Upload folder using huggingface_hub

Dockerfile

@@ -0,0 +1,21 @@
+FROM python:3.9-slim
+
+# Set the working directory
+WORKDIR /app
+
+# Copy requirements and install dependencies
+COPY requirements.txt /app/requirements.txt
+RUN pip install --no-cache-dir --upgrade -r /app/requirements.txt
+
+# Copy source files into the container
+COPY app.py /app/
+COPY gradboost_RSCV.joblib /app/
+COPY RndmFrstReg_RSCV.joblib /app/
+COPY pipeline.joblib /app/
+COPY feature_names.joblib /app/
+
+# Expose the port used by the Hugging Face Docker Space
+EXPOSE 7860
+
+# Command to run the Flask app with gunicorn
+CMD ["gunicorn", "--bind", "0.0.0.0:7860", "app:app"]

app.py

@@ -0,0 +1,103 @@
+
+# Importing necessary libraries
+from flask import Flask, request, jsonify         # Flask framework and JSON utilities
+from flask_cors import CORS                       # To handle Cross-Origin Resource Sharing (CORS)
+import joblib                                     # For loading saved model/pipeline objects
+import numpy as np
+import pandas as pd
+import logging                                    # For logging API activity
+
+# Set logging level and format
+logging.basicConfig(level=logging.DEBUG, format='%(asctime)s - %(levelname)s - %(message)s')
+
+# Initialize the Flask app
+app = Flask(__name__)
+
+# Enable CORS for the '/predict' endpoint
+CORS(app, resources={r"/predict": {"origins": "*"}})
+
+# Load the models, pipeline, and feature list
+try:
+    model_gradboost = joblib.load('gradboost_RSCV.joblib')         # Tuned Gradient Boosting model
+    model_rndmfrst = joblib.load('RndmFrstReg_RSCV.joblib')        # Tuned Random Forest model
+    pipeline = joblib.load('pipeline.joblib')                      # Preprocessing pipeline
+    feature_names = joblib.load('feature_names.joblib')            # Ordered feature list (optional, if used)
+
+except Exception as ex:
+    logging.error(f'Exception in loading joblib file: {ex}')
+
+# List of required input features for prediction
+required_features = [
+    'Product_Weight',
+    'Product_Sugar_Content',
+    'Product_Allocated_Area',
+    'Product_Type',
+    'Product_MRP',
+    'Store_Size',
+    'Store_Location_City_Type',
+    'Store_Type',
+    'Age_Of_Store'
+]
+
+# Default endpoint for status check
+@app.get('/')
+def home():
+    logging.debug("Accessed endpoint of Home page")
+    return "Welcome to Superkart Prediction system"
+
+# Prediction endpoint to handle POST requests
+@app.route('/predict', methods=['POST'])
+def predict():
+    try:
+        # Read JSON payload
+        data = request.get_json()
+        logging.debug(f"Input received: {data}")
+
+        # If no data sent
+        if not data:
+            return jsonify({'Error': 'No data provided for prediction'})
+
+        # Check for missing features
+        if not all(feature in data for feature in required_features):
+            feature_missing = [feature for feature in required_features if feature not in data]
+            logging.error(f"Exception feature missing: {feature_missing}")
+            return jsonify({'Exception': f"Feature missing {feature_missing}"})
+
+        # Convert input JSON to DataFrame
+        feature_for_prediction = pd.DataFrame([{
+            'Product_Weight': float(data['Product_Weight']),
+            'Product_Sugar_Content': data['Product_Sugar_Content'],
+            'Product_Allocated_Area': float(data['Product_Allocated_Area']),
+            'Product_Type': data['Product_Type'],
+            'Product_MRP': float(data['Product_MRP']),
+            'Store_Size': data['Store_Size'],
+            'Store_Location_City_Type': data['Store_Location_City_Type'],
+            'Store_Type': data['Store_Type'],
+            'Age_Of_Store': float(data['Age_Of_Store'])
+        }], columns=required_features)
+
+        # Transform input using the preprocessing pipeline
+        features_scaled = pipeline.transform(feature_for_prediction)
+        logging.debug(f"Features scaled: {features_scaled}")
+
+        # Predict using both models
+        prediction_gradboost = model_gradboost.predict(features_scaled)
+        prediction_randfrst = model_rndmfrst.predict(features_scaled)
+
+        # Log predictions
+        logging.debug(f"Prediction gradboost: {prediction_gradboost}")
+        logging.debug(f"Prediction randmfrst: {prediction_randfrst}")
+
+        # Return predictions as JSON
+        return jsonify({
+            'gradientBoosting': float(prediction_gradboost[0]),
+            'randomForest': float(prediction_randfrst[0])
+        })
+
+    except Exception as ex:
+        logging.error(f'Exception: {ex}')
+        return jsonify({'Exception': str(ex)})
+
+# Run the Flask app on port 7860 (as required by Hugging Face Docker Spaces)
+if __name__ == '__main__':
+    app.run(host='0.0.0.0', port=7860, debug=False)

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
+flask==2.3.3
+gunicorn==20.1.0
+requests==2.28.1
+uvicorn[standard]
+streamlit==1.43.2
+flask-cors==4.0.1