blocks|key|858777|text|使用stringr::str_split_fixed|type|unstyled|depth|inlineStyleRanges|offset|length|style|CODE|entityRanges|data|858778|library(stringr)
str_split_fixed(before$type,+"_and_",+2)|code-block|syntax|javascript|858779|entityMap^0|2|O|0|0^^$0|@$1|2|3|4|5|6|7|M|8|@$9|N|A|O|B|C]]|D|@]|E|$]]|$1|F|3|G|5|H|7|P|8|@]|D|@]|E|$I|J]]|$1|K|3|-4|5|6|7|Q|8|@]|D|@]|E|$]]]|L|$]]

Use <code>stringr::str_split_fixed</code>

<pre><code>library(stringr)
str_split_fixed(before$type, "_and_", 2)
</code></pre>

blocks|key|858809|text|另一种选择是使用新的tidyr包。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|858810|library(dplyr)
library(tidyr)

before+<-+data.frame(
++attr+=+c(1,+30+,4+,6+),+
++type+=+c('foo_and_bar',+'foo_and_bar_2')
)

before+%25>%25
++separate(type,+c("foo",+"bar"),+"_and_")

##+++attr+foo+++bar
##+1++++1+foo+++bar
##+2+++30+foo+bar_2
##+3++++4+foo+++bar
##+4++++6+foo+bar_2|code-block|syntax|javascript|858811|entityMap^0|0|0^^$0|@$1|2|3|4|5|6|7|I|8|@]|9|@]|A|$]]|$1|B|3|C|5|D|7|J|8|@]|9|@]|A|$E|F]]|$1|G|3|-4|5|6|7|K|8|@]|9|@]|A|$]]]|H|$]]

Another option is to use the new tidyr package.

<pre><code>library(dplyr)
library(tidyr)

before &lt;- data.frame(
 attr = c(1, 30 ,4 ,6 ), 
 type = c('foo_and_bar', 'foo_and_bar_2')
)

before %&gt;%
 separate(type, c("foo", "bar"), "_and_")

## attr foo bar
## 1 1 foo bar
## 2 30 foo bar_2
## 3 4 foo bar
## 4 6 foo bar_2
</code></pre>

blocks|key|858733|text|还有另一种方法:在out上使用rbind|type|unstyled|depth|inlineStyleRanges|offset|length|style|CODE|entityRanges|data|858734|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)

+++++[,1]++[,2]+++
[1,]+"foo"+"bar"++
[2,]+"foo"+"bar_2"
[3,]+"foo"+"bar"++
[4,]+"foo"+"bar_2"|code-block|syntax|javascript|858735|并将它们结合起来：|858736|data.frame(before$attr,+do.call(rbind,+out))|858737|entityMap^0|9|3|F|5|0|0|0|0^^$0|@$1|2|3|4|5|6|7|Q|8|@$9|R|A|S|B|C]|$9|T|A|U|B|C]]|D|@]|E|$]]|$1|F|3|G|5|H|7|V|8|@]|D|@]|E|$I|J]]|$1|K|3|L|5|6|7|W|8|@]|D|@]|E|$]]|$1|M|3|N|5|H|7|X|8|@]|D|@]|E|$I|J]]|$1|O|3|-4|5|6|7|Y|8|@]|D|@]|E|$]]]|P|$]]

Yet another approach: use <code>rbind</code> on <code>out</code>:

<pre><code>before &lt;- data.frame(attr = c(1,30,4,6), type=c('foo_and_bar','foo_and_bar_2')) 
out &lt;- strsplit(as.character(before$type),'_and_') 
do.call(rbind, out)

 [,1] [,2] 
[1,] "foo" "bar" 
[2,] "foo" "bar_2"
[3,] "foo" "bar" 
[4,] "foo" "bar_2"
</code></pre>

And to combine:

