public final class FeatureStatsAnomaly extends GeneratedMessageV3 implements FeatureStatsAnomalyOrBuilder
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.
Protobuf type google.cloud.aiplatform.v1beta1.FeatureStatsAnomaly
Inherited Members
com.google.protobuf.GeneratedMessageV3.<ListT>makeMutableCopy(ListT)
Static Fields
public static final int ANOMALY_DETECTION_THRESHOLD_FIELD_NUMBER
| Field Value |
|---|
| Type | Description |
int | |
public static final int ANOMALY_URI_FIELD_NUMBER
| Field Value |
|---|
| Type | Description |
int | |
public static final int DISTRIBUTION_DEVIATION_FIELD_NUMBER
| Field Value |
|---|
| Type | Description |
int | |
public static final int END_TIME_FIELD_NUMBER
| Field Value |
|---|
| Type | Description |
int | |
public static final int SCORE_FIELD_NUMBER
| Field Value |
|---|
| Type | Description |
int | |
public static final int START_TIME_FIELD_NUMBER
| Field Value |
|---|
| Type | Description |
int | |
public static final int STATS_URI_FIELD_NUMBER
| Field Value |
|---|
| Type | Description |
int | |
Static Methods
public static FeatureStatsAnomaly getDefaultInstance()
public static final Descriptors.Descriptor getDescriptor()
public static FeatureStatsAnomaly.Builder newBuilder()
public static FeatureStatsAnomaly.Builder newBuilder(FeatureStatsAnomaly prototype)
public static FeatureStatsAnomaly parseDelimitedFrom(InputStream input)
public static FeatureStatsAnomaly parseDelimitedFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
public static FeatureStatsAnomaly parseFrom(byte[] data)
| Parameter |
|---|
| Name | Description |
data | byte[]
|
public static FeatureStatsAnomaly parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry)
public static FeatureStatsAnomaly parseFrom(ByteString data)
public static FeatureStatsAnomaly parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry)
public static FeatureStatsAnomaly parseFrom(CodedInputStream input)
public static FeatureStatsAnomaly parseFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
public static FeatureStatsAnomaly parseFrom(InputStream input)
public static FeatureStatsAnomaly parseFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
public static FeatureStatsAnomaly parseFrom(ByteBuffer data)
public static FeatureStatsAnomaly parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry)
public static Parser<FeatureStatsAnomaly> parser()
Methods
public boolean equals(Object obj)
| Parameter |
|---|
| Name | Description |
obj | Object
|
Overrides
public double getAnomalyDetectionThreshold()
This is the threshold used when detecting anomalies.
The threshold can be changed by user, so this one might be different from
ThresholdConfig.value.
double anomaly_detection_threshold = 9;
| Returns |
|---|
| Type | Description |
double | The anomalyDetectionThreshold.
|
public String getAnomalyUri()
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.
string anomaly_uri = 4;
| Returns |
|---|
| Type | Description |
String | The anomalyUri.
|
public ByteString getAnomalyUriBytes()
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.
string anomaly_uri = 4;
| Returns |
|---|
| Type | Description |
ByteString | The bytes for anomalyUri.
|
public FeatureStatsAnomaly getDefaultInstanceForType()
public double getDistributionDeviation()
Deviation from the current stats to baseline stats.
- For categorical feature, the distribution distance is calculated by
L-inifinity norm.
- For numerical feature, the distribution distance is calculated by
Jensen–Shannon divergence.
double distribution_deviation = 5;
| Returns |
|---|
| Type | Description |
double | The distributionDeviation.
|
public Timestamp getEndTime()
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).
.google.protobuf.Timestamp end_time = 8;
public TimestampOrBuilder getEndTimeOrBuilder()
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).
.google.protobuf.Timestamp end_time = 8;
public Parser<FeatureStatsAnomaly> getParserForType()
Overrides
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
and
ModelDeploymentMonitoringObjectiveType.FEATURE_ATTRIBUTION_DRIFT.
double score = 1;
| Returns |
|---|
| Type | Description |
double | The score.
|
public int getSerializedSize()
| Returns |
|---|
| Type | Description |
int | |
Overrides
public Timestamp getStartTime()
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).
.google.protobuf.Timestamp start_time = 7;
| Returns |
|---|
| Type | Description |
Timestamp | The startTime.
|
public TimestampOrBuilder getStartTimeOrBuilder()
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).
.google.protobuf.Timestamp start_time = 7;
public String getStatsUri()
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.
string stats_uri = 3;
| Returns |
|---|
| Type | Description |
String | The statsUri.
|
public ByteString getStatsUriBytes()
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.
string stats_uri = 3;
| Returns |
|---|
| Type | Description |
ByteString | The bytes for statsUri.
|
public final UnknownFieldSet getUnknownFields()
Overrides
public boolean hasEndTime()
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).
.google.protobuf.Timestamp end_time = 8;
| Returns |
|---|
| Type | Description |
boolean | Whether the endTime field is set.
|
public boolean hasStartTime()
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).
.google.protobuf.Timestamp start_time = 7;
| Returns |
|---|
| Type | Description |
boolean | Whether the startTime field is set.
|
| Returns |
|---|
| Type | Description |
int | |
Overrides
protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Overrides
public final boolean isInitialized()
Overrides
public FeatureStatsAnomaly.Builder newBuilderForType()
protected FeatureStatsAnomaly.Builder newBuilderForType(GeneratedMessageV3.BuilderParent parent)
Overrides
protected Object newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)
Overrides
public FeatureStatsAnomaly.Builder toBuilder()
public void writeTo(CodedOutputStream output)
Overrides
