1.8.10 : Benchmark: comparison between data.table 1.8.10 and 1.8.11 commit 1048

DT_1.8.10_benchmark.R

# version 1.8.10 
require(data.table)
# Loading required package: data.table
# data.table 1.8.10  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 1 column
## ----------------------------
# setkey on numeric columns - a,b
DT.cp = copy(DT)
system.time(setkey(DT.cp, a))
#   user  system elapsed 
# 51.491   0.426  53.457 
 
# waiting for my laptop to cool down... and running again
DT.cp = copy(DT)
system.time(setkey(DT.cp, b))
#   user  system elapsed 
# 51.030   0.353  54.953 

# setkey on integer column - c
# R's base radix sort won't help here.. will resort to regularorder1
DT.cp = copy(DT)
system.time(setkey(DT.cp, c))
#   user  system elapsed 
# 44.500   0.368  48.012 

# setkey on character column - d 
# should be *very* quick
DT.cp = copy(DT)
system.time(setkey(DT.cp, d))
#   user  system elapsed 
#  9.451   0.178   9.706 

## testing 'setkey' on 2 columns
## -----------------------------
# setkey on numeric columns - a,b
DT.cp = copy(DT)
system.time(setkey(DT.cp, a,b))
#   user  system elapsed 
# 98.412   0.736 102.319 

# setkey on integer+numeric columns - c,a
DT.cp = copy(DT)
system.time(setkey(DT.cp, c,a))
#   user  system elapsed 
# 90.407   0.507  91.512 
 
# setkey on character+numeric columns - d,a
DT.cp = copy(DT)
system.time(setkey(DT.cp, d,a))
#   user  system elapsed 
# 58.047   0.414  59.491 
 
# setkey on numeric+integer columns - a,c
DT.cp = copy(DT)
system.time(setkey(DT.cp, a,c))
#   user  system elapsed 
# 92.641   0.872 100.080 
 
# setkey on numeric+character columns - a,d
DT.cp = copy(DT)
system.time(setkey(DT.cp, a,d))
#   user  system elapsed 
# 58.607   0.602  63.171 
 
# setkey on integer+character columns - c,d
DT.cp = copy(DT)
system.time(setkey(DT.cp, c,d))
#   user  system elapsed 
# 52.147   0.483  55.035 
 
# setkey on character+integer columns - d,c
DT.cp = copy(DT)
system.time(setkey(DT.cp, d,c))
#   user  system elapsed 
# 53.119   0.659  57.779 

## Other tests which are not by reference so that we can run them more than once...
## --------------------------------------------------------------------------------

## Borrowing timing function from Hadley
benchmark <- function(code) {
  code <- substitute(code)

  rbind(
    system.time(eval(code, parent.frame())),
    system.time(eval(code, parent.frame())),
    system.time(eval(code, parent.frame()))    
  )  
}

# filtering/subsetting : vector-scan approach - without key
benchmark(DT[d == "pvuyrlxw"])
#      user.self sys.self elapsed user.child sys.child
# [1,]     6.018    0.329   6.625          0         0
# [2,]     5.939    0.091   6.243          0         0
# [3,]     5.900    0.019   6.169          0         0

# filtering/subsetting : vector-scan approach - with key
DT.cp <- copy(DT)
setkey(DT.cp, d)
benchmark(DT.cp[d == "pvuyrlxw"])
     user.self sys.self elapsed user.child sys.child
# [1,]     2.803    0.009   2.965          0         0
# [2,]     2.790    0.010   2.978          0         0
# [3,]     2.794    0.009   2.897          0         0

# Interesting : setting key helps in vector-scanning... >2x speed-up

# binary search approach
benchmark(DT.cp["pvuyrlxw"])
#     user.self sys.self elapsed user.child sys.child
# [1,]     0.002        0   0.002          0         0
# [2,]     0.002        0   0.002          0         0
# [3,]     0.002        0   0.002          0         0

# summarising : without key - column "c" - for simplicity
benchmark(DT[, mean(b), by=c]) ########################### 900000 groups ######################
#      user.self sys.self elapsed user.child sys.child
# [1,]    45.167    0.357  47.287          0         0
# [2,]    45.148    0.444  47.796          0         0
# [3,]    45.971    0.435  48.342          0         0

# summarising : with key - column "c" - for simplicity
DT.cp <- copy(DT)
setkey(DT.cp, c)
benchmark(DT.cp[, mean(b), by=c]) ########################### 900000 groups ######################
#      user.self sys.self elapsed user.child sys.child
# [1,]     1.800    0.034   1.887          0         0
# [2,]     2.615    0.035   2.790          0         0
# [3,]     1.804    0.030   1.949          0         0