A simple backwards selection, a.k.a. recursive feature selection (RFE), algorithm
Usage
rfe(x, ...)
## Default S3 method:
rfe(x, y,
sizes = 2^(2:4),
metric = ifelse(is.factor(y), "Accuracy", "RMSE"),
maximize = ifelse(metric == "RMSE", FALSE, TRUE),
rfeControl = rfeControl(),
...)
rfeIter(x, y,
testX, testY,
sizes,
rfeControl = rfeControl(),
label = "",
seeds = NA,
...)
## S3 method for class 'rfe'
update(object, x, y, size, ...)
## S3 method for class 'rfe'
predict(object, newdata, ...)
Arguments
x
a matrix or data frame of predictors for model training. This object must have unique column names.
y
a vector of training set outcomes (either numeric or factor)
testX
a matrix or data frame of test set predictors. This must have the same column names as x
testY
a vector of test set outcomes
sizes
a numeric vector of integers corresponding to the number of features that should be retained
metric
a string that specifies what summary metric will be used to select the optimal model. By default, possible values are "RMSE" and "Rsquared" for regression and "Accuracy" and "Kappa" for classification. If custom performance metrics are used (via the functions argument in rfeControl, the value of metric should match one of the arguments.
maximize
a logical: should the metric be maximized or minimized?
This function implements backwards selection of predictors based on predictor importance ranking. The predictors are ranked and the less important ones are sequentially eliminated prior to modeling. The goal is to find a subset of predictors that can be used to produce an accurate model. The web page http://topepo.github.io/caret/featureselection.html#rfe has more details and examples related to this function.
rfe can be used with "explicit parallelism", where different resamples (e.g. cross-validation group) can be split up and run on multiple machines or processors. By default, rfe will use a single processor on the host machine. As of version 4.99 of this package, the framework used for parallel processing uses the foreach package. To run the resamples in parallel, the code for rfe does not change; prior to the call to rfe, a parallel backend is registered with foreach (see the examples below).
rfeIter is the basic algorithm while rfe wraps these operations inside of resampling. To avoid selection bias, it is better to use the function rfe than rfeIter.
When updating a model, if the entire set of resamples were not saved using rfeControl(returnResamp = "final"), the existing resamples are removed with a warning.
Value
A list with elements
finalVariables
a list of size length(sizes) + 1 containing the column names of the “surviving” predictors
at each stage of selection. The first element corresponds to all the predictors (i.e. size = ncol(x))
pred
a data frame with columns for the test set outcome, the predicted outcome and the subset size.
Author(s)
Max Kuhn
See Also
rfeControl
Examples
## Not run:
data(BloodBrain)
x <- scale(bbbDescr[,-nearZeroVar(bbbDescr)])
x <- x[, -findCorrelation(cor(x), .8)]
x <- as.data.frame(x)
set.seed(1)
lmProfile <- rfe(x, logBBB,
sizes = c(2:25, 30, 35, 40, 45, 50, 55, 60, 65),
rfeControl = rfeControl(functions = lmFuncs,
number = 200))
set.seed(1)
lmProfile2 <- rfe(x, logBBB,
sizes = c(2:25, 30, 35, 40, 45, 50, 55, 60, 65),
rfeControl = rfeControl(functions = lmFuncs,
rerank = TRUE,
number = 200))
xyplot(lmProfile$results$RMSE + lmProfile2$results$RMSE ~
lmProfile$results$Variables,
type = c("g", "p", "l"),
auto.key = TRUE)
rfProfile <- rfe(x, logBBB,
sizes = c(2, 5, 10, 20),
rfeControl = rfeControl(functions = rfFuncs))
bagProfile <- rfe(x, logBBB,
sizes = c(2, 5, 10, 20),
rfeControl = rfeControl(functions = treebagFuncs))
set.seed(1)
svmProfile <- rfe(x, logBBB,
sizes = c(2, 5, 10, 20),
rfeControl = rfeControl(functions = caretFuncs,
number = 200),
## pass options to train()
method = "svmRadial")
## classification
data(mdrr)
mdrrDescr <- mdrrDescr[,-nearZeroVar(mdrrDescr)]
mdrrDescr <- mdrrDescr[, -findCorrelation(cor(mdrrDescr), .8)]
set.seed(1)
inTrain <- createDataPartition(mdrrClass, p = .75, list = FALSE)[,1]
train <- mdrrDescr[ inTrain, ]
test <- mdrrDescr[-inTrain, ]
trainClass <- mdrrClass[ inTrain]
testClass <- mdrrClass[-inTrain]
set.seed(2)
ldaProfile <- rfe(train, trainClass,
sizes = c(1:10, 15, 30),
rfeControl = rfeControl(functions = ldaFuncs, method = "cv"))
plot(ldaProfile, type = c("o", "g"))
postResample(predict(ldaProfile, test), testClass)
## End(Not run)
#######################################
## Parallel Processing Example via multicore
## Not run:
library(doMC)
## Note: if the underlying model also uses foreach, the
## number of cores specified above will double (along with
## the memory requirements)
registerDoMC(cores = 2)
set.seed(1)
lmProfile <- rfe(x, logBBB,
sizes = c(2:25, 30, 35, 40, 45, 50, 55, 60, 65),
rfeControl = rfeControl(functions = lmFuncs,
number = 200))
## End(Not run)