ClusterMethods: Clusters outlier detection methods according to the...

Description Usage Arguments Value See Also Examples

Description

Clusters outlier detection methods according to the correlation matrix for min-max and median-iqr normalization methods, using the R package cluster.

Usage

1
ClusterMethods(kk, rocpr = 1, vis = FALSE)

Arguments

kk

The number of clusters

rocpr

If rocpr = 1, then area under ROC cure is used, if rocpr = 2 then area under PR curve is used.

vis

If TRUE then the resulting graphs are plotted.

Value

A pam.object described in the R package cluster.

See Also

pam.object.

Examples

1
2
3
4
5
cls <- ClusterMethods(8)
which(cls$clustering==2)
which(cls$clustering==4)
which(cls$clustering==5)
which(cls$clustering==6)

sevvandi/outselect documentation built on June 1, 2019, 3:58 a.m.