kernelshap: Kernel SHAP

Efficient implementation of Kernel SHAP, see Lundberg and Lee (2017), and Covert and Lee (2021) <http://proceedings.mlr.press/v130/covert21a>. Furthermore, for up to 14 features, exact permutation SHAP values can be calculated. The package plays well together with meta-learning packages like 'tidymodels', 'caret' or 'mlr3'. Visualizations can be done using the R package 'shapviz'.

Getting started

Package details

AuthorMichael Mayer [aut, cre] (<https://orcid.org/0009-0007-2540-9629>), David Watson [aut] (<https://orcid.org/0000-0001-9632-2159>), Przemyslaw Biecek [ctb] (<https://orcid.org/0000-0001-8423-1823>)
MaintainerMichael Mayer <mayermichael79@gmail.com>
LicenseGPL (>= 2)
Version0.7.0
URL https://github.com/ModelOriented/kernelshap
Package repositoryView on CRAN
Installation Install the latest version of this package by entering the following in R:
install.packages("kernelshap")

Try the kernelshap package in your browser

Any scripts or data that you put into this service are public.

kernelshap documentation built on Sept. 11, 2024, 9:35 p.m.