# 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

# Load the freshly trained model from disk
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-logs",
    repo_type="dataset",
    folder_path=log_folder,
    path_in_repo="data",
    every=2
)


# Define the input components
age_input = gr.Slider(minimum=18, maximum=64, step=1, label='Age')
sex_input = gr.Dropdown(['female','male'], label='Sex')
bmi_input = gr.Slider(minimum=15, maximum=50, step=1, label='BMI')

smoker_input = gr.Dropdown(['no','yes'], label='Smoker')
region_input = gr.Dropdown(['northeast', 'northwest', 'southeast', 'southwest'], label='Region')

# Define the output component
model_output = gr.Label(label='Insurance Charge Prediction')

# Define the predict function which will take features, convert to dataframe and make predictions using the saved model

def predict_insurance_charges(age, sex, bmi, smoker, region):

    # Create a dataframe with the input features
    sample = {
        'age': age,
        'sex': sex,
        'bmi': bmi,
        'smoker': smoker,
        'region': region
    }
    data_point = pd.DataFrame([sample])
 
    prediction = model.predict(data_point).tolist()

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

# Create the interface
demo = gr.Interface(
    fn=predict_insurance_charges,
    inputs=[age_input, sex_input, bmi_input, smoker_input, region_input],
    outputs=model_output,
    title="HealthyLife Insurance Charge Prediction",
    description="This API allows you to predict the... ",
    allow_flagging="auto",
    concurrency_limit=8
)

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