linear_SLPE: Supervised Locality Pursuit Embedding

In Rdimtools: Dimension Reduction and Estimation Methods

Supervised Locality Pursuit Embedding

Description

Supervised Locality Pursuit Embedding (SLPE) is a supervised extension of LPE that uses class labels of data points in order to enhance discriminating power in its mapping into a low dimensional space.

Usage

do.slpe(
  X,
  label,
  ndim = 2,
  preprocess = c("center", "scale", "cscale", "decorrelate", "whiten")
)

Arguments

X	an (n\times p) matrix or data frame whose rows are observations and columns represent independent variables.
label	a length-n vector of data class labels.
ndim	an integer-valued target dimension.
preprocess	an additional option for preprocessing the data. Default is "center". See also aux.preprocess for more details.

Value

a named list containing

Y

an (n\times ndim) matrix whose rows are embedded observations.

trfinfo

a list containing information for out-of-sample prediction.

projection

a (p\times ndim) whose columns are basis for projection.

Author(s)

Kisung You

References

\insertRef

zheng_supervised_2006Rdimtools

See Also

do.lpe

Examples

## use iris data
data(iris)
set.seed(100)
subid = sample(1:150, 50)
X     = as.matrix(iris[subid,1:4])
label = as.factor(iris[subid,5])

## compare SLPE with SLPP
out1 <- do.slpp(X, label)
out2 <- do.slpe(X, label)

## visualize
opar <- par(no.readonly=TRUE)
par(mfrow=c(1,2))
plot(out1$Y, pch=19, col=label, main="SLPP")
plot(out2$Y, pch=19, col=label, main="SLPE")
par(opar)

Rdimtools documentation built on Dec. 28, 2022, 1:44 a.m.