graphclust (version 1.3)

ARI: Adjusted Rand index

Description

ARI to compare two clusterings or to compare two entire lists of clusterings

Usage

ARI(x, y)

Value

ARI (scalar of vector)

Arguments

x

vector with clustering, matrix with hot-one-encoding of the clustering, or a list of clusterings (in vector or matrix form)

y

as x

Examples

x <- c(1,1,2,2,3,3)
y <- c(1,1,1,2,2,2)
ARI(x,y)

x <- matrix(0, 3, 6)
x[1,1] <- x[1,2] <- x[2,3] <- x[2,4] <- x[3,5] <- x[3,6] <- 1
y <- matrix(0, 2, 6)
y[1,1] <- y[1,2] <- y[1,3] <- y[2,4] <- y[2,5] <- y[2,6] <- 1
ARI(x,y)

X <- list(c(1,1,2,2,3,3), rep(1,10))
Y <- list(c(1,1,1,2,2,2), rep(1:2,each=5))
ARI(X,Y)