nselectboot: Selection of optimal number of clusters using bootstrap. This...

In nguforche/UnsupRF: Unsupervised Random Forest Clustering

Description

Selection of optimal number of clusters using bootstrap. This is a minor modification of the nselectboot function in the package fpc, so you can use package::nselectboot to run the perferred version if both packaes are loaded. See nselectboot for details.

Usage

nselectboot(data, B = 50, distances = inherits(data, "dist"),
  clustermethod = NULL, classification = "averagedist",
  krange = 2:10, count = FALSE, nnk = 1, ...)

Arguments

data	data or dissimilarity matrix
B	number of boostrap
distances	(logical) is data a dissimilarity matrix ?
clustermethod	clustering method, see nselectboot
classification	see nselectboot
krange	integer vector; numbers of clusters to be tried
count	logical. If TRUE, numbers of clusters and bootstrap runs are printed.
nnk	number of closest neighbors for classification
...	further arguments passed to or from other methods.

nguforche/UnsupRF documentation built on May 5, 2019, 4:51 p.m.