import gradio as gr
import numpy as np
from PIL import Image
import requests
import xgboost

import hopsworks
import joblib

project = hopsworks.login()
fs = project.get_feature_store()


mr = project.get_model_registry()
model = mr.get_model("titanic_modal", version=1)
model_dir = model.download()
model = joblib.load(model_dir + "/titanic_model.pkl")


def titanic(pclass, sex, age, sibs, par_ch, fare, deck, embarked):
    input_list = []
    input_list.append(pclass)
    input_list.append(sex)
    input_list.append(age)
    input_list.append(sibs)
    input_list.append(par_ch)
    input_list.append(fare)
    input_list.append(deck)
    input_list.append(embarked)
    # 'res' is a list of predictions returned as the label.
    res = model.predict(np.asarray(input_list).reshape(1, -1)) 
    # We add '[0]' to the result of the transformed 'res', because 'res' is a list, and we only want 
    # the first element.

    return res[0]
        
demo = gr.Interface(
    fn=titanic,
    title="Titanic Survival Predictive Analytics",
    description="Experiment with passenger class, sex, age, siblings, parents/children, fare, deck, and embarked to predict if a hypothetical passenger survived titanic.",
    allow_flagging="never",
    inputs=[
        gr.inputs.Number(default=0.0, label="Passenger class"),
        gr.inputs.Number(default=0.0, label="Sex"),
        gr.inputs.Number(default=0.0, label="Age"),
        gr.inputs.Number(default=0.0, label="Siblings"),
        gr.inputs.Number(default=0.0, label="Parents/Children"),
        gr.inputs.Number(default=0.0, label="Fare"),
        gr.inputs.Number(default=0.0, label="Deck"),
        gr.inputs.Number(default=0.0, label="Embarked"),
        ],
    outputs=gr.inputs.Number(label="Survived"))

demo.launch()