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
store_product_sales_predictor_api = Flask("SuperKart Store Product Sales Predictor")

# Load the trained machine learning model
model = joblib.load("/content/drive/My Drive/rf_tuned.pk1")

# Define a route for the home page (GET request)
@store_product_sales_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 Product Sale Prediction API!"

# Define an endpoint for single sale prediction (POST request)
@store_product_sales_predictor_api.post('/v1/sales')
def predict_product_sales():
    """
    This function handles POST requests to the '/v1/sales' endpoint.
    It expects a JSON product id and returns the predicted product sales
    as a JSON response.
    """
    # Get the JSON data from the request body
    product_sale = request.get_json()

    # Extract relevant features from the JSON data
    sample = {
        'Product_Weight': product_sale['Product_Weight'],
        'Product_Sugar_Content': product_sale['Product_Sugar_Content'],
        'Product_Allocated_Area': product_sale['Product_Allocated_Area'],
        'Product_Type': product_sale['Product_Type'],
        'Product_Allocated_Area': product_sale['Product_Allocated_Area'],
        'Product_Type': product_sale['Product_Type'],
        'Product_MRP': product_sale['Product_MRP'],
        'Store_Id': product_sale['Store_Id'],
        'Store_Size': product_sale['Store_Size'],
        'Store_Location_City_Type': product_sale['Store_Location_City_Type'],
        'Store_Type': product_sale['Store_Type'],
        'Store_Establishment_Year': product_sale['Store_Establishment_Year']
    }

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

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

    # The target variable was not log-transformed during training, so no need to apply np.exp here.
    # actual_sale = np.exp(predicted_sale)

    # Convert predicted_sale to Python float
    actual_sale = round(float(predicted_sale), 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({'Actual Sale': actual_sale})


# Run the Flask application in debug mode if this script is executed directly
if __name__ == '__main__':
    store_product_sales_predictor_api.run(debug=True)
Overwriting backend_files/app.py
Dependencies File
%%writefile backend_files/requirements.txt
pandas==2.2.2
numpy==2.0.2
scikit-learn==1.6.1
xgboost==2.1.4
joblib==1.4.2
Werkzeug==2.2.2
flask==2.2.2
gunicorn==20.1.0
requests==2.28.1
uvicorn[standard]
streamlit==1.43.2
Writing backend_files/requirements.txt
Dockerfile
%%writefile backend_files/Dockerfile
FROM python:3.9-slim

# Set the working directory inside the container
WORKDIR /app

# Copy all files from the current directory to the container's working directory
COPY . .

# Install dependencies from the requirements file without using cache to reduce image size
RUN pip install --no-cache-dir --upgrade -r requirements.txt

# Define the command to start the application using Gunicorn with 4 worker processes
# - `-w 4`: Uses 4 worker processes for handling requests
# - `-b 0.0.0.0:7860`: Binds the server to port 7860 on all network interfaces
# - `app:app`: Runs the Flask app (assuming `app.py` contains the Flask instance named `app`)
CMD ["gunicorn", "-w", "4", "-b", "0.0.0.0:7860", "app:rental_price_predictor_api"]