Package: glinternet 1.0.12
Michael Lim
glinternet: Learning Interactions via Hierarchical Group-Lasso Regularization
Group-Lasso INTERaction-NET. Fits linear pairwise-interaction models that satisfy strong hierarchy: if an interaction coefficient is estimated to be nonzero, then its two associated main effects also have nonzero estimated coefficients. Accommodates categorical variables (factors) with arbitrary numbers of levels, continuous variables, and combinations thereof. Implements the machinery described in the paper "Learning interactions via hierarchical group-lasso regularization" (JCGS 2015, Volume 24, Issue 3). Michael Lim & Trevor Hastie (2015) <doi:10.1080/10618600.2014.938812>.
Authors:
glinternet_1.0.12.tar.gz
glinternet_1.0.12.tar.gz(r-4.5-noble)glinternet_1.0.12.tar.gz(r-4.4-noble)
glinternet_1.0.12.tgz(r-4.4-emscripten)glinternet_1.0.12.tgz(r-4.3-emscripten)
glinternet.pdf |glinternet.html✨
glinternet/json (API)
| # Install 'glinternet' in R: |
| install.packages('glinternet', repos = c('https://cran.r-universe.dev', 'https://cloud.r-project.org')) |
This package does not link to any Github/Gitlab/R-forge repository. No issue tracker or development information is available.
Last updated 3 years agofrom:67a32a33d0. Checks:OK: 2. Indexed: no.
| Target | Result | Date |
|---|---|---|
| Doc / Vignettes | OK | Dec 01 2024 |
| R-4.5-linux-x86_64 | OK | Dec 01 2024 |
Exports:glinternetglinternet.cv
Dependencies:
Readme and manuals
Help Manual
| Help page | Topics |
|---|---|
| Return main effect and interaction coefficients. | coef.glinternet |
| Fit a linear interaction model with group-lasso regularization that enforces strong hierarchy in the estimated coefficients | glinternet |
| Cross-validation for glinternet | glinternet.cv |
| Plot CV error from 'glinternetCV' object. | plot.glinternet.cv |
| Make predictions from a "glinternet" object. | predict.glinternet |
| Make predictions from a "glinternetCV" object. | predict.glinternet.cv |
