inference.py

"""
Obtain Predictions for Machine Failure Predictor Model using Gradio Client
======================================================================

This script connects to a deployed machine failure predictor model using Gradio Client,
fetches the dataset, preprocesses the data, and generates predictions for a
sample of test data using the deployed model. The resulting predictions are
stored in a list. A time delay of one second is added after each prediction
submission to avoid overloading the model server.
"""

import time

from gradio_client import Client

from sklearn.datasets import fetch_openml
from sklearn.model_selection import train_test_split


client = Client("pgurazada1/machine-failure-predictor")

dataset = fetch_openml(data_id=42890, as_frame=True, parser="auto")

data_df = dataset.data

target = 'Machine failure'
numeric_features = [
    'Air temperature [K]',
    'Process temperature [K]',
    'Rotational speed [rpm]',
    'Torque [Nm]',
    'Tool wear [min]'
]
categorical_features = ['Type']

X = data_df[numeric_features + categorical_features]
y = data_df[target]

Xtrain, Xtest, ytrain, ytest = train_test_split(
    X, y,
    test_size=0.2,
    random_state=42
)

Xtest_sample = Xtest.sample(100)

Xtest_sample_rows = list(Xtest_sample.itertuples(index=False, name=None))

batch_predictions = []

for row in Xtest_sample_rows:
    try:
        job = client.submit(
            air_temperature=row[0],
            process_temperature=row[1],
            rotational_speed=row[2],
            torque=row[3],
            tool_wear=row[4],
            type=row[5],
            api_name="/predict"
        )

        batch_predictions.append(job.result())

        time.sleep(1)

    except Exception as e:
        print(e)