mlcc.reps: Subspace clustering assuming that the number of clusters is...

Description Usage Arguments Details Value Examples

View source: R/mlcc.reps.R

Description

For a fixed number of cluster and fixed number of components per cluster function returns the best partition and basis for each subspace.

Usage

1
2
3
mlcc.reps(X, numb.clusters = 2, numb.runs = 20, stop.criterion = 1,
  max.iter = 20, initial.segmentations = NULL, max.dim = 4,
  scale = TRUE, numb.cores = NULL, estimate.dimensions = TRUE)

Arguments

X

a data frame or a matrix with only continuous variables

numb.clusters

an integer, number of cluster

numb.runs

an integer, number of runs of mlcc.kmeans algorithm with random initialization

stop.criterion

an integer, if an iteration of mlcc.kmeans algorithm makes less changes in partitions than stop.criterion, mlcc.kmeans stops.

max.iter

an integer, maximum number of iterations of mlcc.kmeans algorithm

initial.segmentations

a list of vectors, segmentations that user wants to be used as an initial segmentation in mlcc.kmeans algorithm

max.dim

an integer, dimension of subspaces (all are assumed to be equal)

scale

a boolean, if TRUE (value set by default) then variables in dataset are scaled to zero mean and unit variance

numb.cores

an integer, number of cores to be used, by default all cores are used

estimate.dimensions

a boolean, if TRUE (value set by default) subspaces dimensions are estimated

Details

In more detail, an algorithm mlcc.kmeans is run a numb.runs of times with random initializations. The best partition is selected according to the BIC.

Value

A list consisting of

segmentation

a vector containing the partition of the variables

BIC

a numeric, value of cluster.BIC criterion

basis

a list of matrices, the basis vectors for subspaces

Examples

1
2
sim.data <- data.simulation(n = 100, SNR = 1, K = 5, numb.vars = 30, max.dim = 2)
mlcc.reps(sim.data$X, numb.clusters = 5, numb.runs = 20, max.dim = 4)

psobczyk/public_varclust documentation built on May 24, 2017, 12:20 p.m.