cpi: Conditional Predictive Impact

A general test for conditional independence in supervised learning algorithms as proposed by Watson & Wright (2021) <doi:10.1007/s10994-021-06030-6>. Implements a conditional variable importance measure which can be applied to any supervised learning algorithm and loss function. Provides statistical inference procedures without parametric assumptions and applies equally well to continuous and categorical predictors and outcomes.

Version: 0.1.5
Imports: foreach, mlr3, lgr, knockoff
Suggests: mlr3learners, ranger, glmnet, testthat (≥ 3.0.0), knitr, rmarkdown, doParallel
Published: 2024-11-25
DOI: 10.32614/CRAN.package.cpi
Author: Marvin N. Wright ORCID iD [aut, cre], David S. Watson [aut]
Maintainer: Marvin N. Wright <cran at wrig.de>
BugReports: https://github.com/bips-hb/cpi/issues
License: GPL (≥ 3)
URL: https://github.com/bips-hb/cpi, https://bips-hb.github.io/cpi/
NeedsCompilation: no
Citation: cpi citation info
Materials: README NEWS
CRAN checks: cpi results

Documentation:

Reference manual: cpi.pdf
Vignettes: intro (source, R code)

Downloads:

Package source: cpi_0.1.5.tar.gz
Windows binaries: r-devel: cpi_0.1.4.zip, r-release: cpi_0.1.4.zip, r-oldrel: cpi_0.1.4.zip
macOS binaries: r-release (arm64): cpi_0.1.5.tgz, r-oldrel (arm64): cpi_0.1.5.tgz, r-release (x86_64): cpi_0.1.5.tgz, r-oldrel (x86_64): cpi_0.1.5.tgz
Old sources: cpi archive

Linking:

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