app.py

# Import necessary libraries
import numpy as np
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
import io

# Initialize the Flask application
product_sales_price_predictor_api = Flask("SuperKart Product Sales Predictor")

# Load the trained machine learning model
# Make sure the model file 'product_sales_prediction_model_v1_0.joblib' is in the same directory.
try:
    model = joblib.load("product_sales_prediction_model_v1_0.joblib")
except FileNotFoundError:
    model = None # Handle case where model is not found

# Define a route for the home page (GET request)
@product_sales_price_predictor_api.route('/', methods=['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 Product Sales Prediction API!"

# Define an endpoint for single sales prediction (POST request)
@product_sales_price_predictor_api.route('/v1/predict_sales', methods=['POST'])
def predict_product_sales():
    """
    This function handles POST requests to the '/v1/predict_sales' endpoint.
    It expects a JSON payload containing product and store details and returns
    the predicted sales total as a JSON response.
    """
    if model is None:
        return jsonify({'error': 'Model not loaded. Please check the server configuration.'}), 500

    # Get the JSON data from the request body
    data = request.get_json()

    # Extract relevant features from the JSON data, matching the frontend
    try:
        sample = {
            'Product_Weight': data['Product_Weight'],
            'Product_Sugar_Content': data['Product_Sugar_Content'],
            'Product_Allocated_Area': data['Product_Allocated_Area'],
            'Product_Type': data['Product_Type'],
            'Product_MRP': data['Product_MRP'],
            'Store_Establishment_Year': data['Store_Establishment_Year'],
            'Store_Size': data['Store_Size'],
            'Store_Location_City_Type': data['Store_Location_City_Type'],
            'Store_Type': data['Store_Type']
        }
    except KeyError as e:
        return jsonify({'error': f'Missing key in input data: {e}'}), 400


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

    # Make prediction
    # Assuming the model predicts the actual sales value directly.
    # If it predicts log value, you would need to convert it back (e.g., np.exp).
    predicted_sales = model.predict(input_data)[0]

    # Convert predicted_sales to a standard Python float for JSON serialization
    predicted_sales = round(float(predicted_sales), 2)

    # Return the predicted sales
    return jsonify({'Predicted_Sales': predicted_sales})


# Define an endpoint for batch prediction (POST request)
@product_sales_price_predictor_api.route('/v1/predict_sales_batch', methods=['POST'])
def predict_product_sales_batch():
    """
    This function handles POST requests to the '/v1/predict_sales_batch' endpoint.
    It expects a CSV file containing details for multiple products
    and returns the predicted sales as a JSON response.
    """
    if model is None:
        return jsonify({'error': 'Model not loaded. Please check the server configuration.'}), 500

    # Check if a file was posted
    if 'file' not in request.files:
        return jsonify({'error': 'No file part in the request'}), 400

    file = request.files['file']

    # If the user does not select a file, the browser submits an empty file without a filename.
    if file.filename == '':
        return jsonify({'error': 'No selected file'}), 400

    if file:
        # Read the CSV file into a Pandas DataFrame
        try:
            input_data = pd.read_csv(file)
        except Exception as e:
            return jsonify({'error': f'Could not process CSV file: {e}'}), 400

        # Ensure the required columns exist
        required_columns = [
            'Product_Weight', 'Product_Sugar_Content', 'Product_Allocated_Area',
            'Product_Type', 'Product_MRP', 'Store_Establishment_Year',
            'Store_Size', 'Store_Location_City_Type', 'Store_Type'
        ]
        
        if not all(col in input_data.columns for col in required_columns):
            return jsonify({'error': f'CSV must contain the following columns: {required_columns}'}), 400

        # Make predictions for all products in the DataFrame
        predictions = model.predict(input_data).tolist()

        # Round the predictions
        rounded_predictions = [round(float(p), 2) for p in predictions]
        
        # Add predictions as a new column to the original dataframe
        input_data['Predicted_Sales'] = rounded_predictions

        # Return the DataFrame with predictions as a JSON object
        return input_data.to_json(orient='records')

    return jsonify({'error': 'An unknown error occurred'}), 500

# Run the Flask application in debug mode if this script is executed directly
if __name__ == '__main__':
    # Use 0.0.0.0 to make it accessible from the network
    product_sales_price_predictor_api.run(host='0.0.0.0', port=5000, debug=True)