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 passenger(passengerid, survived, pclass,age, sex, sibsp,parch):
    input_list = []
    input_list.append(passengerid)
    input_list.append(survived)
    input_list.append(pclass)
    input_list.append(age)
    input_list.append(sex)
    input_list.append(sibsp)
    input_list.append(parch)
    # '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.
    titanic_url = "https://raw.githubusercontent.com/AbyelT/ID2223-Scalable-ML-and-DL/main/Lab1/Titanic/assets/" + res[0] + ".png"
    img = Image.open(requests.get(titanic_url, stream=True).raw)            
    return img
        
demo = gr.Interface(
    fn=passenger,
    title="Titanic Survival Predictive Analytics",
    #description="Experiment with sepal/petal lengths/widths to predict which flower it is.",
    allow_flagging="never",
    inputs=[
        gr.inputs.Number(default=1.0, label="passengerid"),
        gr.inputs.Number(default=1.0, label="survived"),
        gr.inputs.Number(default=1.0, label="pclass"),
        gr.inputs.Number(default=1.0, label="age"),
        gr.inputs.Number(default=1.0, label="sex"),
        gr.inputs.Number(default=1.0, label="sibsp"),
        gr.inputs.Number(default=1.0, label="parch"),
        ],
    outputs=gr.Image(type="pil"))

demo.launch()