string：字符串，亦可为字符串向量；locale：设置语种。
# install.packages('stringr') 安装包
library(stringr) #加载包
dog <- "The quick brown dog"
dog1 <- c("The", "quick", "brown", "dog")
# 帮助文档的实例中一般都省略参数名，个人习惯补全参数名，容易理解
str_to_upper(string = dog) #将英文字符串转换成大写## [1] "THE QUICK BROWN DOG"str_to_upper(string = dog1) #string为字符向量时## [1] "THE" "QUICK" "BROWN" "DOG"str_to_lower(string = dog) #将英文字符串转换成小写## [1] "the quick brown dog"str_to_title(string = dog) #将英文字符串中的单词首字母转换大写## [1] "The Quick Brown Dog"# locale可设置不同的语种
str_to_upper(string = "i", locale = "en") # English ## [1] "I"str_to_upper(string = "i", locale = "tr") # Turkish## [1] "<U+0130>"invert_match(loc)，loc是以函数str_locate_all()获取的位置矩阵作为输入。
numbers <- "1 and 2 and 4 and 456"
num_loc <- str_locate_all(string = numbers, pattern = "[0-9]+")[[1]] #匹配数字，返回数字的起始和结束位置
num_loc## start end
## [1,] 1 1
## [2,] 7 7
## [3,] 13 13
## [4,] 19 21str_sub(string = numbers, start = num_loc[, "start"], end = num_loc[, "end"])## [1] "1" "2" "4" "456"text_loc <- invert_match(loc = num_loc) #返回不匹配数字的起始和结束位置
text_loc## start end
## [1,] 0 0
## [2,] 2 6
## [3,] 8 12
## [4,] 14 18
## [5,] 22 -1str_sub(string = numbers, start = text_loc[, "start"], end = text_loc[, "end"])## [1] "" " and " " and " " and " ""3.1 fixed(pattern, ignore_case = FALSE)：Compare literal bytes in the string. This is very fast, but not usually what you want for non-ASCII character sets.
3.2 coll(pattern, ignore_case = FALSE, locale = NULL, …)：Compare strings respecting standard collation rules.
3.3 regex(pattern, ignore_case = FALSE, multiline = FALSE, comments = FALSE, dotall = FALSE, …)：默认使用正则表达式
3.4 boundary(type = c(“character”, “line_break”, “sentence”, “word”), skip_word_none = TRUE, …)：Match boundaries between things.
pattern <- "a.b"
strings <- c("abb", "a.b")
str_detect(string = strings, pattern = pattern)## [1] TRUE TRUEstr_detect(string = strings, pattern = fixed(pattern))## [1] FALSE TRUEstr_detect(string = strings, pattern = coll(pattern))## [1] FALSE TRUE# coll() is useful for locale-aware case-insensitive matching
i <- c("I", "<U+0130>", "i")
i## [1] "I" "<U+0130>" "i"str_detect(string = i, pattern = regex("i", TRUE))## [1] TRUE FALSE TRUEstr_detect(string = i, pattern = fixed("i", TRUE))## [1] TRUE FALSE TRUEstr_detect(string = i, pattern = coll("i", TRUE))## [1] TRUE FALSE TRUEstr_detect(string = i, pattern = coll("i", TRUE, locale = "tr"))## [1] FALSE FALSE TRUE# Word boundaries 单词边界
words <- c("These are some words.")
