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 `superkart_sales_api`)
+CMD ["gunicorn", "-w", "4", "-b", "0.0.0.0:7860", "app:superkart_sales_api"]

app.py

@@ -0,0 +1,93 @@
+# Import necessary libraries
+import numpy as np # For numerical operations
+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_sales_api = Flask("SuperKart Sales Predictor")
+
+# Load the trained machine learning model
+model = joblib.load("superkart_sales_model.pkl")
+
+# Define a route for the home page (GET request)
+@superkart_sales_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 product-store prediction (POST request)
+@superkart_sales_api.post('/v1/predict')
+def predict_sales():
+    """
+    This function handles POST requests to the '/v1/predict' endpoint.
+    It expects a JSON payload containing product and store details and returns
+    the predicted sales total as a JSON response.
+    """
+    # Get the JSON data from the request body
+    input_data = request.get_json()
+
+    # Extract relevant features from the JSON data
+    sample = {
+        'Product_Weight': input_data['Product_Weight'],
+        'Product_Allocated_Area': input_data['Product_Allocated_Area'],
+        'Product_MRP': input_data['Product_MRP'],
+        'Product_Sugar_Content': input_data['Product_Sugar_Content'],
+        'Product_Type': input_data['Product_Type'],
+        'Store_Size': input_data['Store_Size'],
+        'Store_Location_City_Type': input_data['Store_Location_City_Type'],
+        'Store_Type': input_data['Store_Type'],
+        'Store_Age': input_data['Store_Age'],
+        'Product_Category_Code': input_data['Product_Category_Code']
+    }
+
+    # Convert the extracted data into a Pandas DataFrame
+    input_df = pd.DataFrame([sample])
+
+    # Make prediction
+    predicted_sales = model.predict(input_df)[0]
+
+    # Convert predicted_sales to Python float and round
+    predicted_sales = round(float(predicted_sales), 2)
+
+    # Return the predicted sales
+    return jsonify({'Predicted Sales Total': predicted_sales})
+
+# Define an endpoint for batch prediction (POST request)
+@superkart_sales_api.post('/v1/predictbatch')
+def predict_sales_batch():
+    """
+    This function handles POST requests to the '/v1/predictbatch' endpoint.
+    It expects a CSV file containing product-store details for multiple items
+    and returns the predicted sales totals 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 items in the DataFrame
+    predicted_sales = model.predict(input_data)
+
+    # Round the predictions
+    predicted_sales = [round(float(sale), 2) for sale in predicted_sales]
+
+    # Create a dictionary of predictions with item IDs as keys
+    # Assuming there's an 'item_id' column in your CSV
+    if 'item_id' in input_data.columns:
+        item_ids = input_data['item_id'].tolist()
+        output_dict = dict(zip(item_ids, predicted_sales))
+    else:
+        # If no ID column, use index as keys
+        output_dict = {f"item_{i}": sale for i, sale in enumerate(predicted_sales)}
+
+    # Return the predictions dictionary as a JSON response
+    return output_dict
+
+# Run the Flask application
+if __name__ == '__main__':
+    superkart_sales_api.run(debug=True, host='0.0.0.0', port=5000)

requirements.txt

@@ -0,0 +1,8 @@
+pandas==2.2.2
+numpy==2.0.2
+scikit-learn==1.6.1
+joblib==1.4.2
+Werkzeug==2.2.2
+flask==2.2.2
+gunicorn==20.1.0
+requests==2.28.1

superkart_sales_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53a34a781f6fdcd956499cbd58f5703061920b1c9663941cd622722604aabb4c
+size 74376321