localModel: LIME-Based Explanations with Interpretable Inputs Based on Ceteris Paribus Profiles

Local explanations of machine learning models describe, how features contributed to a single prediction. This package implements an explanation method based on LIME (Local Interpretable Model-agnostic Explanations, see Tulio Ribeiro, Singh, Guestrin (2016) <doi:10.1145/2939672.2939778>) in which interpretable inputs are created based on local rather than global behaviour of each original feature.

Version: 0.5
Depends: R (≥ 3.5)
Imports: glmnet, DALEX, ggplot2, partykit, ingredients
Suggests: covr, knitr, rmarkdown, randomForest, testthat
Published: 2021-09-14
Author: Przemyslaw Biecek [aut, cre], Mateusz Staniak [aut], Krystian Igras [ctb], Alicja Gosiewska [ctb], Harel Lustiger [ctb], Willy Tadema [ctb]
Maintainer: Przemyslaw Biecek <przemyslaw.biecek at gmail.com>
BugReports: https://github.com/ModelOriented/localModel/issues
License: GPL-2 | GPL-3 [expanded from: GPL]
URL: https://github.com/ModelOriented/localModel
NeedsCompilation: no
Materials: README NEWS
CRAN checks: localModel results

Documentation:

Reference manual: localModel.pdf
Vignettes: Explaining classification models with localModel package
Methodology behind localModel package
Introduction to localModel package

Downloads:

Package source: localModel_0.5.tar.gz
Windows binaries: r-devel: localModel_0.5.zip, r-release: localModel_0.5.zip, r-oldrel: localModel_0.5.zip
macOS binaries: r-release (arm64): localModel_0.5.tgz, r-oldrel (arm64): localModel_0.5.tgz, r-release (x86_64): localModel_0.5.tgz
Old sources: localModel archive

Reverse dependencies:

Reverse suggests: DALEXtra

Linking:

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