Upload folder using huggingface_hub

Dockerfile

@@ -1,22 +1,16 @@
 FROM python:3.9-slim
 
+# Set the working directory inside the container
 WORKDIR /app
 
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    curl \
-    software-properties-common \
-    git \
-    && rm -rf /var/lib/apt/lists/*
+# Copy all files from the current directory to the container's working directory
+COPY . .
 
-COPY requirements.txt ./
-COPY app.py ./src/
-COPY rental_price_prediction_model_v1_0.joblib ./
+# Install dependencies from the requirements file without using cache to reduce image size
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
 
-RUN pip3 install -r requirements.txt
-
-EXPOSE 8501
-
-HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
-
-ENTRYPOINT ["streamlit", "run", "src/app.py", "--server.port=8501", "--server.address=0.0.0.0"]
+# 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"]

app.py

@@ -1,47 +1,93 @@
-
-import streamlit as st
-import pandas as pd
-import joblib
+# 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
+rental_price_predictor_api = Flask("Airbnb Rental Price Predictor")
+
+# Load the trained machine learning model
+model = joblib.load("rental_price_prediction_model_v1_0.joblib")
+
+# Define a route for the home page (GET request)
+@rental_price_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 Airbnb Rental Price Prediction API!"
+
+# Define an endpoint for single property prediction (POST request)
+@rental_price_predictor_api.post('/v1/rental')
+def predict_rental_price():
+    """
+    This function handles POST requests to the '/v1/rental' 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
+    property_data = request.get_json()
+
+    # Extract relevant features from the JSON data
+    sample = {
+        'room_type': property_data['room_type'],
+        'accommodates': property_data['accommodates'],
+        'bathrooms': property_data['bathrooms'],
+        'cancellation_policy': property_data['cancellation_policy'],
+        'cleaning_fee': property_data['cleaning_fee'],
+        'instant_bookable': property_data['instant_bookable'],
+        'review_scores_rating': property_data['review_scores_rating'],
+        'bedrooms': property_data['bedrooms'],
+        'beds': property_data['beds']
+    }
+
+    # 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]
+
+    # 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({'Predicted Price (in dollars)': predicted_price})
+
+
+# Define an endpoint for batch prediction (POST request)
+@rental_price_predictor_api.post('/v1/rentalbatch')
+def predict_rental_price_batch():
+    """
+    This function handles POST requests to the '/v1/rentalbatch' 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_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 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
 
-# Load the trained model
-@st.cache_resource
-def load_model():
-    return joblib.load("rental_price_prediction_model_v1_0.joblib")
-
-model = load_model()
-
-# Streamlit UI for Price Prediction
-st.title("Airbnb Rental Price Prediction App")
-st.write("This tool predicts the price of an Airbnb listing based on the property details.")
-
-st.subheader("Enter the listing details:")
-
-# Collect user input
-room_type = st.selectbox("Room Type", ["Entire home/apt", "Private room", "Shared room"])
-accommodates = st.number_input("Accommodates (Number of guests)", min_value=1, value=2)
-bathrooms = st.number_input("Bathrooms", min_value=1, step=1, value=2)
-cancellation_policy = st.selectbox("Cancellation Policy (kind of cancellation policy)", ["strict", "flexible", "moderate"])
-cleaning_fee = st.selectbox("Cleaning Fee Charged?", ["True", "False"])
-instant_bookable = st.selectbox("Instantly Bookable?", ["False", "True"])
-review_scores_rating = st.number_input("Review Score Rating", min_value=0.0, max_value=100.0, step=1.0, value=90.0)
-bedrooms = st.number_input("Bedrooms", min_value=0, step=1, value=1)
-beds = st.number_input("Beds", min_value=0, step=1, value=1)
-
-# Convert user input into a DataFrame
-input_data = pd.DataFrame([{
-    'room_type': room_type,
-    'accommodates': accommodates,
-    'bathrooms': bathrooms,
-    'cancellation_policy': cancellation_policy,
-    'cleaning_fee': cleaning_fee,
-    'instant_bookable': 'f' if instant_bookable=="False" else "t",
-    'review_scores_rating': review_scores_rating,
-    'bedrooms': bedrooms,
-    'beds': beds
-}])
-
-# Predict button
-if st.button("Predict"):
-    prediction = model.predict(input_data)
-    st.write(f"The predicted price of the rental property is ${np.exp(prediction)[0]:.2f}.")
+# Run the Flask application in debug mode if this script is executed directly
+if __name__ == '__main__':
+    rental_price_predictor_api.run(debug=True)

requirements.txt

@@ -3,4 +3,9 @@ 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