In classification problems a monotone relation between some predictors and the classes may be assumed. In this package 'isoboost' we propose new boosting algorithms, based on LogitBoost, that incorporate this isotonicity information, yielding more accurate and easily interpretable rules.
| Version: | 1.0.0 |
| Imports: | Iso, isotone, rpart |
| Published: | 2020-01-19 |
| Author: | David Conde [aut, cre], Miguel A. Fernandez [aut], Cristina Rueda [aut], Bonifacio Salvador [aut] |
| Maintainer: | David Conde <dconde at eio.uva.es> |
| License: | GPL-2 | GPL-3 |
| NeedsCompilation: | no |
| Citation: | isoboost citation info |
| CRAN checks: | isoboost results |
| Reference manual: | isoboost.pdf |
| Package source: | isoboost_1.0.0.tar.gz |
| Windows binaries: | r-devel: isoboost_1.0.0.zip, r-release: isoboost_1.0.0.zip, r-oldrel: isoboost_1.0.0.zip |
| macOS binaries: | r-release: isoboost_1.0.0.tgz, r-oldrel: isoboost_1.0.0.tgz |
Please use the canonical form https://CRAN.R-project.org/package=isoboost to link to this page.