Class: Google::Apis::AiplatformV1::GoogleCloudAiplatformV1ModelMonitoringObjectiveConfigPredictionDriftDetectionConfig
- Inherits:
-
Object
- Object
- Google::Apis::AiplatformV1::GoogleCloudAiplatformV1ModelMonitoringObjectiveConfigPredictionDriftDetectionConfig
- Includes:
- Core::Hashable, Core::JsonObjectSupport
- Defined in:
- lib/google/apis/aiplatform_v1/classes.rb,
lib/google/apis/aiplatform_v1/representations.rb,
lib/google/apis/aiplatform_v1/representations.rb
Overview
The config for Prediction data drift detection.
Instance Attribute Summary collapse
-
#attribution_score_drift_thresholds ⇒ Hash<String,Google::Apis::AiplatformV1::GoogleCloudAiplatformV1ThresholdConfig>
Key is the feature name and value is the threshold.
-
#default_drift_threshold ⇒ Google::Apis::AiplatformV1::GoogleCloudAiplatformV1ThresholdConfig
The config for feature monitoring threshold.
-
#drift_thresholds ⇒ Hash<String,Google::Apis::AiplatformV1::GoogleCloudAiplatformV1ThresholdConfig>
Key is the feature name and value is the threshold.
Instance Method Summary collapse
-
#initialize(**args) ⇒ GoogleCloudAiplatformV1ModelMonitoringObjectiveConfigPredictionDriftDetectionConfig
constructor
A new instance of GoogleCloudAiplatformV1ModelMonitoringObjectiveConfigPredictionDriftDetectionConfig.
-
#update!(**args) ⇒ Object
Update properties of this object.
Constructor Details
#initialize(**args) ⇒ GoogleCloudAiplatformV1ModelMonitoringObjectiveConfigPredictionDriftDetectionConfig
Returns a new instance of GoogleCloudAiplatformV1ModelMonitoringObjectiveConfigPredictionDriftDetectionConfig.
12013 12014 12015 |
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 12013 def initialize(**args) update!(**args) end |
Instance Attribute Details
#attribution_score_drift_thresholds ⇒ Hash<String,Google::Apis::AiplatformV1::GoogleCloudAiplatformV1ThresholdConfig>
Key is the feature name and value is the threshold. The threshold here is
against attribution score distance between different time windows.
Corresponds to the JSON property attributionScoreDriftThresholds
11998 11999 12000 |
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 11998 def attribution_score_drift_thresholds @attribution_score_drift_thresholds end |
#default_drift_threshold ⇒ Google::Apis::AiplatformV1::GoogleCloudAiplatformV1ThresholdConfig
The config for feature monitoring threshold.
Corresponds to the JSON property defaultDriftThreshold
12003 12004 12005 |
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 12003 def default_drift_threshold @default_drift_threshold end |
#drift_thresholds ⇒ Hash<String,Google::Apis::AiplatformV1::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.
Corresponds to the JSON property driftThresholds
12011 12012 12013 |
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 12011 def drift_thresholds @drift_thresholds end |
Instance Method Details
#update!(**args) ⇒ Object
Update properties of this object
12018 12019 12020 12021 12022 |
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 12018 def update!(**args) @attribution_score_drift_thresholds = args[:attribution_score_drift_thresholds] if args.key?(:attribution_score_drift_thresholds) @default_drift_threshold = args[:default_drift_threshold] if args.key?(:default_drift_threshold) @drift_thresholds = args[:drift_thresholds] if args.key?(:drift_thresholds) end |