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:rental_price_predictor_api"]

app.py

@@ -1,71 +1,62 @@
-
-import streamlit as st
-import pandas as pd
-import requests
-
-# Set the title of the Streamlit app
-st.title("Superkart Product sales revenue Predictor")
-
-# Section for online prediction
-st.subheader("Online Prediction")
-
-# Collect user input for property features
-
-
-# --- User Inputs ---
-# col1, col2 = st.columns(2)
-# with col1:
-#     Product_Weight = st.number_input("Product Weight", min_value=0.0, max_value=100.0, step=0.1)
-#     Product_Allocated_Area = st.number_input("Allocated Display Area Ratio", min_value=0.0, max_value=1.0, step=0.01)
-#     Product_MRP = st.number_input("Product MRP", min_value=1.0, max_value=10000.0, step=1.0)
-
-# with col2:
-#     Product_Sugar_Content = st.selectbox("Sugar Content", ["Low Sugar", "Regular", "No Sugar"])
-#     Product_Type = st.selectbox("Product Type", [
-#         "Meat","Snack Foods","Hard Drinks","Dairy","Canned","Soft Drinks",
-#         "Health and Hygiene","Baking Goods","Bread","Breakfast","Frozen Foods",
-#         "Fruits and Vegetables","Household","Seafood","Starchy Foods","Others"
-#     ])
-#     Store_Size = st.selectbox("Store Size", ["High", "Medium", "Low"])
-#     Store_Location_City_Type = st.selectbox("City Type", ["Tier 1", "Tier 2", "Tier 3"])
-#     Store_Type = st.selectbox("Store Type", [
-#         "Departmental Store","Supermarket Type 1","Supermarket Type 2","Food Mart"
-#     ])
-
-  Product_Weight = st.number_input("Product Weight", min_value=0.0, max_value=100.0, step=0.1)
-  Product_Allocated_Area = st.number_input("Allocated Display Area Ratio", min_value=0.0, max_value=1.0, step=0.01)
-  Product_MRP = st.number_input("Product MRP", min_value=1.0, max_value=10000.0, step=1.0)
-  Product_Sugar_Content = st.selectbox("Sugar Content", ["Low Sugar", "Regular", "No Sugar"])
-  Product_Type = st.selectbox("Product Type", [
-        "Meat","Snack Foods","Hard Drinks","Dairy","Canned","Soft Drinks",
-        "Health and Hygiene","Baking Goods","Bread","Breakfast","Frozen Foods",
-        "Fruits and Vegetables","Household","Seafood","Starchy Foods","Others"
-    ])
-  Store_Size = st.selectbox("Store Size", ["High", "Medium", "Low"])
-  Store_Location_City_Type = st.selectbox("City Type", ["Tier 1", "Tier 2", "Tier 3"])
-  Store_Type = st.selectbox("Store Type", [
-        "Departmental Store","Supermarket Type 1","Supermarket Type 2","Food Mart"
-    ])
-  Store_Id = st.selectbox("Store Id", ["OUT001","OUT002","OUT003","OUT004"])
-
-# Convert user input into a DataFrame
-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_Size': Store_Size,
-    'Store_Location_City_Type': Store_Location_City_Type,
-    'Store_Type': Store_Type,
-    'Store_Id': Store_Id
-}])
-
-# Make prediction when the "Predict" button is clicked
-if st.button("Predict"):
-    response = requests.post("https://Sandhya-2025-Sandhya-2025/SuperKartRevenuePredictionBackend.hf.space/v1/salesRevenue", json=input_data.to_dict(orient='records')[0])  # Send data to Flask API
-    if response.status_code == 200:
-        prediction = response.json()['Predicted Price (in dollars)']
-        st.success(f"Predicted Rental Price (in dollars): {prediction}")
-    else:
-        st.error("Error making 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_sales_revenue_predictor_api = Flask("Superkart Product sales revenue Predictor")
+
+# Load the trained machine learning model
+model = joblib.load("superkart_revenue_prediction_model_v1_0.joblib")
+
+# Define a route for the home page (GET request)
+@superkart_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 sale revenue Prediction API!"
+
+# Define an endpoint for single property prediction (POST request)
+@superkart_sales_revenue_predictor_api.post('/v1/salesRevenue')
+def predict_product_sales_revenue():
+    """
+    This function handles POST requests to the '/v1/salesRevenue' 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
+    sales_data = request.get_json()
+
+    # Extract relevant features from the JSON data
+    sample = {
+        'Product_Weight': sales_data['Product_Weight'],
+        'Product_Sugar_Content': sales_data['Product_Sugar_Content'],
+        'Product_Allocated_Area': sales_data['Product_Allocated_Area'],
+        'Product_Type': sales_data['Product_Type'],
+        'Product_MRP': sales_data['Product_MRP'],
+        'Store_Size': sales_data['Store_Size'],
+        'Store_Location_City_Type': sales_data['Store_Location_City_Type'],
+        'Store_Type': sales_data['Store_Type'],
+        'Store_Id': sales_data['Store_Id']
+    }
+
+    # Convert the extracted data into a Pandas DataFrame
+    input_data_flask = pd.DataFrame([sample])
+
+    # Make prediction (get log_price)
+    predicted_price = model.predict(input_data_flask)[0]
+
+    # Convert predicted_price to Python float
+    predicted_price = round(float(predicted_price), 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 Price (in dollars)': predicted_price})
+
+# Run the Flask application in debug mode if this script is executed directly
+if __name__ == '__main__':
+    superkart_sales_revenue_predictor_api.run(debug=True)

requirements.txt

@@ -3,4 +3,9 @@ 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