<pre><code>data.frame(before$attr, do.call(rbind, out))
</code></pre>

blocks|key|858621|text|请注意，带有"[“的sapply可用于提取这些列表中的第一项或第二项，因此：|type|unstyled|depth|inlineStyleRanges|entityRanges|data|858622|before$type_1+<-+sapply(strsplit(as.character(before$type),'_and_'),+"[",+1)
before$type_2+<-+sapply(strsplit(as.character(before$type),'_and_'),+"[",+2)
before$type+<-+NULL|code-block|syntax|javascript|858623|下面是一个gsub方法：|858624|before$type_1+<-+gsub("_and_.%2B$",+"",+before$type)
before$type_2+<-+gsub("%5E.%2B_and_",+"",+before$type)
before$type+<-+NULL|858625|entityMap^0|0|0|0|0^^$0|@$1|2|3|4|5|6|7|M|8|@]|9|@]|A|$]]|$1|B|3|C|5|D|7|N|8|@]|9|@]|A|$E|F]]|$1|G|3|H|5|6|7|O|8|@]|9|@]|A|$]]|$1|I|3|J|5|D|7|P|8|@]|9|@]|A|$E|F]]|$1|K|3|-4|5|6|7|Q|8|@]|9|@]|A|$]]]|L|$]]

Notice that sapply with "[" can be used to extract either the first or second items in those lists so:

<pre><code>before$type_1 &lt;- sapply(strsplit(as.character(before$type),'_and_'), "[", 1)
before$type_2 &lt;- sapply(strsplit(as.character(before$type),'_and_'), "[", 2)
before$type &lt;- NULL
</code></pre>

And here's a gsub method:

<pre><code>before$type_1 &lt;- gsub("_and_.+$", "", before$type)
before$type_2 &lt;- gsub("^.+_and_", "", before$type)
before$type &lt;- NULL
</code></pre>

blocks|key|858770|text|下面是一个与aniko的解决方案相同的单行代码，但使用的是hadley的stringr包：|type|unstyled|depth|inlineStyleRanges|entityRanges|data|858771|do.call(rbind,+str_split(before$type,+'_and_'))|code-block|syntax|javascript|858772|entityMap^0|0|0^^$0|@$1|2|3|4|5|6|7|I|8|@]|9|@]|A|$]]|$1|B|3|C|5|D|7|J|8|@]|9|@]|A|$E|F]]|$1|G|3|-4|5|6|7|K|8|@]|9|@]|A|$]]]|H|$]]

here is a one liner along the same lines as aniko's solution, but using hadley's stringr package:

<pre><code>do.call(rbind, str_split(before$type, '_and_'))
</code></pre>

blocks|key|858845|text|要添加选项，您还可以使用我的splitstackshape::cSplit函数，如下所示：|type|unstyled|depth|inlineStyleRanges|offset|length|style|CODE|entityRanges|data|858846|library(splitstackshape)
cSplit(before,+"type",+"_and_")
#++++attr+type_1+type_2
#+1:++++1++++foo++++bar
#+2:+++30++++foo++bar_2
#+3:++++4++++foo++++bar
#+4:++++6++++foo++bar_2|code-block|syntax|javascript|858847|entityMap^0|E|N|0|0^^$0|@$1|2|3|4|5|6|7|M|8|@$9|N|A|O|B|C]]|D|@]|E|$]]|$1|F|3|G|5|H|7|P|8|@]|D|@]|E|$I|J]]|$1|K|3|-4|5|6|7|Q|8|@]|D|@]|E|$]]]|L|$]]

To add to the options, you could also use my <code>splitstackshape::cSplit</code> function like this:

