enpls
Ensemble Partial Least Squares Regression
An algorithmic framework for measuring feature importance, outlier detection, model applicability domain evaluation, and ensemble predictive modeling with (sparse) partial least squares regressions.
enpls offers an algorithmic framework for measuring feature importance, outlier detection, model applicability domain evaluation, and ensemble predictive modeling with (sparse) partial least squares regressions.
Installation
Install enpls from CRAN:
install.packages("enpls")Or try the development version on GitHub:
# install.packages("devtools")devtools::install_github("road2stat/enpls")See the vignette (or open with vignette("enpls") in R) for a quick-start guide.
Gallery
Measuring Feature Importance
Outlier Detection
Model Applicability Domain Evaluation / Ensemble Predictive Modeling
Links
- Web: https://nanx.me/enpls/
- CRAN: https://cran.r-project.org/package=enpls
- GitHub: https://github.com/road2stat/enpls
Contribute
To contribute to this project, please take a look at the Contributing Guidelines first. Please note that this project is released with a Contributor Code of Conduct. By participating in this project you agree to abide by its terms.
News
enpls 6.0 (2018-05-13)
Improvements
- New URL for the documentation website: https://nanx.me/enpls/.
enpls 5.9 (2017-09-27)
Improvements
- Use system font stack instead of Google Fonts in vignettes to avoid pandoc SSL issue.
enpls 5.8 (2017-03-24)
Improvements
- Updated gallery images in
README.md. - Better code indentation style.
- HTTPS enabled for the website.
enpls 5.7 (2017-01-05)
Improvements
- New documentation website generated by pkgdown, with a full set of function documentation and vignettes available.
- Added Windows continuous integration support using AppVeyor.
enpls 5.6 (2016-11-25)
New Features
- New argument
cvfoldsnow available in all applicable functions for finer control of cross-validation folds in automatic parameter selection of each PLS/SPLS model.
Improvements
- Critical implementation improvements for processing the case where argument
maxcomp = NULL(maximum number of components not specified explicitly) inenpls.functions. Now it should correctly determine the maximum number of components to use, considering both cross-validation and special cases such as n < p. Thanks to Dr. You-Wu Lin for the feedback.
enpls 5.0 (2016-10-20)
New Features
- New functions
enpls.ad()andenspls.ad()for PLS and sparse PLS model applicability domain evaluation. - New plot functions
plot.enpls.ad()andplot.enpls.ad()for exploring model applicability domain evaluation results with traditional static plot support and interactive plot support. - New argument
alphaavailable for setting transparency level (to reduce overplotting) inplot.cv.enpls,plot.enpls.od,plot.cv.enspls, andplot.enspls.od.
enpls 4.5 (2016-09-15)
Improvements
- Reduced memory footprints for
enpls.fit()andenspls.fit().
New Features
- New functions
enpls.rmse(),enpls.mae(), andenpls.rmsle()for computing RMSE, MAE, and RMSLE.
enpls 4.0 (2016-08-28)
Improvements
- General improvements on function documentation.
- Changing the argument name
MCtimestoreptimes. - Changing the option name
"bootstrap"to"boot".
enpls 3.0 (2016-06-22)
New Features
- Add sparse partial least squares regression.
Improvements
- Improvements on documentation; rewritten vignette.
enpls 2.0 (2016-06-19)
New Features
- New project website.
Improvements
- General improvements on plotting functions.
Bug Fixes
- Fixed major bugs in
cv.enplsand plotting functions. - Many other bug fixes.
enpls 1.1 (2015-11-26)
Bug Fixes
- Fixed the bugs in automatic component number selection which could make the intercept-only model rank best. Thanks for the test and patch from Max Kuhn <[email protected]>.
enpls 1.0 (2014-10-03)
New Features
- initial release