# Import necessary libraries
import numpy as np
import joblib  # For loading the serialized model
import pandas as pd  # For data manipulation
import os
from flask import Flask, request, jsonify  # For creating the Flask API

# Initialize the Flask application
revenue_predictor_api = Flask("Revenue Predictor")

# Load the trained machine learning model
#model = joblib.load("revenue_prediction_model_v1_0.joblib")

model = joblib.load(os.path.join(os.path.dirname(__file__), "revenue_prediction_model_v1_0.joblib"))
print("Model loaded successfully!")

# Define a route for the home page (GET request)
@revenue_predictor_api.get('/')
def home():
    """
    This function handles GET requests to the root URL ('/') of the API.
    It returns a simple welcome message.
    """
    return "Welcome to the Revenue Prediction API!"

# Define an endpoint for single product revenue prediction (POST request)
@revenue_predictor_api.post('/v1/revenue')
def predict_revenue():
    """
    This function handles POST requests to the '/v1/revenue' endpoint.
    It expects a JSON payload containing property details and returns
    the predicted rental price as a JSON response.
    """
    # Get the JSON data from the request body
    property_data = request.get_json()

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

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

    # Make prediction (get sales_total)
    predicted_sales_total = model.predict(input_data)[0]

    # Calculate actual sales
    predicted_total = np.exp(predicted_sales_total)

    # Convert predicted_total to Python float
    predicted_total = round(float(predicted_total), 2)
    # The conversion above is needed as we convert the model prediction (sales_total) to actual sales using np.exp, which returns predictions as NumPy float32 values.
    # When we send this value directly within a JSON response, Flask's jsonify function encounters a datatype error

    # Return the actual sales
    return jsonify({'Predicted Sales Total (in dollars)': predicted_total})


# Run the Flask application in debug mode if this script is executed directly
if __name__ == '__main__':
    #revenue_predictor_api.run(debug=True)
    port = int(os.environ.get("PORT", 7860))  # Hugging Face provides PORT
    revenue_predictor_api.run(host="0.0.0.0", port=port, debug=True)