app.py

import gradio as gr
from PIL import Image
import requests
import hopsworks
import joblib
import pandas as pd

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


mr = project.get_model_registry()
model = mr.get_model("wine_model", version=1)
model_dir = model.download()
model = joblib.load(model_dir + "/wine_model.pkl")
print("Model downloaded")

def wine(type,fixed_acidity,volatile_acidity,citric_acid,residual_sugar,chlorides,free_sulfur_dioxide,total_sulfur_dioxide,density,ph,sulphates,alcohol):
    print("Calling function")
    df = pd.DataFrame([[type,fixed_acidity,volatile_acidity,citric_acid,residual_sugar,chlorides,free_sulfur_dioxide,total_sulfur_dioxide,density,ph,sulphates,alcohol]], 
                      columns=['type','fixed_acidity','volatile_acidity','citric_acid','residual_sugar','chlorides','free_sulfur_dioxide','total_sulfur_dioxide','density','ph','sulphates','alcohol'])
    print("Predicting")
    print(df)
    # 'res' is a list of predictions returned as the label.
    res = model.predict(df)
    # We add '[0]' to the result of the transformed 'res', because 'res' is a list, and we only want 
    # the first element.
#     print("Res: {0}").format(res)
    print(res)
    # flower_url = "https://raw.githubusercontent.com/featurestoreorg/serverless-ml-course/main/src/01-module/assets/" + res[0] + ".png"
    # img = Image.open(requests.get(flower_url, stream=True).raw)            
    return res[0]
        
demo = gr.Interface(
    fn=wine,
    title="Wine Predictive Analytics",
    description="Experiment with wine features to predict which quality of wine it is.",
    allow_flagging="never",
    inputs=[
        gr.Number(value=0, label="type 0 for white, 1 for red"),
        gr.Number(value=7.0, label="fixed_acidity"),
        gr.Number(value=0.0, label="volatile_acidity"),
        gr.Number(value=0.0, label="citric_acid"),
        gr.Number(value=5.0, label="residual_sugar"),
        gr.Number(value=0.0, label="chlorides"),
        gr.Number(value=30.0, label="free_sulfur_dioxide"),
        gr.Number(value=115.0, label="total_sulfur_dioxide"),
        gr.Number(value=1.0, label="density"),
        gr.Number(value=3.0, label="ph"),
        gr.Number(value=0.0, label="sulphates"),
        gr.Number(value=10.0, label="alcohol")
        ],
    outputs=gr.Label("Predicted Quality")
)

demo.launch(debug=True)