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
+# Set the working directory inside the container to /app
 WORKDIR /app
 
-# Copy all files from the current directory to the container's working directory
+# Copy all files from the current directory on the host to the container's /app 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
+# Install Python dependencies listed in requirements.txt
+RUN pip3 install -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:rental_price_predictor_api"]
+# 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

app.py

@@ -1,95 +1,65 @@
-# 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
-product_store_sales_total_api = Flask("Airbnb Product Store Sales Total")
-
-# Load the trained machine learning model
-model = joblib.load("Product_Store_Sales_Total_prediction_model_v1_0.joblib")
-
-# Define a route for the home page (GET request)
-@product_store_sales_total_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 Airbnb Product Store Sales Total Prediction API!"
-
-# Define an endpoint for single property prediction (POST request)
-@product_store_sales_total_api.post('/v1/totalsales')
-def predict_product_store_sales_total():
-    """
-    This function handles POST requests to the '/v1/totalsales' endpoint.
-    It expects a JSON payload containing property details and returns
-    the predicted product store sales total as a JSON response.
-    """
-    # Get the JSON data from the request body
-    product_store_data = request.get_json()
-
-    # Extract relevant features from the JSON data
-    sample = {
-        'Product_Id': property_data['Product_Id'],
-        '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_Id': property_data['Store_Id'],
-        'Store_Establishment_Year': property_data['Store_Establishment_Year'],
-        'Store_Location_City_Type': property_data['Store_Location_City_Type'],
-        'Store_Type': property_data['Store_Type'],
-        'Product_Store_Sales_Total': property_data['Product_Store_Sales_Total']
-    }
-
-    # Convert the extracted data into a Pandas DataFrame
-    input_data = pd.DataFrame([sample])
-
-    # Make prediction (get log_sales)
-    predicted_log_sales = model.predict(input_data)[0]
-
-    # Calculate actual total sales
-    predicted_sales = np.exp(predicted_log_sales)
-
-    # Convert predicted_sales to Python float
-    predicted_sales = round(float(predicted_sales), 2)
-    # The conversion above is needed as we convert the model prediction (log sales) to actual total sales 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 sales
-    return jsonify({'Predicted total sales (in dollars)': predicted_sales})
-
-
-# Define an endpoint for batch prediction (POST request)
-@product_store_sales_total_api.post('/v1/totalsalesbatch')
-def product_store_sales_total_api_batch():
-    """
-    This function handles POST requests to the '/v1/totalsalesbatch' endpoint.
-    It expects a CSV file containing property details for multiple properties
-    and returns the predicted total sales 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_totalsales)
-    predicted_log_totalsales = model.predict(input_data).tolist()
-
-    # Calculate total sales 
-    predicted_totalsales = [round(float(np.exp(log_sales)), 2) for log_sales in predicted_log_totalsales]
-
-    # 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__':
-    product_store_sales_total_api.run(debug=True)
+import streamlit as st
+import pandas as pd
+import requests
+
+# Set the title of the Streamlit app
+st.title("Airbnb Product Store Sales Total")
+
+# Section for online prediction
+st.subheader("Online Prediction")
+
+# Collect user input for sales prediction
+product_id = input("Enter Product ID (e.g., FD123): ")
+product_weight = float(input("Enter Product Weight (in grams): "))
+product_sugar_content = input("Enter Sugar Content (Low, Regular, No Sugar): ")
+product_allocated_area = float(input("Enter Product Allocated Area ratio (e.g., 0.04): "))
+product_type = input("Enter Product Type (e.g., Snack Foods, Meat, Dairy): ")
+product_mrp = float(input("Enter Product MRP: "))
+
+store_id = input("Enter Store ID (e.g., STR012): ")
+store_est_year = int(input("Enter Store Establishment Year (e.g., 2012): "))
+store_size = input("Enter Store Size (High, Medium, Low): ")
+store_location_city_type = input("Enter Store City Tier (Tier 1, Tier 2, Tier 3): ")
+store_type = input("Enter Store Type (Departmental Store, Supermarket Type 1, Supermarket Type 2, Food Mart): ")
+
+
+# Convert user input into a DataFrame  
+input_data = {
+    "Product_Id": product_id,
+    "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_Establishment_Year": store_est_year,
+    "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://AshwiniBokade/SuperKartTotalSalesBackend.hf.space/v1/totalsales", json=input_data.to_dict(orient='records')[0])  # Send data to Flask API
+    if response.status_code == 200:
+        prediction = response.json()['Product Store Sales Total']
+        st.success(f"Predicted Product Store Sales Total: {prediction.2f}")
+    else:
+        st.error(f"Prediction failed: {response.text}")
+
+# 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://AshwiniBokade/SuperKartTotalSalesBackend.hf.space/v1/totalsalesbatch", 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.")

requirements.txt

@@ -1,11 +1,3 @@
 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