[toc]

stringr

1. str_c粘贴，相当于paste0

  1. > library(stringr)
  2. > str_c('a','b',sep = '-')
  3. [1] "a-b"
  4. > paste0('a','b',sep = '-')
  5. [1] "ab-"
  6. > paste('a','b',sep = '-')
  7. [1] "a-b"

2. str_length() 相当于nchar() 返回字符串长度

  1. > str_length("strinng") 
  2. [1] 7
  3. > nchar("strinng")
  4. [1] 7

3.str_sub and sbustr()( in base package)

  1. > yxf <- 'yi xue fang'
  3. > str_sub(yxf, c(1,4,8), c(2,6,11)) # return value and change value directly
  4. [1] "yi"   "xue"  "fang"
  6. > substr(yxf, c(1,4,8), c(2,6,11))
  7. [1] "yi"
  9. > str_sub(yxf, 1,1) <-  'Y';yxf  # change value
  10. [1] "Yi xue fang"

4.str_dup duplicate strings 重复字符串

  1. > fruit <- c("apple", "pear", "banana")
  2. > str_dup(fruit, 2)
  3. [1] "appleapple"   "pearpear"     "bananabanana"

5.去掉空白字符str_trim

  1. string <- ' Eternal love for YanQ '
  2. str_trim(string, side = 'both')

6.str_extract（）以向量的形式返回提取值

str_extract_all（）以列表的形式返回所有的值，

stri_locate_all() 以列表的形式返回所有位置

  1. > phones <- c(" 219 733 8965", "329-293-8753 ", "banana", "595 794 7569",
  2. +             "387 287 6718", "apple", "233.398.9187  ", "482 952 3315",
  3. +             "239 923 8115 and 842 566 4692", "Work: 579-499-7527", "$1000",
  4. +             "Home: 543.355.3679")
  5. > str_extract(phones, "([2-9][0-9]{2})[- .]([0-9]{3})[- .]([0-9]{4})");phones
  6.  [1] "219 733 8965" "329-293-8753" NA             "595 794 7569"
  7.  [5] "387 287 6718" NA             "233.398.9187" "482 952 3315"
  8.  [9] "239 923 8115" "579-499-7527" NA             "543.355.3679"
  9.  [1] " 219 733 8965"                 "329-293-8753 "                
  10.  [3] "banana"                        "595 794 7569"                 
  11.  [5] "387 287 6718"                  "apple"                        
  12.  [7] "233.398.9187  "                "482 952 3315"                 
  13.  [9] "239 923 8115 and 842 566 4692" "Work: 579-499-7527"           
  14. [11] "$1000"                         "Home: 543.355.3679" 
  17. > shopping_list <- c("apples x4", "bag of flour", "bag of sugar", "milk x2")
  18. > str_extract(shopping_list, "\\d")
  19. [1] "4" NA  NA  "2"
  20. > str_extract(shopping_list, "[a-z]+")
  21. [1] "apples" "bag"    "bag"    "milk"  
  22. > str_extract(shopping_list, "[a-z]{1,4}")
  23. [1] "appl" "bag"  "bag"  "milk"
  24. > str_extract(shopping_list, "\\b[a-z]{1,4}\\b")
  25. [1] NA     "bag"  "bag"  "milk"
  26. > # Extract all matches
  27. > str_extract_all(shopping_list, "[a-z]+")
  28. [[1]]
  29. [1] "apples" "x"     
  31. [[2]]
  32. [1] "bag"   "of"    "flour"
  34. [[3]]
  35. [1] "bag"   "of"    "sugar"
  37. [[4]]
  38. [1] "milk" "x"   
  40. > str_extract_all(shopping_list, "\\b[a-z]+\\b")
  41. [[1]]
  42. [1] "apples"
  44. [[2]]
  45. [1] "bag"   "of"    "flour"
  47. [[3]]
  48. [1] "bag"   "of"    "sugar"
  50. [[4]]
  51. [1] "milk"
  53. > str_extract_all(shopping_list, "\\d")
  54. [[1]]
  55. [1] "4"
  57. [[2]]
  58. character(0)
  60. [[3]]
  61. character(0)
  63. [[4]]
  64. [1] "2"
  66. > # Simplify results into character matrix
  67. > str_extract_all(shopping_list, "\\b[a-z]+\\b", simplify = TRUE)
  68.      [,1]     [,2] [,3]   
  69. [1,] "apples" ""   ""     
  70. [2,] "bag"    "of" "flour"
  71. [3,] "bag"    "of" "sugar"
  72. [4,] "milk"   ""   ""     
  73. > str_extract_all(shopping_list, "\\d", simplify = TRUE)
  74.      [,1]
  75. [1,] "4" 
  76. [2,] ""  
  77. [3,] ""  
  78. [4,] "2" 
  79. > # Extract all words
  80. > str_extract_all("This is, suprisingly, a sentence.", boundary("word"))
  81. [[1]]
  82. [1] "This"        "is"          "suprisingly" "a"           "sentence"

