The hardware and bandwidth for this mirror is donated by METANET, the Webhosting and Full Service-Cloud Provider.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]metanet.ch.

permimp: Conditional Permutation Importance

An add-on to the 'party' package, with a faster implementation of the partial-conditional permutation importance for random forests. The standard permutation importance is implemented exactly the same as in the 'party' package. The conditional permutation importance can be computed faster, with an option to be backward compatible to the 'party' implementation. The package is compatible with random forests fit using the 'party' and the 'randomForest' package. The methods are described in Strobl et al. (2007) <doi:10.1186/1471-2105-8-25> and Debeer and Strobl (2020) <doi:10.1186/s12859-020-03622-2>.

Version: 1.0-2
Depends: R (≥ 3.6.0)
Imports: graphics, grDevices, ipred (≥ 0.9-6), methods, party (≥ 1.3-3), randomForest (≥ 4.6-14), stats, survival (≥ 2.44-1.1), utils
Suggests: knitr, rmarkdown, scales (≥ 0.5.0), testthat
Published: 2021-09-13
DOI: 10.32614/CRAN.package.permimp
Author: Dries Debeer [aut, cre], Torsten Hothorn [aut], Carolin Strobl [aut]
Maintainer: Dries Debeer <debeer.dries at gmail.com>
License: GPL-2 | GPL-3
NeedsCompilation: no
Materials: NEWS
CRAN checks: permimp results

Documentation:

Reference manual: permimp.pdf
Vignettes: The permimp-package

Downloads:

Package source: permimp_1.0-2.tar.gz
Windows binaries: r-devel: permimp_1.0-2.zip, r-release: permimp_1.0-2.zip, r-oldrel: permimp_1.0-2.zip
macOS binaries: r-release (arm64): permimp_1.0-2.tgz, r-oldrel (arm64): permimp_1.0-2.tgz, r-release (x86_64): permimp_1.0-2.tgz, r-oldrel (x86_64): permimp_1.0-2.tgz
Old sources: permimp archive

Reverse dependencies:

Reverse imports: rfvimptest

Linking:

Please use the canonical form https://CRAN.R-project.org/package=permimp to link to this page.

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.