Periksa Laporan untuk Penyimpangan Atribut Fitur dalam Model Produksi

Setelah jadwal yang Anda atur dimulai secara default, Anda harus menunggu eksekusi pertamanya dimulai, dan kemudian menghentikan jadwal untuk menghindari biaya yang dikenakan.

Untuk memeriksa laporan, gunakan kode berikut:

schedule_desc = model_explainability_monitor.describe_schedule()
execution_summary = schedule_desc.get("LastMonitoringExecutionSummary")
if execution_summary and execution_summary["MonitoringExecutionStatus"] in ["Completed", "CompletedWithViolations"]:
    last_model_explainability_monitor_execution = model_explainability_monitor.list_executions()[-1]
    last_model_explainability_monitor_execution_report_uri = last_model_explainability_monitor_execution.output.destination
    print(f'Report URI: {last_model_explainability_monitor_execution_report_uri}')
    last_model_explainability_monitor_execution_report_files = sorted(S3Downloader.list(last_model_explainability_monitor_execution_report_uri))
    print("Found Report Files:")
    print("\n ".join(last_model_explainability_monitor_execution_report_files))
else:
    last_model_explainability_monitor_execution = None
    print("====STOP==== \n No completed executions to inspect further. Please wait till an execution completes or investigate previously reported failures.")

Jika ada pelanggaran dibandingkan dengan baseline, mereka tercantum di sini:

if last_model_explainability_monitor_execution:
    model_explainability_violations = last_model_explainability_monitor_execution.constraint_violations()
    if model_explainability_violations:
        print(model_explainability_violations.body_dict)

Jika model Anda diterapkan ke titik akhir real-time, Anda dapat melihat visualisasi di SageMaker Studio hasil analisis dan CloudWatch metrik dengan memilih tab Endpoints, lalu mengklik dua kali titik akhir.