app.py

# Import the libraries
import os
import uuid
import joblib
import json

import gradio as gr
import pandas as pd

from huggingface_hub import CommitScheduler
from pathlib import Path


# Run the training script placed in the same directory as app.py
# The training script will train and persist a linear regression
# model with the filename 'model.joblib'
import subprocess
try:
    result = subprocess.run(['python', 'train.py'], check=True, capture_output=True, text=True)
    print(f"Training done.{result.stdout}")
except subprocess.CalledProcessError as e:
    print(f"Error occurred:{e.stderr}")
    exit(1)

# Load the freshly trained model from disk
insurance_charge_predictor = joblib.load('model.joblib')

# Prepare the logging functionality
log_file = Path("logs/") / f"data_{uuid.uuid4()}.json"
log_folder = log_file.parent
log_folder.mkdir(parents=True, exist_ok=True) # mkdir!

scheduler = CommitScheduler(
    repo_id="Keytaro/insurance-charge-mlops-logs",  # provide a name "insurance-charge-mlops-logs" for the repo_id
    repo_type="dataset",
    folder_path=log_folder,
    path_in_repo="data",
    every=2,
)

# Define the predict function which will take features, convert to dataframe and make predictions using the saved model
# the functions runs when 'Submit' is clicked or when a API request is made
def predict_insurance_charge(age, bmi, children, sex, smoker, region):
    # Create a DataFrame from the input values
    input_data = pd.DataFrame(
        [[age, bmi, children, sex, smoker, region]],
        columns=['age', 'bmi', 'children', 'sex', 'smoker', 'region']
    )

    # Make a prediction using the loaded model
    prediction = insurance_charge_predictor.predict(input_data)

    # While the prediction is made, log both the inputs and outputs to a  log file
    # While writing to the log file, ensure that the commit scheduler is locked to avoid parallel
    # access

    with scheduler.lock:
        with log_file.open("a") as f:
            f.write(json.dumps(
                {
                    'age': age,
                    'bmi': bmi,
                    'children': children,
                    'sex': sex,
                    'smoker': smoker,
                    'region': region,
                    'prediction': prediction[0]
                }
            ))
            f.write("\n")

    return prediction[0]



# Set up UI components for input and output
inputs = [
    gr.Number(label="Age (Number)"),
    gr.Number(label="BMI (Number)"),
    gr.Number(label="The number of children (Number)"),
    gr.Dropdown(label="Sex", choices=["male", "female"]),
    gr.Dropdown(label="Smoker", choices=["yes", "no"]),
    gr.Dropdown(label="Region", choices=["northeast", "northwest", "southeast", "southwest"])
]

output = gr.Number(label="Predicted Insurance Charge")

# Create the gradio interface, make title "HealthyLife Insurance Charge Prediction"
demo = gr.Interface(
    fn=predict_insurance_charge,
    inputs=inputs,
    outputs=output,
    title="HealthyLife Insurance Charge Predictor",
    description="This API allows you to predict the insurance charges based on personal health data.",
    allow_flagging="auto", #
    concurrency_limit=8 #
)

# Launch with a load balancer
demo.queue()
demo.launch(share=False)