Last active
November 29, 2016 01:06
-
-
Save szilard/b632ca400b40661d18f09ab8ed01f79e to your computer and use it in GitHub Desktop.
data.table 20GB x 3GB join
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
library(data.table) | |
n <- 2e9 | |
m <- 1e9 | |
system.time( d <- data.table(x = sample(m, n, replace=TRUE), y = runif(n)) ) | |
# user system elapsed | |
# 103.843 8.255 112.242 | |
system.time( dm <- data.table(x = sample(m)) ) | |
# user system elapsed | |
# 47.298 1.860 49.288 | |
tables() | |
# NAME NROW NCOL MB COLS KEY | |
#[1,] d 2,000,000,000 2 22,889 x,y | |
#[2,] dm 1,000,000,000 1 3,815 x | |
#Total: 26,704MB | |
system.time( setkey(d, x) ) | |
# user system elapsed | |
# 184.881 4.506 189.789 | |
system.time( print(nrow(d[dm, nomatch=0])) ) | |
# user system elapsed | |
# 349.744 11.486 361.933 | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment