Benchmarking collapse_mask

collapse_mask.R

## Context: https://twitter.com/grant_mcdermott/status/1493400952878952448

options(collapse_mask = "all") # NB: see `help('collapse-options')`

library(dplyr)
library(data.table)
library(collapse) # Needs to come after library(dplyr) for collapse_mask to work

flights = fread('https://raw.githubusercontent.com/Rdatatable/data.table/master/vignettes/flights14.csv')

vars = c('dep_delay', 'arr_delay', 'air_time', 'distance', 'hour')

## Note we explicitly call dplyr::<function> for the 1st line in this benchmark, 
## since we've masked the regular dplyr operations with their collapse 
## equivalents (i.e. 2nd line). 
library(microbenchmark)
microbenchmark(
  dplyr      = flights |> dplyr::group_by(month, day, origin, dest) |> dplyr::summarise(across(vars, sum)),
  collapse   = flights |> group_by(month, day, origin, dest) |> summarise(across(vars, sum)),
  data.table = flights[, lapply(.SD, sum), by=.(month, day, origin, dest), .SDcols=vars],
  times = 2
  )

#> Unit: milliseconds
#>      expr         min          lq        mean      median          uq         max neval cld
#>      dplyr 1041.243193 1041.243193 1061.813553 1061.813553 1082.383912 1082.383912     2   b
#>   collapse   10.350356   10.350356   10.428991   10.428991   10.507626   10.507626     2  a 
#> data.table    9.615242    9.615242    9.778382    9.778382    9.941521    9.941521     2  a