live: Local Interpretable (Model-Agnostic) Visual Explanations

Interpretability of complex machine learning models is a growing concern. This package helps to understand key factors that drive the decision made by complicated predictive model (so called black box model). This is achieved through local approximations that are either based on additive regression like model or CART like model that allows for higher interactions. The methodology is based on Tulio Ribeiro, Singh, Guestrin (2016) <doi:10.1145/2939672.2939778>. More details can be found in Staniak, Biecek (2018) <arXiv:1804.01955>.

Version: 1.5.8
Depends: R (≥ 3.0.2)
Imports: mlr, dplyr, breakDown, data.table, forestmodel, lubridate, shiny, MASS, ggplot2, gower
Suggests: knitr, rmarkdown, testthat, glmnet, e1071, covr, DALEX
Published: 2018-09-24
Author: Mateusz Staniak [cre, aut], Przemysław Biecek [aut]
Maintainer: Mateusz Staniak <mateusz.staniak at math.uni.wroc.pl>
BugReports: https://github.com/MI2DataLab/live/issues
License: MIT + file LICENSE
URL: https://github.com/MI2DataLab/live
NeedsCompilation: no
Citation: live citation info
Materials: README NEWS
CRAN checks: live results

Downloads:

Reference manual: live.pdf
Vignettes: "Case study: wine quality"
Package source: live_1.5.8.tar.gz
Windows binaries: r-devel: live_1.5.7.zip, r-release: live_1.5.7.zip, r-oldrel: live_1.5.7.zip
OS X binaries: r-release: live_1.5.7.tgz, r-oldrel: live_1.5.7.tgz
Old sources: live archive

Linking:

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