | |
| df = pd.DataFrame(data) | |
| # Drop ID column if present, as it's not used in prediction | |
| if "Product_Id" in df.columns: | |
| df = df.drop("Product_Id", axis=1) | |
| # Predict | |
| predictions = model.predict(df) | |
| return jsonify({"predictions": predictions.tolist()}) | |
| except Exception as e: | |
| return jsonify({"error": str(e)}), 400 | |
| # Entry point | |
| if __name__ == "__main__": | |
| app.run(host="0.0.0.0", port=5000) | |