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'
#hugging face HATES !python, python. this seems to be okay
exec(open("train.py").read())


# Load the freshly trained model from disk
insurance_model = joblib.load("model.joblib")

# Prepare the logging functionality
log_file = Path("logs/") / f"data_{uuid.uuid4()}.json"
log_folder = log_file.parent

scheduler = CommitScheduler(
    repo_id="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(age, bmi, children, sex, smoker, region):
    # input2 = {
    #     "age": 10,
    #     "bmi": 30,
    #     "children": 6,
    #     "sex": 'female',
    #     "smoker": 'yes',
    #     "region": 'northwest'
    # }
    input = {
        "age": age,
        "bmi": bmi,
        "children": children,
        "sex": sex,
        "smoker": smoker,
        "region": region
    }

    input_df = pd.DataFrame([input])
    prediction = insurance_model.predict(input_df)

    # 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

    # this was already in here so i'm leaving it for loggin
    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
age_input = gr.Number(label="Age")
bmi_input = gr.Number(label="BMI")
children_input = gr.Slider(minimum=0.0, maximum=15.0, step=1.0, label="Children")
sex_input = gr.Radio(['male', 'female'], label="sex")
smoker_input = gr.Radio(choices=['yes', 'no'], label="smoker")
region_input = gr.Dropdown(['southwest', 'southeast', 'northwest', 'northeast'], label="region")
output = gr.Label(label="Insurance Price")

# Create the gradio interface, make title "HealthyLife Insurance Charge Prediction"
# demo was the existing name in this file, so using that.
demo = gr.Interface(
    fn=predict,
    inputs=[age_input, bmi_input, children_input, sex_input, smoker_input, region_input],
    outputs=output,
    title="HealthyLife Insurance Charge Prediction",
    description="This API allows you to predict insurance prices for HealthlyLife Insurance",
    allow_flagging="auto",
    concurrency_limit=8
)

# Launch with a load balancer
# these two lines were in the file already
demo.queue()
# demo.launch(share=True, debug=True)
demo.launch(share=False)