Rdimtools (version 1.0.6)

do.specs: Supervised Spectral Feature Selection

Description

SPEC algorithm selects features from the data via spectral graph approach. Three types of ranking methods that appeared in the paper are available where the graph laplacian is built via class label information.

Usage

do.specs(
  X,
  label,
  ndim = 2,
  ranking = c("method1", "method2", "method3"),
  preprocess = c("null", "center", "scale", "cscale", "whiten", "decorrelate")
)

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 class labels.

ndim

an integer-valued target dimension.

ranking

types of feature scoring method. See the paper in the reference for more details.

preprocess

an additional option for preprocessing the data. Default is "null". See also aux.preprocess for more details.

Value

a named list containing

Y

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

sscore

a length-\(p\) vector of spectral feature scores.

featidx

a length-\(ndim\) vector of indices with highest scores.

trfinfo

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

projection

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

References

zhao_spectral_2007Rdimtools

See Also

do.specu

Examples

# NOT RUN {
## use iris data
## it is known that feature 3 and 4 are more important.
data(iris)
set.seed(100)
subid = sample(1:150, 50)
iris.dat = as.matrix(iris[subid,1:4])
iris.lab = as.factor(iris[subid,5])

## try different ranking methods
out1 = do.specs(iris.dat, iris.lab, ranking="method1")
out2 = do.specs(iris.dat, iris.lab, ranking="method2")
out3 = do.specs(iris.dat, iris.lab, ranking="method3")

## visualize
opar <- par(no.readonly=TRUE)
par(mfrow=c(1,3))
plot(out1$Y, pch=19, col=iris.lab, main="SPECS::method1")
plot(out2$Y, pch=19, col=iris.lab, main="SPECS::method2")
plot(out3$Y, pch=19, col=iris.lab, main="SPECS::method3")
par(opar)
# }
# NOT RUN {
# }