Boruta: Wrapper Algorithm for All Relevant Feature Selection

Share:

An all relevant feature selection wrapper algorithm. It finds relevant features by comparing original attributes' importance with importance achievable at random, estimated using their permuted copies.

Author
Miron B. Kursa [aut, cre], Witold R. Rudnicki [aut]
Date of publication
2016-08-16 19:46:03
Maintainer
Miron B. Kursa <M.Kursa@icm.edu.pl>
License
GPL (>= 2)
Version
5.1.0
URLs

View on CRAN

Man pages

attStats
Extract attribute statistics
Boruta
Feature selection with the Boruta algorithm
getImpFerns
Random Ferns importance
getImpLegacyRf
randomForest importance adapters
getImpRf
ranger Random Forest importance adapters
getSelectedAttributes
Extract names of the selected attributes
plot.Boruta
Plot Boruta object
plotImpHistory
Plot Boruta object as importance history
print.Boruta
Print Boruta object
TentativeRoughFix
Rough fix of Tentative attributes

Files in this package

Boruta
Boruta/inst
Boruta/inst/CITATION
Boruta/inst/NEWS
Boruta/NAMESPACE
Boruta/R
Boruta/R/Boruta.R
Boruta/R/tools.R
Boruta/R/importance.R
Boruta/MD5
Boruta/DESCRIPTION
Boruta/man
Boruta/man/getSelectedAttributes.Rd
Boruta/man/plot.Boruta.Rd
Boruta/man/TentativeRoughFix.Rd
Boruta/man/attStats.Rd
Boruta/man/plotImpHistory.Rd
Boruta/man/Boruta.Rd
Boruta/man/getImpLegacyRf.Rd
Boruta/man/getImpRf.Rd
Boruta/man/getImpFerns.Rd
Boruta/man/print.Boruta.Rd