如何在R中只捕获字符串的一部分？

Question

我想使用stringr::str_match和rebus::capture捕获字符串的某些部分，但我无法理解正确的模式。

文本可能包含一些特殊字符。类似于：

​

​

数据：

df <- structure(list(ID = c(1, 1, 1, 2, 2), TEXT = c("VERIFIED DATE/TIME: 24/11/2018 16:23, VERIFIED PERSON IN CHARGE: JOHN", 
"HISTORY aaaAAA# 111 FINDINGS Bb123 CONCLUSION 987CCC ccc654", 
"DIAGNOSIS abc def hij", "VERIFIED DATE/TIME: 25/10/2018 16:23, VERIFIED PERSON IN CHARGE: Mary", 
"HISTORY eeeEEE@ 111 FINDINGS Bb321 CONCLUSION 987FFF ggg654"
)), .Names = c("ID", "TEXT"), row.names = c(NA, 5L), class = "data.frame")
#   ID                                                                  TEXT
# 1  1 VERIFIED DATE/TIME: 24/11/2018 16:23, VERIFIED PERSON IN CHARGE: JOHN
# 2  1           HISTORY aaaAAA# 111 FINDINGS Bb123 CONCLUSION 987CCC ccc654
# 3  1                                                 DIAGNOSIS abc def hij
# 4  2 VERIFIED DATE/TIME: 25/10/2018 16:23, VERIFIED PERSON IN CHARGE: Mary
# 5  2           HISTORY eeeEEE@ 111 FINDINGS Bb321 CONCLUSION 987FFF ggg654

所需的输出：I希望将文本拆分为不同的列：

1. 经核实的日期/时间
2. 经核实的负责人
3. 历史
4. 调查结果
5. 结论
6. 诊断

df_out <- structure(ID= c(1，2)，VERIFIED DATE/TIME = c("24/11/2018 16:23 "，"25/10/2018 16:23 ")，VERIFIED PERSON IN CHARGE =c(“约翰”，“玛丽”)，历史= c("aaaAAA# 111"，"eeeEEE@ 111")，调查结果= c("Bb123"，"Bb321")，结论= c("987CCC ccc654"，“987 def ggg654")，诊断= c("abc def hij"，NA)，.Names = c("ID“、”核实日期/时间“、”经核实的负责人“、”历史“、”发现“、”结论“、”诊断“)，row.names = 1:2，class = "data.frame")

代码：

我尝试了以下代码，但它给了我NA：

library(stringr)
library(rebus)
str_match(df$TEXT, pattern = "VERIFIED DATE/TIME:" %R%
            capture(one_or_more(ANY_CHAR)) %R%
            "VERIFIED PERSON IN CHARGE:" %R%
            capture(one_or_more(ANY_CHAR)))

Answer 1

组合库tm和stringr。我们首先为每个ID创建一个完整的文本，并在FINDINGS和CONCLUSION之前添加,以保持一致性。

library(tm)
library(stringr)
library(dplyr)
df = df%>%group_by(ID)%>%summarise(TEXT=paste(TEXT,collapse=", "))%>%mutate(TEXT=gsub("(.*)( FINDINGS.*)( CONCLUSION.*)","\\1,\\2,\\3",TEXT))
> df
# A tibble: 2 x 2
     ID TEXT                                                                                                                                        
  <dbl> <chr>                                                                                                                                       
1     1 VERIFIED DATE/TIME: 24/11/2018 16:23, VERIFIED PERSON IN CHARGE: JOHN, HISTORY aaaAAA# 111, FINDINGS Bb123, CONCLUSION 987CCC ccc654, DIAGN~
2     2 VERIFIED DATE/TIME: 25/10/2018 16:23, VERIFIED PERSON IN CHARGE: Mary, HISTORY eeeEEE@ 111, FINDINGS Bb321, CONCLUSION 987FFF ggg654 

然后将我们感兴趣的名称定义为列名，并将它们从字符串中删除。

titles = c("VERIFIED DATE/TIME: ","VERIFIED PERSON IN CHARGE: ","HISTORY ","FINDINGS ","CONCLUSION ","DIAGNOSIS ")
df$TEXT = removeWords(df$TEXT,titles)
> df
# A tibble: 2 x 2
     ID TEXT                                                                  
  <dbl> <chr>                                                                 
1     1 24/11/2018 16:23, JOHN, aaaAAA# 111, Bb123, 987CCC ccc654, abc def hij
2     2 25/10/2018 16:23, Mary, eeeEEE@ 111, Bb321, 987FFF ggg654 

最后，我们通过,划分列并设置列的名称。

df_fin=str_split_fixed(df$TEXT, ", ",6)
colnames(df_fin)=titles
> df_fin
     VERIFIED DATE/TIME:  VERIFIED PERSON IN CHARGE:  HISTORY       FINDINGS  CONCLUSION      DIAGNOSIS    
[1,] "24/11/2018 16:23"   "JOHN"                      "aaaAAA# 111" "Bb123"   "987CCC ccc654" "abc def hij"
[2,] "25/10/2018 16:23"   "Mary"                      "eeeEEE@ 111" "Bb321"   "987FFF ggg654" "" 

Answer 2

这里有一种使用stringr的方法

library(tidyr)
library(dplyr)
library(stringr)


df2 <- df %>% 
  group_by(ID) %>%
  summarise(conc_text = paste(TEXT, collapse = ", ")) %>%
  mutate(verified_date = apply(str_match(conc_text, "VERIFIED DATE/TIME: (.*?),"), 1, FUN = function(x) x[2]),
         verified_person = apply(str_match(conc_text, "VERIFIED PERSON IN CHARGE: (.*?),"), 1, FUN = function(x) x[2]),
         history = apply(str_match(conc_text, "HISTORY (.*?[0-9]{3})"), 1, FUN = function(x) x[2]),
         findings = apply(str_match(conc_text, "FINDINGS (.*?[0-9]{3})"), 1, FUN = function(x) x[2]),
         conclusions = apply(str_match(conc_text, "CONCLUSION (.*[0-9]{3})"), 1, FUN = function(x) x[2]),
         diagnosis = apply(str_match(conc_text, "DIAGNOSIS (.*$)"), 1, FUN = function(x) x[2]))

首先通过ID对文本进行连接。

假设HISTORY、FINDINGS和CONCLUSIONS变量以3位数结尾，因此为什么会有[0-9]{3}表达式。使用apply函数获取匹配的字符串。