7.str_replace_all（x，a，b）把x里的a全部替换为b

  1. > fruits <- c("one apple", "two pears", "three bananas")
  2. > str_replace_all(fruits, "[aeiou]", "-")
  3. [1] "-n- -ppl-"     "tw- p--rs"     "thr-- b-n-n-s"

stringi

1.连接 连接两个字符串，注意与paste paste0的区别

  1. > library(stringi)
  2. > stri_join(1:7, letters[1:7], sep='-')
  3. [1] "1-a" "2-b" "3-c" "4-d" "5-e" "6-f" "7-g"
  4. > stri_join(1:7, letters[1:7], collapse='-')
  5. [1] "1a-2b-3c-4d-5e-6f-7g"

2.compare字符创比较

  1. > stri_cmp_eq('AB','aB')
  2. [1] FALSE
  3. > stri_cmp_neq('AB','aB')
  4. [1] TRUE
  5. > stri_cmp_gt('a121','b221')
  6. [1] FALSE
  7. > stri_cmp_lt('a121','b221')
  8. [1] TRUE

3.stri_count（a，fixed/regex=b）在a固定或正则匹配计数b

  1. > language <- c('Python','R', 'PHP', 'Ruby', 'Java', 
  2. +               'JavaScript', 'C', 'Oracle', 'C++', 'C#', 'Spark', 'Go',
  3. +               'Room', 'Good', 'Pathon', 'ScriptJava', 'R2R', 'C+','C*',"r")
  4. > stri_count(language, fixed = 'R')
  5.  [1] 0 1 0 1 0 0 0 0 0 0 0 0 1 0 0 0 2 0 0 0
  6. > stri_count(language, regex = '^J')
  7.  [1] 0 0 0 0 1 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0

4.stri_count_boundaries计算边界

  1. > test <- 'The above-mentioned    features are very useful. 
  2. + Warm thanks to their developers.'
  3. > stri_count_boundaries(test, type="word")
  4. [1] 29
  5. > stri_count_boundaries(test, type="sentence")
  6. [1] 2
  7. > stri_count_boundaries(test, type="character")
  8. [1] 82
  9. > stri_count_words(test)
  10. [1] 12

5.stri_dup（a,b）是将a分别重复b此，stri_duplicated是否为重复值

  1. > stri_dup(c("abc", "pqrst"), c(4, 2))
  2. [1] "abcabcabcabc" "pqrstpqrst"  
  4. > stri_duplicated(c("a", "b", "a", NA, "a", NA))
  5. [1] FALSE FALSE  TRUE FALSE  TRUE  TRUE
  7. > stri_duplicated(c("a", "b", "a", NA, "a", NA), fromLast=TRUE)
  8. [1]  TRUE FALSE  TRUE  TRUE FALSE FALSE
  10. > stri_duplicated_any(c("a", "b", "a", NA, "a", NA))
  11. [1] 3

