app.py

import gradio as gr
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")
model_dir = model.download()
model = joblib.load(model_dir + "/wine_model.pkl")
print("Model downloaded")

def wine(fixed_acidity, volatile_acidity, citric_acid, residual_sugar, chlorides, total_sulfur_dioxide, ph, sulphates, alcohol, type):

    if type == "red":
        type = 0
    else:
        type = 1

    print("Calling function")
    df = pd.DataFrame([[fixed_acidity, volatile_acidity, citric_acid, residual_sugar, chlorides, total_sulfur_dioxide, ph, sulphates, alcohol, type]], columns=['fixed acidity', 'volatile acidity', 'citric acid', 'residual sugar', 'chlorides', 'total sulfur dioxide', 'ph', 'sulphates', 'alcohol', 'type'])

    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)
    return res[0]

iface = gr.Interface(
    fn=wine, 
    title="Wine Quality Prediction", 
    description="Predict the quality of a wine based on its features.",
    allow_flagging="never",
    inputs=[
        gr.Number(label="fixed_acidity"),
        gr.Number(label="volatile_acidity"),
        gr.Number(label="citric_acid"),
        gr.Number(label="residual_sugar"),
        gr.Number(label="chlorides"),
        gr.Number(label="total_sulfur_dioxide"),
        gr.Number(label="ph"),
        gr.Number(label="sulphates"),
        gr.Number(label="alcohol"),
        gr.Radio(["red", "white"], label="type")
        ],
    outputs=gr.Number(label="quality"))

iface.launch()