app.py

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

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")

df = pd
features = pd.read_csv(
    "https://raw.githubusercontent.com/Nathanotal/remoteFiles/main/titanicCleaned.csv")
features = features.drop(columns=["survived"])
featureLabels = features.columns


def titanic(input_list):
    # '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.
    # Todo: survivor, "https://fakeface.rest/face/json?maximum_age=50&gender=female&minimum_age=49"
    survivor_url = 'https://picsum.photos/200/300'
    img = Image.open(requests.get(survivor_url, stream=True).raw)
    return img


inputs = []
for feature in featureLabels:
    inputs.append(gr.inputs.Number(default=1.0, label=feature))

demo = gr.Interface(
    fn=titanic,
    title="Titanic Survivor Predictive Analytics",
    description="Experiment with person features to predict which survivor it is.",
    allow_flagging="never",
    inputs=inputs,
    outputs=gr.Image(type="pil"))

demo.launch()