feature_PFA: Principal Feature Analysis

In kisungyou/Rdimtools: Dimension Reduction and Estimation Methods

Principal Feature Analysis

Description

Principal Feature Analysis \insertCitelu_2007_FeatureSelectionUsingRdimtools adopts an idea from the celebrated PCA for unsupervised feature selection.

Usage

do.pfa(X, ndim = 2, ...)

Arguments

X	an (n\times p) matrix or data frame whose rows are observations and columns represent independent variables.
ndim	an integer-valued target dimension (default: 2).
...	extra parameters including cor mode of eigendecomposition. FALSE for decomposing the empirical covariance matrix and TRUE uses the correlation matrix (default: FALSE). preprocess an additional option for preprocessing the data. See also aux.preprocess for more details (default: "center").

References

\insertAllCited

Examples

## 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])

## compare with other methods
out1 = do.pfa(iris.dat)
out2 = do.lscore(iris.dat)
out3 = do.fscore(iris.dat, iris.lab)

## visualize
opar <- par(no.readonly=TRUE)
par(mfrow=c(1,3))
plot(out1$Y, pch=19, col=iris.lab, main="Principal Feature Analysis")
plot(out2$Y, pch=19, col=iris.lab, main="Laplacian Score")
plot(out3$Y, pch=19, col=iris.lab, main="Fisher Score")
par(opar)

kisungyou/Rdimtools documentation built on Jan. 2, 2023, 9:55 a.m.