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:future_sale_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

@@ -1,67 +1,64 @@
-import joblib
+import requests
+import streamlit as st
 import pandas as pd
-from flask import Flask, request, jsonify
 
-# Initialize Flask app with a name
-future_sale_predictor_api = Flask("SuperKart Sales Predictor")
+st.title("SuperKart Sales Prediction")
 
-# Load the trained sales prediction model
-model = joblib.load("deployment_files/xgb_tuned_model.joblib")
+# Online Prediction (Single Product-Store Combination)
+st.subheader("Online Prediction")
 
-# Define a route for the home page
-@future_sale_predictor_api.get('/')
-def home():
-    return "Welcome to the SuperKart Sales Prediction API!, Created by Kumar Utkarsh"
+# Input fields for product-store data
+Product_Weight = st.number_input("Product Weight", min_value=0.0, value=10.0)
+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, value=0.1)
+Product_Type = st.selectbox("Product Type", ['Frozen Foods', 'Dairy', 'Canned', 'Baking Goods', 'Health and Hygiene', 'Snack Foods', 'Household', 'Meat', 'Soft Drinks', 'Breads', 'Hard Drinks', 'Others', 'Starchy Foods', 'Breakfast', 'Seafood'])
+Product_MRP = st.number_input("Product MRP", min_value=0.0, value=100.0)
+Store_Id = st.selectbox("Store ID", ['OUT004', 'OUT003', 'OUT001', 'OUT002'])
+Store_Establishment_Year = st.number_input("Store Establishment Year", min_value=1900, max_value=2024, value=2000)
+Store_Size = st.selectbox("Store Size", ["Medium", "High", "Small"])
+Store_Location_City_Type = st.selectbox("Store Location City Type", ["Tier 2", "Tier 1", "Tier 3"])
+Store_Type = st.selectbox("Store Type", ["Supermarket Type2", "Departmental Store", "Supermarket Type1", "Food Mart"])
 
-# Define an endpoint to predict sales for a single product-store combination
-@future_sale_predictor_api.post('/v1/predict_sale')
-def predict_sale():
-    # Get JSON data from the request
-    sale_data = request.get_json()
 
-    # Extract relevant product-store information from the input data
-    # Ensure these keys match the expected input features for your trained model
-    sample = {
-        'Product_Weight': sale_data['Product_Weight'],
-        'Product_Sugar_Content': sale_data['Product_Sugar_Content'],
-        'Product_Allocated_Area': sale_data['Product_Allocated_Area'],
-        'Product_Type': sale_data['Product_Type'],
-        'Product_MRP': sale_data['Product_MRP'],
-        'Store_Id': sale_data['Store_Id'],
-        'Store_Establishment_Year': sale_data['Store_Establishment_Year'],
-        'Store_Size': sale_data['Store_Size'],
-        'Store_Location_City_Type': sale_data['Store_Location_City_Type'],
-        'Store_Type': sale_data['Store_Type']
-    }
+product_store_data = {
+    '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_Establishment_Year,
+    'Store_Size': Store_Size,
+    'Store_Location_City_Type': Store_Location_City_Type,
+    'Store_Type': Store_Type
+}
 
-    # Convert the extracted data into a DataFrame
-    input_data = pd.DataFrame([sample])
+backend_url = "https://kutkarsh200-SuperKart.hf.space"
 
-    # Make a sales prediction using the trained model
-    prediction = model.predict(input_data).tolist()[0]
+if st.button("Predict Sale", type='primary'):
+    response = requests.post(f"{backend_url}/v1/predict_sale", json=product_store_data)
+    if response.status_code == 200:
+        result = response.json()
+        predicted_sale = result["Predicted_Sales"]
+        st.write(f"The predicted sales for this product-store combination is: {predicted_sale:.2f}")
+    else:
+        st.error(f"Error in API request: {response.status_code}")
+        st.error(f"Response: {response.text}")
 
-    # Return the prediction as a JSON response
-    return jsonify({'Predicted_Sales': prediction})
 
-# Define an endpoint to predict sales for a batch of product-store combinations
-@future_sale_predictor_api.post('/v1/predict_sales_batch')
-def predict_sales_batch():
-    # Get the uploaded CSV file from the request
-    file = request.files['file']
+# Batch Prediction
+st.subheader("Batch Prediction")
 
-    # Read the file into a DataFrame
-    input_data = pd.read_csv(file)
+file = st.file_uploader("Upload CSV file for Batch Prediction", type=["csv"])
+if file is not None:
+    if st.button("Predict for Batch", type='primary'):
+        response = requests.post(f"{backend_url}/v1/predict_sales_batch", files={"file": file})
 
-    # Make predictions for the batch data
-    # Assuming the input CSV for batch prediction has the same columns as the training data
-    predictions = model.predict(input_data).tolist()
-
-    # You might want to return predictions linked to an identifier if available in the batch input
-    # For simplicity, returning a list of predictions
-    return jsonify({'Predicted_Sales_Batch': predictions})
-
-
-# Run the Flask app in debug mode
-if __name__ == '__main__':
-    # Port 7860 is used
-    future_sale_predictor_api.run(debug=True, host='0.0.0.0', port=7860)
+        if response.status_code == 200:
+            result = response.json()
+            st.header("Batch Prediction Results")
+            predictions_df = pd.DataFrame(result['Predicted_Sales_Batch'], columns=['Predicted_Sales'])
+            st.write(predictions_df)
+        else:
+            st.error(f"Error in API request: {response.status_code}")
+            st.error(f"Response: {response.text}")

requirements.txt

@@ -1,8 +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
+streamlit==1.43.2