r - Dplyr 对分组数据同时按值过滤顶行和底行

Question

# Sample dataframe
set.seed(123)
d = data.frame(x = runif(120), grp = gl(3, 40))

# Select top_n
d %>%
  group_by(grp) %>%
  top_n(n=3, wt=x)

如何在同一管道内选择顶部和底部观测值？已尝试以下方法但不起作用

# helper function
my_top_bott = function(x, n, wt) {
      x1 = x %>% top_n(n=n, wt=wt)
      x2 = x %>% top_n(n=n, wt=-wt)
      x = bind_rows(x1, x2)
      return(x)
    }

# Pipe
d %>%
      group_by(grp) %>%
      my_top_bott(., n=3, wt=x)

Answer 1

一种可能性是:

d %>%
 group_by(grp) %>%
 filter(dense_rank(x) <= 3 | dense_rank(desc(x)) <= 3)

         x grp  
      <dbl> <fct>
 1 0.0456   1    
 2 0.957    1    
 3 0.0421   1    
 4 0.994    1    
 5 0.963    1    
 6 0.0246   1    
 7 0.858    2    
 8 0.0458   2    
 9 0.895    2    
10 0.0948   2    
11 0.815    2    
12 0.000625 2    
13 0.103    3    
14 0.985    3    
15 0.0936   3    
16 0.954    3    
17 0.0607   3    
18 0.954    3 

或者@IceCreamToucan提出的可能性:

d %>%
 group_by(grp) %>%
 filter(!between(dense_rank(x), 3 + 1, n() - 3))

或者涉及match()的可能性:

d %>%
    group_by(grp) %>%
    filter(!is.na(x[match(x, sort(x)[c(1:3, (n()-2):n())])]))