# Importing 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


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

scheduler = CommitScheduler(
     repo_id="Insurance_Charge_Prediction_Project",
     repo_type="dataset",
     folder_path=log_folder,
     path_in_repo="data",
     every=2
 )

charges_predictor = joblib.load("model.joblib")


# Inputs

age_input = gr.Number(label="Age")
bmi_input = gr.Number(label="BMI")
children_input = gr.Number(label="Children")

sex_input = gr.Dropdown(
    ["male", "female"],
    label="Sex"
)

smoker_input = gr.Dropdown(
    ["yes", "no"],
    label="Smoker"
)

region_input = gr.Dropdown(
    ["southeast", "southwest", "northeast", "northwest"],
    label="Region"
)


model_output = gr.Textbox(label="Predicted Insurance Cost")


# prediction function

def predict_charges(age, bmi, children, sex, smoker, region):

    sample = {
        "age": age,
        "bmi": bmi,
        "children": children,
        "sex": sex,
        "smoker": smoker,
        "region": region
    }

    data_point = pd.DataFrame([sample])

    prediction = charges_predictor.predict(data_point).tolist()

    # logging
    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 f"${prediction[0]:,.2f}"


# UI

demo = gr.Interface(
    fn=predict_charges,
    inputs=[
        age_input,
        bmi_input,
        children_input,
        sex_input,
        smoker_input,
        region_input
    ],
    outputs=model_output,
    title="HealthyLife Insurance Charge Prediction",
    description="Predict the insurance medical charges based on patient information",
    flagging_mode="manual",
    concurrency_limit=8
)


demo.queue()
demo.launch()