import numpy as np
import pandas as pd
from joblib import load
import gradio as gr
from tensorflow.keras.models import load_model


# filepaths
column_transform_path = "assets/column_transformer.joblib" # change during the creation of the huggingface app
model_path = "assets/insurance_regression_model.keras" # change during the creation of the huggingface app

# instance the models
column_transformer = load(column_transform_path)
insurance_model = load_model(model_path)

# short description of the stuff
title = "Insurance Regressor Model"
description = "POC of a deep learning regression model for estimating insurance charges based on 11 input variables."
article = "The model was implemented in tensorflow. It is simple as i made it as a refresher for reviewing the Tensorflow fundamentals (the problem most likely could be solved using classical regression). The dataset used was [Medical Cost Personal Datasets](https://www.kaggle.com/datasets/mirichoi0218/insurance)."

# processing function
def insurance_prediction(age,gender,bmi,children,smoker,region):
  columns = ['age', 'sex', 'bmi', 'children', 'smoker', 'region']
  # transform some data to the datatypes compatible with column transfomer
  age = int(age)
  gender = "male" if gender else "female"
  children = int(children)
  smoker = "yes" if smoker else "no"
  region = region[0] if len(region) > 0 else 'northeast' # since it is a proof of concept, i left the value there.
  # arange the values into a list
  values = [age,gender,bmi,children,smoker,region]
  # create a dictionary to structure the sample at hand
  sample = {k:v for k,v in zip(columns,values)}
  # create a dataframe using the sample 
  X = pd.DataFrame(data = pd.Series(sample)).T
  # preprocess the dataframe
  X_preprocessed = column_transformer.transform(X)
  # make the prediction accordingly 
  y_pred = insurance_model.predict(X_preprocessed)
  return y_pred[0][0]





demo = gr.Interface(
    fn = insurance_prediction,
    inputs = [
        gr.Number(value = 40,label = "Age",show_label=True),
        gr.Checkbox(value = False,label = "Male",show_label = True),
        gr.Number(value = 30,label = "Body Mass Index",show_label=True),
        gr.Number(value = 1,label = "Number of Children",show_label=True),
        gr.Checkbox(value = False,label = "Smoker",show_label = True),
        gr.CheckboxGroup(choices = ['northeast', 'northwest', 'southeast', 'southwest'],
                         value = ['northeast', 'northwest', 'southeast', 'southwest'],
                         label="Region",
                         info="Will only take into consideration the fist one selected.")
        ],
    outputs = [
        gr.Number(label = "Insurance Charges Estimate (American Dollars)")
        ],
    title = title,
    description = description,
    article = article
)

demo.launch()