str_count(string = words, pattern = boundary("word")) #统计语句中单词的个数## [1] 4str_split(string = words, pattern = " ")[[1]] #将语句分割成单词，最后一个单词带有标点## [1] "These" "are" "some" "words."str_split(string = words, pattern = boundary("word"))[[1]] #最后一个单词不带有标点## [1] "These" "are" "some" "words"# 使用正则表达式
str_extract_all(string = "The Cat in the Hat", pattern = "[a-z]+") #区分大小写## [[1]]
## [1] "he" "at" "in" "the" "at"str_extract_all(string = "The Cat in the Hat", pattern = regex("[a-z]+", TRUE)) #忽略大小写的差异## [[1]]
## [1] "The" "Cat" "in" "the" "Hat"str_extract_all(string = "a\nb\nc", pattern = "^.")## [[1]]
## [1] "a"str_extract_all(string = "a\nb\nc", pattern = regex("^.", multiline = TRUE))## [[1]]
## [1] "a" "b" "c"str_extract_all(string = "a\nb\nc", pattern = "a.")## [[1]]
## character(0)str_extract_all(string = "a\nb\nc", pattern = regex("a.", dotall = TRUE))## [[1]]
## [1] "a\n"4.1 str_c(…, sep = “”, collapse = NULL)
4.2 str_join(…, sep = “”, collapse = NULL)，同str_c
sep：设置向量间的连接符；collapse：将向量的所有元素连接成一个字符串时，设置元素间的连接符。
str_c("Letter", letters[1:5]) #连接2个字符向量## [1] "Lettera" "Letterb" "Letterc" "Letterd" "Lettere"str_c("Letter", letters[1:5], sep = ": ") #sep可设置向量间的连接符## [1] "Letter: a" "Letter: b" "Letter: c" "Letter: d" "Letter: e"# 连接3个不等长的字符向量，出现警告信息，短的向量的元素会自动循环至与最长向量等长。
str_c(letters[1:5], " is for", c("...", "***"))## [1] "a is for..." "b is for***" "c is for..." "d is for***" "e is for..."str_c(letters)## [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q"
## [18] "r" "s" "t" "u" "v" "w" "x" "y" "z"str_c(letters, sep = "-") #当只有1个向量时，sep参数不起作用## [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q"
## [18] "r" "s" "t" "u" "v" "w" "x" "y" "z"# 将向量的所有元素连接成一个字符串，collapse设置元素间的连接符
str_c(letters, collapse = "")## [1] "abcdefghijklmnopqrstuvwxyz"str_c(letters, collapse = ", ")## [1] "a, b, c, d, e, f, g, h, i, j, k, l, m, n, o, p, q, r, s, t, u, v, w, x, y, z"str_c("Letter", letters[1:5], sep = ":", collapse = ",") #同时设置sep和collapse时，与以下语句等价：## [1] "Letter:a,Letter:b,Letter:c,Letter:d,Letter:e"a <- str_c("Letter", letters[1:5], sep = ":")
a## [1] "Letter:a" "Letter:b" "Letter:c" "Letter:d" "Letter:e"str_c(a, collapse = ",")## [1] "Letter:a,Letter:b,Letter:c,Letter:d,Letter:e"# 当字符向量中存在缺失值时，返回的也是缺失值：
str_c(c("a", NA, "b"), "-d")## [1] "a-d" NA "b-d"# 使用函数str_replace_NA 将缺失值替换成‘NA’:
str_c(str_replace_na(c("a", NA, "b")), "-d")## [1] "a-d" "NA-d" "b-d"str_conv(string, encoding)
x <- rawToChar(as.raw(177))
x## [1] "\xb1"str_conv(string = x, encoding = "ISO-8859-2") # Polish 'a with ogonek' ## [1] "<U+0105>"str_conv(string = x, encoding = "ISO-8859-1") # Plus-minus## [1] "±"str_count(string, pattern = “”)
fruit <- c("apple", "banana", "pear", "pineappleapple")
