plotVar.kernel.pca.RdProvides a representation of variable importance in kernel PCA.
plotVar.kernel.pca(
object,
blocks = unique(object$cc.blocks),
ndisplay = 5,
ncol = 2,
...
): a kernel.pca object returned by kernel.pca.
a numerical vector indicating the block variables to display.
integer. The number of important variables per blocks shown in
the representation. Default: 5.
integer. Each block of variables is displayed in a separate
subfigure. ncol sets the number of columns for the global figure.
Default: 2.
external arguments.
plotVar.kernel.pca produces a barplot for each block. The variables for which the
importance has been computed with kernel.pca.permute are
displayed. The representation is limited to the ndisplay most important
variables.
Crone L. and Crosby D. (1995). Statistical applications of a metric on subspaces to satellite meteorology. Technometrics, 37(3), 324-328.
data(TARAoceans)
# compute one kernel for the psychem dataset
phychem.kernel <- compute.kernel(TARAoceans$phychem, kernel.func = "linear")
# perform a KPCA
kernel.pca.result <- kernel.pca(phychem.kernel)
# compute importance for all variables in this kernel
kernel.pca.result <- kernel.pca.permute(kernel.pca.result, phychem = colnames(TARAoceans$phychem))
if (FALSE) plotVar.kernel.pca(kernel.pca.result, ndisplay = 10)