using parallel's parLapply: unable to access variables within parallel code
You need to export those variables to the other R processes in the cluster:
cl <- makeCluster(mc <- getOption("cl.cores", 4))clusterExport(cl=cl, varlist=c("text.var", "ntv", "gc.rate", "pos"))
An alternate method provided by Martin Morgan would work here as well.
This method supplies the objects to each node in the cluster directly in parLapply
call with no need to use cluster export:
library(parallel)text.var <- rep("I like cake and ice cream so much!", 20)ntv <- length(text.var)gc.rate <- 10pos <- function(i) { paste(sapply(strsplit(tolower(i), " "), nchar), collapse=" | ")}cl <- makeCluster(mc <- getOption("cl.cores", 4))parLapply(cl, seq_len(ntv), function(i, pos, text.var, ntv, gc.rate) { x <- pos(text.var[i]) if (i%%gc.rate==0) gc() return(x) }, pos, text.var, ntv, gc.rate)
out1<-lapply(seq_len(ntv), function(i) {x <- pos(text.var[i]);if (i%%gc.rate==0) gc();return(x)})out2<-parLapply(cl, seq_len(ntv), function(i) {x <- pos(text.var[i]);if (i%%gc.rate==0) gc();return(x)})> identical(out1,out2)# [1] TRUErequire(rbenchmark)benchmark(lapply(seq_len(ntv), function(i) {x <- pos(text.var[i]);if (i%%gc.rate==0) gc();return(x)}),parLapply(cl, seq_len(ntv), function(i) {x <- pos(text.var[i]);if (i%%gc.rate==0) gc();return(x)})) test#1 lapply(seq_len(ntv), function(i) {\n x <- pos(text.var[i])\n if (i%%gc.rate == 0) \n gc()\n return(x)\n})#2 parLapply(cl, seq_len(ntv), function(i) {\n x <- pos(text.var[i])\n if (i%%gc.rate == 0) \n gc()\n return(x)\n})# replications elapsed relative user.self sys.self user.child sys.child#1 100 20.03 3.453448 20.31 0.05 NA NA#2 100 5.80 1.000000 0.22 0.03 NA NA> clsocket cluster with 2 nodes on host ‘localhost’