<pre><code>library(splitstackshape)
cSplit(before, "type", "_and_")
# attr type_1 type_2
# 1: 1 foo bar
# 2: 30 foo bar_2
# 3: 4 foo bar
# 4: 6 foo bar_2
</code></pre>

blocks|key|858684|text|一种简单的方法是使用sapply()和[函数：|type|unstyled|depth|inlineStyleRanges|offset|length|style|CODE|entityRanges|data|858685|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_')|code-block|syntax|javascript|858686|例如：|858687|>+data.frame(t(sapply(out,+`[`)))
+++X1++++X2
1+foo+++bar
2+foo+bar_2
3+foo+++bar
4+foo+bar_2|858688|sapply()的结果是一个矩阵，需要转置和转换回一个数据框，然后进行一些简单的操作就可以得到你想要的结果：|858689|after+<-+with(before,+data.frame(attr+=+attr))
after+<-+cbind(after,+data.frame(t(sapply(out,+`[`))))
names(after)[2:3]+<-+paste("type",+1:2,+sep+=+"_")|858690|此时，after就是您想要的|858691|>+after
++attr+type_1+type_2
1++++1++++foo++++bar
2+++30++++foo++bar_2
3++++4++++foo++++bar
4++++6++++foo++bar_2|858692|entityMap^0|A|8|J|1|0|0|0|0|0|8|0|0|3|5|0|0^^$0|@$1|2|3|4|5|6|7|Y|8|@$9|Z|A|10|B|C]|$9|11|A|12|B|C]]|D|@]|E|$]]|$1|F|3|G|5|H|7|13|8|@]|D|@]|E|$I|J]]|$1|K|3|L|5|6|7|14|8|@]|D|@]|E|$]]|$1|M|3|N|5|H|7|15|8|@]|D|@]|E|$I|J]]|$1|O|3|P|5|6|7|16|8|@$9|17|A|18|B|C]]|D|@]|E|$]]|$1|Q|3|R|5|H|7|19|8|@]|D|@]|E|$I|J]]|$1|S|3|T|5|6|7|1A|8|@$9|1B|A|1C|B|C]]|D|@]|E|$]]|$1|U|3|V|5|H|7|1D|8|@]|D|@]|E|$I|J]]|$1|W|3|-4|5|6|7|1E|8|@]|D|@]|E|$]]]|X|$]]

An easy way is to use <code>sapply()</code> and the <code>[</code> function:

<pre><code>before &lt;- data.frame(attr = c(1,30,4,6), type=c('foo_and_bar','foo_and_bar_2'))
out &lt;- strsplit(as.character(before$type),'_and_')
</code></pre>

For example:

<pre><code>&gt; data.frame(t(sapply(out, `[`)))
 X1 X2
1 foo bar
2 foo bar_2
3 foo bar
4 foo bar_2
</code></pre>

<code>sapply()</code>'s result is a matrix and needs transposing and casting back to a data frame. It is then some simple manipulations that yield the result you wanted:

<pre><code>after &lt;- with(before, data.frame(attr = attr))
after &lt;- cbind(after, data.frame(t(sapply(out, `[`))))
names(after)[2:3] &lt;- paste("type", 1:2, sep = "_")
</code></pre>

At this point, <code>after</code> is what you wanted

<pre><code>&gt; after
 attr type_1 type_2
1 1 foo bar
2 30 foo bar_2
3 4 foo bar
4 6 foo bar_2
</code></pre>

blocks|key|858905|text|下面是一个基本的R+one行，它与许多以前的解决方案重叠，但返回一个具有正确名称的data.frame。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|858906|out+<-+setNames(data.frame(before$attr,
++++++++++++++++++do.call(rbind,+strsplit(as.character(before$type),
++++++++++++++++++++++++++++++++++++++++++split="_and_"))),
++++++++++++++++++c("attr",+paste0("type_",+1:2)))
out
++attr+type_1+type_2
1++++1++++foo++++bar
2+++30++++foo++bar_2
3++++4++++foo++++bar
4++++6++++foo++bar_2|code-block|syntax|javascript|858907|它使用strsplit来分解变量，使用data.frame和do.call/rbind将数据放回data.frame中。额外的增量改进是使用setNames向data.frame添加变量名。|offset|length|style|CODE|858908|entityMap^0|0|0|3|8|J|A|U|7|12|5|1Y|8|0^^$0|@$1|2|3|4|5|6|7|O|8|@]|9|@]|A|$]]|$1|B|3|C|5|D|7|P|8|@]|9|@]|A|$E|F]]|$1|G|3|H|5|6|7|Q|8|@$I|R|J|S|K|L]|$I|T|J|U|K|L]|$I|V|J|W|K|L]|$I|X|J|Y|K|L]|$I|Z|J|10|K|L]]|9|@]|A|$]]|$1|M|3|-4|5|6|7|11|8|@]|9|@]|A|$]]]|N|$]]

Here is a base R one liner that overlaps a number of previous solutions, but returns a data.frame with the proper names.

