Is it easy to parallelize training of a random forest model? How can we do it?
Classic MLLevel: IntermediateRandom forest
Is it easy to parallelize training of a random forest model? How can we do it?
Hints
- How are training samples formed and how do ensemble trees differ?
- Consider correlation between model errors, not only individual quality.
Answer
Yes, R provides a simple way to parallelize training of random forests on large scale data. It makes use of a parameter called multicombine which can be set to TRUE for parallelizing random forest computations.
rf <- foreach(ntree=rep(25000, 6), .combine=randomForest::combine,
.multicombine=TRUE, .packages='randomForest') %dopar% {
randomForest(x, y, ntree=ntree)
}
Source and licence: Alexey Grigorev & contributors — Data Science Interviews · CC-BY-4.0