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 `superkart_app.py` contains the Flask instance named `app`)
+CMD ["gunicorn", "-w", "4", "-b", "0.0.0.0:7860", "superkart_app:superkart_sales_predictor_api"]

Store_sales_prediction_model_v1_0.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c87fba09a66a8c846efb84df0699cbe47e3f39b6da17efc6740eb80eaab5c1ec
+size 208397

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_app.py

@@ -0,0 +1,76 @@
+# 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_sales_predictor_api = Flask("SuperKart Sales Predictor")
+
+# Load the trained machine learning model
+# NOTE: Ensure the joblib file name matches your saved model file
+model = joblib.load("Store_sales_prediction_model_v1_0.joblib")
+
+# Define a route for the home page (GET request)
+@superkart_sales_predictor_api.get('/')
+def home():
+    """
+    This function handles GET requests to the root URL ('/') of the API.
+    It returns a simple welcome message for the SuperKart API New.
+    """
+    return "Welcome to the SuperKart Sales Prediction API!"
+
+# Define an endpoint for single product-store prediction (POST request)
+@superkart_sales_predictor_api.post('/v1/sales')
+def predict_sales_total():
+    """
+    This function handles POST requests to the '/v1/sales' 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
+    product_store_data = request.get_json()
+
+    # Extract ALL relevant features from the JSON data.
+    # Features must match the exact order and names used during model training (X_train columns).
+    # NOTE: This list MUST be updated to include all features (including engineered/encoded ones)
+    sample = {
+        # Numerical/Engineered Features
+        'Product_Weight': product_store_data['Product_Weight'],
+        'Product_MRP': product_store_data['Product_MRP'],
+        'Store_Age': product_store_data['Store_Age'],  # Engineered
+        'Product_Allocated_Area_Log': product_store_data['Product_Allocated_Area_Log'], # Engineered/Transformed
+        
+        # Ordinal Encoded Features (if used Label Encoding 0, 1, 2, 3...)
+        'Store_Size_Encoded': product_store_data['Store_Size_Encoded'],
+        'Store_Location_City_Type_Encoded': product_store_data['Store_Location_City_Type_Encoded'],
+        
+        # Nominal/One-Hot Encoded Features (must match model's columns)
+        # Assuming we pass the raw categorical values and let the Pipeline handle encoding.
+        # If your pipeline expects raw data, this is fine. If it expects encoded data,
+        # you need to manually encode or structure the input differently.
+        # For simplicity, we pass the original features here and rely on a comprehensive Pipeline:
+        'Product_Sugar_Content': product_store_data['Product_Sugar_Content'],
+        'Product_Type': product_store_data['Product_Type'],
+        'Store_Type': product_store_data['Store_Type'],
+    }
+
+    # Convert the extracted data into a Pandas DataFrame
+    input_data = pd.DataFrame([sample])
+
+    # Make prediction (predicted_sales_total)
+    # Since our target was NOT log-transformed, we use the prediction directly.
+    predicted_sales_total = model.predict(input_data)[0]
+
+    # Predicted Sales total does not need np.exp or log price conversion.
+    # Convert prediction to Python float and round
+    predicted_sales_total = round(float(predicted_sales_total), 2)
+    # The conversion to float() is still needed to avoid JSON serialization errors from NumPy types.
+
+    # Return the predicted sales
+    return jsonify({'Predicted Sales Total (in dollars)': predicted_sales_total})
+
+# Run the Flask application in debug mode if this script is executed directly
+if __name__ == '__main__':
+    # You might need to specify host='0.0.0.0' for deployment environments like Docker/Hugging Face
+    superkart_sales_predictor_api.run(debug=True)