<pre><code>out &lt;- setNames(data.frame(before$attr,
 do.call(rbind, strsplit(as.character(before$type),
 split="_and_"))),
 c("attr", paste0("type_", 1:2)))
out
 attr type_1 type_2
1 1 foo bar
2 30 foo bar_2
3 4 foo bar
4 6 foo bar_2
</code></pre>

It uses <code>strsplit</code> to break up the variable, and <code>data.frame</code> with <code>do.call</code>/<code>rbind</code> to put the data back into a data.frame. The additional incremental improvement is the use of <code>setNames</code> to add variable names to the data.frame.

blocks|key|1073530|text|这个问题已经很老了，但我将添加我发现的目前最简单的解决方案。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1073531|library(reshape2)
before+=+data.frame(attr+=+c(1,30,4,6),+type=c('foo_and_bar','foo_and_bar_2'))
newColNames+<-+c("type1",+"type2")
newCols+<-+colsplit(before$type,+"_and_",+newColNames)
after+<-+cbind(before,+newCols)
after$type+<-+NULL
after|code-block|syntax|javascript|1073532|entityMap^0|0|0^^$0|@$1|2|3|4|5|6|7|I|8|@]|9|@]|A|$]]|$1|B|3|C|5|D|7|J|8|@]|9|@]|A|$E|F]]|$1|G|3|-4|5|6|7|K|8|@]|9|@]|A|$]]]|H|$]]

This question is pretty old but I'll add the solution I found the be the simplest at present.

<pre><code>library(reshape2)
before = data.frame(attr = c(1,30,4,6), type=c('foo_and_bar','foo_and_bar_2'))
newColNames &lt;- c("type1", "type2")
newCols &lt;- colsplit(before$type, "_and_", newColNames)
after &lt;- cbind(before, newCols)
after$type &lt;- NULL
after
</code></pre>

blocks|key|858998|text|基本但可能很慢：|type|unstyled|depth|inlineStyleRanges|entityRanges|data|858999|n+<-+1
for(i+in+strsplit(as.character(before$type),'_and_')){
+++++before[n,+'type_1']+<-+i[[1]]
+++++before[n,+'type_2']+<-+i[[2]]
+++++n+<-+n+%2B+1
}

##+++attr++++++++++type+type_1+type_2
##+1++++1+++foo_and_bar++++foo++++bar
##+2+++30+foo_and_bar_2++++foo++bar_2
##+3++++4+++foo_and_bar++++foo++++bar
##+4++++6+foo_and_bar_2++++foo++bar_2|code-block|syntax|javascript|859000|entityMap^0|0|0^^$0|@$1|2|3|4|5|6|7|I|8|@]|9|@]|A|$]]|$1|B|3|C|5|D|7|J|8|@]|9|@]|A|$E|F]]|$1|G|3|-4|5|6|7|K|8|@]|9|@]|A|$]]]|H|$]]

base but probably slow:

<pre><code>n &lt;- 1
for(i in strsplit(as.character(before$type),'_and_')){
 before[n, 'type_1'] &lt;- i[[1]]
 before[n, 'type_2'] &lt;- i[[2]]
 n &lt;- n + 1
}

