[R] How to speed this up?

[Jen]

Hi, I'm trying to generate 2.5 million phone numbers.  The code below
generates a random sample of 250K MPNS for Morocco.  It takes about 10
minutes.

I need to generate 2.5 million.  I've run it through once and it took about
45 hours.

Is there a way to speed this up?

Thanks,

Jen

# generate random sample of mobile phone numbers (MPNs) - Morocco

# Mobile phone number format:  +212-6xx-xxxxxx

library(data.table)

# country code

cc <- "+212"

# prefixes

IAM  <- data.table(matrix(c(610,        611,    613,    615,    616,
618,    641,    642,    648,    650,    651,    652,    653,
          654,  655,    658,    659,    661,    662,    666,    667,
668,    670,    671,    672,    673,
          676,  677,    678), dimnames=list(NULL, "IAM")))



Medi <- data.table(matrix(c(612,        614,    617,    619,    644,
645,    649,    656,    657,    660,    663,    664,    665,
          669,  674,    675,    679), dimnames=list(NULL, "Medi")))

MOROC <- data.table(matrix(c(0636, 0637), dimnames=list(NULL, "MOROC")))

# combine

mno <- c(IAM, Medi, MOROC)

# generate MPNs
MPN <- NULL

system.time(for (i in 1:250000){
# randomly select number from list

prefix <- sapply(mno[floor(runif(1, 1, length(mno)+1))], function(x)
sample(x, 1))

MNO <- names(prefix)

# randomly generate 6 numbers between 0 and 9, inclusive

nums <- floor(runif(6, 0, 9))

# concatenate

tmp <- c(paste(c(cc,prefix,t(nums)), sep="", collapse=""), MNO)

MPN[[i]] <- tmp

i <- i+1


})

# unlist

df <- data.table(matrix(unlist(MPN), nrow=length(MPN), ncol=2, byrow=T,
dimnames = list(seq(1, length(MPN),1), c("MPN", "MNO"))   ))

	[[alternative HTML version deleted]]