我们可以用<代码>desc加以总结,以便从一开始就获得缺失的数值。
flights %>%
arrange(desc(is.na(dep_time)),
desc(is.na(dep_delay)),
desc(is.na(arr_time)),
desc(is.na(arr_delay)),
desc(is.na(tailnum)),
desc(is.na(air_time)))
只有在根据这些变量得出的变量中才发现了NA值。
names(flights)[colSums(is.na(flights)) >0]
#[1] "dep_time" "dep_delay" "arr_time" "arr_delay" "tailnum" "air_time"
Instead of passing each variable name at a time, we can also use NSE arrange_
nm1 <- paste0("desc(is.na(", names(flights)[colSums(is.na(flights)) >0], "))")
r1 <- flights %>%
arrange_(.dots = nm1)
r1 %>%
head()
#year month day dep_time sched_dep_time dep_delay arr_time sched_arr_time arr_delay carrier flight tailnum
# <int> <int> <int> <int> <int> <dbl> <int> <int> <dbl> <chr> <int> <chr>
#1 2013 1 2 NA 1545 NA NA 1910 NA AA 133 <NA>
#2 2013 1 2 NA 1601 NA NA 1735 NA UA 623 <NA>
#3 2013 1 3 NA 857 NA NA 1209 NA UA 714 <NA>
#4 2013 1 3 NA 645 NA NA 952 NA UA 719 <NA>
#5 2013 1 4 NA 845 NA NA 1015 NA 9E 3405 <NA>
#6 2013 1 4 NA 1830 NA NA 2044 NA 9E 3716 <NA>
#Variables not shown: origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>,
# time_hour <time>.
Update
With the newer versions of tidyverse (dplyr_0.7.3
, rlang_0.1.2
) , we can also make use of arrange_at
, arrange_all
, arrange_if
nm1 <- names(flights)[colSums(is.na(flights)) >0]
r2 <- flights %>%
arrange_at(vars(nm1), funs(desc(is.na(.))))
或使用<条码>
f <- rlang::as_function(~ any(is.na(.)))
r3 <- flights %>%
arrange_if(f, funs(desc(is.na(.))))
identical(r1, r2)
#[1] TRUE
identical(r1, r3)
#[1] TRUE