CritCF.sel

dataframe for which the number of cluster should be estimated.

data

integer strictly higher than 1: minimum number of clusters.

min.nc

integer (<code>&gt;min.nc</code>): maximum number of clusters.

max.nc

string, clustering algorithm to use. Available values are
"<code>kmeans</code>", "<code>hc</code>" (for <code>hclust()</code>) or "<code>mclust</code>".

method

string, distance between the observations (either "euclidean"
or "manhattan").

distance

Wrapper to estimate the best number of clusters according to <code>CritCF</code>
index

internal

Algorithms for (i) unsupervised learning for dataset with
missing data and/or left-censored data, using multiple imputation and
consensus clustering ; (ii) semi-supervised learning with a survival
endpoint (right-censored) for complete or incomplete datasets, using
multiple imputation and consensus clustering in the latter case. The
methods are described in Faucheux et al. (2021)
<doi:10.1002/bimj.201900366> and Faucheux et al. (2021)
<doi:10.1002/bimj.202000365>, respectively.

CritCF.sel: Number of cluster selection according to `CritCF` index

Description

Usage

Arguments

Value