Package elki.evaluation.outlier
Evaluate an outlier score using a misclassification based cost model.
-
Class Summary Class Description ComputeOutlierHistogram Compute a Histogram to evaluate a ranking algorithm.ComputeOutlierHistogram.Par Parameterization class.JudgeOutlierScores Compute a Histogram to evaluate a ranking algorithm.JudgeOutlierScores.Par Parameterization class.JudgeOutlierScores.ScoreResult Result object for outlier score judgements.OutlierPrecisionAtKCurve Compute a curve containing the precision values for an outlier detection method.OutlierPrecisionAtKCurve.Par Parameterization class.OutlierPrecisionAtKCurve.PrecisionAtKCurve Precision at K curve.OutlierPrecisionRecallCurve Compute a curve containing the precision values for an outlier detection method.OutlierPrecisionRecallCurve.Par Parameterization class.OutlierPrecisionRecallGainCurve Compute a curve containing the precision gain and revall gain values for an outlier detection method.OutlierPrecisionRecallGainCurve.Par Parameterization class.OutlierRankingEvaluation Evaluate outlier scores by their rankingOutlierRankingEvaluation.Par Parameterization class.OutlierROCCurve Compute a ROC curve to evaluate a ranking algorithm and compute the corresponding AUROC value.OutlierROCCurve.Par Parameterization class.OutlierSmROCCurve Smooth ROC curves are a variation of classic ROC curves that takes the scores into account.OutlierSmROCCurve.Par Parameterization class.OutlierSmROCCurve.SmROCResult Result object for Smooth ROC curves.OutlierThresholdClustering Pseudo clustering algorithm that builds clusters based on their outlier score.OutlierThresholdClustering.Par Parameterization helper