Monitoring

1from sagemaker import get_execution_role
2from sagemaker import image_uris
3from sagemaker.model_monitor.dataset_format import DatasetFormat
4
5my_data_monitor = DefaultModelMonitor(
6    role=get_execution_role(),
7    instance_count=1,
8    instance_type='ml.m5.large',
9    volume_size_in_gb=30,
10    max_runtime_in_seconds=3_600)
11
12# base s3 directory
13baseline_dir_uri = 's3://api-trial/data_quality_no_headers/'
14# train data, that I have used to generate baseline
15baseline_data_uri = baseline_dir_uri + 'ch_train_no_target.csv'
16# directory in s3 bucket that I have stored my baseline results to 
17baseline_results_uri = baseline_dir_uri + 'baseline_results_try17/'
18
19
20my_data_monitor.suggest_baseline(
21    baseline_dataset=baseline_data_uri,
22    dataset_format=DatasetFormat.csv(header=True),
23    output_s3_uri=baseline_results_uri,
24    wait=True, logs=False, job_name='ch-dq-baseline-try21'
25)
26

1from sagemaker import get_execution_role
2from sagemaker import image_uris
3from sagemaker.model_monitor.dataset_format import DatasetFormat
4
5my_data_monitor = DefaultModelMonitor(
6    role=get_execution_role(),
7    instance_count=1,
8    instance_type='ml.m5.large',
9    volume_size_in_gb=30,
10    max_runtime_in_seconds=3_600)
11
12# base s3 directory
13baseline_dir_uri = 's3://api-trial/data_quality_no_headers/'
14# train data, that I have used to generate baseline
15baseline_data_uri = baseline_dir_uri + 'ch_train_no_target.csv'
16# directory in s3 bucket that I have stored my baseline results to 
17baseline_results_uri = baseline_dir_uri + 'baseline_results_try17/'
18
19
20my_data_monitor.suggest_baseline(
21    baseline_dataset=baseline_data_uri,
22    dataset_format=DatasetFormat.csv(header=True),
23    output_s3_uri=baseline_results_uri,
24    wait=True, logs=False, job_name='ch-dq-baseline-try21'
25)
26from sagemaker import get_execution_role
27from sagemaker.model_monitor import EndpointInput
28from sagemaker import image_uris
29from sagemaker.model_monitor import CronExpressionGenerator
30from sagemaker.model_monitor import DefaultModelMonitor
31from sagemaker.model_monitor.dataset_format import DatasetFormat
32
33# base s3 directory
34baseline_dir_uri = 's3://api-trial/data_quality_no_headers/'
35
36# train data, that I have used to generate baseline
37baseline_data_uri = baseline_dir_uri + 'ch_train_no_target.csv'
38
39# directory in s3 bucket that I have stored my baseline results to 
40baseline_results_uri = baseline_dir_uri + 'baseline_results_try17/'
41# s3 locations of baseline job outputs
42baseline_statistics = baseline_results_uri + 'statistics.json'
43baseline_constraints = baseline_results_uri + 'constraints.json'
44
45# directory in s3 bucket that I would like to store results of monitoring schedules in
46monitoring_outputs = baseline_dir_uri + 'monitoring_results_try17/'
47
48ch_dq_ep = EndpointInput(endpoint_name=myendpoint_name,
49                         destination="/opt/ml/processing/input_data",
50                         s3_input_mode="File",
51                         s3_data_distribution_type="FullyReplicated")
52
53monitor_schedule_name='ch-dq-monitor-schdl-try21'
54
55my_data_monitor.create_monitoring_schedule(endpoint_input=ch_dq_ep,
56                                           monitor_schedule_name=monitor_schedule_name,
57                                           output_s3_uri=baseline_dir_uri,
58                                           constraints=baseline_constraints,
59                                           statistics=baseline_statistics,
60                                           schedule_cron_expression=CronExpressionGenerator.hourly(),
61                                           enable_cloudwatch_metrics=True)
62

1from sagemaker import get_execution_role
2from sagemaker import image_uris
3from sagemaker.model_monitor.dataset_format import DatasetFormat
4
5my_data_monitor = DefaultModelMonitor(
6    role=get_execution_role(),
7    instance_count=1,
8    instance_type='ml.m5.large',
9    volume_size_in_gb=30,
10    max_runtime_in_seconds=3_600)
11
12# base s3 directory
13baseline_dir_uri = 's3://api-trial/data_quality_no_headers/'
14# train data, that I have used to generate baseline
15baseline_data_uri = baseline_dir_uri + 'ch_train_no_target.csv'
16# directory in s3 bucket that I have stored my baseline results to 
17baseline_results_uri = baseline_dir_uri + 'baseline_results_try17/'
18
19
20my_data_monitor.suggest_baseline(
21    baseline_dataset=baseline_data_uri,
22    dataset_format=DatasetFormat.csv(header=True),
23    output_s3_uri=baseline_results_uri,
24    wait=True, logs=False, job_name='ch-dq-baseline-try21'
25)
26from sagemaker import get_execution_role
27from sagemaker.model_monitor import EndpointInput
28from sagemaker import image_uris
29from sagemaker.model_monitor import CronExpressionGenerator
