public sealed class ModelMonitoringStatsDataPoint.Types.TypedValue.Types.DistributionDataValue : IMessage<ModelMonitoringStatsDataPoint.Types.TypedValue.Types.DistributionDataValue>, IEquatable<ModelMonitoringStatsDataPoint.Types.TypedValue.Types.DistributionDataValue>, IDeepCloneable<ModelMonitoringStatsDataPoint.Types.TypedValue.Types.DistributionDataValue>, IBufferMessage, IMessageReference documentation and code samples for the Cloud AI Platform v1beta1 API class ModelMonitoringStatsDataPoint.Types.TypedValue.Types.DistributionDataValue.
Summary statistics for a population of values.
Implements
IMessageModelMonitoringStatsDataPointTypesTypedValueTypesDistributionDataValue, IEquatableModelMonitoringStatsDataPointTypesTypedValueTypesDistributionDataValue, IDeepCloneableModelMonitoringStatsDataPointTypesTypedValueTypesDistributionDataValue, IBufferMessage, IMessageNamespace
Google.Cloud.AIPlatform.V1Beta1Assembly
Google.Cloud.AIPlatform.V1Beta1.dll
Constructors
DistributionDataValue()
public DistributionDataValue()DistributionDataValue(DistributionDataValue)
public DistributionDataValue(ModelMonitoringStatsDataPoint.Types.TypedValue.Types.DistributionDataValue other)| Parameter | |
|---|---|
| Name | Description |
other |
ModelMonitoringStatsDataPointTypesTypedValueTypesDistributionDataValue |
Properties
Distribution
public Value Distribution { get; set; }Predictive monitoring drift distribution in
tensorflow.metadata.v0.DatasetFeatureStatistics format.
| Property Value | |
|---|---|
| Type | Description |
Value |
|
DistributionDeviation
public double DistributionDeviation { get; set; }Distribution distance deviation from the current dataset's statistics to baseline dataset's statistics.
- For categorical feature, the distribution distance is calculated by L-inifinity norm or Jensen–Shannon divergence.
- For numerical feature, the distribution distance is calculated by Jensen–Shannon divergence.
| Property Value | |
|---|---|
| Type | Description |
double |
|