fairadapt: Fair Data Adaptation with Quantile Preservation

An implementation of the fair data adaptation with quantile preservation described in Plecko & Meinshausen (2019) <arXiv:1911.06685>. The adaptation procedure uses the specified causal graph to pre-process the given training and testing data in such a way to remove the bias caused by the protected attribute. The procedure uses tree ensembles for quantile regression.

Version: 0.2.4
Depends: R (≥ 3.5.0)
Imports: ranger (≥ 0.13.1), assertthat, quantreg, qrnn, igraph, ggplot2, cowplot, scales
Suggests: testthat (≥ 3.0.3), knitr, rmarkdown, rticles, mvtnorm, magick, ggraph, pdftools, microbenchmark, xtable
Published: 2022-07-01
Author: Drago Plecko [aut, cre], Nicolas Bennett [aut]
Maintainer: Drago Plecko <drago.plecko at stat.math.ethz.ch>
BugReports: https://github.com/dplecko/fairadapt/issues
License: GPL (≥ 3)
URL: https://github.com/dplecko/fairadapt
NeedsCompilation: no
Language: en-US
Citation: fairadapt citation info
Materials: README NEWS
CRAN checks: fairadapt results

Documentation:

Reference manual: fairadapt.pdf
Vignettes: fairadapt: Causal Reasoning for Fair Data Pre-processing

Downloads:

Package source: fairadapt_0.2.4.tar.gz
Windows binaries: r-devel: fairadapt_0.2.3.zip, r-release: fairadapt_0.2.3.zip, r-oldrel: fairadapt_0.2.3.zip
macOS binaries: r-release (arm64): fairadapt_0.2.4.tgz, r-oldrel (arm64): fairadapt_0.2.4.tgz, r-release (x86_64): fairadapt_0.2.3.tgz, r-oldrel (x86_64): fairadapt_0.2.3.tgz
Old sources: fairadapt archive

Linking:

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