📖

you generate a baseline model quality that you can use to continuously monitor model quality against. To generate the model quality baseline, you first invoke the endpoint created earlier using validation data. Predictions from the deployed model using this validation data are used as a baseline dataset. You can use either the training or validation dataset to create the baseline.

출처

수집시간

2023/01/06 14:18

연결완료

1 more property

probability,prediction,label
0.01516005303710699,0,0
0.1684480607509613,0,0
0.21427156031131744,0,0
0.06330718100070953,0,0
0.02791607193648815,0,0
0.014169521629810333,0,0
0.00571369007229805,0,0
0.10534518957138062,0,0
0.025899196043610573,0,0
Python
복사
test_data/validation_with_predictions.csv

model_quality_monitor = ModelQualityMonitor(
	...
)

job = model_quality_monitor.suggest_baseline(
    job_name=baseline_job_name,
    baseline_dataset=baseline_dataset_uri, # test_data/validation_with_predictions.csv
    dataset_format=DatasetFormat.csv(header=True),
    output_s3_uri = baseline_results_uri,
    problem_type='BinaryClassification',
    inference_attribute= "prediction",
    probability_attribute= "probability",
    ground_truth_attribute= "label"
)
job.wait(logs=False)
Python
복사