Cloud AI Platform v1 API - Class FeatureStatsAnomaly (2.21.0)

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

Reference documentation and code samples for the Cloud AI Platform v1 API class FeatureStatsAnomaly.

Stats and Anomaly generated at specific timestamp for specific Feature. The start_time and end_time are used to define the time range of the dataset that current stats belongs to, e.g. prediction traffic is bucketed into prediction datasets by time window. If the Dataset is not defined by time window, start_time = end_time. Timestamp of the stats and anomalies always refers to end_time. Raw stats and anomalies are stored in stats_uri or anomaly_uri in the tensorflow defined protos. Field data_stats contains almost identical information with the raw stats in Vertex AI defined proto, for UI to display.

Inheritance

object > FeatureStatsAnomaly

Namespace

Google.Cloud.AIPlatform.V1

Assembly

Google.Cloud.AIPlatform.V1.dll

Constructors

FeatureStatsAnomaly()

public FeatureStatsAnomaly()

FeatureStatsAnomaly(FeatureStatsAnomaly)

public FeatureStatsAnomaly(FeatureStatsAnomaly other)
Parameter
NameDescription
otherFeatureStatsAnomaly

Properties

AnomalyDetectionThreshold

public double AnomalyDetectionThreshold { get; set; }

This is the threshold used when detecting anomalies. The threshold can be changed by user, so this one might be different from [ThresholdConfig.value][google.cloud.aiplatform.v1.ThresholdConfig.value].

Property Value
TypeDescription
double

AnomalyUri

public string AnomalyUri { get; set; }

Path of the anomaly file for current feature values in Cloud Storage bucket. Format: gs://<bucket_name>/<object_name>/anomalies. Example: gs://monitoring_bucket/feature_name/anomalies. Stats are stored as binary format with Protobuf message Anoamlies are stored as binary format with Protobuf message tensorflow.metadata.v0.AnomalyInfo.

Property Value
TypeDescription
string

DistributionDeviation

public double DistributionDeviation { get; set; }

Deviation from the current stats to baseline stats.

  1. For categorical feature, the distribution distance is calculated by L-inifinity norm.
  2. For numerical feature, the distribution distance is calculated by Jensen–Shannon divergence.
Property Value
TypeDescription
double

EndTime

public Timestamp EndTime { get; set; }

The end timestamp of window where stats were generated. For objectives where time window doesn't make sense (e.g. Featurestore Snapshot Monitoring), end_time indicates the timestamp of the data used to generate stats (e.g. timestamp we take snapshots for feature values).

Property Value
TypeDescription
Timestamp

Score

public double Score { get; set; }

Feature importance score, only populated when cross-feature monitoring is enabled. For now only used to represent feature attribution score within range [0, 1] for [ModelDeploymentMonitoringObjectiveType.FEATURE_ATTRIBUTION_SKEW][google.cloud.aiplatform.v1.ModelDeploymentMonitoringObjectiveType.FEATURE_ATTRIBUTION_SKEW] and [ModelDeploymentMonitoringObjectiveType.FEATURE_ATTRIBUTION_DRIFT][google.cloud.aiplatform.v1.ModelDeploymentMonitoringObjectiveType.FEATURE_ATTRIBUTION_DRIFT].

Property Value
TypeDescription
double

StartTime

public Timestamp StartTime { get; set; }

The start timestamp of window where stats were generated. For objectives where time window doesn't make sense (e.g. Featurestore Snapshot Monitoring), start_time is only used to indicate the monitoring intervals, so it always equals to (end_time - monitoring_interval).

Property Value
TypeDescription
Timestamp

StatsUri

public string StatsUri { get; set; }

Path of the stats file for current feature values in Cloud Storage bucket. Format: gs://<bucket_name>/<object_name>/stats. Example: gs://monitoring_bucket/feature_name/stats. Stats are stored as binary format with Protobuf message tensorflow.metadata.v0.FeatureNameStatistics.

Property Value
TypeDescription
string