disdiam: Dissimilarity Diameters of a Partition

In optpart: Optimal Partitioning of Similarity Relations

Description

Calculates the diameter (maximum within-cluster dissimilarity) of all clusters in a partition, as well as the average diameter across all clusters.

Usage

disdiam(x,dist,digits)
## S3 method for class 'stride'
disdiam(x,dist,digits=3)
## S3 method for class 'disdiam'
print(x, ...)

Arguments

x	a vector of integers or an object of class ‘clustering’, ‘partition’, ‘partana’, or ‘stride’
dist	an object of class ‘dist’ from dist, dsvdis, or vegdist
digits	the number of significant digits reported in the output
...	ancillary arguments to the print function

Details

disdiam is a cluster validation routine, and calculates the diameter (maximum within-cluster dissimilarity) of each cluster, as well as the average diameter of across all clusters of size greater than one.

Value

A list with components:

diameters	a data.frame with clusters as rows, and cluster ID, cluster size, and diameter as cols
mean	the weighted mean diameter of clusters of size greater than one. The mean is weighted for cluster size.

Author(s)

David W. Roberts [e-mail]

Examples

data(shoshveg)
dis.bc <- dsvdis(shoshveg,'bray')
opt.5 <- optpart(5,dis.bc)
disdiam(opt.5,dis.bc)

optpart documentation built on March 26, 2020, 6:18 p.m.