# Import necessary libraries
import numpy as np
import joblib
import pandas as pd
from flask import Flask, request, jsonify

# Initialize the Flask application
superkart_sales_forecast_api = Flask("SuperKart Sales Forecast API")

# Load the trained machine learning model
model = joblib.load("superkart_sales_prediction.joblib", mmap_mode=None)

# ---------------- Home Route ----------------
@superkart_sales_forecast_api.get('/')
def home():
    """
    Handles GET requests to the root URL ('/').
    Returns a welcome message.
    """
    return "Welcome to the SuperKart Sales Forecast API!"

# ---------------- Online Forecast Route ----------------
@superkart_sales_forecast_api.post('/v1/sales')
def predict_sales_forecast():
    """
    Handles POST requests to '/v1/sales'.
    Expects a JSON payload of product-store details.
    Returns the predicted sales total.
    """
    try:
        forecast_data = request.get_json()

        sample = {
            'Product_Weight': float(forecast_data['Product_Weight']),
            'Product_MRP': float(forecast_data['Product_MRP']),
            'Product_Sugar_Content': forecast_data['Product_Sugar_Content'],
            'Product_Allocated_Area': float(forecast_data['Product_Allocated_Area']),
            'Product_Type': forecast_data['Product_Type'],
            'Store_Id': forecast_data['Store_Id'],
            'Store_Establishment_Year': int(forecast_data['Store_Establishment_Year']),
            'Store_Size': forecast_data['Store_Size'],
            'Store_Location_City_Type': forecast_data['Store_Location_City_Type'],
            'Store_Type': forecast_data['Store_Type']
        }

        input_df = pd.DataFrame([sample])
        prediction = model.predict(input_df)
        predicted_sales = round(float(prediction[0]), 2)

        return jsonify({'predicted_product_store_sales_total': predicted_sales})
    except Exception as e:
        return jsonify({'error': str(e)}), 500

# ---------------- Batch Forecast Route ----------------
@superkart_sales_forecast_api.post('/v1/salesbatch')
def predict_sales_forecast_batch():
    """
    Handles POST requests to '/v1/salesbatch'.
    Expects a CSV file with product-store rows.
    Returns predicted sales totals per row.
    """
    try:
        file = request.files.get('file')
        if file is None:
            return jsonify({"error": "No file uploaded"}), 400

        input_df = pd.read_csv(file)

        # Predict using the trained model
        predictions = model.predict(input_df)
        input_df["predicted_product_store_sales_total"] = [round(float(x), 2) for x in predictions]

        return jsonify(input_df.to_dict(orient="records"))
    except Exception as e:
        return jsonify({'error': str(e)}), 500

# ---------------- Run the Flask App ----------------
if __name__ == '__main__':
    superkart_sales_forecast_api.run(host='0.0.0.0', port=7860, debug=True)