Class GoogleCloudAiplatformV1beta1ModelMonitor

Vertex AI Model Monitoring Service serves as a central hub for the analysis and visualization of data quality and performance related to models. ModelMonitor stands as a top level resource for overseeing your model monitoring tasks.

Inheritance
object
GoogleCloudAiplatformV1beta1ModelMonitor
Implements
Inherited Members
Namespace: Google.Apis.Aiplatform.v1beta1.Data
Assembly: Google.Apis.Aiplatform.v1beta1.dll
Syntax
public class GoogleCloudAiplatformV1beta1ModelMonitor : IDirectResponseSchema

Properties

CreateTime

object representation of CreateTimeRaw.

Declaration
[JsonIgnore]
[Obsolete("This property is obsolete and may behave unexpectedly; please use CreateTimeDateTimeOffset instead.")]
public virtual object CreateTime { get; set; }
Property Value
Type Description
object

CreateTimeDateTimeOffset

DateTimeOffset representation of CreateTimeRaw.

Declaration
[JsonIgnore]
public virtual DateTimeOffset? CreateTimeDateTimeOffset { get; set; }
Property Value
Type Description
DateTimeOffset?

CreateTimeRaw

Output only. Timestamp when this ModelMonitor was created.

Declaration
[JsonProperty("createTime")]
public virtual string CreateTimeRaw { get; set; }
Property Value
Type Description
string

DisplayName

The display name of the ModelMonitor. The name can be up to 128 characters long and can consist of any UTF-8.

Declaration
[JsonProperty("displayName")]
public virtual string DisplayName { get; set; }
Property Value
Type Description
string

ETag

The ETag of the item.

Declaration
public virtual string ETag { get; set; }
Property Value
Type Description
string

ExplanationSpec

Optional model explanation spec. It is used for feature attribution monitoring.

Declaration
[JsonProperty("explanationSpec")]
public virtual GoogleCloudAiplatformV1beta1ExplanationSpec ExplanationSpec { get; set; }
Property Value
Type Description
GoogleCloudAiplatformV1beta1ExplanationSpec

ModelMonitoringSchema

Monitoring Schema is to specify the model's features, prediction outputs and ground truth properties. It is used to extract pertinent data from the dataset and to process features based on their properties. Make sure that the schema aligns with your dataset, if it does not, we will be unable to extract data from the dataset. It is required for most models, but optional for Vertex AI AutoML Tables unless the schem information is not available.

Declaration
[JsonProperty("modelMonitoringSchema")]
public virtual GoogleCloudAiplatformV1beta1ModelMonitoringSchema ModelMonitoringSchema { get; set; }
Property Value
Type Description
GoogleCloudAiplatformV1beta1ModelMonitoringSchema

ModelMonitoringTarget

The entity that is subject to analysis. Currently only models in Vertex AI Model Registry are supported. If you want to analyze the model which is outside the Vertex AI, you could register a model in Vertex AI Model Registry using just a display name.

Declaration
[JsonProperty("modelMonitoringTarget")]
public virtual GoogleCloudAiplatformV1beta1ModelMonitorModelMonitoringTarget ModelMonitoringTarget { get; set; }
Property Value
Type Description
GoogleCloudAiplatformV1beta1ModelMonitorModelMonitoringTarget

Name

Immutable. Resource name of the ModelMonitor. Format: projects/{project}/locations/{location}/modelMonitors/{model_monitor}.

Declaration
[JsonProperty("name")]
public virtual string Name { get; set; }
Property Value
Type Description
string

NotificationSpec

Optional default notification spec, it can be overridden in the ModelMonitoringJob notification spec.

Declaration
[JsonProperty("notificationSpec")]
public virtual GoogleCloudAiplatformV1beta1ModelMonitoringNotificationSpec NotificationSpec { get; set; }
Property Value
Type Description
GoogleCloudAiplatformV1beta1ModelMonitoringNotificationSpec

OutputSpec

Optional default monitoring metrics/logs export spec, it can be overridden in the ModelMonitoringJob output spec. If not specified, a default Google Cloud Storage bucket will be created under your project.

Declaration
[JsonProperty("outputSpec")]
public virtual GoogleCloudAiplatformV1beta1ModelMonitoringOutputSpec OutputSpec { get; set; }
Property Value
Type Description
GoogleCloudAiplatformV1beta1ModelMonitoringOutputSpec

SatisfiesPzi

Output only. Reserved for future use.

Declaration
[JsonProperty("satisfiesPzi")]
public virtual bool? SatisfiesPzi { get; set; }
Property Value
Type Description
bool?

SatisfiesPzs

Output only. Reserved for future use.

Declaration
[JsonProperty("satisfiesPzs")]
public virtual bool? SatisfiesPzs { get; set; }
Property Value
Type Description
bool?

TabularObjective

Optional default tabular model monitoring objective.

Declaration
[JsonProperty("tabularObjective")]
public virtual GoogleCloudAiplatformV1beta1ModelMonitoringObjectiveSpecTabularObjective TabularObjective { get; set; }
Property Value
Type Description
GoogleCloudAiplatformV1beta1ModelMonitoringObjectiveSpecTabularObjective

TrainingDataset

Optional training dataset used to train the model. It can serve as a reference dataset to identify changes in production.

Declaration
[JsonProperty("trainingDataset")]
public virtual GoogleCloudAiplatformV1beta1ModelMonitoringInput TrainingDataset { get; set; }
Property Value
Type Description
GoogleCloudAiplatformV1beta1ModelMonitoringInput

UpdateTime

object representation of UpdateTimeRaw.

Declaration
[JsonIgnore]
[Obsolete("This property is obsolete and may behave unexpectedly; please use UpdateTimeDateTimeOffset instead.")]
public virtual object UpdateTime { get; set; }
Property Value
Type Description
object

UpdateTimeDateTimeOffset

DateTimeOffset representation of UpdateTimeRaw.

Declaration
[JsonIgnore]
public virtual DateTimeOffset? UpdateTimeDateTimeOffset { get; set; }
Property Value
Type Description
DateTimeOffset?

UpdateTimeRaw

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

Declaration
[JsonProperty("updateTime")]
public virtual string UpdateTimeRaw { get; set; }
Property Value
Type Description
string

Implements