6.stri_dect（a，b） 字符创a中是否含有b，返回逻辑值

fixed 是完全匹配，regex是正则匹配

  1. > stri_detect_fixed(c("stringi R", "REXAMINE", "123"), c('i', 'R', '0'))
  2. [1]  TRUE  TRUE FALSE
  4. > stri_detect_regex(c("above", "abort", "about", "abnormal", 'abandon'), '^ab')
  5. [1] TRUE TRUE TRUE TRUE TRUE
  7. > stri_detect_regex(c("above", "abort", "about", "abnormal", 'abandon'), 't\\b')
  8. [1] FALSE  TRUE  TRUE FALSE FALSE
  10. > stri_detect_regex(c('ABOUT','abort','AboVE'), '^ab', case_insensitive = TRUE)
  11. [1] TRUE TRUE TRUE
  13. > stri_startswith_fixed(c("a1", "a2", "b3", "a4", "c5"), "a")
  14. [1]  TRUE  TRUE FALSE  TRUE FALSE
  16. > stri_startswith_fixed(c("a1", "a2", "b3", "a4", "c5"), "a1")
  17. [1]  TRUE FALSE FALSE FALSE FALSE
  19. > stri_startswith_fixed(c("abaDc", "aabadc",'ababa'), "ba", from=2)
  20. [1]  TRUE FALSE  TRUE
  22. > stri_endswith_fixed(c("abaDc", "aabadc",'ababa'),'ba')
  23. [1] FALSE FALSE  TRUE
  25. > stri_endswith_fixed(c("abaDc", "aabadc",'ababa'),'ba', to = 3)
  26. [1]  TRUE FALSE  TRUE

7.stri_extract_all() 提取字符创的内容,返回值列表

These functions extract all substrings matching a given pattern.

  • stri_extract_all_* extracts all the matches.
  • stri_extract_first_* and stri_extract_last_* yield the first or the last matches, respectively.
  1. > tEmp_text <- c('EU_FRA02_C1_S2008','AF_COM12_B0_2004',
  2. +               'EU-FRA-C3-S2007','NAUSA02E02005','AS_CHN12_N0_05')
  3. > #Generate a strings composed by several sequence names.
  4. > stri_extract_all(tEmp_text, regex = '[0-9]{2,4}\\b')
  5. [[1]]
  6. [1] "2008"
  8. [[2]]
  9. [1] "2004"
  11. [[3]]
  12. [1] "2007"
  14. [[4]]
  15. [1] "2005"
  17. [[5]]
  18. [1] "05"
  20. > stri_extract_all_fixed("abaBAba", "Aba", case_insensitive=TRUE, overlap=TRUE)
  21. [[1]]
  22. [1] "aba" "aBA" "Aba"
  23. #case_insensitive=TRUE 不区分大小写
  25. > stri_extract_all_boundaries("stringi: THE string processing package 123.48...")
  26. [[1]]
  27. [1] "stringi: "   "THE "        "string "     "processing " "package "   
  28. [6] "123.48..."  
  30. > stri_extract_all_words("stringi: THE string processing package 123.48...")
  31. [[1]]
  32. [1] "stringi"    "THE"        "string"     "processing" "package"   
  33. [6] "123.48"    
  35. > stri_count_boundaries("stringi: THE string processing package 123.48...", type="word")
  36. [1] 15

7.stri_isempty（）判断字符创或向量是否为空

  1. > stri_isempty(c(',', '', 'abc', '123', '\u0105\u0104',' ',''))
  2. [1] FALSE  TRUE FALSE FALSE FALSE FALSE  TRUE

8 stri_locate_all（a，fixed = b） 返回字符串b在字符创a中的全部位置

  1. > stri_locate_all('I want to learn R to promote my statistical skills', fixed='to')
  2. [[1]]
  3.      start end
  4. [1,]     8   9
  5. [2,]    19  20

strto系列 转换字母大小写

  1. > library(stringr)
  2. > a = c("PTPRC","EPCAM", 'MME',"CD3G","CD3E", "CD68", "CD79A")
  3. > str_to_title(a)
  4. [1] "Ptprc" "Epcam" "Mme"   "Cd3g"  "Cd3e"  "Cd68"  "Cd79a"
  5. > dog <- "The quick brown dog"
  6. > str_to_upper(dog)  #全部大写
  7. [1] "THE QUICK BROWN DOG"
  8. > str_to_lower(dog) #全部小写
  9. [1] "the quick brown dog"
  10. > str_to_title(dog) #首字母大写
  11. [1] "The Quick Brown Dog"
  12. > str_to_sentence("the quick brown dog") #句子第一个词的第一个字母大写
  13. [1] "The quick brown dog"
  16. #另一个包里的函数capitalize
  17. > library(Hmisc)
  18. > a = c("PTPRC","EPCAM", 'MME',"CD3G","CD3E", "CD68", "CD79A")
  19. > capitalize(tolower(a))
  20. [1] "Ptprc" "Epcam" "Mme"   "Cd3g"  "Cd3e"  "Cd68"  "Cd79a"