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:sales_predictor_api"]

app.py

@@ -1,56 +1,91 @@
-import streamlit as st
-import pandas as pd
-import requests
-
-# Set the title of the Streamlit app
-st.title("Superkart Sales Prediction")
-
-# Section for online prediction
-st.subheader("Online Prediction")
-
-# Collect user input for property features
-store_type = st.selectbox("Store Type", ["Supermarket Type1", "Supermarket Type2", "Food Mart", "Departmental Store"])
-store_location_city_type = st.selectbox("Store Location City Type", ['Tier 2' 'Tier 1' 'Tier 3'])
-store_size = st.selectbox("Store Size", ['Medium' 'High' 'Small'])
-store_id = st.selectbox("Store Id", ['OUT004' 'OUT003' 'OUT001' 'OUT002'])
-product_sugar_content = st.number_input("Product Sugar Content", ['Low Sugar', 'Regular', 'No Sugar'])
-product_type = st.selectbox("Product Type", ['Frozen Foods', 'Dairy', 'Canned', 'Baking Goods', 'Health and Hygiene', 'Snack Foods', 'Meat', 'Household', 'Hard Drinks', 'Fruits and Vegetables', 'Breads', 'Soft Drinks', 'Breakfast', 'Others', 'Starchy Foods', 'Seafood'])
-
-# user_name = 'nrajwani'
-# repo_id = "nrajwani/SalesPredictionBackend" 
-
-# Convert user input into a DataFrame
-input_data = pd.DataFrame([{
-    'store_type': store_type,
-    'store_location_city_type': store_location_city_type,
-    'store_size': store_size,
-    'store_id': store_id,
-    'product_sugar_content': product_sugar_content,
-    'product_type': product_type
-}])
-
-# Make prediction when the "Predict" button is clicked
-if st.button("Predict"):
-    response = requests.post("https://<username>-<repo_id>.hf.space/v1/sales", json=input_data.to_dict(orient='records')[0])  # Send data to Flask API
-    if response.status_code == 200:
-        prediction = response.json()['Predicted Sales (in dollars)']
-        st.success(f"Predicted Sales (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://<username>-<repo_id>.hf.space/v1/salesbatch", 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
+sales_predictor_api = Flask("Superkart Sales Predictor")
+
+# Load the trained machine learning model
+model = joblib.load("superkart_sales_prediction_model_v1_0.joblib")
+
+# Define a route for the home page (GET request)
+@sales_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 Sales Prediction API!"
+
+# Define an endpoint for single property prediction (POST request)
+@sales_predictor_api.post('/v1/sales')
+def predict_sales():
+    """
+    This function handles POST requests to the '/v1/sales' 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
+    data = request.get_json()
+
+    # Extract relevant features from the JSON data
+    sample = {
+        'product_sugar_content': data['Product_Sugar_Content'],
+        'product_type': data['Product_Type'],
+        # 'store_establishment_year': data['Store_Establishment_Year'],
+        'store_size': data['Store_Size'],
+        'store_location_city_type': data['Store_Location_City_Type'],
+        'store_type': data['Store_Type'],
+        'store_id': data['Store_Id']
+    }
+
+    # Convert the extracted data into a Pandas DataFrame
+    input_data = pd.DataFrame([sample])
+
+    # Make prediction (get log_price)
+    predicted_log_sales = model.predict(input_data)[0]
+
+    # Calculate actual price
+    predicted_sales = np.exp(predicted_log_sales)
+
+    # Convert predicted_price to Python float
+    predicted_sales = round(float(predicted_sales), 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_sales})
+
+
+# Define an endpoint for batch prediction (POST request)
+@sales_predictor_api.post('/v1/salesbatch')
+def predict_sales_price_batch():
+    """
+    This function handles POST requests to the '/v1/salesbatch' 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_log_sales = model.predict(input_data).tolist()
+
+    # Calculate actual prices
+    predicted_sales = [round(float(np.exp(log_sales)), 2) for log_sales in predicted_log_sales]
+
+    # Create a dictionary of predictions with property IDs as keys
+    store_ids = input_data['Store_Id'].tolist()  # Assuming 'id' is the property ID column
+    output_dict = dict(zip(store_ids, predicted_sales))  # 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__':
+    sales_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