Upload folder using huggingface_hub

Dockerfile

@@ -0,0 +1,16 @@
+FROM python:3.12-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_revenue_predictor_api"]

app.py

@@ -0,0 +1,121 @@
+# Import necessary libraries
+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
+from datetime import datetime  # added for dynamic current year
+
+# Initialize the Flask application
+sales_revenue_predictor_api = Flask("SuperKart Sales Revenue Predictor")
+
+# Load the trained machine learning model
+model = joblib.load("superkart_sales_revenue_prediction_model_v1_0.joblib")
+
+# Define a route for the home page (GET request)
+@sales_revenue_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 SuperKart Product Sales Revenue Prediction API !"
+
+# Define an endpoint for single product sales revenue prediction (POST request)
+@sales_revenue_predictor_api.post('/v1/revenue')
+def predict_sales_revenue():
+    """
+    This function handles POST requests to the '/v1/revenue' endpoint.
+    It expects a JSON payload containing property details and returns
+    the predicted product sales revenue as a JSON response.
+    """
+    # Get the JSON data from the request body
+    property_data = request.get_json()
+
+    # Extract relevant features from the JSON data
+    sample = {
+        'Product_Weight': property_data['Product_Weight'],
+        'Product_Sugar_Content': property_data['Product_Sugar_Content'],
+        'Product_Allocated_Area': property_data['Product_Allocated_Area'],
+        'Product_Type': property_data['Product_Type'],
+        'Product_MRP': property_data['Product_MRP'],
+        'Store_Size': property_data['Store_Size'],
+        'Store_Location_City_Type': property_data['Store_Location_City_Type'],
+        'Store_Type': property_data['Store_Type'],
+        'Store_Establishment_Year': property_data['Store_Establishment_Year']
+    }
+
+    # Convert the extracted data into a Pandas DataFrame
+    record_input_data = pd.DataFrame([sample])
+
+    # Compute Store_Age
+    current_year_value = datetime.now().year
+    record_input_data['Store_Age'] = current_year_value - record_input_data['Store_Establishment_Year']
+
+    # Define bins and labels (open-ended last bin for 50+ years)
+    age_bins = [0, 10, 20, 30, float("inf")]
+    age_labels = ["<10 Years", "10–20 Years", "20–30 Years", "30+ Years"]
+
+    # Create binned column
+    record_input_data["Store_Age_Binned"] = pd.cut(
+        record_input_data["Store_Age"],
+        bins=age_bins,
+        labels=age_labels,
+        right=False
+    )
+
+    # Make prediction (get revenue)
+    predicted_store_revenue = model.predict(record_input_data)[0]
+
+    # Convert predicted_price to Python float
+    predicted_store_revenue = round(float(predicted_store_revenue), 2)
+    # When we send this value directly within a JSON response, Flask's jsonify function encounters a datatype error
+
+    # Return the actual price
+    return jsonify({'Predicted Product_Store_Sales_Total': predicted_store_revenue})
+
+
+# Define an endpoint for batch prediction (POST request)
+@sales_revenue_predictor_api.post('/v1/revenuebatch')
+def predict_sales_revenue_batch():
+    """
+    This function handles POST requests to the '/v1/revenuebatch' endpoint.
+    It expects a CSV file containing property details for multiple properties
+    and returns the predicted product sales revenue 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
+    csv_input_data = pd.read_csv(file)
+
+    # Compute Store_Age
+    current_year_value = datetime.now().year
+    csv_input_data['Store_Age'] = current_year_value - csv_input_data['Store_Establishment_Year']
+    # Define bins and labels (open-ended last bin for 50+ years)
+    age_bins = [0, 10, 20, 30, float("inf")]
+    age_labels = ["<10 Years", "10–20 Years", "20–30 Years", "30+ Years"]
+
+    # Create binned column
+    csv_input_data["Store_Age_Binned"] = pd.cut(
+        csv_input_data["Store_Age"],
+        bins=age_bins,
+        labels=age_labels,
+        right=False
+    )
+
+    # Make predictions for all properties in the DataFrame (get log_prices)
+    predicted_store_revenues = model.predict(csv_input_data).tolist()
+
+    # Create a dictionary of predictions with product IDs as keys
+    if 'Product_Id' not in csv_input_data.columns:
+        return jsonify({"error": "Input file must contain a 'Product_Id' column"}), 400
+
+    # Create a dictionary of predictions with Product IDs as keys
+    product_ids = csv_input_data['Product_Id'].tolist()  # Assuming 'Product_Id' is the property ID column
+    output_dict = dict(zip(product_ids, predicted_store_revenues))  # Use actual prices
+
+    # Return the predictions dictionary as a JSON response
+    return jsonify(output_dict)
+
+# Run the Flask application in debug mode if this script is executed directly
+if __name__ == '__main__':
+    sales_revenue_predictor_api.run(debug=True)

requirements.txt

@@ -0,0 +1,11 @@
+pandas==2.3.0
+numpy==2.0.2
+scikit-learn==1.6.1
+xgboost==3.0.2
+joblib==1.5.0
+Werkzeug==3.1.3
+flask==3.1.2
+gunicorn==23.0.0
+requests==2.32.3
+uvicorn==0.34.2
+streamlit==1.49.1

superkart_sales_revenue_prediction_model_v1_0.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:518ece4da7aeae64791149e877fcc0685d327540441f7ecd2d09479a0c55a5ff
+size 19050522