from flask import Flask, request, jsonify
import joblib
import pandas as pd
import numpy as np

app = Flask("Sales Prediction")

# Load the serialized model
model = joblib.load('best_sales_forecasting_model.joblib')

@app.route('/', methods=['GET'])
def home():
    return jsonify({"status": "running", "message": "Sales Prediction API is live"})

@app.route('/predict_single', methods=['POST'])
def predict_single():
    """
    API endpoint for single prediction.
    Expects a JSON object with the features for one product-store combination.
    """
    try:
        data = request.get_json(force=True)
        # Convert the dictionary to a pandas DataFrame
        df = pd.DataFrame([data])
        # Ensure columns are in the same order as during training
        df = df[model.feature_names_in_]
        prediction = model.predict(df)
        # Return the prediction as a JSON response
        return jsonify({'prediction': prediction[0].tolist()})
    except Exception as e:
        return jsonify({'error': str(e)})

@app.route('/predict_batch', methods=['POST'])
def predict_batch():
    """
    API endpoint for batch predictions.
    Expects a JSON array of JSON objects, where each object is a product-store combination.
    """
    try:
        data = request.get_json(force=True)
        # Convert the list of dictionaries to a pandas DataFrame
        df = pd.DataFrame(data)
        # Ensure columns are in the same order as during training
        df = df[model.feature_names_in_]
        predictions = model.predict(df)
        # Return the predictions as a JSON response
        return jsonify({'predictions': predictions.tolist()})
    except Exception as e:
        return jsonify({'error': str(e)})

# if __name__ == '__main__':
#     # Run the Flask app
#     # Setting debug=True allows for automatic reloading and provides a debugger
#     app.run(debug=True, host='0.0.0.0', port=7860)