Question



Threading in R

Is there a way to have a computationally intense algorithm such as randomForest be distributed across processor cores?





Answers and follow-up questions





Answer or follow-up question 1

http://stackoverflow.com/questions/10835122/multithreading-with-r

This might be helpful


Answer or follow-up question 2

Dear student,

Yes there is:
use the combine() function in the randomForest package.

You'll need foreach and a parallel backend.

Beware that if you're using Windows, this will require more RAM.

See page 8 on:
https://cran.r-project.org/web/packages/foreach/vignettes/foreach.pdf

Michel Ballings



Sign in to be able to add an answer or mark this question as resolved.