Upload folder using huggingface_hub

Dockerfile

@@ -0,0 +1,16 @@
+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:revenue_predictor_api"]

Superkart_prediction_model_v1_0.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb4e0820ccebeb7409dfd3701eac8201c539eece7dc98e5b2c1a01a690311bb7
+size 189205

app.py

@@ -0,0 +1,93 @@
+# 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
+Revenue_predictor_api = Flask("SuperKart Revenue Predictor CSV")
+
+# Load the trained machine learning model
+model = joblib.load("Superkart_prediction_model_v1_0.joblib")
+
+# Define a route for the home page (GET request)
+@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 Airbnb Rental Price Prediction API!"
+
+# Define an endpoint for single property prediction (POST request)
+@Revenue_predictor_api.post('/v1/revenue')
+def predict_revenue():
+    """
+    This function handles POST requests to the '/v1/revenue' endpoint.
+    It expects a JSON payload containing product details and returns
+    the predicted revenue as a JSON response.
+    """
+    # Get the JSON data from the request body
+   Revenue_data = request.get_json()
+
+    # Extract relevant features from the JSON data
+    sample = {
+    "Product_Type": Product_Type,['Product_Type']
+    "Product_MRP": Product_MRP,['Product_MRP']
+    "Product_Weight": Product_Weight,['Product_Weight']
+    "Product_Sugar_Content": Product_Sugar_Content,['Product_Sugar_Content']
+    "Store_Size": Store_Size,['Store_Size']
+    "Store_Location_City": Store_Location_City,['Store_Location_City']
+    "Store_Type": Store_Type,['Store_Type']
+    "Product_Allocated_Area": Product_Allocated_Area,['Product_Allocated_Area']
+    "Store_Establishment_Year": Store_Establishment_Year['Store_Establishment_Year']
+}])
+
+    # Convert the extracted data into a Pandas DataFrame
+    input_data = pd.DataFrame([sample])
+
+    # Make prediction (get log_Revenue)
+    predicted_log_revenue = model.predict(input_data)[0]
+
+    # Calculate actual Revenue
+    predicted_revenue = np.exp(predicted_log_revenue)
+
+    # Convert predicted_Revenue to Python float
+    predicted_revenue = round(float(predicted_revenue), 2)
+    # The conversion above is needed as we convert the model prediction (log revenue) to actual revenue 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 Revenue
+    return jsonify({'Predicted revenue (in dollars)': predicted_revenue})
+
+
+# Define an endpoint for batch prediction (POST request)
+@revenue_predictor_api.post('/v1/revenuebatch')
+def predict_revenue_batch():
+    """
+    This function handles POST requests to the '/v1/revenuebatch' endpoint.
+    It expects a CSV file containing product details for multiple products
+    and returns the predicted Revenue 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)
+
+    # Make predictions for all product in the DataFrame (get log_revenue)
+    predicted_log_revenue = model.predict(input_data).tolist()
+
+    # Calculate actual revenue
+    predicted_revenue = [round(float(np.exp(log_revenue)), 2) for log_revenue in predicted_log_revenue]
+
+    # Create a dictionary of predictions with product IDs as keys
+    property_ids = input_data['id'].tolist()  # Assuming 'id' is the product ID column
+    output_dict = dict(zip(product_ids, predicted_revenue))  # Use actual revenue
+
+    # 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__':
+    revenue_predictor_api.run(debug=True)

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