This is a package for Nonnegative Linear Models (NNLM). It implements fast sequential coordinate descent algorithms for nonnegative linear regression and nonnegative matrix factorization (NMF or NNMF). It supports mean square error and Kullback-Leibler divergence loss. Many other features are also implemented, including missing value imputation, domain knowledge integration, designable W and H matrices and multiple forms of regularizations.
library(devtools)
install_github('linxihui/NNLM')
# get a release version from CRAN
# NOT LONGER available
# install.packages('NNLM')
A short answer: existent packages are not efficient for relative large matrices and lack many cool and new features.
k
.
(Not a built-in function yet and will be in next version shortly, but one can do it easily).For more details, one can read the vignette.