Klasse MetricNMEntropy

java.lang.Object
org.deidentifier.arx.metric.Metric<org.deidentifier.arx.metric.InformationLossDefault>
Alle implementierten Schnittstellen:
Serializable

public class MetricNMEntropy extends MetricEntropy
This class provides an efficient implementation of a non-monotonic and non-uniform entropy metric. It avoids a cell-by-cell process by utilizing a three-dimensional array that maps identifiers to their frequency for all quasi-identifiers and generalization levels. It further reduces the overhead induced by subsequent calls by caching the results for previous columns and generalization levels. It takes supressed tuples into account by adding the information loss induced by suppressing the transformed representation of the outliers.
Siehe auch: