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

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, fare):
    input_list = []

    bins = [-np.infty, 20, 25, 29, 30, 40, np.infty]
    input_list.append(int(np.digitize([age], bins)[0]))
    input_list.append(int(sex))
    input_list.append(int(pclass + 1))
    input_list.append(fare)
    # '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.
    # print('The result we get :: ', str(res[0]))
    passenger_survival_url = "https://raw.githubusercontent.com/abdullabdull/id2223-images/main/" + str(res[0]) + ".png"
    img = Image.open(requests.get(passenger_survival_url, stream=True).raw)
    return img


demo = gr.Interface(
    fn=titanic,
    title="Titanic Survival Predictive Analytics",
    description="Experiment with different passenger features to predict if they survived or not.",
    allow_flagging="never",
    inputs=[
        gr.inputs.Dropdown(choices=["Class 1", "Class 2", "Class 3"], type="index", label="Pclass"),
        gr.inputs.Dropdown(choices=["Male", "Female"], type="index", label="Sex"),
        gr.inputs.Number(default=1, label="Age"),
        gr.inputs.Slider(minimum=0, maximum=550, default=50, label="Fare"),
    ],
    outputs=gr.Image(type="pil"))

demo.launch()