Upload folder using huggingface_hub

Dockerfile

@@ -0,0 +1,19 @@
+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
+
+# Expose the port the Flask app will run on
+#EXPOSE 7860
+
+# 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:sales_predictor_api`: Specifies the application entry point (app.py with Flask instance named sales_predictor_api)
+CMD ["gunicorn", "-w", "4", "-b", "0.0.0.0:7860", "app:sales_predictor_api"]

app.py

@@ -0,0 +1,58 @@
+# 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
+import os
+
+# Initialize the Flask application
+sales_predictor_api = Flask("Superkart Sales Predictor")
+
+# Load the trained machine learning model
+model_filename = joblib.load("best_random_forest_model_v1.0.joblib")
+
+# Define a route for the home page (GET request)
+@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 SuperKart Sales Prediction API!"
+
+# Define an endpoint for single property prediction (POST request)
+@sales_predictor_api.post('/v1/sales')
+def predict_rental_price():
+    """
+    This function handles POST requests to the '/v1/sales' endpoint.
+    It expects a JSON payload containing property details and returns
+    the predicted rental price as a JSON response.
+    """
+    # Get the JSON data from the request body
+    sales_data = request.get_json()
+
+    # Extract relevant features from the JSON data
+    sample = {
+          'Product_Weight': sales_data['Product_Weight']
+    }
+
+    # Convert the extracted data into a Pandas DataFrame
+    input_data = pd.DataFrame([sample])
+
+    # Make prediction (get log_price)
+    predicted_log_sales = model_filename.predict(input_data)[0]
+
+    # Calculate actual price
+    predicted_sales = np.exp(predicted_log_sales)
+
+    # Convert predicted_price to Python float
+    predicted_sales = round(float(predicted_sales), 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({'predicted_sales': predicted_sales})
+
+  # Run the Flask application in debug mode if this script is executed directly
+if __name__ == '__main__':
+    sales_predictor_api.run()

best_random_forest_model_v1.0.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6ee8c6fca4440cad1bb44cc11a7e057a1f8c571ccd18927e1c0e3e06a27d79e
+size 24974954

requirements.txt

@@ -0,0 +1,11 @@
+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