30from sagemaker.model_monitor import DefaultModelMonitor
31from sagemaker.model_monitor.dataset_format import DatasetFormat
32
33# base s3 directory
34baseline_dir_uri = 's3://api-trial/data_quality_no_headers/'
35
36# train data, that I have used to generate baseline
37baseline_data_uri = baseline_dir_uri + 'ch_train_no_target.csv'
38
39# directory in s3 bucket that I have stored my baseline results to 
40baseline_results_uri = baseline_dir_uri + 'baseline_results_try17/'
41# s3 locations of baseline job outputs
42baseline_statistics = baseline_results_uri + 'statistics.json'
43baseline_constraints = baseline_results_uri + 'constraints.json'
44
45# directory in s3 bucket that I would like to store results of monitoring schedules in
46monitoring_outputs = baseline_dir_uri + 'monitoring_results_try17/'
47
48ch_dq_ep = EndpointInput(endpoint_name=myendpoint_name,
49                         destination="/opt/ml/processing/input_data",
50                         s3_input_mode="File",
51                         s3_data_distribution_type="FullyReplicated")
52
53monitor_schedule_name='ch-dq-monitor-schdl-try21'
54
55my_data_monitor.create_monitoring_schedule(endpoint_input=ch_dq_ep,
56                                           monitor_schedule_name=monitor_schedule_name,
57                                           output_s3_uri=baseline_dir_uri,
58                                           constraints=baseline_constraints,
59                                           statistics=baseline_statistics,
60                                           schedule_cron_expression=CronExpressionGenerator.hourly(),
61                                           enable_cloudwatch_metrics=True)
62import boto3
63boto3_sm_client = boto3.client('sagemaker')
64boto3_sm_client.describe_monitoring_schedule(MonitoringScheduleName='ch-dq-monitor-schdl-try17')
65

1from sagemaker import get_execution_role
2from sagemaker import image_uris
3from sagemaker.model_monitor.dataset_format import DatasetFormat
4
5my_data_monitor = DefaultModelMonitor(
6    role=get_execution_role(),
7    instance_count=1,
8    instance_type='ml.m5.large',
9    volume_size_in_gb=30,
10    max_runtime_in_seconds=3_600)
11
12# base s3 directory
13baseline_dir_uri = 's3://api-trial/data_quality_no_headers/'
14# train data, that I have used to generate baseline
15baseline_data_uri = baseline_dir_uri + 'ch_train_no_target.csv'
16# directory in s3 bucket that I have stored my baseline results to 
17baseline_results_uri = baseline_dir_uri + 'baseline_results_try17/'
18
19
20my_data_monitor.suggest_baseline(
21    baseline_dataset=baseline_data_uri,
22    dataset_format=DatasetFormat.csv(header=True),
23    output_s3_uri=baseline_results_uri,
24    wait=True, logs=False, job_name='ch-dq-baseline-try21'
25)
26from sagemaker import get_execution_role
27from sagemaker.model_monitor import EndpointInput
28from sagemaker import image_uris
29from sagemaker.model_monitor import CronExpressionGenerator
30from sagemaker.model_monitor import DefaultModelMonitor
31from sagemaker.model_monitor.dataset_format import DatasetFormat
32
33# base s3 directory
34baseline_dir_uri = 's3://api-trial/data_quality_no_headers/'
35
36# train data, that I have used to generate baseline
37baseline_data_uri = baseline_dir_uri + 'ch_train_no_target.csv'
38
39# directory in s3 bucket that I have stored my baseline results to 
40baseline_results_uri = baseline_dir_uri + 'baseline_results_try17/'
41# s3 locations of baseline job outputs
42baseline_statistics = baseline_results_uri + 'statistics.json'
43baseline_constraints = baseline_results_uri + 'constraints.json'
44
45# directory in s3 bucket that I would like to store results of monitoring schedules in
46monitoring_outputs = baseline_dir_uri + 'monitoring_results_try17/'
47
48ch_dq_ep = EndpointInput(endpoint_name=myendpoint_name,
49                         destination="/opt/ml/processing/input_data",
50                         s3_input_mode="File",
51                         s3_data_distribution_type="FullyReplicated")
52
53monitor_schedule_name='ch-dq-monitor-schdl-try21'
54
55my_data_monitor.create_monitoring_schedule(endpoint_input=ch_dq_ep,
56                                           monitor_schedule_name=monitor_schedule_name,
57                                           output_s3_uri=baseline_dir_uri,
58                                           constraints=baseline_constraints,
59                                           statistics=baseline_statistics,
60                                           schedule_cron_expression=CronExpressionGenerator.hourly(),
61                                           enable_cloudwatch_metrics=True)
62import boto3
63boto3_sm_client = boto3.client('sagemaker')
64boto3_sm_client.describe_monitoring_schedule(MonitoringScheduleName='ch-dq-monitor-schdl-try17')
65'MonitoringExecutionStatus': 'Failed',
66  ...
