breakDown: Model Agnostic Explainers for Individual Predictions

Model agnostic tool for decomposition of predictions from black boxes. Break Down Table shows contributions of every variable to a final prediction. Break Down Plot presents variable contributions in a concise graphical way. This package work for binary classifiers and general regression models.

Version: 0.2.1
Depends: R (≥ 3.0)
Imports: ggplot2
Suggests: knitr, rmarkdown, e1071, kernlab, xgboost, caret, randomForest, DALEX, ranger, testthat
Published: 2021-01-20
Author: Przemyslaw Biecek [aut, cre], Aleksandra Grudziaz [ctb]
Maintainer: Przemyslaw Biecek <przemyslaw.biecek at gmail.com>
BugReports: https://github.com/pbiecek/breakDown/issues
License: GPL-2
URL: https://pbiecek.github.io/breakDown/
NeedsCompilation: no
Citation: breakDown citation info
Materials: NEWS
CRAN checks: breakDown results

Documentation:

Reference manual: breakDown.pdf
Vignettes: breakDown plots for the generalised linear model
breakDown plots for the linear model
model agnostic breakDown plots for SVM model
model agnostic breakDown plots for xgboost

Downloads:

Package source: breakDown_0.2.1.tar.gz
Windows binaries: r-devel: breakDown_0.2.1.zip, r-release: breakDown_0.2.1.zip, r-oldrel: breakDown_0.2.1.zip
macOS binaries: r-release (arm64): breakDown_0.2.1.tgz, r-oldrel (arm64): breakDown_0.2.1.tgz, r-release (x86_64): breakDown_0.2.1.tgz, r-oldrel (x86_64): breakDown_0.2.1.tgz
Old sources: breakDown archive

Reverse dependencies:

Reverse imports: live, modelDown

Linking:

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