Anomaly Detection EvaluatorΒΆ

The documentation is generated based on the sources available at dotnet/machinelearning and released under MIT License.

Type: evaluator Aliases: AnomalyDetectionEvaluator, AnomalyDetection, Anomaly Namespace: Microsoft.ML.Runtime.Data Assembly: Microsoft.ML.Data.dll Microsoft Documentation: Anomaly Detection Evaluator

Description

Parameters

Name Short name Default Description
k   10 Expected number of false positives
maxAucExamples numauc -1 The number of samples to use for AUC calculation. If 0, AUC is not computed. If -1, the whole dataset is used
numTopResults n 50 Number of top-scored predictions to display
p   0.01 Expected false positive rate
stream   True Whether to calculate metrics in one pass