67  'FailureReason': 'Job inputs had no data'},
68

1from sagemaker import get_execution_role
2from sagemaker import image_uris
3from sagemaker.model_monitor.dataset_format import DatasetFormat
4
5my_data_monitor = DefaultModelMonitor(
6    role=get_execution_role(),
7    instance_count=1,
8    instance_type='ml.m5.large',
9    volume_size_in_gb=30,
10    max_runtime_in_seconds=3_600)
11
12# base s3 directory
13baseline_dir_uri = 's3://api-trial/data_quality_no_headers/'
14# train data, that I have used to generate baseline
15baseline_data_uri = baseline_dir_uri + 'ch_train_no_target.csv'
16# directory in s3 bucket that I have stored my baseline results to 
17baseline_results_uri = baseline_dir_uri + 'baseline_results_try17/'
18
19
20my_data_monitor.suggest_baseline(
21    baseline_dataset=baseline_data_uri,
22    dataset_format=DatasetFormat.csv(header=True),
23    output_s3_uri=baseline_results_uri,
24    wait=True, logs=False, job_name='ch-dq-baseline-try21'
25)
26from sagemaker import get_execution_role
27from sagemaker.model_monitor import EndpointInput
28from sagemaker import image_uris
29from sagemaker.model_monitor import CronExpressionGenerator
30from sagemaker.model_monitor import DefaultModelMonitor
31from sagemaker.model_monitor.dataset_format import DatasetFormat
32
33# base s3 directory
34baseline_dir_uri = 's3://api-trial/data_quality_no_headers/'
35
36# train data, that I have used to generate baseline
37baseline_data_uri = baseline_dir_uri + 'ch_train_no_target.csv'
38
39# directory in s3 bucket that I have stored my baseline results to 
40baseline_results_uri = baseline_dir_uri + 'baseline_results_try17/'
41# s3 locations of baseline job outputs
42baseline_statistics = baseline_results_uri + 'statistics.json'
43baseline_constraints = baseline_results_uri + 'constraints.json'
44
45# directory in s3 bucket that I would like to store results of monitoring schedules in
46monitoring_outputs = baseline_dir_uri + 'monitoring_results_try17/'
47
48ch_dq_ep = EndpointInput(endpoint_name=myendpoint_name,
49                         destination="/opt/ml/processing/input_data",
50                         s3_input_mode="File",
51                         s3_data_distribution_type="FullyReplicated")
52
53monitor_schedule_name='ch-dq-monitor-schdl-try21'
54
55my_data_monitor.create_monitoring_schedule(endpoint_input=ch_dq_ep,
56                                           monitor_schedule_name=monitor_schedule_name,
57                                           output_s3_uri=baseline_dir_uri,
58                                           constraints=baseline_constraints,
59                                           statistics=baseline_statistics,
60                                           schedule_cron_expression=CronExpressionGenerator.hourly(),
61                                           enable_cloudwatch_metrics=True)
62import boto3
63boto3_sm_client = boto3.client('sagemaker')
64boto3_sm_client.describe_monitoring_schedule(MonitoringScheduleName='ch-dq-monitor-schdl-try17')
65'MonitoringExecutionStatus': 'Failed',
66  ...
