KmeansPP: Perform the k-means++ clustering algorithm on a data matrix.

In clusternor: A Parallel Clustering Non-Uniform Memory Access ('NUMA') Optimized Package

Description

A parallel and scalable implementation of the algorithm described in Ostrovsky, Rafail, et al. "The effectiveness of Lloyd-type methods for the k-means problem." Journal of the ACM (JACM) 59.6 (2012): 28.

Usage

KmeansPP(
  data,
  centers,
  nrow = -1,
  ncol = -1,
  nstart = 1,
  nthread = -1,
  dist.type = c("sqeucl", "eucl", "cos", "taxi")
)

Arguments

data	Data file name on disk (NUMA optimized) or In memory data matrix
centers	The number of centers (i.e., k)
nrow	The number of samples in the dataset
ncol	The number of features in the dataset
nstart	The number of iterations of kmeans++ to run
nthread	The number of parallel threads to run
dist.type	What dissimilarity metric to use c("taxi", "eucl", "cos")

Value

A list containing the attributes of the output. cluster: A vector of integers (from 1:k) indicating the cluster to which each point is allocated. centers: A matrix of cluster centres. size: The number of points in each cluster. energy: The sum of distances for each sample from it's closest cluster. best.start: The sum of distances for each sample from it's closest cluster.

Author(s)

Disa Mhembere <[e-mail]>

Examples

iris.mat <- as.matrix(iris[,1:4])
k <- length(unique(iris[, dim(iris)[2]])) # Number of unique classes
nstart <- 3
km <- KmeansPP(iris.mat, k, nstart=nstart)

clusternor documentation built on March 26, 2020, 7:31 p.m.