a <- data.frame("geneid1"=rep("TabHLH1",3),"geneid2"=c("TabHLH2.1","TabHLH2.2","TabHLH2.3"),"geneid3"=rep("TabHLH3",3))
结果如下：
geneid1 geneid2 geneid3
1 TabHLH1 TabHLH2.1 TabHLH3
2 TabHLH1 TabHLH2.2 TabHLH3
3 TabHLH1 TabHLH2.3 TabHLH3
加载函数包
library(dplyr)
library(tidyr)
将第二列以“.”分列
b <- a %>% separate(geneid2, c("gene","id"), "[.]")
结果如下
geneid1 gene id geneid3
1 TabHLH1 TabHLH2 1 TabHLH3
2 TabHLH1 TabHLH2 2 TabHLH3
3 TabHLH1 TabHLH2 3 TabHLH3
R中根据匹配原则将一列拆分为几列的方法
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
1. 使用stringr包的str_split_fixed函数
library(stringr)
str_split_fixed(before$type, "_and_", 2)
2. 使用do.call函数 （do.call(what, args, quote = FALSE, envir = parent.frame())）
before <- data.frame(attr = c(1,30,4,6), type=c('foo_and_bar','foo_and_bar_2'))
out <- strsplit(as.character(before$type),'_and_')
do.call(rbind, out)
3. 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_")
4. 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 = "_")
5. 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")
标签: R
怎么用R语言把表格CSV文件中的数据变成一列，并且行名为原列名呢，1，csv文件，可以用fread函数读取，命名,为dd
2，数据变为一列，如果没有ID这一列，全部都是性状，可以这样运行：melt(dd)，达到的效果如下：
