Class ModelDeploymentMonitoringJob (1.2.0)

public sealed class ModelDeploymentMonitoringJob : IMessage<ModelDeploymentMonitoringJob>, IEquatable<ModelDeploymentMonitoringJob>, IDeepCloneable<ModelDeploymentMonitoringJob>, IBufferMessage, IMessage

Represents a job that runs periodically to monitor the deployed models in an endpoint. It will analyze the logged training & prediction data to detect any abnormal behaviors.

Inheritance

Object > ModelDeploymentMonitoringJob

Implements

IMessage<ModelDeploymentMonitoringJob>, IEquatable<ModelDeploymentMonitoringJob>, IDeepCloneable<ModelDeploymentMonitoringJob>, IBufferMessage, IMessage

Inherited Members

Object.GetHashCode()

Object.GetType()

Object.MemberwiseClone()

Object.ToString()

Namespace

Google.Cloud.AIPlatform.V1

Assembly

Google.Cloud.AIPlatform.V1.dll

Constructors

ModelDeploymentMonitoringJob()

public ModelDeploymentMonitoringJob()

ModelDeploymentMonitoringJob(ModelDeploymentMonitoringJob)

public ModelDeploymentMonitoringJob(ModelDeploymentMonitoringJob other)

Parameter
Name	Description
`other`	`ModelDeploymentMonitoringJob`

Properties

AnalysisInstanceSchemaUri

public string AnalysisInstanceSchemaUri { get; set; }

YAML schema file uri describing the format of a single instance that you want Tensorflow Data Validation (TFDV) to analyze.

If this field is empty, all the feature data types are inferred from [predict_instance_schema_uri][google.cloud.aiplatform.v1.ModelDeploymentMonitoringJob.predict_instance_schema_uri], meaning that TFDV will use the data in the exact format(data type) as prediction request/response. If there are any data type differences between predict instance and TFDV instance, this field can be used to override the schema. For models trained with Vertex AI, this field must be set as all the fields in predict instance formatted as string.

Property Value
Type	Description
`String`

BigqueryTables

public RepeatedField<ModelDeploymentMonitoringBigQueryTable> BigqueryTables { get; }

Output only. The created bigquery tables for the job under customer project. Customer could do their own query & analysis. There could be 4 log tables in maximum:

Training data logging predict request/response
Serving data logging predict request/response

Property Value
Type	Description
`RepeatedField<ModelDeploymentMonitoringBigQueryTable>`

CreateTime

public Timestamp CreateTime { get; set; }

Output only. Timestamp when this ModelDeploymentMonitoringJob was created.

Property Value
Type	Description
`Timestamp`

DisplayName

public string DisplayName { get; set; }

Required. The user-defined name of the ModelDeploymentMonitoringJob. The name can be up to 128 characters long and can be consist of any UTF-8 characters. Display name of a ModelDeploymentMonitoringJob.

Property Value
Type	Description
`String`

EnableMonitoringPipelineLogs

public bool EnableMonitoringPipelineLogs { get; set; }

If true, the scheduled monitoring pipeline logs are sent to Google Cloud Logging, including pipeline status and anomalies detected. Please note the logs incur cost, which are subject to Cloud Logging pricing.

Property Value
Type	Description
`Boolean`

EncryptionSpec

public EncryptionSpec EncryptionSpec { get; set; }

Customer-managed encryption key spec for a ModelDeploymentMonitoringJob. If set, this ModelDeploymentMonitoringJob and all sub-resources of this ModelDeploymentMonitoringJob will be secured by this key.

Property Value
Type	Description
`EncryptionSpec`

Endpoint

public string Endpoint { get; set; }

Required. Endpoint resource name. Format: projects/{project}/locations/{location}/endpoints/{endpoint}

Property Value
Type	Description
`String`

EndpointAsEndpointName

public EndpointName EndpointAsEndpointName { get; set; }

EndpointName-typed view over the Endpoint resource name property.

Property Value
Type	Description
`EndpointName`

Error

public Status Error { get; set; }

Output only. Only populated when the job's state is JOB_STATE_FAILED or JOB_STATE_CANCELLED.

