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 +1,96 @@
+# 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
+cust_predictor_api = Flask("ExtraaLearn Customer Predictor")
+
+# Load the trained machine learning model
+model = joblib.load("customer_prediction_model_v1_0.joblib")
+
+# Define a route for the home page (GET request)
+@cust_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 Customer Prediction API!"
+
+classification_threshold = 0.45
+
+# Define an endpoint for customer prediction (POST request)
+@cust_predictor_api.post('/v1/cust_lead')
+def predict_cust_lead():
+    """
+    This function handles POST requests to the '/v1/cust_lead' endpoint.
+    It expects a JSON payload containing customer details and returns
+    the predicted customer probability as a JSON response.
+    """
+    # Get the JSON data from the request body
+    cust_data = request.get_json()
+
+    # Extract relevant features from the JSON data
+    sample = {
+		'age' 	: cust_data['age'],
+		'current_occupation' 	: cust_data['current_occupation'],
+		'first_interaction' 	: cust_data['first_interaction'],
+		'profile_completed' 	: cust_data['profile_completed'],
+		'website_visits' 	: cust_data['website_visits'],
+		'time_spent_on_website' 	: cust_data['time_spent_on_website'],
+		'page_views_per_visit' 	: cust_data['page_views_per_visit'],
+		'last_activity' 	: cust_data['last_activity'],
+		'print_media_type1' 	: cust_data['print_media_type1'],
+		'print_media_type2' 	: cust_data['print_media_type2'],
+		'digital_media' 	: cust_data['digital_media'],
+		'educational_channels' 	: cust_data['educational_channels'],
+		'referral' 	: cust_data['referral']
+    }
+
+    # Convert the extracted data into a Pandas DataFrame
+    input_data = pd.DataFrame([sample])
+
+    # Make prediction
+    predicted_cust = model.predict_proba(input_data)[0][1]
+
+    # convert continuous prob as 0/1
+    predicted_cust = (predicted_cust >= classification_threshold).astype(int)
+
+    # Return the actual prediction status
+    return jsonify({'Predicted customer status': predicted_cust})
+
+
+# Define an endpoint for batch prediction (POST request)
+@cust_predictor_api.post('/v1/cust_lead_batch')
+def predict_cust_lead_batch():
+    """
+    This function handles POST requests to the '/v1/cust_lead_batch' endpoint.
+    It expects a CSV file containing property details for multiple properties
+    and returns the predicted status 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_cust_list = model.predict_proba(input_data)[0][1]
+    predicted_cust_list = predicted_cust_list.tolist()
+
+    # Calculate actual prices
+    predicted_cust_list = [round(float(np.exp(log_price)), 2) for log_price in predicted_log_prices]
+    predicted_cust_list = [(predicted_cust >= classification_threshold).astype(int)  for predicted_cust in predicted_cust_list]
+
+    # Create a dictionary of predictions with customer IDs as keys
+    ids = input_data['ID'].tolist()
+    output_dict = dict(zip(ids, predicted_cust_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__':
+    cust_predictor_api.run(debug=True)

customer_prediction_model_v1_0.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e2425b12bddf6216ec8c59f98d436ca8208715459c071d369c456457028d292
+size 54050

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