## attr type type_1 type_2
## 1 1 foo_and_bar foo bar
## 2 30 foo_and_bar_2 foo bar_2
## 3 4 foo_and_bar foo bar
## 4 6 foo_and_bar_2 foo bar_2
</code></pre>

blocks|key|1073281|text|如果您想继续使用strsplit()，另一种方法是使用unlist()命令。这里有一个沿着这些路线的解决方案。|type|unstyled|depth|inlineStyleRanges|offset|length|style|CODE|entityRanges|data|1073282|tmp+<-+matrix(unlist(strsplit(as.character(before$type),+'_and_')),+ncol=2,
+++byrow=TRUE)
after+<-+cbind(before$attr,+as.data.frame(tmp))
names(after)+<-+c("attr",+"type_1",+"type_2")|code-block|syntax|javascript|1073283|entityMap^0|8|A|R|8|0|0^^$0|@$1|2|3|4|5|6|7|M|8|@$9|N|A|O|B|C]|$9|P|A|Q|B|C]]|D|@]|E|$]]|$1|F|3|G|5|H|7|R|8|@]|D|@]|E|$I|J]]|$1|K|3|-4|5|6|7|S|8|@]|D|@]|E|$]]]|L|$]]

Another approach if you want to stick with <code>strsplit()</code> is to use the <code>unlist()</code> command. Here's a solution along those lines.

<pre><code>tmp &lt;- matrix(unlist(strsplit(as.character(before$type), '_and_')), ncol=2,
 byrow=TRUE)
after &lt;- cbind(before$attr, as.data.frame(tmp))
names(after) &lt;- c("attr", "type_1", "type_2")
</code></pre>

blocks|key|859054|text|这是另一个base+R解决方案。我们可以使用read.table，但由于它只接受一个字节的sep参数，并且这里有多字节分隔符，我们可以使用gsub将多字节分隔符替换为任何单字节分隔符，并将其用作read.table中的sep参数|type|unstyled|depth|inlineStyleRanges|offset|length|style|CODE|entityRanges|data|859055|cbind(before[1],+read.table(text+=+gsub('_and_',+'\t',+before$type),+
+++++++++++++++++sep+=+"\t",+col.names+=+paste0("type_",+1:2)))

#++attr+type_1+type_2
#1++++1++++foo++++bar
#2+++30++++foo++bar_2
#3++++4++++foo++++bar
#4++++6++++foo++bar_2|code-block|syntax|javascript|859056|在这种情况下，我们还可以通过将其替换为默认的sep参数来缩短它，这样我们就不必显式地提到它|859057|cbind(before[1],+read.table(text+=+gsub('_and_',+'+',+before$type),+
+++++++++++++++++col.names+=+paste0("type_",+1:2)))|859058|entityMap^0|M|A|19|3|1X|4|2P|A|31|3|0|0|M|3|0|0^^$0|@$1|2|3|4|5|6|7|Q|8|@$9|R|A|S|B|C]|$9|T|A|U|B|C]|$9|V|A|W|B|C]|$9|X|A|Y|B|C]|$9|Z|A|10|B|C]]|D|@]|E|$]]|$1|F|3|G|5|H|7|11|8|@]|D|@]|E|$I|J]]|$1|K|3|L|5|6|7|12|8|@$9|13|A|14|B|C]]|D|@]|E|$]]|$1|M|3|N|5|H|7|15|8|@]|D|@]|E|$I|J]]|$1|O|3|-4|5|6|7|16|8|@]|D|@]|E|$]]]|P|$]]

Here is another base R solution. We can use <code>read.table</code> but since it accepts only one-byte <code>sep</code> argument and here we have multi-byte separator we can use <code>gsub</code> to replace the multibyte separator to any one-byte separator and use that as <code>sep</code> argument in <code>read.table</code>

<pre><code>cbind(before[1], read.table(text = gsub('_and_', '\t', before$type), 
 sep = "\t", col.names = paste0("type_", 1:2)))

# attr type_1 type_2
#1 1 foo bar
#2 30 foo bar_2
#3 4 foo bar
#4 6 foo bar_2
</code></pre>

In this case, we can also make it shorter by replacing it with default <code>sep</code> argument so we don't have to mention it explicitly

