app.py

# Import necessary libraries
import numpy as np
import joblib
import pandas as pd
from flask import Flask, request, jsonify

# Initialize the Flask application
superkart_sales_forecast_api = Flask("SuperKart Sales Forecast API")

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

# Define a route for the home page (GET request)
@superkart_sales_forecast_api.get('/')
def home():
    """
    Handles GET requests to the root URL ('/').
    Returns a welcome message.
    """
    return "Welcome to the SuperKart Sales Forecast API!"

# Define an endpoint for single prediction (POST request)
@superkart_sales_forecast_api.post('/v1/forecast')
def predict_sales_forecast():
    """
    Handles POST requests to '/v1/forecast'.
    Expects a JSON payload of product-store details.
    Returns the predicted sales total.
    """
    forecast_data = request.get_json()

    sample = {
        'Product_Weight': float(forecast_data['Product_Weight']),
        'Product_MRP': float(forecast_data['Product_MRP']),
        'Product_Sugar_Content': forecast_data['Product_Sugar_Content'],
        'Product_Allocated_Area': float(forecast_data['Product_Allocated_Area']),
        'Product_Type': forecast_data['Product_Type'],
        'Store_Id': forecast_data['Store_Id'],
        'Store_Establishment_Year': int(forecast_data['Store_Establishment_Year']),
        'Store_Size': forecast_data['Store_Size'],
        'Store_Location_City_Type': forecast_data['Store_Location_City_Type'],
        'Store_Type': forecast_data['Store_Type']
    }

    input_df = pd.DataFrame([sample])
    prediction = model.predict(input_df)
    predicted_sales = round(float(prediction[0]), 2)

    return jsonify({'predicted_product_store_sales_total': predicted_sales})

# Define an endpoint for batch prediction (POST request)
@superkart_sales_forecast_api.post('/v1/forecastbatch')
def predict_sales_forecast_batch():
    """
    Handles POST requests to '/v1/forecastbatch'.
    Expects a CSV file with product-store rows.
    Returns a dictionary of predicted sales totals.
    """
    file = request.files['file']
    input_df = pd.read_csv(file)

    predictions = model.predict(input_df).tolist()
    predictions = [round(float(x), 2) for x in predictions]

    if 'id' in input_df.columns:
        ids = input_df['id'].tolist()
    else:
        ids = list(range(1, len(predictions) + 1))

    result = dict(zip(ids, predictions))
    return jsonify(result)

# Run the Flask app
if __name__ == '__main__':
    superkart_sales_forecast_api.run(debug=True)