Class: Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1ModelDeploymentMonitoringJob

Inherits:
Object
  • Object
show all
Includes:
Core::Hashable, Core::JsonObjectSupport
Defined in:
lib/google/apis/aiplatform_v1beta1/classes.rb,
lib/google/apis/aiplatform_v1beta1/representations.rb,
lib/google/apis/aiplatform_v1beta1/representations.rb

Overview

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.

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(**args) ⇒ GoogleCloudAiplatformV1beta1ModelDeploymentMonitoringJob

Returns a new instance of GoogleCloudAiplatformV1beta1ModelDeploymentMonitoringJob.



15928
15929
15930
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 15928

def initialize(**args)
   update!(**args)
end

Instance Attribute Details

#analysis_instance_schema_uri ⇒ 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. Corresponds to the JSON property analysisInstanceSchemaUri

Returns:

  • (String) 


15783
15784
15785
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 15783

def analysis_instance_schema_uri
  @analysis_instance_schema_uri
end

#bigquery_tables ⇒ Array<Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1ModelDeploymentMonitoringBigQueryTable>

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 Corresponds to the JSON property bigqueryTables

Returns:



15791
15792
15793
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 15791

def bigquery_tables
  @bigquery_tables
end

#create_time ⇒ String

Output only. Timestamp when this ModelDeploymentMonitoringJob was created. Corresponds to the JSON property createTime

Returns:

  • (String) 


15796
15797
15798
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 15796

def create_time
  @create_time
end

#display_name ⇒ 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. Corresponds to the JSON property displayName

Returns:

  • (String) 


15803
15804
15805
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 15803

def display_name
  @display_name
end

#enable_monitoring_pipeline_logs ⇒ Boolean Also known as: enable_monitoring_pipeline_logs?

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. Corresponds to the JSON property enableMonitoringPipelineLogs

Returns:

  • (Boolean) 


15811
15812
15813
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 15811

def enable_monitoring_pipeline_logs
  @enable_monitoring_pipeline_logs
end

#encryption_spec ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1EncryptionSpec

Represents a customer-managed encryption key spec that can be applied to a top- level resource. Corresponds to the JSON property encryptionSpec

Returns:



15818
15819
15820
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 15818

def encryption_spec
  @encryption_spec
end

#endpoint ⇒ String

Required. Endpoint resource name. Format: projects/project/locations/ location/endpoints/endpoint` Corresponds to the JSON propertyendpoint`

Returns:

  • (String) 


15824
15825
15826
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 15824

def endpoint
  @endpoint
end

#error ⇒ Google::Apis::AiplatformV1beta1::GoogleRpcStatus

The Status type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by gRPC. Each Status message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the API Design Guide. Corresponds to the JSON property error

Returns:



15834
15835
15836
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 15834

def error
  @error
end

#labels ⇒ Hash<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. Corresponds to the JSON property labels

Returns:

  • (Hash<String,String>) 


15843
15844
15845
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 15843

def labels
  @labels
end

#latest_monitoring_pipeline_metadata ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1ModelDeploymentMonitoringJobLatestMonitoringPipelineMetadata

All metadata of most recent monitoring pipelines. Corresponds to the JSON property latestMonitoringPipelineMetadata

Returns:



15848
15849
15850
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 15848

def latest_monitoring_pipeline_metadata
  @latest_monitoring_pipeline_metadata
end

#log_ttl ⇒ String

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. Corresponds to the JSON property logTtl

Returns:

  • (String) 


15855
15856
15857
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 15855

def log_ttl
  @log_ttl
end

#logging_sampling_strategy ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1SamplingStrategy

Sampling Strategy for logging, can be for both training and prediction dataset. Corresponds to the JSON property loggingSamplingStrategy

Returns:



15860
15861
15862
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 15860

def logging_sampling_strategy
  @logging_sampling_strategy
end

#model_deployment_monitoring_objective_configs ⇒ Array<Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1ModelDeploymentMonitoringObjectiveConfig>

Required. The config for monitoring objectives. This is a per DeployedModel config. Each DeployedModel needs to be configured separately. Corresponds to the JSON property modelDeploymentMonitoringObjectiveConfigs

Returns:



15866
15867
15868
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 15866

def model_deployment_monitoring_objective_configs
  @model_deployment_monitoring_objective_configs
end

#model_deployment_monitoring_schedule_config ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1ModelDeploymentMonitoringScheduleConfig

The config for scheduling monitoring job. Corresponds to the JSON property modelDeploymentMonitoringScheduleConfig

Returns:



15871
15872
15873
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 15871

def model_deployment_monitoring_schedule_config
  @model_deployment_monitoring_schedule_config
end

