A general framework for constructing variable importance plots from various types of machine learning models in R. Aside from some standard model- specific variable importance measures, this package also provides model- agnostic approaches that can be applied to any supervised learning algorithm. These include 1) an efficient permutation-based variable importance measure, 2) variable importance based on Shapley values (Strumbelj and Kononenko, 2014) <doi:10.1007/s10115-013-0679-x>, and 3) the variance-based approach described in Greenwell et al. (2018) <doi:10.48550/arXiv.1805.04755>. A variance-based method for quantifying the relative strength of interaction effects is also included (see the previous reference for details).
| Version: | 0.4.5 |
| Depends: | R (≥ 4.1.0) |
| Imports: | foreach,ggplot2 (≥ 0.9.0), stats,tibble, utils,yardstick |
| Suggests: | bookdown,DT,covr,doParallel,dplyr,fastshap (≥ 0.1.0),knitr,lattice,mlbench,modeldata,NeuralNetTools,pdp,rmarkdown,tinytest (≥ 1.4.1),varImp |
| Enhances: | C50,caret,Cubist,earth,gbm,glmnet,h2o,lightgbm,mixOmics,mlr,mlr3,neuralnet,nnet,parsnip (≥ 0.1.7),party,partykit,pls,randomForest,ranger,rpart,RSNNS,sparklyr (≥ 0.8.0),tidymodels,workflows (≥ 0.2.3),xgboost |
| Published: | 2025-12-12 |
| DOI: | 10.32614/CRAN.package.vip |
| Author: | Brandon M. Greenwell [aut, cre], Brad Boehmke [aut] |
| Maintainer: | Brandon M. Greenwell <greenwell.brandon at gmail.com> |
| BugReports: | https://github.com/koalaverse/vip/issues |
| License: | GPL-2 |GPL-3 [expanded from: GPL (≥ 2)] |
| URL: | https://github.com/koalaverse/vip/,https://koalaverse.github.io/vip/ |
| NeedsCompilation: | no |
| Citation: | vip citation info |
| Materials: | README,NEWS |
| CRAN checks: | vip results |