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_model_api"]

app.py

@@ -1,82 +1,95 @@
-import streamlit as st
-import pandas as pd
-import requests
-
-# Set the title of the Streamlit app
-st.title("SuperKart's Deceison Making Model")
-
-# Section for online prediction
-st.subheader("Online SuperKart's Model")
-
-# Collect user input for property features
-# Product features
-product_weight = st.number_input("Product Weight (in grams)", min_value=0.0, step=0.1)
-product_sugar_content = st.selectbox(
-    "Product Sugar Content",
-    ["Low Sugar", "Regular", "No Sugar"]  # make sure matches your training dataset categories
-)
-product_allocated_area = st.number_input(
-    "Producted Allocated Area (sq. ft.)", min_value=0.01, step=0.01, value=0.01
-)
-product_type = st.selectbox(
-    "Product Type",
-    ["Dairy", "Snack", "Beverage", "Household", "Frozen", "Health"]  # adjust based on dataset
-)
-product_mrp = st.number_input(
-    "Product MRP (in dollars)", min_value=1.0, step=0.5, value=10.0
-)
-# Store features
-store_establishment_year = st.number_input(
-    "Store Establishment Year", min_value=1900, max_value=2025, step=1, value=2000
-)
-store_size = st.selectbox(
-    "Store Size",
-    ["Small", "Medium", "High"]  # adjust categories to dataset
-)
-store_location_city_type = st.selectbox(
-    "Store Location City Type",
-    ["Tier 1", "Tier 2", "Tier 3"]  # typical encoding in retail datasets
-)
-store_type = st.selectbox(
-    "Store Type",
-    ["Grocery Store", "Supermarket", "Hypermarket"]  # adjust to match dataset
-)
-
-# 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_establishment_year': store_establishment_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://anithajk-SuperKart_Model_Deployment.hf.space/v1/productsale", 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://anithajk-SuperKart_Model_Deployment.hf.space/v1/productsalebatch", 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_model_api = Flask("SuperKart’s Decision-Making System")
+
+# Load the trained machine learning model
+model = joblib.load("deployment_files/superkart_decision_making_model_v1_0.joblib")
+
+# Define a route for the home page (GET request)
+@superkart_model_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’s Decision-Making System API!"
+
+# Define an endpoint for single product sale prediction (POST request)
+@superkart_model_api.post('/v1/productsale')
+def predict_product_sales():
+    """
+    This function handles POST requests to the '/v1/productsale' endpoint.
+    It expects a JSON payload containing product and store details and returns
+    total revenue by the sale of that particular product in that particular store as a JSON response.
+    """
+    # Get the JSON data from the request body
+    product_data = request.get_json()
+
+    # Extract relevant features from the JSON data
+    sample = {
+        'product_weight': product_data['product_weight'],
+        'product_sugar_content': product_data['product_sugar_content'],
+        'product_allocated_area': product_data['product_allocated_area'],
+        'product_type': product_data['product_type'],
+        'product_mrp': product_data['product_mrp'],
+        'store_establishment_year': product_data['store_establishment_year'],
+        'store_size': product_data['store_size'],
+        'store_location_city_type': product_data['store_location_city_type'],
+        'store_type': product_data['store_type']
+    }
+
+    # Convert the extracted data into a Pandas DataFrame
+    input_data = pd.DataFrame([sample])
+
+    # Make prediction (get log_price)
+    predicted_log_price = model.predict(input_data)[0]
+    print(f"Predicted log price: {predicted_log_price}")
+
+    # Calculate actual price
+    predicted_price = np.exp(predicted_log_price)
+
+    # 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({'Total Revenue (in dollars)': predicted_price})
+
+
+# Define an endpoint for batch prediction (POST request)
+@superkart_model_api.post('/v1/productsalebatch')
+def predict_product_sale_price_batch():
+    """
+    This function handles POST requests to the '/v1/productsalebatch' endpoint.
+    It expects a CSV file containing product and store details and returns the predicted
+    total 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
+    input_data = pd.read_csv(file)
+
+    # Make predictions for all product sale in the stores in the DataFrame (get log_prices)
+    predicted_log_prices = model.predict(input_data).tolist()
+
+    # Calculate actual prices
+    predicted_prices = [round(float(np.exp(log_price)), 2) for log_price in predicted_log_prices]
+
+    # Create a dictionary of predictions with product IDs as keys
+    product_ids = input_data['id'].tolist()  # Assuming 'id' is the product ID column
+    output_dict = dict(zip(product_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_model_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

superkart_decision_making_model_v1_0.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a75f9ddeac467a30178c6147ec5601df2397f3de05d36dae990c142a40b1b2c3
+size 351975