Support IRLBA method and use it as default for sparse matrices

hredestig / pcaMethods

Perform PCA on data with missing values in R

GNU General Public License v2.0

45 stars 10 forks source link

Support IRLBA method and use it as default for sparse matrices #7

Closed flying-sheep closed 1 year ago

flying-sheep commented 5 years ago

The irlba package handles sparse matrices (from the Matrix package) without converting them into a dense matrix. This can make the difference between blowing up the memory and just working.

pcaMethods should use the irlba method and use it as a default for sparse matrices.

hredestig commented 5 years ago

Ouch surely wouldn't want to blow any memory up. Happy to review a pull request if you want send one.

flying-sheep commented 1 year ago

Hi! What release/PR is this completed in?

hredestig commented 1 year ago

It isn't, sorry, adding irlba is not that straight-forward and I don't have the bandwidth to work on it.

flying-sheep commented 1 year ago

I asked because you closed it as completed as opposed to “not planned”: