fastshap: Fast Approximate Shapley Values

Computes fast (relative to other implementations) approximate Shapley values for any supervised learning model. Shapley values help to explain the predictions from any black box model using ideas from game theory; see Strumbel and Kononenko (2014) <doi:10.1007/s10115-013-0679-x> for details.

Version: 0.1.0
Depends: R (≥ 3.6.0)
Imports: foreach, Rcpp (≥ 1.0.1), utils
LinkingTo: Rcpp, RcppArmadillo
Suggests: AmesHousing, covr, knitr, ranger, rmarkdown, shapviz (≥ 0.8.0), tibble, tinytest (≥ 1.4.1)
Enhances: lightgbm, xgboost
Published: 2023-06-06
Author: Brandon Greenwell ORCID iD [aut, cre]
Maintainer: Brandon Greenwell <greenwell.brandon at gmail.com>
BugReports: https://github.com/bgreenwell/fastshap/issues
License: GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
URL: https://github.com/bgreenwell/fastshap, https://bgreenwell.github.io/fastshap/
NeedsCompilation: yes
Materials: NEWS
In views: MachineLearning
CRAN checks: fastshap results

Documentation:

Reference manual: fastshap.pdf
Vignettes: fastshap

Downloads:

Package source: fastshap_0.1.0.tar.gz
Windows binaries: r-devel: fastshap_0.1.0.zip, r-release: fastshap_0.1.0.zip, r-oldrel: fastshap_0.1.0.zip
macOS binaries: r-release (arm64): fastshap_0.1.0.tgz, r-oldrel (arm64): fastshap_0.1.0.tgz, r-release (x86_64): fastshap_0.1.0.tgz
Old sources: fastshap archive

Reverse dependencies:

Reverse imports: flowml, itsdm
Reverse suggests: ENMTools, innsight, nestedcv, vip
Reverse enhances: shapviz

Linking:

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