kohonen (version 1.1.1)

predict.kohonen: Classify using a trained Kohonen map

Description

Map objects to a trained Kohonen map. The map may be obtained by supervised methods (xyf, bdk), but only the X-space is considered in prediction. If the classification is already known, the function returns the similarity for each object to the unit it is mapped to.

Usage

predict.kohonen(object, newdata, trainX, trainY, unit.predictions,
                 threshold = 0, ...)

Arguments

object

Trained network.

newdata

Data matrix for which predictions are to be made. If not given, defaults to the training data (when available).

trainX

Training data for obtaining predictions for unsupervised maps; necessary for som maps trained with the keep.data = FALSE option.

trainY

Values for the dependent variable for the training data; only necessary for som maps.

unit.predictions

Possible override of the predictions for each unit.

threshold

Used in class predictions; see classmat2classvec.

...

Currently not used.

Value

• Returns a list with components
• unit.classif
  unit numbers to which objects in the data matrix are mapped.
• classif
  classes associated with the units (only for the supervised bdk and xyf networks).
• distances
  similarities, expressed as distances, of objects to codebook vectors.

See Also

som,xyf,bdk, map

Examples

### Simulated example
library(MASS)

csize <- 15
c1 <- mvrnorm(csize, mu=c(5,3,4),
              Sigma=matrix(c(2, 0,0,0, 2, 1, 0, 1, 2),3,3))
c2 <- mvrnorm(csize, mu=c(5.5, 3.5, 4.5),
              Sigma=matrix(c(2, 0,0,0, 2, 1, 0, 1, 2),3,3))
c3 <- mvrnorm(csize, mu=c(0,0,0),
              Sigma=matrix(c(2, 0,0,0, 2, 1, 0, 1, 2),3,3))

X <- rbind(c1, c2, c3)
classes <- c(rep(1, csize), rep(2, csize), rep(3, csize))

bdkmod <- bdk(X, classvec2classmat(classes), somgrid(4, 4, "hexagonal"))

predict(bdkmod)