distimage: Distance image

In rdetools: Relevant Dimension Estimation (RDE) in Feature Spaces

Description

If you've done a model selection with selectmodel, this function can draw you a map, in which the distances of the original label vector and the estimated label vectors are shown. This is done by a filled.contour plot.

Usage

distimage(model,
          color.palette = terrain.colors,
	  log = TRUE,
	  plottitle = "Distance of Ys",
	  ...)

Arguments

model	list of model selection data as it has been returned by selectmodel. selectmodel must have been called with ydist parameter set to TRUE!
color.palette	color palette function to use, see rainbow
log	leave this TRUE, if the axis of the model parameter should be logarithmically scaled. Set this to FALSE if you want linear scaling.
plottitle	title of the plot
...	additional parameters for filled.contour

Author(s)

Jan Saputra Mueller

References

M. L. Braun, J. M. Buhmann, K. R. Mueller (2008) \_On Relevant Dimensions in Kernel Feature Spaces\_

See Also

selectmodel, modelimage, drawkpc, filled.contour, rainbow

Examples

## model selection with RBF-kernel and graphical illustration
## of the distances of the labels
d <- sincdata(100, 0.1) # generate sinc data
# do model selection
m <- selectmodel(d$X, d$y, ydist = TRUE, sigma = logspace(-3, 3, 100))
distimage(m) # distance image

rdetools documentation built on May 2, 2019, 7:02 a.m.