Upload folder using huggingface_hub

Dockerfile

@@ -0,0 +1,16 @@
+FROM python:3.9-slim
+
+# Set the working directory inside the container
+WORKDIR /app
+
+# Copy all files from the current directory to the container's working 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
+
+# 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

@@ -0,0 +1,105 @@
+# 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
+extraalearn_predictor_api = Flask("Extraalearn Predictor")
+
+# Load the trained machine learning model
+model = joblib.load("extraalearn_model_v1_0.joblib")
+
+# Define a route for the home page (GET request)
+@extraalearn_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 ExtraaLearn Prediction API!"
+
+# Define an endpoint for prediction (POST request)
+@extraalearn_predictor_api.post('/v1/extraalearn')
+def predict_rental_price():
+    """
+    This function handles POST requests to the '/v1/extraalearn' endpoint.
+    It expects a JSON payload containing property details and returns
+    the predicted product 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 =
+
+    {
+    'ID': data['ID'],
+    'Age': data['age'],
+    'Current_Occupation': data['current_occupation'],
+    'First_Interaction': data['first_interaction'],
+    'Profile_Completed': data['profile_completed'],
+    'Website_Visits': data['website_visits'],
+    'Time_Spent_On_Website': data['time_spent_on_website'],
+    'Page_Views_Per_Visit': data['page_views_per_visit'],
+    'Last_Activity': data['last_activity'],
+    'Print_Media_Type1': data['print_media_type1'],
+    'Print_Media_Type2': data['print_media_type2'],
+    'Digital_Media': data['digital_media'],
+    'Educational_Channels': data['educational_channels'],
+    'Referral': data['referral'],
+    'Status': data['status']
+
+
+}
+
+    # 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)
+@extraalearn_predictor_api.post('/v1/extraalearnbatch')
+def predict_rental_price_batch():
+    """
+    This function handles POST requests to the '/v1/extraalearnbatch' 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_status = [round(float(np.exp(log_price)), 2) for log_price in predicted_log_prices]
+
+    # Create a dictionary of predictions with property IDs as keys
+ # Example: using 'ID' as the key
+    ids = input_data['ID'].tolist()   # This is like Product_Id
+    output_dict = dict(zip(ids, predicted_status))  # predicted_status = your model's output list
+
+
+    # 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__':
+    extraalearn_predictor_api.run(debug=True)

extraalearn_model_v1_0.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dc9ab9fac09a2b8663913336d98c12b35e22918d66659a91a25ccd3421846f5
+size 272846

requirements.txt

@@ -0,0 +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