使用标点符号解析字符串，在 r 中的大列表的不均匀行中

Question

我的数据包含我要导入的词库。这个问题的不同之处在于我将单词和标点符号分开。我的原始文件大约有 1,000,000 行。我想出了如何分隔标点符号。但是，我发现我的行现在不均匀并且它们被回收以匹配行的最长长度。我试图停止回收，而是为回收添加 NA 值。我附上了我正在导入的数据 = df.我的预期输出为 = 输出。

#--------Upload 1st dataset and edit-------#
library("stringr")
sent1<-c("How did Quebec? 1 2 3")
sent2<-c("Why does valve = .245")
sent3<-c("How do I use a period (.) comma [,] and hyphen {-} to columns?")
df <- data.frame(text = c(sent1,sent2,sent3))

#--Parse the punctation and the words from df
df<-do.call(cbind, lapply(gsub("([[:punct:]])", " \1 ", 
        df$text), function(x) scan(text = x, what = "", quiet = TRUE)))

这是我现在得到的结果...

> do.call(cbind, lapply(gsub("([[:punct:]])", " \1 ", 
+         df$text), function(x) scan(text = x, what = "", quiet = TRUE)))

      [,1]     [,2]    [,3]     
 [1,] "How"    "Why"   "How"    
 [2,] "did"    "does"  "do"     
 [3,] "Quebec" "valve" "I"      
 [4,] "?"      "="     "use"    
 [5,] "1"      "."     "a"      
 [6,] "2"      "245"   "period" 
 [7,] "3"      "Why"   "("      
 [8,] "How"    "does"  "."      
 [9,] "did"    "valve" ")"      
[10,] "Quebec" "="     "comma"  
[11,] "?"      "."     "["      
[12,] "1"      "245"   ","      
[13,] "2"      "Why"   "]"      
[14,] "3"      "does"  "and"    
[15,] "How"    "valve" "hyphen" 
[16,] "did"    "="     "{"      
[17,] "Quebec" "."     "-"      
[18,] "?"      "245"   "}"      
[19,] "1"      "Why"   "to"     
[20,] "2"      "does"  "columns"
[21,] "3"      "valve" "?"

这是我想要的输出...

#-------------output-------------#
words1<-c("How", "did" ,"Quebec"," ? ","1", "2" ,"3",NA,NA,NA,NA,NA,NA,NA,NA,NA,NA,NA,NA,NA,NA)
words2<-c('Why', "does", "valve"," = ",".","245" ,NA,NA,NA,NA,NA,NA,NA,NA,NA,NA,NA,NA,NA,NA,NA)
words3<-c("How" ,"do", "I", "use", "a", "period", '(',".",')', "comma" ,'[',",","]" ,"and" ,"hyphen" ,"{","-",'}' ,"to" ,"columns",'?')
output<-data.frame(words1,words2,words3)

输出

> data.frame(words1,words2,words3)
   words1 words2  words3
1     How    Why     How
2     did   does      do
3  Quebec  valve       I
4      ?      =      use
5       1      .       a
6       2    245  period
7       3   <NA>       (
8    <NA>   <NA>       .
9    <NA>   <NA>       )
10   <NA>   <NA>   comma
11   <NA>   <NA>       [
12   <NA>   <NA>       ,
13   <NA>   <NA>       ]
14   <NA>   <NA>     and
15   <NA>   <NA>  hyphen
16   <NA>   <NA>       {
17   <NA>   <NA>       -
18   <NA>   <NA>       }
19   <NA>   <NA>      to
20   <NA>   <NA> columns
21   <NA>   <NA>       ?

Answer 1

您可以使用 rowr 包中的 cbind.fill 和附加参数 fill = NA

library(rowr)
do.call(cbind.fill, c(lapply(gsub("([[:punct:]])", " \1 ", 
        df$text), function(x) scan(text = x, what = "", quiet = TRUE)), fill = NA))

#   object object  object
#1     How    Why     How
#2     did   does      do
#3  Quebec  valve       I
#4       ?      =     use
#5       1      .       a
#6       2    245  period
#7       3   <NA>       (
#8    <NA>   <NA>       .
#9    <NA>   <NA>       )
#10   <NA>   <NA>   comma
#11   <NA>   <NA>       [
#12   <NA>   <NA>       ,
#13   <NA>   <NA>       ]
#14   <NA>   <NA>     and
#15   <NA>   <NA>  hyphen
#16   <NA>   <NA>       {
#17   <NA>   <NA>       -
#18   <NA>   <NA>       }
#19   <NA>   <NA>      to
#20   <NA>   <NA> columns
#21   <NA>   <NA>       ?

或使用 sapply

的基础 R 选项

list_df <- lapply(gsub("([[:punct:]])", " \1 ", 
               df$text), function(x) scan(text = x, what = "", quiet = TRUE))

sapply(list_df, '[', 1:max(lengths(list_df)))

#       [,1]     [,2]    [,3]     
# [1,] "How"    "Why"   "How"    
# [2,] "did"    "does"  "do"     
# [3,] "Quebec" "valve" "I"      
# [4,] "?"      "="     "use"    
# [5,] "1"      "."     "a"      
# [6,] "2"      "245"   "period" 
# [7,] "3"      NA      "("      
# [8,] NA       NA      "."      
# [9,] NA       NA      ")"      
#[10,] NA       NA      "comma"  
#[11,] NA       NA      "["      
#......

使用标点符号解析字符串，在 r 中的大列表的不均匀行中

Parsing strings with punctuation, in uneven rows from a large list in r

r

parsing

word

recycle