Vertex AI V1 API - Class Google::Cloud::AIPlatform::V1::ModelDeploymentMonitoringJob (v0.23.0)

Reference documentation and code samples for the Vertex AI V1 API class Google::Cloud::AIPlatform::V1::ModelDeploymentMonitoringJob.

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.

Inherits

Object

Extended By

Google::Protobuf::MessageExts::ClassMethods

Includes

Google::Protobuf::MessageExts

Methods

#analysis_instance_schema_uri

def analysis_instance_schema_uri() -> ::String

Returns

(::String) — 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, 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.

#analysis_instance_schema_uri=

def analysis_instance_schema_uri=(value) -> ::String

Parameter

value (::String) — 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, 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.

Returns

(::String) — 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, 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.

#bigquery_tables

def bigquery_tables() -> ::Array<::Google::Cloud::AIPlatform::V1::ModelDeploymentMonitoringBigQueryTable>

Returns

(::Array<::Google::Cloud::AIPlatform::V1::ModelDeploymentMonitoringBigQueryTable>) —
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:
1. Training data logging predict request/response
2. Serving data logging predict request/response

#create_time

def create_time() -> ::Google::Protobuf::Timestamp

Returns

(::Google::Protobuf::Timestamp) — Output only. Timestamp when this ModelDeploymentMonitoringJob was created.

#display_name

def display_name() -> ::String

Returns

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

#display_name=

def display_name=(value) -> ::String

Parameter

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

Returns

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

#enable_monitoring_pipeline_logs

def enable_monitoring_pipeline_logs() -> ::Boolean

Returns

(::Boolean) — 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.

#enable_monitoring_pipeline_logs=

def enable_monitoring_pipeline_logs=(value) -> ::Boolean

Parameter

value (::Boolean) — 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.

Returns

(::Boolean) — 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.

#encryption_spec

def encryption_spec() -> ::Google::Cloud::AIPlatform::V1::EncryptionSpec

Returns

(::Google::Cloud::AIPlatform::V1::EncryptionSpec) — 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.

#encryption_spec=

def encryption_spec=(value) -> ::Google::Cloud::AIPlatform::V1::EncryptionSpec

Parameter

value (::Google::Cloud::AIPlatform::V1::EncryptionSpec) — 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.

Returns

(::Google::Cloud::AIPlatform::V1::EncryptionSpec) — 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.

#endpoint

def endpoint() -> ::String

Returns

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

#endpoint=

def endpoint=(value) -> ::String

Parameter

value (::String) — Required. Endpoint resource name. Format: projects/{project}/locations/{location}/endpoints/{endpoint}

Returns

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

#error

def error() -> ::Google::Rpc::Status

Returns

(::Google::Rpc::Status) — Output only. Only populated when the job's state is JOB_STATE_FAILED or JOB_STATE_CANCELLED.

#labels

def labels() -> ::Google::Protobuf::Map{::String => ::String}

Returns

(::Google::Protobuf::Map{::String => ::String}) — 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.

#labels=

def labels=(value) -> ::Google::Protobuf::Map{::String => ::String}

Parameter

value (::Google::Protobuf::Map{::String => ::String}) — 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.

Returns

(::Google::Protobuf::Map{::String => ::String}) — 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.

#latest_monitoring_pipeline_metadata

def latest_monitoring_pipeline_metadata() -> ::Google::Cloud::AIPlatform::V1::ModelDeploymentMonitoringJob::LatestMonitoringPipelineMetadata

Returns

(::Google::Cloud::AIPlatform::V1::ModelDeploymentMonitoringJob::LatestMonitoringPipelineMetadata) — Output only. Latest triggered monitoring pipeline metadata.

#log_ttl

def log_ttl() -> ::Google::Protobuf::Duration

Returns

(::Google::Protobuf::Duration) — 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.

#log_ttl=

def log_ttl=(value) -> ::Google::Protobuf::Duration

Parameter

value (::Google::Protobuf::Duration) — 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.

Returns

(::Google::Protobuf::Duration) — 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.

#logging_sampling_strategy

def logging_sampling_strategy() -> ::Google::Cloud::AIPlatform::V1::SamplingStrategy

Returns

(::Google::Cloud::AIPlatform::V1::SamplingStrategy) — Required. Sample Strategy for logging.

#logging_sampling_strategy=

def logging_sampling_strategy=(value) -> ::Google::Cloud::AIPlatform::V1::SamplingStrategy

Parameter

value (::Google::Cloud::AIPlatform::V1::SamplingStrategy) — Required. Sample Strategy for logging.

Returns

(::Google::Cloud::AIPlatform::V1::SamplingStrategy) — Required. Sample Strategy for logging.

#model_deployment_monitoring_objective_configs

def model_deployment_monitoring_objective_configs() -> ::Array<::Google::Cloud::AIPlatform::V1::ModelDeploymentMonitoringObjectiveConfig>

Returns

(::Array<::Google::Cloud::AIPlatform::V1::ModelDeploymentMonitoringObjectiveConfig>) — Required. The config for monitoring objectives. This is a per DeployedModel config. Each DeployedModel needs to be configured separately.

