例如我们需要将一下数据的第二列从and处拆分为两列:before = data.frame(attr = c(1,30,4,6), type=c('foo_and_bar','foo_and_bar_2'))
attr type
1 1 foo_and_bar
2 30 foo_and_bar_2
3 4 foo_and_bar
4 6 foo_and_bar_2
==>
attr type_1 type_2
1 1 foo bar
2 30 foo bar_2
3 4 foo bar
4 6 foo bar_2
- 使用stringr包的str_split_fixed函数
library(stringr)
str_split_fixed(before$type, "_and_", 2)
- 使用do.call函数 (
do.call(what, args, quote = FALSE, envir = parent.frame())
)
before <- data.frame(attr = c(1,30,4,6), type=c('foo_and_bar','foo_and_bar_2'))
out <- strsplit(as.character(before$type),'_and_')
do.call(rbind, out)
- 使用tidyr包
library(dplyr)
library(tidyr)
before <- data.frame(attr = c(1, 30 ,4 ,6 ), type = c('foo_and_bar', 'foo_and_bar_2'))
before %>% separate(type, c("foo", "bar"), "_and_")
- 使用sapply 以及 "["
before$type_1 < sapply(strsplit(as.character(before$type),'_and_'), "[", 1)
before$type_2 < sapply(strsplit(as.character(before$type),'_and_'), "[", 2)
或者
before <- data.frame(attr = c(1,30,4,6), type=c('foo_and_bar','foo_and_bar_2'))
after <- with(before, data.frame(attr = attr))
after <- cbind(after, data.frame(t(sapply(out, `[`))))
names(after)[2:3] <- paste("type", 1:2, sep = "_")
- 使用unlist后重新划分矩阵
before <- data.frame(attr = c(1,30,4,6), type=c('foo_and_bar','foo_and_bar_2'))
tmp <- matrix(unlist(strsplit(as.character(before$type), '_and_')), ncol=2,byrow=TRUE) #you should show how many columns you would get after spliting
after <- cbind(before$attr, as.data.frame(tmp))
names(after) <- c("attr", "type_1", "type_2")