# Import necessary libraries
import numpy as np  # For numerical operations
import joblib  # For loading the serialized model
import pandas as pd  # For data manipulation
from flask import Flask, request, jsonify  # For creating the Flask API
from flask_cors import CORS  # Enable Cross-Origin Resource Sharing (CORS) for the API

# Initialize the Flask application
superkart_sales_api = Flask("SuperKart Sales Predictor")
CORS(superkart_sales_api)

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

# Define a route for the home page (GET request)
@superkart_sales_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 SuperKart Sales Prediction API!"

# Define an endpoint for single product-store prediction (POST request)
@superkart_sales_api.post('/v1/predict')
def predict_sales():
    """
    This function handles POST requests to the '/v1/predict' endpoint.
    It expects a JSON payload containing product and store details and returns
    the predicted sales total as a JSON response.
    """
    try:
        # Get the JSON data from the request body
        input_data = request.get_json()

        # Check if data is provided
        if not input_data:
            return jsonify({'error': 'No data provided'}), 400

        # DataFrame with ALL expected features, filling missing ones with defaults
        expected_features = {
            'Product_Weight': 0.0,
            'Product_Allocated_Area': 0.0,
            'Product_MRP': 0.0,
            'Product_Sugar_Content': 'Missing',
            'Product_Type': 'Missing',
            'Store_Size': 'Missing',
            'Store_Location_City_Type': 'Missing',
            'Store_Type': 'Missing',
            'Store_Age': 0,
            'Product_Category_Code': 0,
            'Store_Age_Group': 'Missing'  # This was the missing feature
        }

        # Update with the provided values, keep defaults for missing ones
        for key in expected_features:
            if key in input_data:
                expected_features[key] = input_data[key]

        # Convert to DataFrame
        input_df = pd.DataFrame([expected_features])

        # Make prediction
        predicted_sales = model.predict(input_df)[0]

        # Convert predicted_sales to Python float and round
        predicted_sales = round(float(predicted_sales), 2)

        # Return the predicted sales
        return jsonify({'Predicted Sales Total': predicted_sales})

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

# Define an endpoint for batch prediction (POST request)
@superkart_sales_api.post('/v1/predictbatch')
def predict_sales_batch():
    """
    This function handles POST requests to the '/v1/predictbatch' endpoint.
    It expects a CSV file containing product-store details for multiple items
    and returns the predicted sales totals as a dictionary in the JSON response.
    """
    try:
        # Get the uploaded CSV file from the request
        file = request.files['file']

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

        # Make predictions for all items in the DataFrame
        predicted_sales = model.predict(input_data)

        # Round the predictions
        predicted_sales = [round(float(sale), 2) for sale in predicted_sales]

        # Create a dictionary of predictions with item IDs as keys
        # Assuming there's an 'item_id' column in your CSV
        if 'item_id' in input_data.columns:
            item_ids = input_data['item_id'].tolist()
            output_dict = dict(zip(item_ids, predicted_sales))
        else:
            # If no ID column, use index as keys
            output_dict = {f"item_{i}": sale for i, sale in enumerate(predicted_sales)}

        # Return the predictions dictionary as a JSON response
        return output_dict
        
    except Exception as e:
        return jsonify({'error': str(e)}), 500

# Run the Flask application
if __name__ == '__main__':
    superkart_sales_api.run(debug=True, host='0.0.0.0', port=5000)