kmeansppn: Run the k-means++ algorithm n times and return the solution...

In bwrc/corecluster-r: Core clustering of datasets.

Description

Run the k-means++ algorithm n times and return the solution with the smallest loss.

Usage

kmeansppn(x, k, n = 10, iter.max = 1000, algorithm = "Lloyd")

Arguments

x	Data matrix with rows corresponding to data items.
k	Number of clusters.
n	Number of repeats to run. Optional. Default is 10.
algorithm	Clustering algorithm to use. Optional. Default is Lloyd. See documentation for kmeans for details.
iter	The maximum number of iterations. Optional. Default is 1000.

Value

See documentation for kmeans for details.

References

Arthur & Vassilivitskii (2007) k-means++: the advantages of careful seeding. In Proc SODA '07, 1027-1035.

bwrc/corecluster-r documentation built on May 13, 2019, 9:12 a.m.