67  'FailureReason': 'Job inputs had no data'},
68```
69{'MonitoringScheduleArn': 'arn:aws:sagemaker:ap-south-1:<my-account-id>:monitoring-schedule/ch-dq-monitor-schdl-try21',
70 'MonitoringScheduleName': 'ch-dq-monitor-schdl-try21',
71 'MonitoringScheduleStatus': 'Scheduled',
72 'MonitoringType': 'DataQuality',
73 'CreationTime': datetime.datetime(2021, 9, 14, 13, 7, 31, 899000, tzinfo=tzlocal()),
74 'LastModifiedTime': datetime.datetime(2021, 9, 14, 14, 1, 13, 247000, tzinfo=tzlocal()),
75 'MonitoringScheduleConfig': {'ScheduleConfig': {'ScheduleExpression': 'cron(0 * ? * * *)'},
76  'MonitoringJobDefinitionName': 'data-quality-job-definition-2021-09-14-13-07-31-483',
77  'MonitoringType': 'DataQuality'},
78 'EndpointName': 'ch-dq-nh-try21',
79 'LastMonitoringExecutionSummary': {'MonitoringScheduleName': 'ch-dq-monitor-schdl-try21',
80  'ScheduledTime': datetime.datetime(2021, 9, 14, 14, 0, tzinfo=tzlocal()),
81  'CreationTime': datetime.datetime(2021, 9, 14, 14, 1, 9, 405000, tzinfo=tzlocal()),
82  'LastModifiedTime': datetime.datetime(2021, 9, 14, 14, 1, 13, 236000, tzinfo=tzlocal()),
83  'MonitoringExecutionStatus': 'Failed',
84  'EndpointName': 'ch-dq-nh-try21',
85  'FailureReason': 'Job inputs had no data'},
86 'ResponseMetadata': {'RequestId': 'dd729244-fde9-44b5-9904-066eea3a49bb',
87  'HTTPStatusCode': 200,
88  'HTTPHeaders': {'x-amzn-requestid': 'dd729244-fde9-44b5-9904-066eea3a49bb',
89   'content-type': 'application/x-amz-json-1.1',
90   'content-length': '835',
91   'date': 'Tue, 14 Sep 2021 14:27:53 GMT'},
92  'RetryAttempts': 0}}
93```

1from sagemaker import get_execution_role
2from sagemaker import image_uris
3from sagemaker.model_monitor.dataset_format import DatasetFormat
4
5my_data_monitor = DefaultModelMonitor(
6    role=get_execution_role(),
7    instance_count=1,
8    instance_type='ml.m5.large',
9    volume_size_in_gb=30,
10    max_runtime_in_seconds=3_600)
11
12# base s3 directory
13baseline_dir_uri = 's3://api-trial/data_quality_no_headers/'
14# train data, that I have used to generate baseline
15baseline_data_uri = baseline_dir_uri + 'ch_train_no_target.csv'
16# directory in s3 bucket that I have stored my baseline results to 
17baseline_results_uri = baseline_dir_uri + 'baseline_results_try17/'
18
19
20my_data_monitor.suggest_baseline(
21    baseline_dataset=baseline_data_uri,
22    dataset_format=DatasetFormat.csv(header=True),
23    output_s3_uri=baseline_results_uri,
24    wait=True, logs=False, job_name='ch-dq-baseline-try21'
25)
26from sagemaker import get_execution_role
27from sagemaker.model_monitor import EndpointInput
28from sagemaker import image_uris
29from sagemaker.model_monitor import CronExpressionGenerator
30from sagemaker.model_monitor import DefaultModelMonitor
31from sagemaker.model_monitor.dataset_format import DatasetFormat
32
33# base s3 directory
34baseline_dir_uri = 's3://api-trial/data_quality_no_headers/'
35
36# train data, that I have used to generate baseline
37baseline_data_uri = baseline_dir_uri + 'ch_train_no_target.csv'
38
39# directory in s3 bucket that I have stored my baseline results to 
40baseline_results_uri = baseline_dir_uri + 'baseline_results_try17/'
41# s3 locations of baseline job outputs
42baseline_statistics = baseline_results_uri + 'statistics.json'
43baseline_constraints = baseline_results_uri + 'constraints.json'
44
45# directory in s3 bucket that I would like to store results of monitoring schedules in
46monitoring_outputs = baseline_dir_uri + 'monitoring_results_try17/'
47
48ch_dq_ep = EndpointInput(endpoint_name=myendpoint_name,
49                         destination="/opt/ml/processing/input_data",
50                         s3_input_mode="File",
51                         s3_data_distribution_type="FullyReplicated")
52
53monitor_schedule_name='ch-dq-monitor-schdl-try21'
54
55my_data_monitor.create_monitoring_schedule(endpoint_input=ch_dq_ep,
56                                           monitor_schedule_name=monitor_schedule_name,
57                                           output_s3_uri=baseline_dir_uri,
58                                           constraints=baseline_constraints,
59                                           statistics=baseline_statistics,
60                                           schedule_cron_expression=CronExpressionGenerator.hourly(),
61                                           enable_cloudwatch_metrics=True)
62import boto3
63boto3_sm_client = boto3.client('sagemaker')
64boto3_sm_client.describe_monitoring_schedule(MonitoringScheduleName='ch-dq-monitor-schdl-try17')
65'MonitoringExecutionStatus': 'Failed',
66  ...
