GoogleCloudAiplatformV1ModelMonitoringObjectiveConfigPredictionDriftDetectionConfig
import type { GoogleCloudAiplatformV1ModelMonitoringObjectiveConfigPredictionDriftDetectionConfig } from "https://googleapis.deno.dev/v1/aiplatform:v1.ts";
The config for Prediction data drift detection.
interface GoogleCloudAiplatformV1ModelMonitoringObjectiveConfigPredictionDriftDetectionConfig {
attributionScoreDriftThresholds?: {};
[key: string]: GoogleCloudAiplatformV1ThresholdConfig;
defaultDriftThreshold?: GoogleCloudAiplatformV1ThresholdConfig;
driftThresholds?: {};
}[key: string]: GoogleCloudAiplatformV1ThresholdConfig;
§Properties
§
attributionScoreDriftThresholds?: {}
[src][key: string]: GoogleCloudAiplatformV1ThresholdConfig;
Key is the feature name and value is the threshold. The threshold here is against attribution score distance between different time windows.
§
defaultDriftThreshold?: GoogleCloudAiplatformV1ThresholdConfig
[src]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.
§
driftThresholds?: {}
[src][key: string]: GoogleCloudAiplatformV1ThresholdConfig;
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.