Fit a random forests with 1000 trees on the iris data set as an example on sequential and parallel execution in R.

rf_seq_parallel.R

library(randomForest)
data(iris)
mydata = iris


###############################################################################
### sequential
###############################################################################
randomForest(Species ~ ., data = mydata, ntree = 1000)


###############################################################################
### parallel with snowfall
###############################################################################
library(snowfall)

# inititalize the cluster with 2 CPUs, export libraries and data and setup the
# RNG
sfInit(parallel = TRUE, cpus = 2)
sfLibrary(randomForest)
sfExport("mydata")
sfClusterSetupRNG(seed = 1)

# fit a forest on exported "mydata" with n trees
fit = function(n) {
  randomForest(Species ~ ., data = mydata, ntree = n)
}

# fit 10 forests with 100 trees each
res = sfLapply(rep(100, 10), fit)

# stop the cluster
sfStop()

# reduce results with randomForest::combine to a forest with 1000 trees
Reduce(combine, res)


###############################################################################
### parallel with mclapply
###############################################################################
library(parallel)
fit = function(mydata, n) {
  randomForest(Species ~ ., data = mydata, ntree = n)
}
res = mclapply(rep(100, 10), fit, mydata = mydata)
Reduce(combine, res)


###############################################################################
### parallel with BatchJobs
###############################################################################
# note that this in intended to be used with the default "interactive" backend
library(BatchJobs)

fit = function(mydata, n) {
  randomForest(Species ~ ., data = mydata, ntree = n)
}
reg = batchMapQuick(fit, n = rep(100, 10), more.args = list(mydata = mydata))
reduceResults(reg, fun = function(aggr, job, res) combine(aggr, res))

# cleanup temporary directory
unlink(reg$file.dir, recursive = TRUE)