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:sales_predictor_api"]

app.py

@@ -0,0 +1,87 @@
+# backend_files/app.py
+
+import numpy as np
+import joblib
+import pandas as pd
+from flask import Flask, request, jsonify
+
+# Initialize Flask app
+sales_predictor_api = Flask("Retail Sales Prediction API")
+
+# Load your trained model (change filename to your saved model file)
+model = joblib.load("SuperKart_sales_rf_tuned_prediction_model_p1_0.joblib")  
+
+# Define a route for the home page (GET request)
+@sales_predictor_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 Retail Sales Prediction API!"
+
+
+# Single prediction endpoint (POST)
+@sales_predictor_api.route('/v1/sales', methods=['POST'])
+def predict_sales():
+    """
+    Expects JSON with feature key-value pairs.
+    Returns predicted sales value.
+    """
+    data = request.get_json()
+
+    # Extract features for prediction (replace keys with your exact feature names)
+    features = {
+        'Store_Establishment_Year': data['Store_Establishment_Year'],
+        'Product_MRP': data['Product_MRP'],
+        'Product_Weight': data['Product_Weight'],
+        'Store_Id': data['Store_Id'],
+        'Product_Type': data['Product_Type'],
+        'Product_Sugar_Content': data['Product_Sugar_Content'],
+        'Store_Location_City_Type': data['Store_Location_City_Type'],
+        'Store_Size': data['Store_Size'],
+        'Product_Allocated_Area': data['Product_Allocated_Area'],
+        'Product_id': data['Product_id'],
+        'Store_Type': data['Store_Type'],
+        # Add or remove features per your model input
+    }
+
+    # Convert to DataFrame for model input
+    input_df = pd.DataFrame([features])
+
+    # Predict sales
+    predicted_sales = model.predict(input_df)[0]
+
+    # Convert to float and round for JSON serialization
+    predicted_sales = round(float(predicted_sales), 2)
+
+    return jsonify({'Predicted_Sales': predicted_sales})
+
+
+# Batch prediction endpoint (POST)
+@sales_predictor_api.route('/v1/salesbatch', methods=['POST'])
+def predict_sales_batch():
+    """
+    Expects uploaded CSV file with all required features and an 'id' column.
+    Returns a JSON dict of {id: predicted_sales} for all entries.
+    """
+    try:
+        file = request.files['file']
+        input_df = pd.read_csv(file)
+
+        # Predict sales for batch
+        preds = model.predict(input_df).tolist()
+        preds_rounded = [round(float(p), 2) for p in preds]
+
+        # Map property/product ID to prediction
+        ids = input_df['id'].tolist()  # Ensure 'id' column exists in your batch data
+        results = dict(zip(ids, preds_rounded))
+
+        return jsonify(results)
+
+    except Exception as e:
+        return jsonify({"error": str(e)}), 400
+
+# Run the Flask application in debug mode if this script is executed directly
+if __name__ == "__main__":
+    sales_predictor_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