作者：黄天元，复旦大学博士在读，热爱数据科学与开源工具（R），致力于利用数据科学迅速积累行业经验优势和科学知识发现，涉猎内容包括但不限于信息计量、机器学习、数据可视化、应用统计建模、知识图谱等，著有《R语言高效数据处理指南》（《R语言数据高效处理指南》(黄天元)【摘要 书评 试读】- 京东图书）。知乎专栏：R语言数据挖掘。邮箱：huang.tian-yuan@qq.com.欢迎合作交流。
dplyr的1.0.0版本已经发布了，这里针对其多列原位汇总（参考自https://cran.r-project.org/web/packages/dplyr/vignettes/colwise.html）进行一个演示，并给出tidyfst中相对应的操作。
library(pacman)
p_load(tidyfst,dplyr)
# dplyr
starwars %>%
summarise(across(where(is.character), ~ length(unique(.x))))
#> # A tibble: 1 x 8
#> name hair_color skin_color eye_color sex gender homeworld species
#> <int> <int> <int> <int> <int> <int> <int> <int>
#> 1 87 13 31 15 5 3 49 38
# tidyfst
starwars %>%
summarise_vars(is.character,uniqueN)
#> name hair_color skin_color eye_color sex gender homeworld species
#> <int> <int> <int> <int> <int> <int> <int> <int>
#> 1: 87 13 31 15 5 3 49 38
# dplyr
starwars %>%
group_by(species) %>%
filter(n() > 1) %>%
summarise(across(c(sex, gender, homeworld), ~ length(unique(.x))))
#> `summarise()` ungrouping output (override with `.groups` argument)
#> # A tibble: 9 x 4
#> species sex gender homeworld
#> <chr> <int> <int> <int>
#> 1 Droid 1 2 3
#> 2 Gungan 1 1 1
#> 3 Human 2 2 16
#> 4 Kaminoan 2 2 1
#> 5 Mirialan 1 1 1
#> 6 Twi'lek 2 2 1
#> 7 Wookiee 1 1 1
#> 8 Zabrak 1 1 2
#> 9 <NA> 1 1 3
# tidyfst
starwars %>%
group_dt(
by = species,
filter_dt(.N > 1) %>%
summarise_vars("sex|gender|homeworld",uniqueN)
)
#> species sex gender homeworld
#> <char> <int> <int> <int>
#> 1: Human 2 2 16
#> 2: Droid 1 2 3
#> 3: Wookiee 1 1 1
#> 4: Gungan 1 1 1
#> 5: <NA> 1 1 3
#> 6: Zabrak 1 1 2
#> 7: Twi'lek 2 2 1
#> 8: Mirialan 1 1 1
#> 9: Kaminoan 2 2 1
# dplyr
starwars %>%
group_by(homeworld) %>%
filter(n() > 1) %>%
summarise(across(where(is.numeric), ~ mean(.x, na.rm = TRUE)))
#> `summarise()` ungrouping output (override with `.groups` argument)
#> # A tibble: 10 x 4
#> homeworld height mass birth_year
#> <chr> <dbl> <dbl> <dbl>
#> 1 Alderaan 176. 64 43
#> 2 Corellia 175 78.5 25
#> 3 Coruscant 174. 50 91
#> 4 Kamino 208. 83.1 31.5
#> 5 Kashyyyk 231 124 200
#> 6 Mirial 168 53.1 49
#> 7 Naboo 175. 64.2 55
#> 8 Ryloth 179 55 48
#> 9 Tatooine 170. 85.4 54.6
#> 10 <NA> 139. 82 334.
# tidyfst
starwars %>%
group_dt(
by = homeworld,
filter_dt(.N > 1) %>%
summarise_vars(is.numeric,function(x) mean(x,na.rm = TRUE))
)
#> homeworld height mass birth_year
#> <char> <num> <num> <num>
#> 1: Tatooine 169.8000 85.37500 54.64444
#> 2: Naboo 175.4545 64.16667 55.00000
#> 3: Alderaan 176.3333 64.00000 43.00000
#> 4: Kashyyyk 231.0000 124.00000 200.00000
#> 5: Corellia 175.0000 78.50000 25.00000
#> 6: <NA> 138.7500 82.00000 334.33333
#> 7: Kamino 208.3333 83.10000 31.50000
#> 8: Coruscant 173.6667 50.00000 91.00000
#> 9: Ryloth 179.0000 55.00000 48.00000
#> 10: Mirial 168.0000 53.10000 49.00000
# dplyr
df <- data.frame(g = c(1, 1, 2), x = c(-1, 1, 3), y = c(-1, -4, -9))
df %>%
group_by(g) %>%
summarise(across(where(is.numeric), sum))
#> `summarise()` ungrouping output (override with `.groups` argument)
#> # A tibble: 2 x 3
#> g x y
#> <dbl> <dbl> <dbl>
#> 1 1 0 -5
#> 2 2 3 -9
# tidyfst
df %>%
summarise_vars(is.numeric,sum,by = g)
#> g x y
#> <num> <num> <num>
#> 1: 1 0 -5
#> 2: 2 3 -9
操作环境为：
sessionInfo()
#> R version 4.0.0 (2020-04-24)
#> Platform: x86_64-w64-mingw32/x64 (64-bit)
#> Running under: Windows 10 x64 (build 18363)
#>
#> Matrix products: default
#>
#> locale:
#> [1] LC_COLLATE=Chinese (Simplified)_China.936
#> [2] LC_CTYPE=Chinese (Simplified)_China.936
#> [3] LC_MONETARY=Chinese (Simplified)_China.936
#> [4] LC_NUMERIC=C
#> [5] LC_TIME=Chinese (Simplified)_China.936
#>
#> attached base packages:
#> [1] stats graphics grDevices utils datasets methods base
#>
#> loaded via a namespace (and not attached):
#> [1] compiler_4.0.0 magrittr_1.5 tools_4.0.0 htmltools_0.4.0
#> [5] yaml_2.2.1 Rcpp_1.0.4.6 stringi_1.4.6 rmarkdown_2.1
#> [9] highr_0.8 knitr_1.28 stringr_1.4.0 xfun_0.13
#> [13] digest_0.6.25 rlang_0.4.6 evaluate_0.14
稍微进行一些思考，觉得dplyr有点变了。across、where等函数给操作带来了“灵活性”的同事，更难理解，代码也不好撰写。tidyfst将不会让自己与之百分百相同，后面会坚持使用便捷的列选择来完成，优化的路还很长。
