rIMethods: Rand index for cluster configurations of different methods.

In funcy: Functional Clustering Algorithms

Description

Calculates a matrix of Rand indices for the configurations of all cluster method combinations.

Usage

rIMethods(methodNames = NULL, cls, trueCluster = NULL)

Arguments

methodNames	Character Vector of names for the methods.
cls	Numeric or character matrix of cluster outcomes for different methods.
trueCluster	Vector of true clusters if knows.

Details

If trueCluster is given, the Rand index between the true cluster outcome and the clusters calculated by the methods is on diagonal.

Value

A matrix of Rand indices showing the similarity of the methods.

Author(s)

Christina Yassouridis

Examples

set.seed(1234)
ds <- sampleFuncy(obsNr=80, timeNr=20, reg=TRUE, k=4, sd=.4)
res1 <- funcit(methods=1:3, data=Data(ds), k=4, clusters=Cluster(ds))

cls <- Cluster(res1)
rIMethods(methodNames=c("method1","method2","method3"),cls=cls, trueCluster=Cluster(ds))

funcy documentation built on May 2, 2019, 9:22 a.m.