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

from flask_cors import CORS
app = Flask(__name__)
CORS(app, resources={r"/v1/*": {"origins": "*"}})

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

# Load the trained machine learning model
model = joblib.load("superkart_sales_prediction_model_v1_0.joblib")


# Define a route for the home page (GET request)
@sales_forecast_api.get('/')
def home():
    return "Welcome to the SuperKart Sales Forecast API!"

# Define an endpoint for single prediction (POST request)
@sales_forecast_api.post('/v1/sales')
def predict_sales():
    """
    This function handles POST requests to the '/v1/sales' endpoint.
    It expects a JSON payload with product and store attributes and returns
    the predicted product-store sales revenue.
    """
    # Get the JSON data
    data = request.get_json()

    # Extract features based on the data dictionary
    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']
    }

    # Convert to DataFrame
    input_df = pd.DataFrame([sample])

    # Predict sales
    predicted_sales = model.predict(input_df)[0]
    predicted_sales = round(float(predicted_sales), 2)

    return jsonify({'prediction': predicted_sales})

# Define an endpoint for batch prediction (POST request)
@sales_forecast_api.post('/v1/salesbatch')
def predict_sales_batch():
    """
    Handles POST requests to '/v1/salesbatch'.
    Accepts a CSV file and returns predicted sales totals for each product-store.
    """
    # Read the uploaded file
    file = request.files['file']
    input_df = pd.read_csv(file)

    # Predict sales for the batch
    predictions = model.predict(input_df).tolist()
    predictions = [round(float(pred), 2) for pred in predictions]

    # Use Product_Id and Store_Id as combined key if available
    if 'Product_Id' in input_df.columns and 'Store_Id' in input_df.columns:
        keys = input_df['Product_Id'] + "_" + input_df['Store_Id']
    else:
        keys = list(range(len(predictions)))

    results = dict(zip(keys, predictions))

    return jsonify(results)

# Run the application
if __name__ == '__main__':
    sales_forecast_api.run(debug=True)