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_revenue_predictor_api = Flask("Predict Product Store Sales based on product and store attributes")

# Load the trained machine learning model
model = joblib.load("superkart_revenue_prediction_model_v1_0.joblib")

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

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

    # Extract relevant features from the JSON data
    json_extract = {
        '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_Id': product_data['Store_Id'],
        'Store_Size': product_data['Store_Size'],
        'Store_Location_City_Type': product_data['Store_Location_City_Type'],
        'Store_Type': product_data['Store_Type'],
        'Product_Category': product_data['Product_Category'],
        'Perishable': product_data['Perishable'],
        'Store_Age': product_data['Store_Age']
    }

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

    # Change MRP to Log as this is done before pipeline (feature engineering)
    input_data['MRP_log'] = np.log(input_data['Product_MRP'])
    input_data['Price_Per_Display'] = input_data['Product_MRP'] * input_data['Product_Allocated_Area']

    # Make prediction 
    predicted_price = model.predict(input_data)[0]

    # Return the actual price
    return jsonify({'Predicted Sales': predicted_price})


# Define an endpoint for batch prediction (POST request)
@superkart_revenue_predictor_api.post('/v1/salesbatch')
def predict_salesprice_batch():
    """
    This function handles POST requests to the '/v1/salesbatch' endpoint.
    It expects a CSV file containing property details for multiple properties
    and returns the predicted sales prices 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)

    # Change MRP to Log as this is done before pipeline (feature engineering)
    input_data['MRP_log'] = np.log(input_data['Product_MRP'])
    input_data['Price_Per_Display'] = input_data['Product_MRP'] * input_data['Product_Allocated_Area']
    
    # Save ID
    product_ids = input_data['Product_Id']

    # Drop ID
    input_data = input_data.drop('Product_Id', axis=1)

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

    # Create a dictionary of predictions with property IDs as keys
    output_dict = dict(zip(product_ids, predicted_prices))  

    # Return the predictions dictionary as a JSON response
    return output_dict

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