rfcv: Random Forest Cross-Valdidation for feature selection

Description

This function shows the cross-validated prediction performance of models with sequentially reduced number of predictors (ranked by variable importance) via a nested cross-validation procedure.

Usage

rfcv(trainx, trainy, cv.fold=5, scale="log", step=0.5,
     mtry=function(p) max(1, floor(sqrt(p))), recursive=FALSE, ...)

Arguments

trainx

matrix or data frame containing columns of predictor variables

trainy

vector of response, must have length equal to the number of rows in trainx

cv.fold

number of folds in the cross-validation

scale

if "log", reduce a fixed proportion (step) of variables at each step, otherwise reduce step variables at a time

step

if log=TRUE, the fraction of variables to remove at each step, else remove this many variables at a time

mtry

a function of number of remaining predictor variables to use as the mtry parameter in the randomForest call

recursive

whether variable importance is (re-)assessed at each step of variable reduction

...

other arguments passed on to randomForest

Value

A list with the following components:

list(n.var=n.var, error.cv=error.cv, predicted=cv.pred)

n.var

vector of number of variables used at each step

error.cv

corresponding vector of error rates or MSEs at each step

predicted

list of n.var components, each containing the predicted values from the cross-validation

References

Svetnik, V., Liaw, A., Tong, C. and Wang, T., ``Application of Breiman's Random Forest to Modeling Structure-Activity Relationships of Pharmaceutical Molecules'', MCS 2004, Roli, F. and Windeatt, T. (Eds.) pp. 334-343.

Examples

Run this code

# NOT RUN {
set.seed(647)
myiris <- cbind(iris[1:4], matrix(runif(96 * nrow(iris)), nrow(iris), 96))
result <- rfcv(myiris, iris$Species, cv.fold=3)
with(result, plot(n.var, error.cv, log="x", type="o", lwd=2))

## The following can take a while to run, so if you really want to try
## it, copy and paste the code into R.

# }
# NOT RUN {
result <- replicate(5, rfcv(myiris, iris$Species), simplify=FALSE)
error.cv <- sapply(result, "[[", "error.cv")
matplot(result[[1]]$n.var, cbind(rowMeans(error.cv), error.cv), type="l",
        lwd=c(2, rep(1, ncol(error.cv))), col=1, lty=1, log="x",
        xlab="Number of variables", ylab="CV Error")
# }