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_revenue_predictor_api"]

app.py

@@ -1,64 +1,92 @@
-import streamlit as st
-import pandas as pd
-import requests
-
-# Set the title of the Streamlit app
-st.title("Sales Revenue Prediction")
-
-# Section for online prediction
-st.subheader("Online Prediction")
-
-# Collect user input for property features
-Product_Id = st.text_input("Product Id")
-Product_Weight = st.number_input("Product Weight", min_value=0.0)
-Product_Sugar_Content = st.selectbox("Product Sugar Content", ["Low Sugar", "No Sugar", "Regular"])
-Product_Allocated_Area = st.number_input("Product Allocated Area", min_value=0.0)
-Product_Type = st.selectbox("Product Type", ["Fruits and Vegetables", "Snack Foods","Frozen Foods","Dairy",
-                                             "Household","Baking Goods","Canned","Health and Hygiene",
-                                             "Meat","Soft Drinks","Breads","Hard Drinks","Others",
-                                             "Starchy Foods","Breakfast","Seafood"])
-Product_MRP = st.number_input("Product MRP", min_value=0.0)
-Store_Id = st.text_input("Store Id")
-Store_Establishment_Year = st.number_input("Store Establishment Year", min_value=0)
-Store_Size = st.selectbox("Store Size", ["Small", "Medium", "High"])
-Store_Location_City_Type = st.selectbox("Store Location City Type", ["Tier 1", "Tier 2", "Tier 3"])
-Store_Type = st.selectbox("Store Type", ["Supermarket Type2", "Supermarket Type1", "Departmental Store","Food Mart"])
-
-
-# Convert user input into a DataFrame
-input_data = pd.DataFrame([{'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_Establishment_Year,
-        '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://pragmat-SalesRevenuePredictionBackend.hf.space/v1/revenue", json=input_data.to_dict(orient='records')[0])  # Send data to Flask API
-    if response.status_code == 200:
-        prediction = response.json()['Predicted Sales Revenue (in dollars)']
-        st.success(f"Predicted Sales 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://pragmat-SalesRevenuePredictionBackend.hf.space/v1/revenuebatch", 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_revenue_predictor_api = Flask("Sales Revenue Predictor")
+
+# Load the trained machine learning model
+model = joblib.load("sales_revenue_prediction_model_v1_0.joblib")
+
+# Define a route for the home page (GET request)
+@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 Sales Revenue Prediction API!"
+
+# Define an endpoint for single property prediction (POST request)
+@sales_revenue_predictor_api.post('/v1/revenue')
+def predict_rental_price():
+    """
+    This function handles POST requests to the '/v1/revenue' endpoint.
+    It expects a JSON payload containing property details and returns
+    the predicted sales revenue 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': product_store_data['Product_Id'],
+        'Product_Weight': product_store_data['Product_Weight'],
+        'Product_Sugar_Content': product_store_data['Product_Sugar_Content'],
+        'Product_Allocated_Area': product_store_data['Product_Allocated_Area'],
+        'Product_Type': product_store_data['Product_Type'],
+        'Product_MRP': product_store_data['Product_MRP'],
+        'Store_Id': product_store_data['Store_Id'],
+        'Store_Establishment_Year': product_store_data['Store_Establishment_Year'],
+        'Store_Location_City_Type': product_store_data['Store_Location_City_Type'],
+        'Store_Type': product_store_data['Store_Type']
+    }
+
+    # Convert the extracted data into a Pandas DataFrame
+    input_data = pd.DataFrame([sample])
+
+    # Make prediction (get product_store_sales_total )
+    predicted_product_Store_Sales_Total = model.predict(input_data)[0]
+
+    # Calculate actual revenue
+    predicted_revenue = np.exp(predicted_product_Store_Sales_Total)
+
+    # Convert predicted_revenue to Python float
+    predicted_revenue = round(float(predicted_revenue), 2)
+   
+    # Return the actual revenue
+    return jsonify({'Predicted Revenue (in dollars)': predicted_revenue})
+
+
+# Define an endpoint for batch prediction (POST request)
+@sales_revenue_predictor_api.post('/v1/revenuebatch')
+def predict_revenue_batch():
+    """
+    This function handles POST requests to the '/v1/revenuebatch' endpoint.
+    It expects a CSV file containing property details for multiple properties
+    and returns the predicted 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 properties in the DataFrame (get predicted_product_Store_Sales_Total)
+    predicted_product_Store_Sales_Total = model.predict(input_data).tolist()
+
+    # Calculate actual revenue
+    predicted_revenue = [round(float(np.exp(log_price)), 2) for log_price in predicted_product_Store_Sales_Total]
+
+    # Create a dictionary of predictions with product IDs as keys
+    ids = str(input_data['Product_Id']+input_data['Store_Id']).tolist()  
+    output_dict = dict(zip(ids, predicted_revenue))  # Use actual revenue
+
+    # 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_revenue_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