cv.pls: Cross Validation for Partial Least Squares Regression

In wind22zhu/enpls1.2: Ensemble Partial Least Squares Regression

Description

This function performs k-fold cross validation for partial least squares regression.

Usage

cv.pls(x, y, random = TRUE, nfolds = 5, maxcomp = NULL,
  use.scale = TRUE, verbose = TRUE, ...)

Arguments

x	predictor matrix
y	response vector
random	randomization of y
nfolds	number of folds - default is 5.
maxcomp	Maximum number of components included within the models, if not specified, default is the variable (column) numbers in x.
use.scale	scale
verbose	shall we print the cross validation process
...	other arguments that can be passed to enpls.en

Details

This function performs k-fold cross validation for partial least squares regression.

Value

A list containing four components:

• y - response vector

• ypred - predicted y

• residual - cross validation result (y.pred - y.real)

• RMSE - RMSE

• R2 - R2

Author(s)

Min-feng Zhu <[e-mail]>, Nan Xiao <[e-mail]>

See Also

See cv.enpls for Cross Validation for ensemble PLS regression.

Examples

data(alkanes)
x = alkanes$x
y = alkanes$y

set.seed(42)
cv.enpls.fit = cv.enpls(x, y, MCtimes = 10)
print(cv.enpls.fit)
plot(cv.enpls.fit)

wind22zhu/enpls1.2 documentation built on May 4, 2019, 6:31 a.m.