Comparing 1.8.11 to 1.8.10

DT_1.8.10vs1.8.11.R

# version 1.8.11 (commit 1048)
require(data.table)
# Loading required package: data.table
# data.table 1.8.11  For help type: help("data.table")

## create a huge data.table:
## -------------------------
set.seed(1)
N <- 2e7 # size of DT

# generate a character vector of length about 1e5
foo <- function() paste(sample(letters, sample(5:9, 1), TRUE), collapse="")
ch <- replicate(1e5, foo())
ch <- unique(ch)

# > length(ch)
# [1] 99982

# DT now
DT <- data.table(a = as.numeric(sample(c(NA, Inf, -Inf, NaN, rnorm(1e6)*1e6), N, TRUE)), 
                 b = as.numeric(sample(rnorm(1e6), N, TRUE)), 
                 c = sample(c(NA_integer_, 1e5:1e6), N, TRUE), 
                 d = sample(ch, N, TRUE))

# > tables()
#      NAME       NROW  MB COLS    KEY
# [1,] DT   20,000,000 539 a,b,c,d    
# Total: 539MB

## testing 'setkey' on column 2 (numeric)
## --------------------------------------
# waiting for my laptop to cool down... and running again
DT.cp = copy(DT)
system.time(setkey(DT.cp, b)) # takes 55 seconds on 1.8.10
#   user  system elapsed 
#  6.778   0.359   7.204   

# setkey on integer column - c
DT.cp = copy(DT)
system.time(setkey(DT.cp, c)) # takes 48 seconds on 1.8.10
#   user  system elapsed 
#  6.756   0.175   6.985 

## testing 'setkey' on 2 columns
## -----------------------------
# setkey on numeric columns - a,b
DT.cp = copy(DT)
system.time(setkey(DT.cp, a,b)) # takes 102 seconds on 1.8.10
#   user  system elapsed 
# 15.289   1.131  16.934 


## testing 'cold' by aggregation
## -----------------------------
DT.cp = copy(DT)
DT[, mean(b),  by=c]
#   user  system elapsed  # takes 47 seconds on 1.8.10
#  7.948   0.441   8.708