app.py

# backend_files/app.py

from flask import Flask, request, jsonify
import joblib
import pandas as pd
import os
import datetime


app = Flask(__name__)

# Load model
#model = joblib.load('random_forest_best_model.pkl')
model = joblib.load('bagging_best_model.pkl')

@app.route('/')
def home():
    return "SuperKart Sales Forecasting API"

# @app.route('/predict', methods=['POST'])
# def predict():
#     try:
#         data = request.json
#         features = [
#             'Product_Id', 'Product_Weight', 'Product_Sugar_Content',
#             'Product_Allocated_Area', 'Product_Type', 'Product_MRP',
#             'Store_Id', 'Store_Establishment_Year', 'Store_Size',
#             'Store_Location_City_Type', 'Store_Type'
#         ]
#         df = pd.DataFrame([data], columns=features)
        
#         prediction = model.predict(df)
#         return jsonify({'prediction': float(prediction[0])})
    
#     except Exception as e:
#         return jsonify({'error': str(e)}), 400

@app.route('/predict', methods=['POST'])
def predict():
    try:
        # Parse incoming JSON
        data = request.get_json()

        # Convert to DataFrame
        input_df = pd.DataFrame([data])

        # Calculate Store_Age
        current_year = datetime.datetime.now().year
        if 'Store_Establishment_Year' in input_df.columns:
            input_df['Store_Age'] = current_year - input_df['Store_Establishment_Year']
            input_df.drop('Store_Establishment_Year', axis=1, inplace=True)
        else:
            return jsonify({"error": "Missing 'Store_Establishment_Year'"}), 400

        # Predict
        prediction = model.predict(input_df)
        return jsonify({"prediction": round(prediction[0], 2)})

    except Exception as e:
        return jsonify({"error": str(e)}), 400

if __name__ == '__main__':
    #port = int(os.environ.get('PORT', 5000))
    port = int(os.environ.get('PORT', 7860))
    app.run(host='0.0.0.0', port=port)