如何生成一组依赖于R中具有相同前缀的其他几个列中的值的虚拟变量?

Question

我有一个数据框架，我试图把我可以用于我的分析，看起来如下格式:

<表类> ID 名称 年 K1 K2 … K50 tbody><<tr>1合同XYZ2000交通大象2协议ABC2003笔音乐3文档1232003大象4空白2004音乐交通

这对你有帮助吗?

library(tidyverse)
document <- data.frame(
stringsAsFactors = FALSE,
ID = c(1L, 2L, 3L, 4L),
Name = c("Contract XYZ","Agreement ABC",
"Document 123","Empty Space"),
Year = c(2000L, 2003L, 2003L, 2004L),
K1 = c("transport", "pens", "elephants", "music"),
K2 = c("elephants", "music", NA, NA),
K50 = c(NA, NA, NA, "transport")
)
document %>%
pivot_longer(starts_with("K")) %>%
select(-name) %>%
filter(! is.na(value)) %>%
mutate(has_property = 1) %>%
pivot_wider(names_from = value, values_from = has_property)
#> # A tibble: 4 x 7
#>      ID Name           Year transport elephants  pens music
#>   <int> <chr>         <int>     <dbl>     <dbl> <dbl> <dbl>
#> 1     1 Contract XYZ   2000         1         1    NA    NA
#> 2     2 Agreement ABC  2003        NA        NA     1     1
#> 3     3 Document 123   2003        NA         1    NA    NA
#> 4     4 Empty Space    2004         1        NA    NA     1

^{由reprex包(v2.0.1)在2021-09-21创建}

我们可以使用具有dummy_columns功能的fastDummies包。使用来自@danlooo

的示例数据

document %>% pivot_longer(matches('K\d+'), names_to = NULL) %>%
filter(!is.na(value)) %>%
fastDummies::dummy_columns('value') %>%
rename_with(~str_remove(.x, '^value_'), starts_with('value_'))
# A tibble: 7 x 8
ID Name           Year value     elephants music  pens transport
<int> <chr>         <int> <chr>         <int> <int> <int>     <int>
1     1 Contract XYZ   2000 transport         0     0     0         1
2     1 Contract XYZ   2000 elephants         1     0     0         0
3     2 Agreement ABC  2003 pens              0     0     1         0
4     2 Agreement ABC  2003 music             0     1     0         0
5     3 Document 123   2003 elephants         1     0     0         0
6     4 Empty Space    2004 music             0     1     0         0
7     4 Empty Space    2004 transport         0     0     0         1

document <- data.frame(
stringsAsFactors = FALSE,
ID = c(1L, 2L, 3L, 4L),
Name = c("Contract XYZ","Agreement ABC",
"Document 123","Empty Space"),
Year = c(2000L, 2003L, 2003L, 2004L),
K1 = c("transport", "pens", "elephants", "music"),
K2 = c("elephants", "music", NA, NA),
K50 = c(NA, NA, NA, "transport")
)
> document
ID          Name Year        K1        K2       K50
1  1  Contract XYZ 2000 transport elephants      <NA>
2  2 Agreement ABC 2003      pens     music      <NA>
3  3  Document 123 2003 elephants      <NA>      <NA>
4  4   Empty Space 2004     music      <NA> transport