public interface FeatureStatsAndAnomalyOrBuilder extends MessageOrBuilderImplements
MessageOrBuilderMethods
getDistributionDeviation()
public abstract 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 = 3;
| Returns | |
|---|---|
| Type | Description |
double |
The distributionDeviation. |
getDriftDetected()
public abstract boolean getDriftDetected()If set to true, indicates current stats is detected as and comparing with baseline stats.
bool drift_detected = 5;
| Returns | |
|---|---|
| Type | Description |
boolean |
The driftDetected. |
getDriftDetectionThreshold()
public abstract double getDriftDetectionThreshold()This is the threshold used when detecting drifts, which is set in FeatureMonitor.FeatureSelectionConfig.FeatureConfig.drift_threshold
double drift_detection_threshold = 4;
| Returns | |
|---|---|
| Type | Description |
double |
The driftDetectionThreshold. |
getFeatureId()
public abstract String getFeatureId()Feature Id.
string feature_id = 1;
| Returns | |
|---|---|
| Type | Description |
String |
The featureId. |
getFeatureIdBytes()
public abstract ByteString getFeatureIdBytes()Feature Id.
string feature_id = 1;
| Returns | |
|---|---|
| Type | Description |
ByteString |
The bytes for featureId. |
getFeatureMonitorId()
public abstract String getFeatureMonitorId()The ID of the FeatureMonitor that this FeatureStatsAndAnomaly generated according to.
string feature_monitor_id = 8;
| Returns | |
|---|---|
| Type | Description |
String |
The featureMonitorId. |
getFeatureMonitorIdBytes()
public abstract ByteString getFeatureMonitorIdBytes()The ID of the FeatureMonitor that this FeatureStatsAndAnomaly generated according to.
string feature_monitor_id = 8;
| Returns | |
|---|---|
| Type | Description |
ByteString |
The bytes for featureMonitorId. |
getFeatureMonitorJobId()
public abstract long getFeatureMonitorJobId()The ID of the FeatureMonitorJob that generated this FeatureStatsAndAnomaly.
int64 feature_monitor_job_id = 7;
| Returns | |
|---|---|
| Type | Description |
long |
The featureMonitorJobId. |
getFeatureStats()
public abstract Value getFeatureStats()Feature stats. e.g. histogram buckets. In the format of tensorflow.metadata.v0.DatasetFeatureStatistics.
.google.protobuf.Value feature_stats = 2;
| Returns | |
|---|---|
| Type | Description |
Value |
The featureStats. |
getFeatureStatsOrBuilder()
public abstract ValueOrBuilder getFeatureStatsOrBuilder()Feature stats. e.g. histogram buckets. In the format of tensorflow.metadata.v0.DatasetFeatureStatistics.
.google.protobuf.Value feature_stats = 2;
| Returns | |
|---|---|
| Type | Description |
ValueOrBuilder |
|
getStatsTime()
public abstract Timestamp getStatsTime()The timestamp we take snapshot for feature values to generate stats.
.google.protobuf.Timestamp stats_time = 6;
| Returns | |
|---|---|
| Type | Description |
Timestamp |
The statsTime. |
getStatsTimeOrBuilder()
public abstract TimestampOrBuilder getStatsTimeOrBuilder()The timestamp we take snapshot for feature values to generate stats.
.google.protobuf.Timestamp stats_time = 6;
| Returns | |
|---|---|
| Type | Description |
TimestampOrBuilder |
|
hasFeatureStats()
public abstract boolean hasFeatureStats()Feature stats. e.g. histogram buckets. In the format of tensorflow.metadata.v0.DatasetFeatureStatistics.
.google.protobuf.Value feature_stats = 2;
| Returns | |
|---|---|
| Type | Description |
boolean |
Whether the featureStats field is set. |
hasStatsTime()
public abstract boolean hasStatsTime()The timestamp we take snapshot for feature values to generate stats.
.google.protobuf.Timestamp stats_time = 6;
| Returns | |
|---|---|
| Type | Description |
boolean |
Whether the statsTime field is set. |