app.py

# 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)