代码之家 › 专栏 › 技术社区 › TarJae

如何在对数据进行分类时将head()和tail()与case_一起使用

dplyr r

-1

TarJae · 技术社区 · 4 年前

我尝试使用 head tail 功能:

我的数据帧:

df <- structure(list(x = c(21, 21, 22.8, 21.4, 18.7, 18.1, 14.3, 24.4, 
22.8, 19.2, 17.8, 16.4, 17.3, 15.2, 10.4, 10.4, 14.7, 32.4, 30.4, 
33.9, 21.5, 15.5, 15.2, 13.3, 19.2, 27.3, 26, 30.4, 15.8, 19.7, 
15, 21.4), y = c(160, 160, 108, 258, 360, 225, 360, 146.7, 140.8, 
167.6, 167.6, 275.8, 275.8, 275.8, 472, 460, 440, 78.7, 75.7, 
71.1, 120.1, 318, 304, 350, 400, 79, 120.3, 95.1, 351, 145, 301, 
121)), row.names = c(NA, -32L), class = c("tbl_df", "tbl", "data.frame"


       x     y
   <dbl> <dbl>
 1  21    160 
 2  21    160 
 3  22.8  108 
 4  21.4  258 
 5  18.7  360 
 6  18.1  225 
 7  14.3  360 
 8  24.4  147.
 9  22.8  141.
10  19.2  168.
# ... with 22 more rows

期望输出:

      x     y      z
1  21.0 160.0  top_n
2  21.0 160.0  top_n
3  22.8 108.0  top_n
4  21.4 258.0  top_n
5  18.7 360.0  top_n
6  18.1 225.0  top_n
7  14.3 360.0  top_n
8  24.4 146.7  top_n
9  22.8 140.8  top_n
10 19.2 167.6  top_n
11 17.8 167.6 middle
12 16.4 275.8 middle
13 17.3 275.8 middle
14 15.2 275.8 middle
15 10.4 472.0 middle
16 10.4 460.0 middle
17 14.7 440.0 middle
18 32.4  78.7 middle
19 30.4  75.7 middle
20 33.9  71.1 middle
21 21.5 120.1 middle
22 15.5 318.0 middle
23 15.2 304.0 last_n
24 13.3 350.0 last_n
25 19.2 400.0 last_n
26 27.3  79.0 last_n
27 26.0 120.3 last_n
28 30.4  95.1 last_n
29 15.8 351.0 last_n
30 19.7 145.0 last_n
31 15.0 301.0 last_n
32 21.4 121.0 last_n

df %>%   
  mutate(category = case_when(head(10) ~ "top_10",
                              tail(10) ~ "last_10",
                              TRUE ~ "middle"))

其他可能的解决方案,如使用 row_number() 等

我想学习 head() 和 tail() 内部功能 case_when

1 回复 | 直到 4 年前

Kra.P 4 年前

这可能不是你想要的,但你可以用这些方法得到同样的结果。

as.data.frame

library(dplyr)
library(xts)

`row_number()`

df %>%
  mutate(category = case_when(
    row_number() %in% c(1:10) ~ "top_10",
    row_number() %in% c((max(row_number())-9) : max(row_number()) ) ~ "last_10",
    TRUE ~ "middle"
  )) %>%
  as.data.frame()

`xts::first` 和 `xts::last`

df %>%
  mutate(cat = 1:n()) %>%
  mutate(category = case_when(
    cat %in% first(cat,10) ~ "top_10",
    cat %in% last(cat,10) ~ "last_10",
    TRUE ~ "middle"
  )) %>%
  as.data.frame() %>%
  select(-cat)

`head` 和 `tail`

df %>%
  mutate(cat = 1:n()) %>%
  mutate(category = case_when(
    cat %in% head(cat,10) ~ "top_10",
    cat %in% tail(cat,10) ~ "last_10",
    TRUE ~ "middle"
  )) %>%
  as.data.frame() %>%
  select(-cat)

      x     y category
1  21.0 160.0   top_10
2  21.0 160.0   top_10
3  22.8 108.0   top_10
4  21.4 258.0   top_10
5  18.7 360.0   top_10
6  18.1 225.0   top_10
7  14.3 360.0   top_10
8  24.4 146.7   top_10
9  22.8 140.8   top_10
10 19.2 167.6   top_10
11 17.8 167.6   middle
12 16.4 275.8   middle
13 17.3 275.8   middle
14 15.2 275.8   middle
15 10.4 472.0   middle
16 10.4 460.0   middle
17 14.7 440.0   middle
18 32.4  78.7   middle
19 30.4  75.7   middle
20 33.9  71.1   middle
21 21.5 120.1   middle
22 15.5 318.0   middle
23 15.2 304.0  last_10
24 13.3 350.0  last_10
25 19.2 400.0  last_10
26 27.3  79.0  last_10
27 26.0 120.3  last_10
28 30.4  95.1  last_10
29 15.8 351.0  last_10
30 19.7 145.0  last_10
31 15.0 301.0  last_10
32 21.4 121.0  last_10

如何在对数据进行分类时将head()和tail()与case_一起使用

row_number()

xts::first 和 xts::last

head 和 tail

`row_number()`

`xts::first` 和 `xts::last`

`head` 和 `tail`