#model_monitoring_alert_config ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1ModelMonitoringAlertConfig

The alert config for model monitoring. Corresponds to the JSON property modelMonitoringAlertConfig

Returns:



15876
15877
15878
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 15876

def model_monitoring_alert_config
  @model_monitoring_alert_config
end

#name ⇒ String

Output only. Resource name of a ModelDeploymentMonitoringJob. Corresponds to the JSON property name

Returns:

  • (String) 


15881
15882
15883
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 15881

def name
  @name
end

#next_schedule_time ⇒ String

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

Returns:

  • (String) 


15887
15888
15889
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 15887

def next_schedule_time
  @next_schedule_time
end

#predict_instance_schema_uri ⇒ 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. Corresponds to the JSON property predictInstanceSchemaUri

Returns:

  • (String) 


15894
15895
15896
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 15894

def predict_instance_schema_uri
  @predict_instance_schema_uri
end

#sample_predict_instance ⇒ Object

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. Corresponds to the JSON property samplePredictInstance

Returns:

  • (Object) 


15902
15903
15904
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 15902

def sample_predict_instance
  @sample_predict_instance
end

#schedule_state ⇒ String

Output only. Schedule state when the monitoring job is in Running state. Corresponds to the JSON property scheduleState

Returns:

  • (String) 


15907
15908
15909
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 15907

def schedule_state
  @schedule_state
end

#state ⇒ String

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'. Corresponds to the JSON property state

Returns:

  • (String) 


15915
15916
15917
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 15915

def state
  @state
end

#stats_anomalies_base_directory ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1GcsDestination

The Google Cloud Storage location where the output is to be written to. Corresponds to the JSON property statsAnomaliesBaseDirectory

Returns:



15920
15921
15922
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 15920

def stats_anomalies_base_directory
  @stats_anomalies_base_directory
end

#update_time ⇒ String

Output only. Timestamp when this ModelDeploymentMonitoringJob was updated most recently. Corresponds to the JSON property updateTime

Returns:

  • (String) 


15926
15927
15928
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 15926

def update_time
  @update_time
end

Instance Method Details

#update!(**args) ⇒ Object

Update properties of this object



15933
15934
15935
15936
15937
15938
15939
15940
15941
15942
15943
15944
15945
15946
15947
15948
15949
15950
15951
15952
15953
15954
15955
15956
15957
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 15933

def update!(**args)
  @analysis_instance_schema_uri = args[:analysis_instance_schema_uri] if args.key?(:analysis_instance_schema_uri)
  @bigquery_tables = args[:bigquery_tables] if args.key?(:bigquery_tables)
  @create_time = args[:create_time] if args.key?(:create_time)
  @display_name = args[:display_name] if args.key?(:display_name)
  @enable_monitoring_pipeline_logs = args[:enable_monitoring_pipeline_logs] if args.key?(:enable_monitoring_pipeline_logs)
  @encryption_spec = args[:encryption_spec] if args.key?(:encryption_spec)
  @endpoint = args[:endpoint] if args.key?(:endpoint)
  @error = args[:error] if args.key?(:error)
  @labels = args[:labels] if args.key?(:labels)
  @latest_monitoring_pipeline_metadata = args[:latest_monitoring_pipeline_metadata] if args.key?(:latest_monitoring_pipeline_metadata)
  @log_ttl = args[:log_ttl] if args.key?(:log_ttl)
  @logging_sampling_strategy = args[:logging_sampling_strategy] if args.key?(:logging_sampling_strategy)
  @model_deployment_monitoring_objective_configs = args[:model_deployment_monitoring_objective_configs] if args.key?(:model_deployment_monitoring_objective_configs)
  @model_deployment_monitoring_schedule_config = args[:model_deployment_monitoring_schedule_config] if args.key?(:model_deployment_monitoring_schedule_config)
  @model_monitoring_alert_config = args[:model_monitoring_alert_config] if args.key?(:model_monitoring_alert_config)
  @name = args[:name] if args.key?(:name)
  @next_schedule_time = args[:next_schedule_time] if args.key?(:next_schedule_time)
  @predict_instance_schema_uri = args[:predict_instance_schema_uri] if args.key?(:predict_instance_schema_uri)
  @sample_predict_instance = args[:sample_predict_instance] if args.key?(:sample_predict_instance)
  @schedule_state = args[:schedule_state] if args.key?(:schedule_state)
  @state = args[:state] if args.key?(:state)
  @stats_anomalies_base_directory = args[:stats_anomalies_base_directory] if args.key?(:stats_anomalies_base_directory)
  @update_time = args[:update_time] if args.key?(:update_time)
end