Fast Sparse Wrapper Algorithm for Generalized Linear Models and Testing Procedures for Network of Highly Predictive Variables R package swaglm version 0.0.1 Provides a fast implementation of the SWAG algorithm for Generalized Linear Models which allows to perform a meta-learning procedure that combines screening and wrapper methods to find a set of extremely low-dimensional attribute combinations. The package then performs test on the network of selected models to identify the variables that are highly predictive by using entropy-based network measures. Software Imports: Rcpp, fastglm, stats, igraph, gdata, plyr, progress, DescTools, scales, fields LinkingTo: Rcpp, RcppArmadillo Suggests: knitr, MASS, rmarkdown Lionel Voirol <lionelvoirol@hotmail.com> Comprehensive R Archive Network (CRAN) Lionel Voirol [aut, cre] (ORCID: <https://orcid.org/0000-0003-1696-1407>), Yagmur Ozdemir [aut] AGPL-3 2025-09-18 application/tgz https://CRAN.R-project.org/package=swaglm doi:10.32614/CRAN.package.swaglm