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

# Initialize Flask app
super_kart_api = Flask("Super Kart Product Sales Predictor")

# Load the trained model
model = joblib.load("super_kart_model_v1_0.joblib")

# Define a route for the home page
@super_kart_api.get('/')
def home():
    return "Welcome to the Super Kart Product Sales Prediction API!"

# Define an endpoint to predict price for a single product
@super_kart_api.post('/v1/product')
def predict_product_sales_price():
    # Get JSON data from the request
    product_data = request.get_json()
    current_year = datetime.now().year

    # Extract relevant product features from the input data
    sample = {
        'Product_Weight': product_data['Product_Weight'],
        'Product_Sugar_Content': product_data['Product_Sugar_Content'],
        'Product_Type': product_data['Product_Type'],
        'Product_MRP': product_data['Product_MRP'],
        'Store_Id': product_data['Store_Id'],
        'Store_Size': product_data['Store_Size'],
        'Store_Location_City_Type': product_data['Store_Location_City_Type'],
        'Store_Type': product_data['Store_Type'],
        'Store_Age': int(current_year - product_data['Store_Establishment_Year'])
    }

    # Convert the extracted data into a DataFrame
    input_data = pd.DataFrame([sample])

    # Make a prediction using the trained model
    prediction = model.predict(input_data).tolist()[0]

    # Return the prediction as a JSON response
    return jsonify({'Predicted_Product_Sales': prediction})

# Define an endpoint to predict product sales price for a batch of product
@super_kart_api.post('/v1/productbatch')
def predict_product_batch():
   # Get the uploaded CSV file from the request
    file = request.files['file']

    # Read the file into a DataFrame
    data = pd.read_csv(file)

    current_year = datetime.now().year
    input_data = data.copy()
    input_data['Store_Establishment_Year'] = pd.to_numeric(input_data['Store_Establishment_Year'], errors='coerce')
    input_data['Store_Age'] = current_year - input_data['Store_Establishment_Year']
    input_data = input_data.drop(['Product_Id','Store_Establishment_Year','Product_Allocated_Area'],axis=1)

    #Data Cleaning
    input_data["Product_Sugar_Content"] = input_data["Product_Sugar_Content"].replace("reg", "Regular")

    # Make predictions for the batch data
    predictions = model.predict(input_data).tolist()

    # Add predictions to the DataFrame
    data['Predicted_Product_Sales'] = predictions

    # Convert results to dictionary
    result = data.to_dict(orient="records")

    return jsonify(result)


# Run the Flask app in debug mode
if __name__ == '__main__':
    super_kart_api.run(debug=True)