67  'FailureReason': 'Job inputs had no data'},
68```
69{'MonitoringScheduleArn': 'arn:aws:sagemaker:ap-south-1:<my-account-id>:monitoring-schedule/ch-dq-monitor-schdl-try21',
70 'MonitoringScheduleName': 'ch-dq-monitor-schdl-try21',
71 'MonitoringScheduleStatus': 'Scheduled',
72 'MonitoringType': 'DataQuality',
73 'CreationTime': datetime.datetime(2021, 9, 14, 13, 7, 31, 899000, tzinfo=tzlocal()),
74 'LastModifiedTime': datetime.datetime(2021, 9, 14, 14, 1, 13, 247000, tzinfo=tzlocal()),
75 'MonitoringScheduleConfig': {'ScheduleConfig': {'ScheduleExpression': 'cron(0 * ? * * *)'},
76  'MonitoringJobDefinitionName': 'data-quality-job-definition-2021-09-14-13-07-31-483',
77  'MonitoringType': 'DataQuality'},
78 'EndpointName': 'ch-dq-nh-try21',
79 'LastMonitoringExecutionSummary': {'MonitoringScheduleName': 'ch-dq-monitor-schdl-try21',
80  'ScheduledTime': datetime.datetime(2021, 9, 14, 14, 0, tzinfo=tzlocal()),
81  'CreationTime': datetime.datetime(2021, 9, 14, 14, 1, 9, 405000, tzinfo=tzlocal()),
82  'LastModifiedTime': datetime.datetime(2021, 9, 14, 14, 1, 13, 236000, tzinfo=tzlocal()),
83  'MonitoringExecutionStatus': 'Failed',
84  'EndpointName': 'ch-dq-nh-try21',
85  'FailureReason': 'Job inputs had no data'},
86 'ResponseMetadata': {'RequestId': 'dd729244-fde9-44b5-9904-066eea3a49bb',
87  'HTTPStatusCode': 200,
88  'HTTPHeaders': {'x-amzn-requestid': 'dd729244-fde9-44b5-9904-066eea3a49bb',
89   'content-type': 'application/x-amz-json-1.1',
90   'content-length': '835',
91   'date': 'Tue, 14 Sep 2021 14:27:53 GMT'},
92  'RetryAttempts': 0}}
93```{"captureData":{"endpointInput":{"observedContentType":"application/json","mode":"INPUT","data":"{\"longitude\": [-122.32, -117.58], \"latitude\": [37.55, 33.6], \"housing_median_age\": [50.0, 5.0], \"total_rooms\": [2501.0, 5348.0], \"total_bedrooms\": [433.0, 659.0], \"population\": [1050.0, 1862.0], \"households\": [410.0, 555.0], \"median_income\": [4.6406, 11.0567]}","encoding":"JSON"},"endpointOutput":{"observedContentType":"text/html; charset=utf-8","mode":"OUTPUT","data":"eyJtZWRpYW5faG91c2VfdmFsdWUiOiBbNDUyOTU3LjY5LCA0NjcyMTQuNF19","encoding":"BASE64"}},"eventMetadata":{"eventId":"9804d438-eb4c-4cb4-8f1b-d0c832b641aa","inferenceId":"ef07163d-ea2d-4730-92f3-d755bc04ae0d","inferenceTime":"2021-09-14T13:59:03Z"},"eventVersion":"0"}
94