<pre><code>cbind(before[1], read.table(text = gsub('_and_', ' ', before$type), 
 col.names = paste0("type_", 1:2)))
</code></pre>

blocks|key|1073666|text|令人惊讶的是，另一个tidyverse解决方案仍然缺失--您也可以使用带有正则表达式的tidyr::extract。|type|unstyled|depth|inlineStyleRanges|offset|length|style|CODE|entityRanges|data|1073667|library(tidyr)
before+<-+data.frame(attr+=+c(1,+30,+4,+6),+type+=+c("foo_and_bar",+"foo_and_bar_2"))

##+regex+-+getting+all+characters+except+an+underscore+till+the+first+underscore,+
##+inspired+by+Akrun+https://stackoverflow.com/a/49752920/7941188+

extract(before,+col+=+type,+into+=+paste0("type",+1:2),+regex+=+"(%5E[%5E_]*)_(.*)")
#>+++attr+type1+++++type2
#>+1++++1+++foo+++and_bar
#>+2+++30+++foo+and_bar_2
#>+3++++4+++foo+++and_bar
#>+4++++6+++foo+and_bar_2|code-block|syntax|javascript|1073668|entityMap^0|17|E|0|0^^$0|@$1|2|3|4|5|6|7|M|8|@$9|N|A|O|B|C]]|D|@]|E|$]]|$1|F|3|G|5|H|7|P|8|@]|D|@]|E|$I|J]]|$1|K|3|-4|5|6|7|Q|8|@]|D|@]|E|$]]]|L|$]]

Surprisingly, another tidyverse solution is still missing - you can also use <code>tidyr::extract</code>, with a regex.
<pre class="lang-r prettyprint-override"><code>library(tidyr)
before &lt;- data.frame(attr = c(1, 30, 4, 6), type = c(&quot;foo_and_bar&quot;, &quot;foo_and_bar_2&quot;))

## regex - getting all characters except an underscore till the first underscore, 
## inspired by Akrun https://stackoverflow.com/a/49752920/7941188 

extract(before, col = type, into = paste0(&quot;type&quot;, 1:2), regex = &quot;(^[^_]*)_(.*)&quot;)
#&gt; attr type1 type2
#&gt; 1 1 foo and_bar
#&gt; 2 30 foo and_bar_2
#&gt; 3 4 foo and_bar
#&gt; 4 6 foo and_bar_2
</code></pre>

I'd like to take data of the form

<pre><code>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
</code></pre>

and use <code>split()</code> on the column "<code>type</code>" from above to get something like this:

<pre><code> attr type_1 type_2
1 1 foo bar
2 30 foo bar_2
3 4 foo bar
4 6 foo bar_2
</code></pre>

I came up with something unbelievably complex involving some form of <code>apply</code> that worked, but I've since misplaced that. It seemed far too complicated to be the best way. I can use <code>strsplit</code> as below, but then unclear how to get that back into 2 columns in the data frame.

<pre><code>&gt; strsplit(as.character(before$type),'_and_')
[[1]]
[1] "foo" "bar"

[[2]]
[1] "foo" "bar_2"

[[3]]
[1] "foo" "bar"

[[4]]
[1] "foo" "bar_2"
</code></pre>

Thanks for any pointers. I've not quite groked R lists just yet.

Split data frame string column into multiple columns

我想把表格中的数据before = data.frame(attr = c(1,30,4,6), type=c('foo_and_bar','foo_and_bar_2'))  attr          type1    1   foo_and_bar2   30 foo_and_bar_23    4   foo_and_bar4    6 foo_and_bar_2并在上面的"type“列上

问将数据框字符串列拆分为多列
EN

回答 13

Stack Overflow用户

Stack Overflow用户

Stack Overflow用户

社区

活动

资源

关于

腾讯云开发者

热门产品

热门推荐

更多推荐

问将数据框字符串列拆分为多列EN

回答 13

Stack Overflow用户

Stack Overflow用户

Stack Overflow用户

社区

活动

资源

关于

腾讯云开发者

热门产品

热门推荐

更多推荐

问将数据框字符串列拆分为多列
EN