# plot.kohonen

0th

Percentile

##### Plot kohonen object

Plot objects of class kohonen. Several types of plots are supported.

Keywords
classif
##### Usage
# S3 method for kohonen
plot(x, type = c("codes", "changes", "counts",
"dist.neighbours", "mapping", "property", "quality"),
whatmap = NULL, classif = NULL, labels = NULL,
pchs = NULL, main = NULL, palette.name = NULL,
ncolors, bgcol = NULL, zlim = NULL,
heatkey = TRUE, property, codeRendering = NULL,
keepMargins = FALSE, heatkeywidth = .2,
shape = c("round", "straight"), border = "black",
…)
# S3 method for kohonen
identify(x, …)
add.cluster.boundaries(x, clustering, lwd = 5, ...)
##### Arguments
x

kohonen object.

type

type of plot. (Wow!)

whatmap

For a "codes" plot: what maps to show; for the "dist.neighbours" plot: what maps to take into account when calculating distances to neighbouring units.

classif

classification object, as returned by predict.kohonen, or vector of unit numbers. Only needed if type equals "mapping" and "counts".

labels

labels to plot when type equals "mapping".

pchs

symbols to plot when type equals "mapping".

main

title of the plot.

palette.name

colors to use as unit background for "codes", "counts", "prediction", "property", and "quality" plotting types.

ncolors

number of colors to use for the unit backgrounds. Default is 20 for continuous data, and the number of distinct values (if less than 20) for categorical data.

bgcol

optional argument to colour the unit backgrounds for the "mapping" and "codes" plotting type. Defaults to "gray" and "transparent" in both types, respectively.

zlim

optional range for color coding of unit backgrounds.

heatkey

whether or not to generate a heatkey at the left side of the plot in the "property" and "counts" plotting types.

property

values to use with the "property" plotting type.

codeRendering

How to show the codes. Possible choices: "segments", "stars" and "lines".

keepMargins

if FALSE (the default), restore the original graphical parameters after plotting the kohonen map. If TRUE, one retains the map coordinate system so that one can add symbols to the plot, or map unit numbers using the identify function.

heatkeywidth

width of the colour key; the default of 0.2 should work in most cases but in some cases, e.g. when plotting multiple figures, it may need to be adjusted.

shape

kind shape to be drawn: "round" (circle) or "straight". Choosing "straight" produces a map of squares when the grid is "rectangular", and produces a map of hexagons when the grid is "hexagonal".

border

color of the shape's border.

lwd, …

other graphical parameters.

clustering

cluster labels of the map units.

##### Details

Several different types of plots are supported:

"changes"

shows the mean distance to the closest codebook vector during training.

"codes"

shows the codebook vectors.

"counts"

shows the number of objects mapped to the individual units. Empty units are depicted in gray.

"dist.neighbours"

shows the sum of the distances to all immediate neighbours. This kind of visualisation is also known as a U-matrix plot. Units near a class boundary can be expected to have higher average distances to their neighbours. Only available for the "som" and "supersom" maps, for the moment.

"mapping"

shows where objects are mapped. It needs the "classif" argument, and a "labels" or "pchs" argument.

"property"

properties of each unit can be calculated and shown in colour code. It can be used to visualise the similarity of one particular object to all units in the map, to show the mean similarity of all units and the objects mapped to them, etcetera. The parameter property contains the numerical values. See examples below.

"quality"

shows the mean distance of objects mapped to a unit to the codebook vector of that unit. The smaller the distances, the better the objects are represented by the codebook vectors.

Function identify.kohonen shows the number of a unit that is clicked on with the mouse. The tolerance is calculated from the ratio of the plotting region and the user coordinates, so clicking at any place within a unit should work.

Function add.cluster.boundaries will add to an existing plot of a map thick lines, visualizing which units would be clustered together. In toroidal maps, boundaries at the edges will only be shown on the top and right sides to avoid double boundaries.

##### Value

Several types of plots return useful values (invisibly): the "counts", "dist.neighbours", and "quality" return vectors corresponding to the information visualized in the plot (unit background colours and heatkey).

som, supersom, xyf, predict.kohonen

##### Aliases
• plot.kohonen
• identify.kohonen
##### Examples
# NOT RUN {
data(wines)
set.seed(7)

kohmap <- xyf(scale(wines), vintages,
grid = somgrid(5, 5, "hexagonal"), rlen=100)
plot(kohmap, type="changes")
counts <- plot(kohmap, type="counts", shape = "straight")

## show both sets of codebook vectors in the map
par(mfrow = c(1,2))
plot(kohmap, type="codes", main = c("Codes X", "Codes Y"))

par(mfrow = c(1,1))
similarities <- plot(kohmap, type="quality", palette.name = terrain.colors)
plot(kohmap, type="mapping",
labels = as.integer(vintages), col = as.integer(vintages),
main = "mapping plot")

## add background colors to units according to their predicted class labels
xyfpredictions <- classmat2classvec(getCodes(kohmap, 2))
bgcols <- c("gray", "pink", "lightgreen")
plot(kohmap, type="mapping", col = as.integer(vintages),
pchs = as.integer(vintages), bgcol = bgcols[as.integer(xyfpredictions)],
main = "another mapping plot", shape = "straight", border = NA)

## Show 'component planes'
set.seed(7)
sommap <- som(scale(wines), grid = somgrid(6, 4, "hexagonal"))
plot(sommap, type = "property", property = getCodes(sommap, 1)[,1],
main = colnames(getCodes(sommap, 1))[1])

## Show the U matrix
Umat <- plot(sommap, type="dist.neighbours", main = "SOM neighbour distances")
## use hierarchical clustering to cluster the codebook vectors
som.hc <- cutree(hclust(object.distances(sommap, "codes")), 5)

## and the same for rectangular maps
set.seed(7)
sommap <- som(scale(wines),grid = somgrid(6, 4, "rectangular"))
plot(sommap, type="dist.neighbours", main = "SOM neighbour distances")
## use hierarchical clustering to cluster the codebook vectors
som.hc <- cutree(hclust(object.distances(sommap, "codes")), 5)