ceterisParibus: Ceteris Paribus Profiles

Ceteris Paribus Profiles (What-If Plots) are designed to present model responses around selected points in a feature space. For example around a single prediction for an interesting observation. Plots are designed to work in a model-agnostic fashion, they are working for any predictive Machine Learning model and allow for model comparisons. Ceteris Paribus Plots supplement the Break Down Plots from 'breakDown' package.

Version: 0.3.1
Depends: R (≥ 3.3), ggplot2, gower
Imports: DALEX, knitr
Suggests: randomForest, ggiraph, e1071, testthat, rpart
Published: 2019-01-29
Author: Przemyslaw Biecek ORCID iD [aut, cre]
Maintainer: Przemyslaw Biecek <przemyslaw.biecek at gmail.com>
BugReports: https://github.com/pbiecek/ceterisParibus/issues
License: GPL-2
URL: https://pbiecek.github.io/ceterisParibus/
NeedsCompilation: no
Materials: NEWS
CRAN checks: ceterisParibus results

Downloads:

Reference manual: ceterisParibus.pdf
Vignettes: Ceteris Paribus Profiles
Ceteris Paribus Plots for classification
Local Fit Plots / Wangkardu Explanations
What If Plots
What If 2D Plots
Package source: ceterisParibus_0.3.1.tar.gz
Windows binaries: r-devel: ceterisParibus_0.3.1.zip, r-devel-gcc8: ceterisParibus_0.3.1.zip, r-release: ceterisParibus_0.3.1.zip, r-oldrel: ceterisParibus_0.3.1.zip
OS X binaries: r-release: ceterisParibus_0.3.1.tgz, r-oldrel: ceterisParibus_0.3.1.tgz
Old sources: ceterisParibus archive

Linking:

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