sominit.pca: Initialise the prototypes of a SOM with PCA

In yasomi: Yet Another Self Organising Map Implementation

Description

Initialise the prototypes of a Self-Organising Map with Principal Component Analysis or a related method (e.g., classical multidimensional scaling for a dissimilarity matrix).

Usage

sominit.pca(data, somgrid, ...)

Arguments

data	the data to which the SOM will be fitted. This can be, e.g., a matrix or data frame of observations (which should be scaled), or a distance matrix
somgrid	a somgrid object
...	additional parameters to be passed to methods

Value

A list with at least a component prototypes containing initial prototypes. Different implementations of the function provide other components, in particular the results of the PCA or the related method used to compute the prototypes.

Author(s)

Fabrice Rossi

See Also

sominit.pca.default and sominit.pca.dist for implementations, and sominit.random for an alternative.

yasomi documentation built on May 2, 2019, 5:59 p.m.