map_ecm: map_ecm: Constructs an Exposure Continuum Map using Kohonen's...

In johnlpearce/ECM: ECM: Exposure Continuum Mapping

Description

This function applies Kohonen's Self-Organizing Map algorithm in order to construct a low-dimensional mapping of the data.

Usage

map_ecm(
  trn_dat,
  xdim = 5,
  ydim = 4,
  maptopo = NULL,
  itermax = NULL,
  inits = NULL,
  distmet = NULL,
  lmode = NULL
)

Arguments

trn_dat	is a data object to map. Should be a numerical or factor based data matrix.
xdim	is x-dimension of the SOM
ydim	is y-dimension of the SOM
maptopo	specifies the topology of the SOM grid as either "rectangular" or "hexagonal"
itermax	specifies the number if learning iterations
inits	specifies if optimal initialization values are to be used.
distmet	specifies dissimilarity metric. Current options include "sumofsquares", "euclidean", "manhattan", and "tanimoto". Default is to use "Euclidean" for continuous data, and "tanimoto" for factors.
lmode	specifies the learning algorithm. The default is "online" but "batch" and "pbatch" are available via kohonen

Value

a 'kohonen' object

References

Kohonen, T. (1995) Self-Organizing Maps. Springer-Verlag

johnlpearce/ECM documentation built on Dec. 21, 2021, 2:13 a.m.