Upload folder using huggingface_hub

Dockerfile

@@ -1,20 +1,16 @@
-FROM python:3.13.5-slim
+FROM python:3.9-slim
 
+# Set the working directory inside the container
 WORKDIR /app
 
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    curl \
-    git \
-    && rm -rf /var/lib/apt/lists/*
+# Copy all files from the current directory to the container's working directory
+COPY . .
 
-COPY requirements.txt ./
-COPY src/ ./src/
+# Install dependencies from the requirements file without using cache to reduce image size
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
 
-RUN pip3 install -r requirements.txt
-
-EXPOSE 8501
-
-HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
-
-ENTRYPOINT ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]
+# 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:superkart_model_api"]

app.py

@@ -0,0 +1,94 @@
+# 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
+superkart_model_api = Flask("SuperKart’s Decision-Making System")
+
+# Load the trained machine learning model
+model = joblib.load("superkart_decision_making_model_v1_0.joblib")
+
+# Define a route for the home page (GET request)
+@superkart_model_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’s Decision-Making System API!"
+
+# Define an endpoint for single product sale prediction (POST request)
+@superkart_model_api.post('/v1/productsale')
+def predict_product_sales():
+    """
+    This function handles POST requests to the '/v1/productsale' endpoint.
+    It expects a JSON payload containing product and store details and returns
+    total revenue by the sale of that particular product in that particular store as a JSON response.
+    """
+    # Get the JSON data from the request body
+    product_data = request.get_json()
+
+    # Extract relevant features from the JSON data
+    sample = {
+        'product_weight': product_data['product_weight'],
+        'product_sugar_content': product_data['product_sugar_content'],
+        'product_allocated_area': product_data['product_allocated_area'],
+        'product_type': product_data['product_type'],
+        'product_mrp': product_data['product_mrp'],
+        'store_establishment_year': product_data['store_establishment_year'],
+        'store_size': product_data['store_size'],
+        'store_location_city_type': product_data['store_location_city_type'],
+        'store_type': product_data['store_type']
+    }
+
+    # Convert the extracted data into a Pandas DataFrame
+    input_data = pd.DataFrame([sample])
+
+    # Make prediction (get log_price)
+    predicted_log_price = model.predict(input_data)[0]
+
+    # Calculate actual price
+    predicted_price = np.exp(predicted_log_price)
+
+    # Convert predicted_price to Python float
+    predicted_price = round(float(predicted_price), 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({'Total Revenue (in dollars)': predicted_price})
+
+
+# Define an endpoint for batch prediction (POST request)
+@superkart_model_api.post('/v1/productsalebatch')
+def predict_product_sale_price_batch():
+    """
+    This function handles POST requests to the '/v1/productsalebatch' endpoint.
+    It expects a CSV file containing product and store details and returns the predicted
+    total 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 sale in the stores in the DataFrame (get log_prices)
+    predicted_log_prices = model.predict(input_data).tolist()
+
+    # Calculate actual prices
+    predicted_prices = [round(float(np.exp(log_price)), 2) for log_price in predicted_log_prices]
+
+    # Create a dictionary of predictions with product IDs as keys
+    product_ids = input_data['id'].tolist()  # Assuming 'id' is the product ID column
+    output_dict = dict(zip(product_ids, predicted_prices))  # Use actual prices
+
+    # 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__':
+    superkart_model_api.run(debug=True)

requirements.txt

@@ -1,3 +1,11 @@
-altair
-pandas
-streamlit
+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