A Nonnegative Matrix Factorization algorithm based on alternating least squares and coordinate descent.
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Failed to load latest commit information.
R
man
src
.gitignore
DESCRIPTION
NAMESPACE
README.md

README.md

bignmf

##Warning

This package is deprecated and no longer maintained!

This R package intends to solve Nonnegative Matrix Factorization efficiently. The algorithm bases on alternating least squares while solving nonnegative constrained regression via coordinate descent. The coordinate descent method is modified from glmnet (See Regularization Paths for Generalized Linear Models via Coordinate Descent, by J Friedman et al. 2010).

The inner part of the algorithm is implemented in C++. This package is currently tested only on Ubuntu.

##How to install

In Linux teminal, go to some directory:

cd  ~/mypackages/ 

Download it with:

git clone https://github.com/panlanfeng/bignmf.git

Build with:

R CMD build bignmf

Then in R:

install.packages("~/mypackages/bignmf_0.1.tar.gz", repos = NULL, type = "source")   
library(bignmf)