bartXViz: Visualization of BART and BARP using SHAP

The contribution of variables in Bayesian Additive Regression Trees (BART) and Bayesian Additive Regression Trees with Post-Stratification (BARP) models is computed using permutation-based Shapley values. The computed SHAP values are then utilized to visualize the contribution of each variable through various plots. The computation of SHAP values for most models follows the methodology proposed by Strumbel and Kononenko (2014) <doi:10.1007/s10115-013-0679-x>, while for XGBoost, the approach introduced by Lundberg et al. (2020) <doi:10.1038/s42256-019-0138-9> was also considered. The BART model was referenced based on the works of Chipman, George, and McCulloch (2010) <doi:10.1214/09-AOAS285> and Kapelner and Bleich (2013) <doi:10.18637/jss.v070.i04>, while the methodology for the BARP model was based on Bisbee (2019) <doi:10.1017/S0003055419000480>.

Version:	1.0.3
Depends:	R (≥ 3.5.0), SuperLearner
Imports:	bartMachine, BART, ggplot2, ggforce, data.table, ggfittext, ggpubr, foreach, gggenes, Rcpp, dplyr, tidyr, stringr, abind, data.table, utils, grid, dbarts, forcats, gridExtra, reshape2, missForest
LinkingTo:	Rcpp, RcppArmadillo
Published:	2025-04-28
DOI:	10.32614/CRAN.package.bartXViz
Author:	Dong-eun Lee [aut, cre], Eun-Kyung Lee [aut]
Maintainer:	Dong-eun Lee <ldongeun.leel at gmail.com>
License:	GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
NeedsCompilation:	yes
CRAN checks:	bartXViz results

Documentation:

Reference manual:

bartXViz.pdf

Downloads:

Package source:	bartXViz_1.0.3.tar.gz
Windows binaries:	r-devel: bartXViz_1.0.3.zip, r-release: bartXViz_1.0.3.zip, r-oldrel: not available
macOS binaries:	r-release (arm64): bartXViz_1.0.3.tgz, r-oldrel (arm64): bartXViz_1.0.3.tgz, r-release (x86_64): bartXViz_1.0.3.tgz, r-oldrel (x86_64): bartXViz_1.0.3.tgz

Linking:

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