otclust: Mean partition by optimal transport alignment.

In OTclust: Mean Partition, Uncertainty Assessment, Cluster Validation and Visualization Selection for Cluster Analysis

Mean partition by optimal transport alignment.

Description

This function calculates the mean partition of an ensemble of partitions by optimal transport alignment and uncertainty/stability measures.

Usage

otclust(ensemble, idx = NULL)

Arguments

ensemble	– a matrix of ensemble partition. Use ensemble() to generate an ensemble of perturbed partitions.
idx	– an integer indicating the index of reference partition in ensemble. If not specified, median partition is used as the reference partition.

Value

a list of alignment result.

idx	the index of reference partition.
avedist	average distances between each partition and all ensemble partitions.
meanpart	a list of mean partition.
distance	Wasserstein distances between mean partition and the others.
numcls	the number of clusters for each partition.
statistics	average tightness ratio, average coverage ratio, 1-average jaccard distance.
cap	cluster alignment and points based (CAP) separability.
id	switched labels.
cps	covering point set.
match	topological relationship statistics between the reference partition and the others.
Weight	weight matrix.

Examples

data(sim1)
# the number of clusters.
C = 4
ens.data = ensemble(sim1$X[1:100,], nbs=10, clust_param=C, clustering="kmeans", perturb_method=1)
# find mean partition and uncertainty statistics.
ota = otclust(ens.data)

OTclust documentation built on Oct. 6, 2023, 5:09 p.m.