R 将多个因素的级别重新编码到指定范围

R 将多个因素的级别重新编码到指定范围,r,dplyr,forcats,R,Dplyr,Forcats,我有以下数据框: library(tidyverse) df <- tibble(a = c(1, 2, 3, 4, 5), b = c("Y", "N", "N", "Y", "N"), c = c("A", "B", "C", "A", "B&qu

我有以下数据框:

library(tidyverse)
df <- tibble(a = c(1, 2, 3, 4, 5),
             b = c("Y", "N", "N", "Y", "N"),
             c = c("A", "B", "C", "A", "B"))

df <- df %>%
  mutate_if(is.character, funs(as.factor))
我想将所有因子(
b
c
变量)级别重新编码为整数:如果一个因子只有两个级别,则应将其重新编码为{0,1},否则应将其编码为{1,2,3,}级别。因此,输出应为:

      a b     c    
  <dbl> <fct> <fct>
1     1 1     1    
2     2 0     2    
3     3 0     3    
4     4 1     1    
5     5 0     2    
abc
1     1 1     1    
2     2 0     2    
3     3 0     3    
4     4 1     1    
5     5 0     2    
我可以单独(逐个)重新编码变量,但我想知道是否有更方便的方法。

df%
df <- df %>%
  mutate_if(
    is.character,
    function(x) {
      out <- as.integer(as.factor(x))
      if (n_distinct(out) == 2) out <- out - 1L
      out
    }
  )
df

#       a     b     c
#   <dbl> <int> <int>
# 1     1     1     1
# 2     2     0     2
# 3     3     0     3
# 4     4     1     1
# 5     5     0     2
变异( 这是我的性格, 功能(x){ out这是否有效:

> library(dplyr)
> df %>% mutate(b_fac = match(b,unique(b)) - 1, c_fac = match(c, unique(c))) %>% 
+       mutate(b_fac = ifelse(b_fac == 1, 0, 1)) %>% mutate(b_fac = as.factor(b_fac), c_fac = as.factor(c_fac))  %>% 
+       select(-2,-3) %>% rename(b = b_fac, c = c_fac)
# A tibble: 5 x 3
      a b     c    
  <dbl> <fct> <fct>
1     1 1     1    
2     2 0     2    
3     3 0     3    
4     4 1     1    
5     5 0     2    
> 
>库(dplyr)
>df%>%突变(b_fac=match(b,unique(b))-1,c_fac=match(c,unique(c)))%>%
+突变(b_fac=ifelse(b_fac==1,0,1))%>%突变(b_fac=as.factor(b_fac),c_fac=as.factor(c_fac))%>%
+选择(-2,-3)%>%重命名(b=b\u fac,c=c\u fac)
#一个tibble:5x3
a、b、c
1     1 1     1    
2     2 0     2    
3     3 0     3    
4     4 1     1    
5     5 0     2    
> 

一个
dplyr
选项可以是:

df %>%
 mutate(across(where(is.factor), 
               ~ if(n_distinct(.) == 2) factor(., labels = 0:1) else factor(., labels = 1:n_distinct(.))))

      a b     c    
  <dbl> <fct> <fct>
1     1 1     1    
2     2 0     2    
3     3 0     3    
4     4 1     1    
5     5 0     2
df%>%
突变(跨越(其中(是因子),
~if(n_distinct(.)==2)因子(,labels=0:1)else因子(,labels=1:n_distinct()
a、b、c
1     1 1     1    
2     2 0     2    
3     3 0     3    
4     4 1     1    
5     5 0     2
df %>%
 mutate(across(where(is.factor), 
               ~ if(n_distinct(.) == 2) factor(., labels = 0:1) else factor(., labels = 1:n_distinct(.))))

      a b     c    
  <dbl> <fct> <fct>
1     1 1     1    
2     2 0     2    
3     3 0     3    
4     4 1     1    
5     5 0     2