Reference documentation and code samples for the Google Cloud Ai Platform V1 Client class PredictionDriftDetectionConfig.
The config for Prediction data drift detection.
Generated from protobuf message google.cloud.aiplatform.v1.ModelMonitoringObjectiveConfig.PredictionDriftDetectionConfig
Methods
__construct
Constructor.
| Parameters | |
|---|---|
| Name | Description |
data |
array
Optional. Data for populating the Message object. |
↳ drift_thresholds |
array|Google\Protobuf\Internal\MapField
Key is the feature name and value is the threshold. If a feature needs to be monitored for drift, a value threshold must be configured for that feature. The threshold here is against feature distribution distance between different time windws. |
↳ attribution_score_drift_thresholds |
array|Google\Protobuf\Internal\MapField
Key is the feature name and value is the threshold. The threshold here is against attribution score distance between different time windows. |
↳ default_drift_threshold |
Google\Cloud\AIPlatform\V1\ThresholdConfig
Drift anomaly detection threshold used by all features. When the per-feature thresholds are not set, this field can be used to specify a threshold for all features. |
getDriftThresholds
Key is the feature name and value is the threshold. If a feature needs to be monitored for drift, a value threshold must be configured for that feature. The threshold here is against feature distribution distance between different time windws.
Generated from protobuf field map<string, .google.cloud.aiplatform.v1.ThresholdConfig> drift_thresholds = 1;
| Returns | |
|---|---|
| Type | Description |
Google\Protobuf\Internal\MapField | |
setDriftThresholds
Key is the feature name and value is the threshold. If a feature needs to be monitored for drift, a value threshold must be configured for that feature. The threshold here is against feature distribution distance between different time windws.
Generated from protobuf field map<string, .google.cloud.aiplatform.v1.ThresholdConfig> drift_thresholds = 1;
| Parameter | |
|---|---|
| Name | Description |
var |
array|Google\Protobuf\Internal\MapField
|
| Returns | |
|---|---|
| Type | Description |
$this | |
getAttributionScoreDriftThresholds
Key is the feature name and value is the threshold. The threshold here is against attribution score distance between different time windows.
Generated from protobuf field map<string, .google.cloud.aiplatform.v1.ThresholdConfig> attribution_score_drift_thresholds = 2;
| Returns | |
|---|---|
| Type | Description |
Google\Protobuf\Internal\MapField | |
setAttributionScoreDriftThresholds
Key is the feature name and value is the threshold. The threshold here is against attribution score distance between different time windows.
Generated from protobuf field map<string, .google.cloud.aiplatform.v1.ThresholdConfig> attribution_score_drift_thresholds = 2;
| Parameter | |
|---|---|
| Name | Description |
var |
array|Google\Protobuf\Internal\MapField
|
| Returns | |
|---|---|
| Type | Description |
$this | |
getDefaultDriftThreshold
Drift anomaly detection threshold used by all features.
When the per-feature thresholds are not set, this field can be used to specify a threshold for all features.
Generated from protobuf field .google.cloud.aiplatform.v1.ThresholdConfig default_drift_threshold = 5;
| Returns | |
|---|---|
| Type | Description |
Google\Cloud\AIPlatform\V1\ThresholdConfig|null | |
hasDefaultDriftThreshold
clearDefaultDriftThreshold
setDefaultDriftThreshold
Drift anomaly detection threshold used by all features.
When the per-feature thresholds are not set, this field can be used to specify a threshold for all features.
Generated from protobuf field .google.cloud.aiplatform.v1.ThresholdConfig default_drift_threshold = 5;
| Parameter | |
|---|---|
| Name | Description |
var |
Google\Cloud\AIPlatform\V1\ThresholdConfig
|
| Returns | |
|---|---|
| Type | Description |
$this | |