主要学习stringr包的用法。

构建字符串

安装stringr包，构建示例字符串。

  1. > rm(list = ls())
  2. > if(!require(stringr))install.packages('stringr')
  3. > library(stringr)
  4. > x <- "The birch canoe slid on the smooth planks."
  5. > x
  6. [1] "The birch canoe slid on the smooth planks."

检测长度

主要是str_length()函数。

  1. > str_length(x) #空格和符号也计算在内
  2. [1] 42
  3. > length(x)
  4. [1] 1

image.png

字符串拆分与组合

主要是str_split()函数，拆分后可以取子集。

  1. > x
  2. [1] "The birch canoe slid on the smooth planks."
  4. > str_split(x," ")
  5. [[1]]
  6. [1] "The"     "birch"   "canoe"   "slid"    "on"      "the"     "smooth"  "planks."
  8. > x2 = str_split(x," ")[[1]]
  9. > x2
  10. [1] "The"     "birch"   "canoe"   "slid"    "on"      "the"     "smooth"  "planks."

注意simplify参数的用法，可以形成一个矩阵。

  1. > y = c("jimmy 150","nicker 140","tony 152")
  2. > str_split(y," ")
  3. [[1]]
  4. [1] "jimmy" "150"  
  6. [[2]]
  7. [1] "nicker" "140"   
  9. [[3]]
  10. [1] "tony" "152" 
  12. > str_split(y," ",simplify = T)
  13.      [,1]     [,2] 
  14. [1,] "jimmy"  "150"
  15. [2,] "nicker" "140"
  16. [3,] "tony"   "152"

str_c()函数可以实现字符串的连接。
collapse参数可以作为分隔符，sep是把向量中的每一个元素都与另一字符串相连。

  1. > x2
  2. [1] "The"     "birch"   "canoe"   "slid"    "on"      "the"     "smooth"  "planks."
  3. > str_c(x2,collapse = " ")
  4. [1] "The birch canoe slid on the smooth planks."
  5. > str_c(x2,1234,sep = "+")
  6. [1] "The+1234"     "birch+1234"   "canoe+1234"   "slid+1234"    "on+1234"     
  7. [6] "the+1234"     "smooth+1234"  "planks.+1234"

提取字符串的一部分

str_sub()函数可以从起始位置到终止位置取字符。

  1. > x
  2. [1] "The birch canoe slid on the smooth planks."
  3. > str_sub(x,5,9)
  4. [1] "birch"

字符定位

str_locate()在向量中定位需要检测的字符。

  1. > x2
  2. [1] "The"     "birch"   "canoe"   "slid"    "on"      "the"     "smooth"  "planks."
  3. > str_locate(x2,"th")
  4.      start end
  5. [1,]    NA  NA
  6. [2,]    NA  NA
  7. [3,]    NA  NA
  8. [4,]    NA  NA
  9. [5,]    NA  NA
  10. [6,]     1   2
  11. [7,]     5   6
  12. [8,]    NA  NA
  13. > str_locate(x2,"h")
  14.      start end
  15. [1,]     2   2
  16. [2,]     5   5
  17. [3,]    NA  NA
  18. [4,]    NA  NA
  19. [5,]    NA  NA
  20. [6,]     2   2
  21. [7,]     6   6
  22. [8,]    NA  NA

字符检测

str_detect()检测向量中每个字符串是否含有待检测的字符。

  1. > x2
  2. [1] "The"     "birch"   "canoe"   "slid"    "on"      "the"     "smooth"  "planks."
  3. > str_detect(x2,"h")
  4. [1]  TRUE  TRUE FALSE FALSE FALSE  TRUE  TRUE FALSE
  5. > ###与sum和mean连用，可以统计匹配的个数和比例
  6. > sum(str_detect(x2,"h"))
  7. [1] 4
  8. > mean(str_detect(x2,"h"))
  9. [1] 0.5

字符替换

  1. > x2
  2. [1] "The"     "birch"   "canoe"   "slid"    "on"      "the"     "smooth"  "planks."
  3. > str_replace(x2,"o","A")
  4. [1] "The"     "birch"   "canAe"   "slid"    "An"      "the"     "smAoth"  "planks."
  5. > str_replace_all(x2,"o","A")
  6. [1] "The"     "birch"   "canAe"   "slid"    "An"      "the"     "smAAth"  "planks."

提取匹配到的字符

  1. > x2
  2. [1] "The"     "birch"   "canoe"   "slid"    "on"      "the"     "smooth"  "planks."
  3. > str_extract(x2,"o|e")
  4. [1] "e" NA  "o" NA  "o" "e" "o" NA 
  5. > str_extract_all(x2,"o|e")
  6. [[1]]
  7. [1] "e"
  9. [[2]]
  10. character(0)
  12. [[3]]
  13. [1] "o" "e"
  15. [[4]]
  16. character(0)
  18. [[5]]
  19. [1] "o"
  21. [[6]]
  22. [1] "e"
  24. [[7]]
  25. [1] "o" "o"
  27. [[8]]
  28. character(0)
  30. > str_extract_all(x2,"o|e",simplify = T)
  31.      [,1] [,2]
  32. [1,] "e"  ""  
  33. [2,] ""   ""  
  34. [3,] "o"  "e" 
  35. [4,] ""   ""  
  36. [5,] "o"  ""  
  37. [6,] "e"  ""  
  38. [7,] "o"  "o" 
  39. [8,] ""   ""

字符删除

  1. > x
  2. [1] "The birch canoe slid on the smooth planks."
  3. > str_remove(x," ")
  4. [1] "Thebirch canoe slid on the smooth planks."
  5. > str_remove_all(x," ")
  6. [1] "Thebirchcanoeslidonthesmoothplanks."