Become an expert in R — Interactive courses, Cheat Sheets, certificates and more!
Get Started for Free

removeConstantFeatures

Remove constant features from a data set.


Description

Constant features can lead to errors in some models and obviously provide no information in the training set that can be learned from. With the argument “perc”, there is a possibility to also remove features for which less than “perc” percent of the observations differ from the mode value.

Usage

removeConstantFeatures(
  obj,
  perc = 0,
  dont.rm = character(0L),
  na.ignore = FALSE,
  wrap.tol = .Machine$double.eps^0.5,
  show.info = getMlrOption("show.info"),
  ...
)

Arguments

obj

(data.frame | Task)
Input data.

perc

(numeric(1))
The percentage of a feature values in [0, 1) that must differ from the mode value. Default is 0, which means only constant features with exactly one observed level are removed.

dont.rm

(character)
Names of the columns which must not be deleted. Default is no columns.

na.ignore

(logical(1))
Should NAs be ignored in the percentage calculation? (Or should they be treated as a single, extra level in the percentage calculation?) Note that if the feature has only missing values, it is always removed. Default is FALSE.

wrap.tol

(numeric(1))
Numerical tolerance to treat two numbers as equal. Variables stored as double will get rounded accordingly before computing the mode. Default is sqrt(.Maschine$double.eps).

show.info

(logical(1))
Print verbose output on console? Default is set via configureMlr.

...

To ensure backward compatibility with old argument tol

Value

data.frame | Task. Same type as obj.

See Also


mlr

Machine Learning in R

v2.19.0
BSD_2_clause + file LICENSE
Authors
Bernd Bischl [aut] (<https://orcid.org/0000-0001-6002-6980>), Michel Lang [aut] (<https://orcid.org/0000-0001-9754-0393>), Lars Kotthoff [aut], Patrick Schratz [aut, cre] (<https://orcid.org/0000-0003-0748-6624>), Julia Schiffner [aut], Jakob Richter [aut], Zachary Jones [aut], Giuseppe Casalicchio [aut] (<https://orcid.org/0000-0001-5324-5966>), Mason Gallo [aut], Jakob Bossek [ctb] (<https://orcid.org/0000-0002-4121-4668>), Erich Studerus [ctb] (<https://orcid.org/0000-0003-4233-0182>), Leonard Judt [ctb], Tobias Kuehn [ctb], Pascal Kerschke [ctb] (<https://orcid.org/0000-0003-2862-1418>), Florian Fendt [ctb], Philipp Probst [ctb] (<https://orcid.org/0000-0001-8402-6790>), Xudong Sun [ctb] (<https://orcid.org/0000-0003-3269-2307>), Janek Thomas [ctb] (<https://orcid.org/0000-0003-4511-6245>), Bruno Vieira [ctb], Laura Beggel [ctb] (<https://orcid.org/0000-0002-8872-8535>), Quay Au [ctb] (<https://orcid.org/0000-0002-5252-8902>), Martin Binder [ctb], Florian Pfisterer [ctb], Stefan Coors [ctb], Steve Bronder [ctb], Alexander Engelhardt [ctb], Christoph Molnar [ctb], Annette Spooner [ctb]
Initial release

We don't support your browser anymore

Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.