probably: Tools for Post-Processing Predicted Values

Models can be improved by post-processing class probabilities, by: recalibration, conversion to hard probabilities, assessment of equivocal zones, and other activities. 'probably' contains tools for conducting these operations as well as calibration tools and conformal inference techniques for regression models.

Version: 1.0.3
Depends: R (≥ 3.6)
Imports: butcher, cli, dplyr (≥ 1.1.0), furrr, generics (≥ 0.1.3), ggplot2, hardhat, pillar, purrr, rlang (≥ 1.0.4), tidyr (≥ 1.3.0), tidyselect (≥ 1.1.2), tune (≥ 1.1.2), vctrs (≥ 0.4.1), withr, workflows (≥ 1.1.4), yardstick (≥ 1.3.0)
Suggests: betacal, covr, knitr, MASS, mgcv, modeldata (≥ 1.1.0), nnet, parsnip (≥ 1.2.0), quantregForest, randomForest, recipes, rmarkdown, rsample, testthat (≥ 3.0.0)
Published: 2024-02-23
DOI: 10.32614/CRAN.package.probably
Author: Max Kuhn [aut, cre], Davis Vaughan [aut], Edgar Ruiz [aut], Posit Software, PBC [cph, fnd]
Maintainer: Max Kuhn <max at>
License: MIT + file LICENSE
NeedsCompilation: no
Materials: README NEWS
CRAN checks: probably results


Reference manual: probably.pdf
Vignettes: Equivocal zones
Where does probably fit in?


Package source: probably_1.0.3.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
macOS binaries: r-release (arm64): probably_1.0.3.tgz, r-oldrel (arm64): probably_1.0.3.tgz, r-release (x86_64): probably_1.0.3.tgz, r-oldrel (x86_64): probably_1.0.3.tgz
Old sources: probably archive

Reverse dependencies:

Reverse suggests: yardstick


Please use the canonical form to link to this page.