Upload folder using huggingface_hub

Dockerfile

@@ -1,16 +1,16 @@
-# Use a minimal base image with Python 3.9 installed
 FROM python:3.9-slim
 
-# Set the working directory inside the container to /app
+# Set the working directory inside the container
 WORKDIR /app
 
-# Copy all files from the current directory on the host to the container's /app directory
+# Copy all files from the current directory to the container's working directory
 COPY . .
 
-# Install Python dependencies listed in requirements.txt
-RUN pip3 install -r requirements.txt
+# 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 run the Streamlit app on port 8501 and make it accessible externally
-CMD ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0", "--server.enableXsrfProtection=false"]
-
-# NOTE: Disable XSRF protection for easier external access in order to make batch predictions
+# 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:superkart_predictor_api"]

app.py

@@ -1,61 +1,94 @@
-import streamlit as st
-import pandas as pd
-import requests
-
-# Set the title of the Streamlit app
-st.title("Superkart Revenue Prediction")
-
-# Section for online prediction
-st.subheader("Online Prediction")
-
-# Collect user input for property features
-product_weight = st.number_input("Product_Weight", min_value=0.0, max_value=1000.0, step=0.1, value=12.66)
-product_sugar_content = st.selectbox("Product_Sugar_Content", ["Low Sugar", "Regular", "No Sugar"])
-product_allocated_area = st.number_input("Product_Allocated_Area", min_value=0.0, max_value=1.0, step=0.001, value=0.027)
-product_type = st.selectbox("Product_Type", ["Frozen Foods", "Dairy", "Canned", "Baking Goods", "Health and Hygiene", "Snack Foods"])
-product_mrp = st.number_input("Product_MRP", min_value=0.0, max_value=1000.0, step=0.1, value=117.08)
-store_id = st.text_input("Store_Id", ["OUT001", "OUT002", "OUT003", "OUT004"])
-store_current_age = st.number_input("Store_Current_Age", min_value=0, max_value=100, step=1, value=10)
-store_size = st.selectbox("Store_Size", ["Small", "Medium", "High"])
-store_location_city_type = st.selectbox("Store_Location_City_Type", ["Tier 1", "Tier 2", "Tier 3"])
-store_type = st.selectbox("Store_Type", ["Supermarket Type1", "Supermarket Type2", "Departmental Store", "Food Mart"])
-#product_store_sales_total = st.number_input("Product_Store_Sales_Total", min_value=0.0, max_value=10000.0, step=0.1, value=2842.4)
-
-input_data = pd.DataFrame([{
-    "Product_Weight": product_weight,
-    "Product_Sugar_Content": product_sugar_content,
-    "Product_Allocated_Area": product_allocated_area,
-    "Product_Type": product_type,
-    "Product_MRP": product_mrp,
-    "Store_Id": store_id,
-    "Store_Current_Age": store_current_age,
-    "Store_Size": store_size,
-    "Store_Location_City_Type": store_location_city_type,
-    "Store_Type": store_type,
-}])
-
-# Make prediction when the "Predict" button is clicked
-if st.button("Predict"):
-    response = requests.post("https://KishoreKT-SuperKartPredictionBackend.hf.space/v1/revenue", json=input_data.to_dict(orient='records')[0])  # Send data to Flask API
-    if response.status_code == 200:
-        prediction = response.json()['Predicted Revenue (in dollars)']
-        st.success(f"Predicted  Revenue (in dollars): {prediction}")
-    else:
-        st.error("Error making prediction.")
-
-# Section for batch prediction
-st.subheader("Batch Prediction")
-
-# Allow users to upload a CSV file for batch prediction
-uploaded_file = st.file_uploader("Upload CSV file for batch prediction", type=["csv"])
-
-# Make batch prediction when the "Predict Batch" button is clicked
-if uploaded_file is not None:
-    if st.button("Predict Batch"):
-        response = requests.post("https://KishoreKT-SuperKartPredictionBackend.hf.space/v1/revenuebatch", files={"file": uploaded_file})  # Send file to Flask API
-        if response.status_code == 200:
-            predictions = response.json()
-            st.success("Batch predictions completed!")
-            st.write(predictions)  # Display the predictions
-        else:
-            st.error("Error making batch prediction.")
+# 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_predictor_api = Flask("Superkart Predictor Price Predictor")
+
+# Load the trained machine learning model
+model = joblib.load("superKart_prediction_model_v1_0.joblib")
+
+# Define a route for the home page (GET request)
+@superkart_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_Predictor Price Prediction API!"
+
+# Define an endpoint for single property prediction (POST request)
+@superkart_predictor_api.post('/v1/revenue')
+def predict_revenue_price():
+    """
+    This function handles POST requests to the '/v1/rental' endpoint.
+    It expects a JSON payload containing property details and returns
+    the predicted rental price 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_Allocated_Area': property_data['Product_Allocated_Area'],
+        'Store_Current_Age': property_data['Store_Current_Age'],
+        'Product_MRP': property_data['Product_MRP'],
+        'Product_Sugar_Content': property_data['Product_Sugar_Content'],
+        'Product_Type': property_data['Product_Type'],
+        'Store_Location_City_Type': property_data['Store_Location_City_Type'],
+        'Store_Id': property_data['Store_Id'],
+        'Store_Type': property_data['Store_Type'],
+        'Store_Size': property_data['Store_Size']
+    }
+
+    # Convert the extracted data into a Pandas DataFrame
+    input_data = pd.DataFrame([sample])
+
+    # Make prediction (get log_price)
+    predicted_revenue = model.predict(input_data)[0]
+
+    # Calculate actual price
+    #predicted_revenue = np.exp(predicted_log_revenue)
+
+    # Convert predicted_price to Python float
+    #predicted_revenue = round(float(predicted_revenue), 2)
+    # The conversion above is needed as we convert the model prediction (log price) to actual price using np.exp, which returns predictions as NumPy float32 values.
+    # 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 revenue (in dollars)': predicted_revenue})
+
+
+# Define an endpoint for batch prediction (POST request)
+@superkart_predictor_api.post('/v1/revenuebatch')
+def predict_revenue_batch():
+    """
+    This function handles POST requests to the '/v1/rentalbatch' endpoint.
+    It expects a CSV file containing property details for multiple properties
+    and returns the predicted rental prices 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 properties in the DataFrame (get log_prices)
+    predicted_revenues = model.predict(input_data).tolist()
+
+    # Calculate actual prices
+    #predicted_revenues = [round(float(np.exp(Product_Store_Sales_Total)), 2) for log_price in predicted_log_revenues]
+    return predicted_revenues
+    # Create a dictionary of predictions with property IDs as keys
+    #property_ids = input_data['id'].tolist()  # Assuming 'id' is the property ID column
+    #output_dict = dict(zip(property_ids, predicted_prices))  # Use actual prices
+
+    # Return the predictions dictionary as a JSON response
+    #return output_dict
+
+# Run the Flask application in debug mode if this script is executed directly
+if __name__ == '__main__':
+    superkart_predictor_api.run(debug=True)

requirements.txt

@@ -1,3 +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