flashlight: Shed Light on Black Box Machine Learning Models

Shed light on black box machine learning models by the help of model performance, variable importance, global surrogate models, ICE profiles, partial dependence (Friedman J. H. (2001) <doi:10.1214/aos/1013203451>), accumulated local effects (Apley D. W. (2016) <arXiv:1612.08468>), further effects plots, scatter plots, interaction strength, and variable contribution breakdown (approximate SHAP) for single observations (Gosiewska and Biecek (2019) <arXiv:1903.11420>). All tools are implemented to work with case weights and allow for stratified analysis. Furthermore, multiple flashlights can be combined and analyzed together.

Version: 0.8.0
Depends: R (≥ 3.2.0)
Imports: dplyr (≥ 1.0.0), cowplot, ggplot2, MetricsWeighted (≥ 0.3.0), rpart, rpart.plot, stats, tidyr (≥ 1.0.0), tidyselect, utils, withr
Suggests: knitr, caret, mlr3, mlr3learners, moderndive, ranger, rmarkdown, testthat, xgboost
Published: 2021-04-21
Author: Michael Mayer [aut, cre, cph]
Maintainer: Michael Mayer <mayermichael79 at gmail.com>
BugReports: https://github.com/mayer79/flashlight/issues
License: GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
URL: https://github.com/mayer79/flashlight
NeedsCompilation: no
Materials: README NEWS
CRAN checks: flashlight results


Reference manual: flashlight.pdf
Vignettes: Using flashlight with caret
Using flashlight
Using flashlight with mlr3


Package source: flashlight_0.8.0.tar.gz
Windows binaries: r-devel: flashlight_0.8.0.zip, r-release: flashlight_0.8.0.zip, r-oldrel: flashlight_0.8.0.zip
macOS binaries: r-release (arm64): flashlight_0.8.0.tgz, r-release (x86_64): flashlight_0.8.0.tgz, r-oldrel: flashlight_0.8.0.tgz
Old sources: flashlight archive

Reverse dependencies:

Reverse imports: vivid


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