Property Value
Type	Description
`Status`

Labels

public MapField<string, string> Labels { get; }

The labels with user-defined metadata to organize your ModelDeploymentMonitoringJob.

Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed.

See https://goo.gl/xmQnxf for more information and examples of labels.

Property Value
Type	Description
`MapField<String, String>`

LoggingSamplingStrategy

public SamplingStrategy LoggingSamplingStrategy { get; set; }

Required. Sample Strategy for logging.

Property Value
Type	Description
`SamplingStrategy`

LogTtl

public Duration LogTtl { get; set; }

The TTL of BigQuery tables in user projects which stores logs. A day is the basic unit of the TTL and we take the ceil of TTL/86400(a day). e.g. { second: 3600} indicates ttl = 1 day.

Property Value
Type	Description
`Duration`

ModelDeploymentMonitoringJobName

public ModelDeploymentMonitoringJobName ModelDeploymentMonitoringJobName { get; set; }

ModelDeploymentMonitoringJobName-typed view over the Name resource name property.

Property Value
Type	Description
`ModelDeploymentMonitoringJobName`

ModelDeploymentMonitoringObjectiveConfigs

public RepeatedField<ModelDeploymentMonitoringObjectiveConfig> ModelDeploymentMonitoringObjectiveConfigs { get; }

Required. The config for monitoring objectives. This is a per DeployedModel config. Each DeployedModel needs to be configured separately.

Property Value
Type	Description
`RepeatedField<ModelDeploymentMonitoringObjectiveConfig>`

ModelDeploymentMonitoringScheduleConfig

public ModelDeploymentMonitoringScheduleConfig ModelDeploymentMonitoringScheduleConfig { get; set; }

Required. Schedule config for running the monitoring job.

Property Value
Type	Description
`ModelDeploymentMonitoringScheduleConfig`

ModelMonitoringAlertConfig

public ModelMonitoringAlertConfig ModelMonitoringAlertConfig { get; set; }

Alert config for model monitoring.

Property Value
Type	Description
`ModelMonitoringAlertConfig`

Name

public string Name { get; set; }

Output only. Resource name of a ModelDeploymentMonitoringJob.

Property Value
Type	Description
`String`

NextScheduleTime

public Timestamp NextScheduleTime { get; set; }

Output only. Timestamp when this monitoring pipeline will be scheduled to run for the next round.

Property Value
Type	Description
`Timestamp`

PredictInstanceSchemaUri

public string PredictInstanceSchemaUri { get; set; }

YAML schema file uri describing the format of a single instance, which are given to format this Endpoint's prediction (and explanation). If not set, we will generate predict schema from collected predict requests.

Property Value
Type	Description
`String`

SamplePredictInstance

public Value SamplePredictInstance { get; set; }

Sample Predict instance, same format as [PredictRequest.instances][google.cloud.aiplatform.v1.PredictRequest.instances], this can be set as a replacement of [ModelDeploymentMonitoringJob.predict_instance_schema_uri][google.cloud.aiplatform.v1.ModelDeploymentMonitoringJob.predict_instance_schema_uri]. If not set, we will generate predict schema from collected predict requests.

Property Value
Type	Description
`Value`

ScheduleState

public ModelDeploymentMonitoringJob.Types.MonitoringScheduleState ScheduleState { get; set; }

Output only. Schedule state when the monitoring job is in Running state.

Property Value
Type	Description
`ModelDeploymentMonitoringJob.Types.MonitoringScheduleState`

State

public JobState State { get; set; }

Output only. The detailed state of the monitoring job. When the job is still creating, the state will be 'PENDING'. Once the job is successfully created, the state will be 'RUNNING'. Pause the job, the state will be 'PAUSED'. Resume the job, the state will return to 'RUNNING'.

Property Value
Type	Description
`JobState`

StatsAnomaliesBaseDirectory

public GcsDestination StatsAnomaliesBaseDirectory { get; set; }

Stats anomalies base folder path.

Property Value
Type	Description
`GcsDestination`

UpdateTime

public Timestamp UpdateTime { get; set; }

Output only. Timestamp when this ModelDeploymentMonitoringJob was updated most recently.

Property Value
Type	Description
`Timestamp`