Sequential data table benchmark

library(data.table)

set.seed(107)
n <- 1000000
m <- 10000
td <- data.frame(val=rnorm(n), id=sample(m, n, replace=TRUE))

start <- proc.time()[3]
DT <- data.table(td)
DT[, means := mean(DT[-.I, val]), by = id]
elapsed <- proc.time()[3] - start

library(digest)
res <- DT$means
cat("Sequential data table version:\n")
cat(sprintf("Elapsed time: %f, MD5 hash: %s\n", elapsed, digest(res)))