relevel.predkmeans {predkmeans}

Re-order cluster labels

Description

Function for re-ordering the order of clusters in a predkmeans object.

Usage

## S3 method for class 'predkmeans'
relevel(x, ref = NULL, order = NULL, ...)

Arguments

x

object of class predkmeans

ref

New reference group ("Cluster 1"). Only used if order is NULL.

order

New order of clusters.

...

Ignored additional arguments.

Details

The elements of the order argument should refer to the current position of clusters, with the position giving the new order. So c(3, 1, 2) moves 1 to 2, 2 to 3, and 3 to 1.

Author(s)

Joshua Keller

See Also

Other methods for predkmeans objects: predictML.predkmeans()

Examples

n <- 200
r1 <- rnorm(n)
r2 <- rnorm(n)
u1 <- rbinom(n, size=1,prob=0)
cluster <- ifelse(r1<0, ifelse(u1, "A", "B"), ifelse(r2<0, "C", "D"))
mu1 <- c(A=2, B=2, C=-2, D=-2)
mu2 <- c(A=1, B=-1, C=-1, D=-1)
x1 <- rnorm(n, mu1[cluster], 4)
x2 <- rnorm(n, mu2[cluster], 4)
R <- model.matrix(~r1 + r2)
X <- cbind(x1, x2)
pkm <- predkmeans(X=cbind(x1, x2), R=R, K=4)
table(pkm$cluster)

# Move cluster '4' to be first
pkm2 <- relevel(pkm, ref=4)
table(pkm2$cluster)
# Re-order based upon number of observations in each cluster
pkm3 <- relevel(pkm, order=order(table(pkm$cluster), decreasing=TRUE))
table(pkm3$cluster)