#model_deployment_monitoring_objective_configs=

def model_deployment_monitoring_objective_configs=(value) -> ::Array<::Google::Cloud::AIPlatform::V1::ModelDeploymentMonitoringObjectiveConfig>

Parameter

value (::Array<::Google::Cloud::AIPlatform::V1::ModelDeploymentMonitoringObjectiveConfig>) — Required. The config for monitoring objectives. This is a per DeployedModel config. Each DeployedModel needs to be configured separately.

Returns

(::Array<::Google::Cloud::AIPlatform::V1::ModelDeploymentMonitoringObjectiveConfig>) — Required. The config for monitoring objectives. This is a per DeployedModel config. Each DeployedModel needs to be configured separately.

#model_deployment_monitoring_schedule_config

def model_deployment_monitoring_schedule_config() -> ::Google::Cloud::AIPlatform::V1::ModelDeploymentMonitoringScheduleConfig

Returns

(::Google::Cloud::AIPlatform::V1::ModelDeploymentMonitoringScheduleConfig) — Required. Schedule config for running the monitoring job.

#model_deployment_monitoring_schedule_config=

def model_deployment_monitoring_schedule_config=(value) -> ::Google::Cloud::AIPlatform::V1::ModelDeploymentMonitoringScheduleConfig

Parameter

value (::Google::Cloud::AIPlatform::V1::ModelDeploymentMonitoringScheduleConfig) — Required. Schedule config for running the monitoring job.

Returns

(::Google::Cloud::AIPlatform::V1::ModelDeploymentMonitoringScheduleConfig) — Required. Schedule config for running the monitoring job.

#model_monitoring_alert_config

def model_monitoring_alert_config() -> ::Google::Cloud::AIPlatform::V1::ModelMonitoringAlertConfig

Returns

(::Google::Cloud::AIPlatform::V1::ModelMonitoringAlertConfig) — Alert config for model monitoring.

#model_monitoring_alert_config=

def model_monitoring_alert_config=(value) -> ::Google::Cloud::AIPlatform::V1::ModelMonitoringAlertConfig

Parameter

value (::Google::Cloud::AIPlatform::V1::ModelMonitoringAlertConfig) — Alert config for model monitoring.

Returns

(::Google::Cloud::AIPlatform::V1::ModelMonitoringAlertConfig) — Alert config for model monitoring.

#name

def name() -> ::String

Returns

(::String) — Output only. Resource name of a ModelDeploymentMonitoringJob.

#next_schedule_time

def next_schedule_time() -> ::Google::Protobuf::Timestamp

Returns

(::Google::Protobuf::Timestamp) — Output only. Timestamp when this monitoring pipeline will be scheduled to run for the next round.

#predict_instance_schema_uri

def predict_instance_schema_uri() -> ::String

Returns

(::String) — 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.

#predict_instance_schema_uri=

def predict_instance_schema_uri=(value) -> ::String

Parameter

value (::String) — 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.

Returns

(::String) — 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.

#sample_predict_instance

def sample_predict_instance() -> ::Google::Protobuf::Value

Returns

(::Google::Protobuf::Value) — Sample Predict instance, same format as PredictRequest.instances, this can be set as a replacement of ModelDeploymentMonitoringJob.predict_instance_schema_uri. If not set, we will generate predict schema from collected predict requests.

#sample_predict_instance=

def sample_predict_instance=(value) -> ::Google::Protobuf::Value

Parameter

value (::Google::Protobuf::Value) — Sample Predict instance, same format as PredictRequest.instances, this can be set as a replacement of ModelDeploymentMonitoringJob.predict_instance_schema_uri. If not set, we will generate predict schema from collected predict requests.

Returns

(::Google::Protobuf::Value) — Sample Predict instance, same format as PredictRequest.instances, this can be set as a replacement of ModelDeploymentMonitoringJob.predict_instance_schema_uri. If not set, we will generate predict schema from collected predict requests.

#schedule_state

def schedule_state() -> ::Google::Cloud::AIPlatform::V1::ModelDeploymentMonitoringJob::MonitoringScheduleState

Returns

(::Google::Cloud::AIPlatform::V1::ModelDeploymentMonitoringJob::MonitoringScheduleState) — Output only. Schedule state when the monitoring job is in Running state.

#state

def state() -> ::Google::Cloud::AIPlatform::V1::JobState

Returns

(::Google::Cloud::AIPlatform::V1::JobState) — 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'.

#stats_anomalies_base_directory

def stats_anomalies_base_directory() -> ::Google::Cloud::AIPlatform::V1::GcsDestination

Returns

(::Google::Cloud::AIPlatform::V1::GcsDestination) — Stats anomalies base folder path.

#stats_anomalies_base_directory=

def stats_anomalies_base_directory=(value) -> ::Google::Cloud::AIPlatform::V1::GcsDestination

Parameter

value (::Google::Cloud::AIPlatform::V1::GcsDestination) — Stats anomalies base folder path.

Returns

(::Google::Cloud::AIPlatform::V1::GcsDestination) — Stats anomalies base folder path.

#update_time

def update_time() -> ::Google::Protobuf::Timestamp

Returns

(::Google::Protobuf::Timestamp) — Output only. Timestamp when this ModelDeploymentMonitoringJob was updated most recently.