benchmark.R

## From https://github.com/szilard/benchm-dplyr-dt, thanks Szilárd!

library(dplyr)

n <- 100000000
m <- 1000000

d <- data.frame(x = sample(m, n, replace=TRUE), y = runif(n))
dm <- data.frame(x = sample(m))

r1 <- d %>% filter(x>=10, x<20)

r2 <- d %>% arrange(x)

r3 <- d %>% mutate(y2 = 2*y)

r4 <- d %>% group_by(x) %>% summarize(ym = mean(y))

r5 <- d %>% inner_join(dm, by="x")