index.H {clusterSim}

Calculates Hartigan index

Description

Calculates Hartigan index

Usage

index.H (x,clall,d=NULL,centrotypes="centroids")

Arguments

x

data

clall

Two vectors of integers indicating the cluster to which each object is allocated in partition of n objects into u and u+1 clusters

d

optional distance matrix, used for calculations if centrotypes="medoids"

centrotypes

"centroids" or "medoids"

Details

See file $R_HOME\library\clusterSim\pdf\indexH_details.pdf for further details

Value

Hartigan index

Author(s)

Marek Walesiak [e-mail], Andrzej Dudek [e-mail]

Department of Econometrics and Computer Science, University of Economics, Wroclaw, Poland

References

Hartigan, J. (1975), Clustering algorithms, Wiley, New York. ISBN 047135645X.

Milligan, G.W., Cooper, M.C. (1985), An examination of procedures of determining the number of cluster in a data set, "Psychometrika", vol. 50, no. 2, 159-179. Available at: doi:10.1007/BF02294245.

Tibshirani, R., Walther, G., Hastie, T. (2001), Estimating the number of clusters in a data set via the gap statistic, "Journal of the Royal Statistical Society", ser. B, vol. 63, part 2, 411-423. Available at: doi:10.1111/1467-9868.00293.

See Also

index.G1, index.G2, index.G3, index.C, index.S, index.KL, index.Gap, index.DB

Examples

# Example 1
library(clusterSim)
data(data_ratio)
cl1<-pam(data_ratio,4)
cl2<-pam(data_ratio,5)
clall<-cbind(cl1$clustering,cl2$clustering)
index.H(data_ratio,clall)

# Example 2
library(clusterSim)
data(data_ratio)
md <- dist(data_ratio, method="euclidean")
# nc - number_of_clusters
min_nc=1
max_nc=20
min <- 0
res <- array(0, c(max_nc-min_nc+1, 2))
res[,1] <- min_nc:max_nc
found <- FALSE
clusters <- NULL
for (nc in min_nc:max_nc)
{
	print(nc)
	hc <- hclust(md, method="complete")
	cl1 <- cutree(hc, k=nc)
	cl2 <- cutree(hc, k=nc+1)
	clall <- cbind(cl1,cl2)
	res[nc-min_nc+1,2] <- H <- index.H(data_ratio,clall,centrotypes="centroids")
	if ((res[nc-min_nc+1, 2]<10) && (!found)){
       nc1 <- nc
       min <- H
       clopt <- cl1
		   found <- TRUE
	}
}
if (found)
{
	print(paste("minimal nc for H<=10 equals",nc1,"for H=",min))
	print("clustering for minimal nc where H<=10")
	print(clopt)
}else
{
	print("Clustering not found with H<=10")
}
#write.table(res,file="H_res.csv",sep=";",dec=",",row.names=TRUE,col.names=FALSE)
plot(res,type="p",pch=0,xlab="Number of clusters",ylab="H",xaxt="n")
abline(h=10, untf=FALSE)
axis(1, c(min_nc:max_nc))

# Example 3
library(clusterSim)
data(data_ratio)
md <- dist(data_ratio, method="manhattan")
# nc - number_of_clusters
min_nc=1
max_nc=20
min <- 0
res <- array(0, c(max_nc-min_nc+1, 2))
res[,1] <- min_nc:max_nc
found <- FALSE
clusters <- NULL
for (nc in min_nc:max_nc)
{
	print(nc)
	hc <- hclust(md, method="complete")
	cl1 <- cutree(hc, k=nc)
	cl2 <- cutree(hc, k=nc+1)
	clall <- cbind(cl1,cl2)
	res[nc-min_nc+1,2] <- H <- index.H(data_ratio,clall,d=md,centrotypes="medoids")
	if ((res[nc-min_nc+1, 2]<10) && (!found)){
       nc1 <- nc
       min <- H
       clopt <- cl1
		   found <- TRUE
	}
}
if (found)
{
	print(paste("minimal nc for H<=10 equals",nc1,"for H=",min))
	print("clustering for minimal nc where H<=10")
	print(clopt)
}else
{
	print("Clustering not found with H<=10")
}
#write.table(res,file="H_res.csv",sep=";",dec=",",row.names=TRUE,col.names=FALSE)
plot(res,type="p",pch=0,xlab="Number of clusters",ylab="H",xaxt="n")
abline(h=10, untf=FALSE)
axis(1, c(min_nc:max_nc))