app.py

# Import necessary libraries
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 datetime import datetime  # added for dynamic current year

# Initialize the Flask application
sales_revenue_predictor_api = Flask("SuperKart Sales Revenue Predictor")

# Load the trained machine learning model
model = joblib.load("superkart_sales_revenue_prediction_model_v1_0.joblib")

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

# Define an endpoint for single product sales revenue prediction (POST request)
@sales_revenue_predictor_api.post('/v1/revenue')
def predict_sales_revenue():
    """
    This function handles POST requests to the '/v1/revenue' endpoint.
    It expects a JSON payload containing property details and returns
    the predicted product sales revenue 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_Size': property_data['Store_Size'],
        'Store_Location_City_Type': property_data['Store_Location_City_Type'],
        'Store_Type': property_data['Store_Type'],
        'Store_Establishment_Year': property_data['Store_Establishment_Year']
    }

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

    # Compute Store_Age
    current_year_value = datetime.now().year
    record_input_data['Store_Age'] = current_year_value - record_input_data['Store_Establishment_Year']

    # Define bins and labels (open-ended last bin for 50+ years)
    age_bins = [0, 10, 20, 30, float("inf")]
    age_labels = ["<10 Years", "10–20 Years", "20–30 Years", "30+ Years"]

    # Create binned column
    record_input_data["Store_Age_Binned"] = pd.cut(
        record_input_data["Store_Age"],
        bins=age_bins,
        labels=age_labels,
        right=False
    )

    # Make prediction (get revenue)
    predicted_store_revenue = model.predict(record_input_data)[0]

    # Convert predicted_price to Python float
    predicted_store_revenue = round(float(predicted_store_revenue), 2)
    # When we send this value directly within a JSON response, Flask's jsonify function encounters a datatype error

    # Return the actual price
    return jsonify({'Predicted Product_Store_Sales_Total': predicted_store_revenue})


# Define an endpoint for batch prediction (POST request)
@sales_revenue_predictor_api.post('/v1/revenuebatch')
def predict_sales_revenue_batch():
    """
    This function handles POST requests to the '/v1/revenuebatch' endpoint.
    It expects a CSV file containing property details for multiple properties
    and returns the predicted product sales 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
    csv_input_data = pd.read_csv(file)

    # Compute Store_Age
    current_year_value = datetime.now().year
    csv_input_data['Store_Age'] = current_year_value - csv_input_data['Store_Establishment_Year']
    # Define bins and labels (open-ended last bin for 50+ years)
    age_bins = [0, 10, 20, 30, float("inf")]
    age_labels = ["<10 Years", "10–20 Years", "20–30 Years", "30+ Years"]

    # Create binned column
    csv_input_data["Store_Age_Binned"] = pd.cut(
        csv_input_data["Store_Age"],
        bins=age_bins,
        labels=age_labels,
        right=False
    )

    # Make predictions for all properties in the DataFrame (get log_prices)
    predicted_store_revenues = model.predict(csv_input_data).tolist()

    # Create a dictionary of predictions with product IDs as keys
    if 'Product_Id' not in csv_input_data.columns:
        return jsonify({"error": "Input file must contain a 'Product_Id' column"}), 400

    # Create a dictionary of predictions with Product IDs as keys
    product_ids = csv_input_data['Product_Id'].tolist()  # Assuming 'Product_Id' is the property ID column
    output_dict = dict(zip(product_ids, predicted_store_revenues))  # Use actual prices

    # Return the predictions dictionary as a JSON response
    return jsonify(output_dict)

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