lime: Local Interpretable Model-Agnostic Explanations

When building complex models, it is often difficult to explain why the model should be trusted. While global measures such as accuracy are useful, they cannot be used for explaining why a model made a specific prediction. 'lime' (a port of the 'lime' 'Python' package) is a method for explaining the outcome of black box models by fitting a local model around the point in question an perturbations of this point. The approach is described in more detail in the article by Ribeiro et al. (2016) <arXiv:1602.04938>.

Version: 0.3.1
Imports: glmnet, stats, ggplot2, tools, stringi, Matrix, stringdist, Rcpp, assertthat, htmlwidgets, shiny, shinythemes
LinkingTo: Rcpp, RcppEigen
Suggests: xgboost, testthat, mlr, h2o, text2vec, MASS, covr, knitr, rmarkdown, devtools
Published: 2017-11-24
Author: Thomas Lin Pedersen [cre, aut], Michaël Benesty [aut]
Maintainer: Thomas Lin Pedersen <thomasp85 at gmail.com>
BugReports: https://github.com/thomasp85/lime/issues
License: MIT + file LICENSE
URL: https://github.com/thomasp85/lime
NeedsCompilation: yes
Materials: README NEWS
CRAN checks: lime results

Downloads:

Reference manual: lime.pdf
Vignettes: Understanding lime
Package source: lime_0.3.1.tar.gz
Windows binaries: r-devel: lime_0.3.0.zip, r-release: lime_0.3.0.zip, r-oldrel: lime_0.3.0.zip
OS X El Capitan binaries: r-release: lime_0.3.0.tgz
OS X Mavericks binaries: r-oldrel: lime_0.3.0.tgz
Old sources: lime archive

Linking:

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