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:rental_price_predictor_api"]

app.py

@@ -0,0 +1,89 @@
+# 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
+sales_forecast_api = Flask("SuperKart Sales Forecast API")
+
+# Load the trained machine learning model
+model = joblib.load("superkart_sales_prediction_model_v1_0.joblib")
+
+# Define a route for the home page (GET request)
+@sales_forecast_api.get('/')
+def home():
+    """
+    Handles GET requests to the root URL ('/') of the API.
+    Returns a simple welcome message.
+    """
+    return "Welcome to the SuperKart Sales Forecast API!"
+
+# Define an endpoint for single product-store sales prediction (POST request)
+@sales_forecast_api.post('/v1/sales/predict')
+def predict_sales():
+    """
+    Handles POST requests to the '/v1/sales/predict' endpoint.
+    Expects a JSON payload containing product and store details,
+    and returns the predicted sales revenue as a JSON response.
+    """
+    # Get the JSON data from the request body
+    product_store_data = request.get_json()
+
+    # Extract relevant features from the JSON data
+    sample = {
+        'Product_Weight': product_store_data['Product_Weight'],
+        'Product_Sugar_Content': product_store_data['Product_Sugar_Content'],
+        'Product_Allocated_Area': product_store_data['Product_Allocated_Area'],
+        'Product_Type': product_store_data['Product_Type'],
+        'Product_MRP': product_store_data['Product_MRP'],
+        'Store_Size': product_store_data['Store_Size'],
+        'Store_Location_City_Type': product_store_data['Store_Location_City_Type'],
+        'Store_Type': product_store_data['Store_Type'],
+        'Store_Age': product_store_data['Store_Age']  # Assuming transformation of Store_Age during preprocessing
+    }
+
+    # Convert the extracted data into a Pandas DataFrame
+    input_data = pd.DataFrame([sample])
+
+    # Make prediction for sales revenue
+    predicted_sales = model.predict(input_data)[0]
+
+    # Round and convert prediction to Python float (handle NumPy data type issues)
+    predicted_sales = round(float(predicted_sales), 2)
+
+    # Return the predicted sales revenue
+    return jsonify({'Predicted Sales Revenue (in dollars)': predicted_sales})
+
+
+# Define an endpoint for batch sales prediction (POST request)
+@sales_forecast_api.post('/v1/salesbatch/predict')
+def predict_sales_batch():
+    """
+    Handles POST requests to the '/v1/salesbatch/predict' endpoint.
+    Expects a CSV file containing product and store details for multiple products,
+    and returns predicted sales revenues 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 rows in the DataFrame
+    predicted_sales = model.predict(input_data).tolist()
+
+    # Round sales predictions and ensure conversion to Python floats
+    predicted_sales = [round(float(sales), 2) for sales in predicted_sales]
+
+    # Create a dictionary of predictions using 'Product_Id' and 'Store_Id' as keys
+    # Concatenate Product_Id and Store_Id for unique identification
+    unique_identifiers = (input_data['Product_Id'] + "_" + input_data['Store_Id']).tolist()
+    output_dict = dict(zip(unique_identifiers, predicted_sales))  # Pairing identifiers with predictions
+
+    # Return the dictionary of predictions as a JSON response
+    return jsonify(output_dict)
+
+# Run the Flask application in debug mode if executed directly
+if __name__ == '__main__':
+    sales_forecast_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

superkart_sales_prediction_model_v1_0.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df2165390ea7f962ff37a9f875dc84cfdbbe5bd6e2c3d71b6f3e2469d1cf3d7d
+size 63811155