Create inference.py

inference.py

@@ -0,0 +1,68 @@
+"""
+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)