Vertex AI v1beta1 API - Class ModelMonitoringObjectiveSpec.Types.DataDriftSpec (1.0.0-beta78)

1.0.0-beta78 (latest) 1.0.0-beta77

public sealed class ModelMonitoringObjectiveSpec.Types.DataDriftSpec : IMessage<ModelMonitoringObjectiveSpec.Types.DataDriftSpec>, IEquatable<ModelMonitoringObjectiveSpec.Types.DataDriftSpec>, IDeepCloneable<ModelMonitoringObjectiveSpec.Types.DataDriftSpec>, IBufferMessage, IMessage

Reference documentation and code samples for the Vertex AI v1beta1 API class ModelMonitoringObjectiveSpec.Types.DataDriftSpec.

Data drift monitoring spec. Data drift measures the distribution distance between the current dataset and a baseline dataset. A typical use case is to detect data drift between the recent production serving dataset and the training dataset, or to compare the recent production dataset with a dataset from a previous period.

Inheritance

object > ModelMonitoringObjectiveSpec.Types.DataDriftSpec

Implements

IMessageModelMonitoringObjectiveSpecTypesDataDriftSpec, IEquatableModelMonitoringObjectiveSpecTypesDataDriftSpec, IDeepCloneableModelMonitoringObjectiveSpecTypesDataDriftSpec, IBufferMessage, IMessage

Inherited Members

object.GetHashCode()

object.GetType()

object.ToString()

Namespace

Google.Cloud.AIPlatform.V1Beta1

Assembly

Google.Cloud.AIPlatform.V1Beta1.dll

Constructors

DataDriftSpec()

public DataDriftSpec()

DataDriftSpec(DataDriftSpec)

public DataDriftSpec(ModelMonitoringObjectiveSpec.Types.DataDriftSpec other)

Parameter
Name	Description
other	ModelMonitoringObjectiveSpecTypesDataDriftSpec

Properties

CategoricalMetricType

public string CategoricalMetricType { get; set; }

Supported metrics type:

• l_infinity
• jensen_shannon_divergence

Property Value
Type	Description
string

DefaultCategoricalAlertCondition

public ModelMonitoringAlertCondition DefaultCategoricalAlertCondition { get; set; }

Default alert condition for all the categorical features.

Property Value
Type	Description
ModelMonitoringAlertCondition

DefaultNumericAlertCondition

public ModelMonitoringAlertCondition DefaultNumericAlertCondition { get; set; }

Default alert condition for all the numeric features.

Property Value
Type	Description
ModelMonitoringAlertCondition

FeatureAlertConditions

public MapField<string, ModelMonitoringAlertCondition> FeatureAlertConditions { get; }

Per feature alert condition will override default alert condition.

Property Value
Type	Description
MapFieldstringModelMonitoringAlertCondition

Features

public RepeatedField<string> Features { get; }

Feature names / Prediction output names interested in monitoring. These should be a subset of the input feature names or prediction output names specified in the monitoring schema. If the field is not specified all features / prediction outputs outlied in the monitoring schema will be used.

Property Value
Type	Description
RepeatedFieldstring

NumericMetricType

public string NumericMetricType { get; set; }

Supported metrics type:

• jensen_shannon_divergence

Property Value
Type	Description
string