from flask import Flask, request, jsonify
import joblib
import pandas as pd
import numpy as np # Import numpy to handle numpy data types

# Load the saved model pipeline
model = joblib.load("SuperKart_prediction_model_v1_0.joblib")

app = Flask(__name__)

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

@app.route('/predict', methods=['POST'])
def predict():
    try:
        # Get the data from the request
        data = request.get_json(force=True)

        # Convert the data to a pandas DataFrame
        # Ensure the column order matches the training data used for the pipeline
        # The keys in the input JSON should match the original column names in X_train
        input_data = pd.DataFrame([data])

        # Make prediction using the loaded model pipeline
        prediction = model.predict(input_data)

        # Convert the prediction (which is a NumPy float) to a standard Python float
        predicted_value = float(prediction[0])

        # Return the prediction as JSON
        return jsonify({'prediction': predicted_value})

    except Exception as e:
        return jsonify({'error': str(e)})

if __name__ == '__main__':
    # You can run this locally for testing
    # app.run(debug=True)
    pass # This is for deployment, Flask will be run by the serving environment