Rclusterpp.hclust: Hierarchical Clustering

In nolanlab/Rclusterpp: Linkable C++ Clustering

Hierarchical Clustering

Description

Hierarchical clustering on both disimilarities and data

Usage

Rclusterpp.hclust(x, method = "ward", members = NULL, distance = "euclidean", p = 2)

Arguments

x	A numeric data matrix, data frame or a dissimilarity structure as produced by dist.
method	The agglomeration method to be used. This must be one of "ward", "single", "complete" or "average".
members	NULL or a vector with length size of x. See hclust.
distance	The distance measure to be used. This must be one of "euclidiean", "manhattan", "maximum", or "minkowski".
p	The power of the Minkowski distance.

Details

If x is a disimilarity matrix, execution defaults to standard hclust. If x is a set of observations, specialized native clustering routines are invoked. These routines are optimized for O(n) memory footprint and multicore execution to permit clustering of large datasets.

Value

An object of class *hclust* which describes the tree produced by the clustering process. See hclust.

Note

Support for different agglomeration methods and distance metrics is evolving.

Author(s)

Michael Linderman

References

Murtagh, F. (1983), "A survey of recent advances in hierarchical clustering algorithms", Computer Journal, 26, 354-359. Sibson, R. (1973), "SLINK: An optimally efficient algorithm for the single-link cluster method", Computer Journal, 16, 30-34.

See Also

hclust

Examples

h <- Rclusterpp.hclust(USArrests, method="ward", distance="euclidean")

nolanlab/Rclusterpp documentation built on Aug. 24, 2022, 5:41 p.m.