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

# Initialize Flask app with a name
product_sales_predictor_api = Flask("Product Sales Predictor")

# Load the trained churn prediction model
model = joblib.load("product_sales_prediction_model_v1_0.joblib")

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

# Define an endpoint to predict sales for a single product
@product_sales_predictor_api.post('/v1/product')
def predict_sales():
    # Get JSON data from the request
    product_sales = request.get_json()

    # Extract relevant product features from the input data
    sample = {
        'Product_Weight': product_sales['Product_Weight'],
        'Product_Sugar_Content': product_sales['Product_Sugar_Content'],
        'Product_Allocated_Area': product_sales['Product_Allocated_Area'],
        'Product_Type': product_sales['Product_Type'],
        'Product_MRP': product_sales['Product_MRP'],
        'Store_Id': product_sales['Store_Id'],
        'Store_Establishment_Year': product_sales['Store_Establishment_Year'],
        'Store_Size': product_sales['Store_Size'],
        'Store_Location_City_Type': product_sales['Store_Location_City_Type'],
        'Store_Type': product_sales['Store_Type']
    }

    # Convert the extracted data into a DataFrame
    input_data = pd.DataFrame([sample])
    print('inside post')
    print(input_data)
    print(model.predict(input_data).tolist()[0])

    # Make a sales prediction using the trained model and convert to float
    predicted_sales = model.predict(input_data).tolist()[0]
    predicted_sales = round(float(predicted_sales),2)

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

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

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

    # Make predictions for the batch data and convert raw predictions into a readable format
    predicted_sales = [round(float(sales),2) for sales in model.predict(input_data).tolist()]

    # Create a dictionary of predictions with Product ID and Predicted sales
    product_id = input_data['Product_ID'].tolist()  # Assuming id as the key or product id
    output_dict = dict(zip(product_id, predicted_sales))  # Sales value

    # Return the predictions dictionary as a JSON response
    return output_dict

# Run the Flask app in debug mode
if __name__ == '__main__':
    product_sales_predictor_api.run(host='0.0.0.0', port=8501, debug=True)