fdm2id (version 0.9.5)

FEATURESELECTION: Classification with Feature selection

Description

Apply a classification method after a subset of features has been selected.

Usage

FEATURESELECTION(
  train,
  labels,
  algorithm = c("ranking", "forward", "backward", "exhaustive"),
  unieval = if (algorithm[1] == "ranking") c("fisher", "fstat", "relief",
    "inertiaratio") else NULL,
  uninb = NULL,
  unithreshold = NULL,
  multieval = if (algorithm[1] == "ranking") NULL else c("cfs", "fstat",
    "inertiaratio", "wrapper"),
  wrapmethod = NULL,
  mainmethod = wrapmethod,
  tune = FALSE,
  ...
)

Arguments

train

The training set (description), as a data.frame.

labels

Class labels of the training set (vector or factor).

algorithm

The feature selection algorithm.

unieval

The (univariate) evaluation criterion. uninb, unithreshold or multieval must be specified.

uninb

The number of selected feature (univariate evaluation).

unithreshold

The threshold for selecting feature (univariate evaluation).

multieval

The (multivariate) evaluation criterion.

wrapmethod

The classification method used for the wrapper evaluation.

mainmethod

The final method used for data classification. If a wrapper evaluation is used, the same classification method should be used.

tune

If true, the function returns paramters instead of a classification model.

...

Other parameters.

See Also

selectfeatures, predict.selection, selection-class

Examples

# NOT RUN {
require (datasets)
data (iris)
FEATURESELECTION (iris [, -5], iris [, 5], uninb = 2, mainmethod = LDA)
# }