Calculates two sets of post-hoc variable importance measures for multivariate random forests. The first set of variable importance measures are given by the sum of mean split improvements for splits defined by feature j measured on user-defined examples (i.e., training or testing samples). The second set of importance measures are calculated on a per-outcome variable basis as the sum of mean absolute difference of node values for each split defined by feature j measured on user-defined examples (i.e., training or testing samples). The user can optionally threshold both sets of importance measures to include only splits that are statistically significant as measured using an F-test.
Version: | 0.0.2 |
Depends: | R (≥ 2.10) |
Imports: | MultivariateRandomForest (≥ 1.1.5), MASS (≥ 7.3.0) |
Suggests: | testthat (≥ 3.0.0) |
Published: | 2021-12-15 |
DOI: | 10.32614/CRAN.package.MulvariateRandomForestVarImp |
Author: | Sikdar Sharmistha [aut], Hooker Giles [aut], Kadiyali Vrinda [ctb], Dogonadze Nika [cre] |
Maintainer: | Dogonadze Nika <nika.dogonadze at toptal.com> |
BugReports: | https://github.com/Megatvini/VIM/issues |
License: | GPL (≥ 3) |
URL: | https://github.com/Megatvini/VIM/ |
NeedsCompilation: | no |
Materials: | README |
CRAN checks: | MulvariateRandomForestVarImp results |
Reference manual: | MulvariateRandomForestVarImp.pdf |
Package source: | MulvariateRandomForestVarImp_0.0.2.tar.gz |
Windows binaries: | r-devel: MulvariateRandomForestVarImp_0.0.2.zip, r-release: MulvariateRandomForestVarImp_0.0.2.zip, r-oldrel: MulvariateRandomForestVarImp_0.0.2.zip |
macOS binaries: | r-release (arm64): MulvariateRandomForestVarImp_0.0.2.tgz, r-oldrel (arm64): MulvariateRandomForestVarImp_0.0.2.tgz, r-release (x86_64): MulvariateRandomForestVarImp_0.0.2.tgz, r-oldrel (x86_64): MulvariateRandomForestVarImp_0.0.2.tgz |
Old sources: | MulvariateRandomForestVarImp archive |
Please use the canonical form https://CRAN.R-project.org/package=MulvariateRandomForestVarImp to link to this page.