library(dplyr)
#>
#> Attaching package: 'dplyr'
#> The following objects are masked from 'package:stats':
#>
#> filter, lag
#> The following objects are masked from 'package:base':
#>
#> intersect, setdiff, setequal, union
library(tidyr)
library(purrr)
just_group <- function(df) {
df %>%
group_by(id, cyl) %>%
summarise(
mpg = mean(mpg),
hp = mean(hp)
) %>%
ungroup()
}
nest_map <- function(df) {
df %>%
nest(-id) %>%
mutate(data = map(data, ~ {
.x %>%
group_by(cyl) %>%
summarise(
mpg = mean(mpg),
hp = mean(hp)
) %>%
ungroup()
})) %>%
unnest()
}
bench::press(
n = 10^(3:5),
{
df <- mtcars %>%
crossing(id = seq_len(n))
bench::mark(
just_group(df),
nest_map(df)
)
}
) -> bm
#> Running with:
#> n
#> 1 1000
#> Warning: Some expressions had a GC in every iteration; so filtering is
#> disabled.
#> 2 10000
#> Warning: Some expressions had a GC in every iteration; so filtering is
#> disabled.
#> 3 100000
#> Warning: Some expressions had a GC in every iteration; so filtering is
#> disabled.
bm
#> # A tibble: 6 x 11
#> expression n min mean median max `itr/sec` mem_alloc
#> <chr> <dbl> <bch:tm> <bch:tm> <bch:tm> <bch:tm> <dbl> <bch:byt>
#> 1 just_grou~ 1000 5.47ms 6.87ms 6.37ms 13.3ms 146. 496.13KB
#> 2 nest_map(~ 1000 2.2s 2.2s 2.2s 2.2s 0.454 12.03MB
#> 3 just_grou~ 10000 51.67ms 56.62ms 54.66ms 66.28ms 17.7 1.61MB
#> 4 nest_map(~ 10000 24.2s 24.2s 24.2s 24.2s 0.0413 115.38MB
#> 5 just_grou~ 100000 897.01ms 897.01ms 897.01ms 897.01ms 1.11 16.03MB
#> 6 nest_map(~ 100000 3.44m 3.44m 3.44m 3.44m 0.00485 1.1GB
#> # ... with 3 more variables: n_gc <dbl>, n_itr <int>, total_time <bch:tm>
ggplot2::autoplot(bm)
#> Error in loadNamespace(name): there is no package called 'ggbeeswarm'Created on 2019-02-05 by the reprex package (v0.2.1.9000)
Session info
devtools::session_info()
#> - Session info ----------------------------------------------------------
#> setting value
#> version R version 3.5.2 (2018-12-20)
#> os Windows 10 x64
#> system x86_64, mingw32
#> ui RTerm
#> language (EN)
#> collate English_United Kingdom.1252
#> ctype English_United Kingdom.1252
#> tz Europe/Helsinki
#> date 2019-02-05
#>
#> - Packages --------------------------------------------------------------
#> package * version date lib
#> assertthat 0.2.0 2017-04-11 [1]
#> backports 1.1.3 2018-12-14 [1]
#> bench 1.0.1 2018-06-06 [1]
#> bindr 0.1.1 2018-03-13 [1]
#> bindrcpp * 0.2.2 2018-03-29 [1]
#> callr 3.1.1 2018-12-21 [1]
#> cli 1.0.1 2018-09-25 [1]
#> colorspace 1.4-0 2019-01-13 [1]
#> crayon 1.3.4 2017-09-16 [1]
#> desc 1.2.0 2018-05-01 [1]
#> devtools 2.0.1 2018-10-26 [1]
#> digest 0.6.18 2018-10-10 [1]
#> dplyr * 0.7.8 2018-11-10 [1]
#> evaluate 0.12 2018-10-09 [1]
#> fansi 0.4.0 2018-12-04 [1]
#> fs 1.2.6 2018-08-23 [1]
#> ggplot2 3.1.0 2018-10-25 [1]
#> glue 1.3.0 2018-07-17 [1]
#> gtable 0.2.0 2016-02-26 [1]
#> highr 0.7 2018-06-09 [1]
#> htmltools 0.3.6 2017-04-28 [1]
#> knitr 1.21 2018-12-10 [1]
#> lazyeval 0.2.1 2017-10-29 [1]
#> magrittr 1.5 2014-11-22 [1]
#> memoise 1.1.0 2017-04-21 [1]
#> munsell 0.5.0 2018-06-12 [1]
#> pillar 1.3.1.9000 2019-01-22 [1]
#> pkgbuild 1.0.2 2018-10-16 [1]
#> pkgconfig 2.0.2 2018-08-16 [1]
#> pkgload 1.0.2 2018-10-29 [1]
#> plyr 1.8.4 2016-06-08 [1]
#> prettyunits 1.0.2 2015-07-13 [1]
#> processx 3.2.1 2018-12-05 [1]
#> profmem 0.5.0 2018-01-30 [1]
#> ps 1.3.0 2018-12-21 [1]
#> purrr * 0.3.0.9000 2019-02-05 [1]
#> R6 2.3.0 2018-10-04 [1]
#> Rcpp 1.0.0 2018-11-07 [1]
#> remotes 2.0.2 2018-10-30 [1]
#> rlang 0.3.1 2019-01-08 [1]
#> rmarkdown 1.11 2018-12-08 [1]
#> rprojroot 1.3-2 2018-01-03 [1]
#> scales 1.0.0 2018-08-09 [1]
#> sessioninfo 1.1.1 2018-11-05 [1]
#> stringi 1.2.4 2018-07-20 [1]
#> stringr 1.3.1 2018-05-10 [1]
#> testthat 2.0.0.9000 2018-05-29 [1]
#> tibble 2.0.99.9000 2019-01-22 [1]
#> tidyr * 0.8.2 2018-10-28 [1]
#> tidyselect 0.2.5 2018-10-11 [1]
#> usethis 1.4.0 2018-08-14 [1]
#> utf8 1.1.4 2018-05-24 [1]
#> withr 2.1.2 2018-03-15 [1]
#> xfun 0.4 2018-10-23 [1]
#> yaml 2.2.0 2018-07-25 [1]
#> source
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.1)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.2)
#> Github (brodieG/fansi@ab11e9c)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.1)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.2)
#> Github (r-lib/pillar@3a54b8d)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.1)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.2)
#> Github (tidyverse/purrr@28a6811)
#> CRAN (R 3.5.1)
#> CRAN (R 3.5.1)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.1)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.1)
#> CRAN (R 3.5.2)
#> Github (r-lib/testthat@ca2280b)
#> Github (tidyverse/tibble@5a6e727)
#> CRAN (R 3.5.1)
#> CRAN (R 3.5.1)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.2)
#> CRAN (R 3.5.2)
#>
#> [1] C:/Users/mikkmart/OneDrive - Orion Corporation/R/win-library/3.5
#> [2] C:/Users/mikkmart/R/R-3.5.2/library
further inspection showed that this was just because of an outdated dplyr version