Question

这确实是这个问题的重复 r-split-string-using-tidyrseparate，但我不能将MWE用于我的目的，因为我不知道如何调整正则表达式。我基本上想要相同的东西，但在最后一个下划线之后拆分变量。

原因：我有一些数据，其中某些列显示多次相同的因子/类型。我想我可以在类型字符串之前将值变量分开并将其再次扩展为具有较少列的宽格式。我的问题是我的变量名有不同的下划线，我想学习如何在我事先添加的最后一个下划线之后分开。

MWE

library(tidyr)
library(data.table)
dt<-data.table(Name=c("A","B","C"),Var_1_EVU=c(2,NA,NA),Var_1_BdS=c(NA,3,4),Var_2_BdS=c(NA,3,4))
dt.long<-melt(dt, id.vars=c("Name"))
dt.long<-separate(dt.long,variable, c("test","type"), sep='/[^_]*$/')
dt.wide<-spread(dt.long,key=Name,value=value)

我想要像

这样的东西

   Name type Var1 Var2
1:    A  BdS   NA   NA
2:    A  EVU    2   NA
3:    B  BdS    3    3
4:    B  EVU   NA   NA
5:    C  BdS    4    4
6:    C  EVU   NA   NA

Answer 1

library(tidyr)

df <- data.frame(Name = c("A","B","C"),
                 Var_1_EVU = c(2,NA,NA),
                 Var_1_BdS = c(NA,3,4),
                 Var_2_BdS = c(NA,3,4))

df %>% 
  gather("type", "value", -Name) %>% 
  separate(type, into = c("type", "type_num", "var")) %>% 
  unite(type, type, type_num, sep = "") %>% 
  spread(type, value)

#   Name var Var1 Var2
# 1    A BdS   NA   NA
# 2    A EVU    2   NA
# 3    B BdS    3    3
# 4    B EVU   NA   NA
# 5    C BdS    4    4
# 6    C EVU   NA   NA

使用tidyr::extract来处理具有任意数量下划线的varnames的示例...

library(dplyr)
library(tidyr)

df <- data.frame(Name = c("A","B","C"),
                 Var_x_1_EVU = c(2,NA,NA),
                 Var_x_1_BdS = c(NA,3,4),
                 Var_x_y_2_BdS = c(NA,3,4))

df %>% 
  gather("col_name", "value", -Name) %>% 
  extract(col_name, c("var", "type"), "(.*)_(.*)") %>% 
  spread(var, value)

#   Name type Var_x_1 Var_x_y_2
# 1    A  BdS      NA        NA
# 2    A  EVU       2        NA
# 3    B  BdS       3         3
# 4    B  EVU      NA        NA
# 5    C  BdS       4         4
# 6    C  EVU      NA        NA

您可以通过首先使用mutate(n = row_number())添加行号列/变量来避免重复观察的潜在问题，以使每个观察都是唯一的，并且可以避免tidyr::extract被magrittr屏蔽通过tidyr::extract ...

明确地调用它

library(dplyr)
library(tidyr)
library(data.table)
library(magrittr)

dt <- data.table(Name = c("A", "A", "B", "C"),
                 Var_1_EVU = c(1, 2, NA, NA),
                 Var_1_BdS = c(1, NA, 3, 4),
                 Var_x_2_BdS = c(1, NA, 3, 4))

dt %>% 
  mutate(n = row_number()) %>% 
  gather("col_name", "value", -n, -Name) %>% 
  tidyr::extract(col_name, c("var", "type"), "(.*)_(.*)") %>% 
  spread(var, value)

#   Name n type Var_1 Var_x_2
# 1    A 1  BdS     1       1
# 2    A 1  EVU     1      NA
# 3    A 2  BdS    NA      NA
# 4    A 2  EVU     2      NA
# 5    B 3  BdS     3       3
# 6    B 3  EVU    NA      NA
# 7    C 4  BdS     4       4
# 8    C 4  EVU    NA      NA

Answer 2

这是使用tstrsplit / melt / dcast的替代data.table解决方案在这种情况下，我个人会坚持使用data.table，因为spread没有fun参数，因此，如果再次传播时有欺骗行为，则会出现错误。< / p>

library(magrittr) # people like pipes these days
dt %>%
  # convert ot long format like you did
  melt(., id = "Name") %>% 
  # split by the last underscore
  .[, c("variable", "grp") := tstrsplit(variable, "_(?!.*_)", perl = TRUE)] %>% 
  # convert back to wide format
  dcast(., Name + grp ~ variable) 

#    Name grp Var_1 Var_2
# 1:    A BdS    NA    NA
# 2:    A EVU     2    NA
# 3:    B BdS     3     3
# 4:    B EVU    NA    NA
# 5:    C BdS     4     4
# 6:    C EVU    NA    NA

最后一个下划线后分隔字符串

2 个答案: