PMO.hclustering: Multiple Hierarchical clusterings using Plus Minus One (PMO)...

In clusterv: Assessment of Cluster Stability by Randomized Maps

Multiple Hierarchical clusterings using Plus Minus One (PMO) random projections

Description

Multiple Hierarchical clusterings using Plus Minus One (PMO) random projections of the data.

Usage

PMO.hclustering(M, dim, c = 3, hmethod = "average", n = 50, 
                scale = TRUE, seed = 100, distance="euclidean")

PMO.hclustering.tree(M, dim, hmethod = "average", n = 50, 
                     scale = TRUE, seed = 100, distance = "euclidean")

Arguments

M	matrix of data: rows are variables and columns are examples
dim	subspace dimension
c	number of clusters
hmethod	the agglomeration method to be used. This should be one of "ward.D", "single", "complete", "average", "mcquitty", "median" or "centroid", according to the hclust method of the package stats.
n	number of random projections
scale	if TRUE (default) Achlioptas random projections are scaled
seed	numerical seed for the random generator
distance	it must be one of the two: "euclidean" (default) or "pearson" (that is 1 - Pearson correlation)

Value

a list with components "cluster" and "tree":

cluster	list of the n clusterings obtained. Each element is in turn a list of vectors that correspond to the clusters of the clustering. Each cluster is represented by a vector of integers whose values corresponds to the indices of the columns (examples) of the original data.
tree	list of the trees generated by the multiple clusterings

PMO.hclustering.tree returns only the list of the trees.

Author(s)

Giorgio Valentini [e-mail]

See Also

Plus.Minus.One.random.projection

Examples

# 20 hierarchical clusterings on multiple PMO projected data 
# with subspace dimension equal to 100
M <- generate.sample0(n=10, m=2, sigma=1, dim=800)
l <- PMO.hclustering(M, dim=100, hmethod = "average", n = 20, scale = TRUE)
# Equal as above, but only the trees are generated
l <- PMO.hclustering.tree(M, dim=100, hmethod = "average", n = 20, scale = TRUE)
# 10 hierarchical clusterings on multiple PMO projected data 
# with subspace dimension equal to 200
M <- generate.sample0(n=8, m=1, sigma=2, dim=1000)
l <- PMO.hclustering(M, dim=200, hmethod = "average", n = 10, scale = TRUE)

clusterv documentation built on June 8, 2025, 10:21 a.m.