tune.func: Functions for Tuning Appropriate Number of Components

Description

Tune appropriate number of components (ncomp) for plsc, plslda or pcalda.

Usage

tune.plsc(x,y, pls="simpls",ncomp=10, tune.pars,...)
tune.plslda(x,y, pls="simpls",ncomp=10, tune.pars,...)
tune.pcalda(x,y, ncomp=NULL, tune.pars,...)

Value

A list including:

ncomp: The best number of components.
acc.tune: Accuracy rate of components.

Arguments

x

A matrix or data frame containing the explanatory variables if no formula is given as the principal argument.

y

A factor specifying the class for each observation if no formula principal argument is given.

pls

A method for calculating PLS scores and loadings. The following methods are supported:

simpls: SIMPLS algorithm.
kernelpls: kernel algorithm.
oscorespls: orthogonal scores algorithm.

For details, see simpls.fit, kernelpls.fit and oscorespls.fit in package pls.

ncomp

The number of components to be used in the classification.

tune.pars

A list of parameters using by the resampling method. See valipars for details.

...

Further parameters passed to tune.

Author

Wanchang Lin

Examples

Run this code

if (FALSE) {
data(abr1)
cl   <- factor(abr1$fact$class)
dat  <- preproc(abr1$pos , y=cl, method=c("log10"),add=1)[,110:500]

## divide data as training and test data
idx <- sample(1:nrow(dat), round((2/3)*nrow(dat)), replace=FALSE) 

## construct train and test data 
train.dat  <- dat[idx,]
train.t    <- cl[idx]
test.dat   <- dat[-idx,]        
test.t     <- cl[-idx] 

## tune the best number of components
ncomp.plsc   <- tune.plsc(dat,cl, pls="simpls",ncomp=20)
ncomp.plslda <- tune.plslda(dat,cl, pls="simpls",ncomp=20)
ncomp.pcalda <- tune.pcalda(dat,cl, ncomp=60)

## model fit
(z.plsc   <- plsc(train.dat,train.t, ncomp=ncomp.plsc$ncomp))
(z.plslda <- plslda(train.dat,train.t, ncomp=ncomp.plslda$ncomp))
(z.pcalda <- pcalda(train.dat,train.t, ncomp=ncomp.pcalda$ncomp))

## or indirect use tune function in model fit
z.plsc   <- plsc(train.dat,train.t, ncomp=20, tune=TRUE)
z.plslda <- plslda(train.dat,train.t, ncomp=20, tune=TRUE)
z.pcalda <- pcalda(train.dat,train.t, ncomp=60, tune=TRUE)

## predict test data
pred.plsc   <- predict(z.plsc, test.dat)$class
pred.plslda <- predict(z.plslda, test.dat)$class
pred.pcalda <- predict(z.pcalda, test.dat)$class

## classification rate and confusion matrix
cl.rate(test.t, pred.plsc)
cl.rate(test.t, pred.plslda)
cl.rate(test.t, pred.pcalda)

}