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

# Initialize the Flask application
superkart_model_api = Flask("SuperKart’s Decision-Making System")

# Load the trained machine learning model
model = joblib.load("superkart_decision_making_model_v1_0.joblib")

# Define a route for the home page (GET request)
@superkart_model_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’s Decision-Making System API!"

# Define an endpoint for single product sale prediction (POST request)
@superkart_model_api.post('/v1/productsale')
def predict_product_sales():
    """
    This function handles POST requests to the '/v1/productsale' endpoint.
    It expects a JSON payload containing product and store details and returns
    total revenue by the sale of that particular product in that particular store as a JSON response.
    """
    # Get the JSON data from the request body
    product_data = request.get_json()

    # Extract relevant features from the JSON data
    sample = {
        'Product_Weight': product_data['product_weight'],
        'Product_Sugar_Content': product_data['product_sugar_content'],
        'Product_Allocated_Area': product_data['product_allocated_area'],
        'Product_Type': product_data['product_type'],
        'Product_MRP': product_data['product_mrp'],
        'Store_Size': product_data['store_size'],
        'Store_Location_City_Type': product_data['store_location_city_type'],
        'Store_Type': product_data['store_type']
    }

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

    # Make prediction (get Product_Store_Sales_Total)
    predicted_Product_Store_Sales_Total = model.predict(input_data)[0]
    print(f"Predicted Product_Store_Sales_Total: {predicted_Product_Store_Sales_Total}")

    # Convert predicted_price to Python float
    predicted_price = round(float(predicted_Product_Store_Sales_Total), 2)

    # The conversion above is needed as we convert the model prediction (log price) to actual price 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 price
    return jsonify({'Total Revenue (in dollars)': predicted_price})


# Define an endpoint for batch prediction (POST request)
@superkart_model_api.post('/v1/productsalebatch')
def predict_product_sale_price_batch():
    """
    This function handles POST requests to the '/v1/productsalebatch' endpoint.
    It expects a CSV file containing product and store details and returns the predicted
    total revenue as a dictionary in the JSON response.

    """
    # 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 product sale in the stores in the DataFrame (get log_prices)
    predicted_Product_Store_Sales_Total = model.predict(input_data).tolist()

    # Calculate actual prices
    predicted_prices = [round(float(total_sale_price), 2) for total_sale_price in predicted_Product_Store_Sales_Total]

    # Create a dictionary of predictions with product IDs as keys
    product_ids = input_data['Product_Id'].tolist()  # Assuming 'id' is the product ID column

    # Create a dictionary of predictions with Store IDs as keys
    store_ids = input_data['Store_Id'].tolist()

    # Build predictions with both Product and Store IDs
    output_list = []

    for pid, sid, price in zip(product_ids, store_ids, predicted_prices):
        output_list.append({
            "Product_Id": pid,
            "Store_Id": sid,
            "Predicted_Revenue": round(float(price), 2)
        })

    # Return as JSON response
    return jsonify({"predictions": output_list})

# Run the Flask application in debug mode if this script is executed directly
if __name__ == '__main__':
    superkart_model_api.run(debug=True)