str_count(string = fruit, pattern = "a") #计算向量fruit的每个元素含有a的数目## [1] 1 3 1 2str_count(string = fruit, pattern = "p")## [1] 2 0 1 5str_count(string = fruit, pattern = "ap")## [1] 1 0 0 2str_count(string = fruit, pattern = "[a-e]")## [1] 2 4 2 5# 统计'apple'中的'a'的个数，~~~，'pineappleapple'中'p'的个数：
str_count(string = fruit, pattern = c("a", "b", "p", "p"))## [1] 1 1 1 5str_count(string = c("a.", "...", ".a.a"), pattern = ".") #正则表达式中‘.’是指单个字符，不仅仅是字符‘.’## [1] 2 3 4str_count(string = c("a.", "...", ".a.a"), pattern = fixed(".")) #fixed('.')指字符‘.’## [1] 1 3 2str_detect(string, pattern)，结果返回逻辑向量
fruit <- c("apple1", "banana", "pear", "pinapple")
str_detect(string = fruit, pattern = "a") #fruit的元素是否包含a## [1] TRUE TRUE TRUE TRUEstr_detect(string = fruit, pattern = "pp")## [1] TRUE FALSE FALSE TRUEstr_detect(string = fruit, pattern = "^a") #fruit的元素是否以a开头## [1] TRUE FALSE FALSE FALSEstr_detect(string = fruit, pattern = "a$") #fruit的元素是否以a结尾## [1] FALSE TRUE FALSE FALSEstr_detect(string = fruit, pattern = "[aeiou]") #fruit的元素是否包含[aeiou]中的一个字符## [1] TRUE TRUE TRUE TRUE# 向量化运算中，短的向量的元素会被循环使用
str_detect(string = fruit, pattern = c("ap", "ba", "pe", "pin"))## [1] TRUE TRUE TRUE TRUE# string的长度大于pattern的长度，结果返回与string等长的逻辑向量：
str_detect(string = fruit, pattern = c("ap", "pin"))## [1] TRUE FALSE FALSE TRUE# string的长度小于pattern的长度，结果返回与pattern等长的逻辑向量：
str_detect(string = fruit, pattern = c("ap", "ba", "pe", "pin", "e1"))## [1] TRUE TRUE TRUE TRUE TRUEstr_dup(string, times)
fruit <- c("apple", "pear", "banana")
str_dup(string = fruit, times = 2) # 向量的每个元素重复2次，然后连接起来## [1] "appleapple" "pearpear" "bananabanana"str_dup(string = fruit, times = 1:3)## [1] "apple" "pearpear" "bananabananabanana"str_c("ba", str_dup("na", 0:5))## [1] "ba" "bana" "banana" "bananana"
## [5] "banananana" "bananananana"str_extract(string, pattern) 提取匹配的第一个字符串
str_extract_all(string, pattern, simplify = FALSE) 提取匹配的所有字符串
shopping_list <- c("apples 4x4", "bag of flour", "bag of sugar", "milk x2")
# 提取匹配模式的第一个字符串
str_extract(string = shopping_list, pattern = "\\d") #提取数字## [1] "4" NA NA "2"str_extract(string = shopping_list, pattern = "[a-z]+") #提取字母## [1] "apples" "bag" "bag" "milk"str_extract(string = shopping_list, pattern = "[a-z]{1,4}")## [1] "appl" "bag" "bag" "milk"str_extract(string = shopping_list, pattern = "\\b[a-z]{1,4}\\b")## [1] NA "bag" "bag" "milk"# 提取所有匹配模式的字符串，结果返回一个列表
str_extract_all(string = shopping_list, pattern = "[a-z]+")## [[1]]
## [1] "apples" "x"
##
## [[2]]
## [1] "bag" "of" "flour"
##
## [[3]]
## [1] "bag" "of" "sugar"
##
## [[4]]
## [1] "milk" "x"str_extract_all(string = shopping_list, pattern = "\\b[a-z]+\\b")## [[1]]
## [1] "apples"
##
## [[2]]
## [1] "bag" "of" "flour"
##
## [[3]]
## [1] "bag" "of" "sugar"
##
## [[4]]
## [1] "milk"str_extract_all(string = shopping_list, pattern = "\\d")## [[1]]
## [1] "4" "4"
##
## [[2]]
## character(0)
##
## [[3]]
## character(0)
##
## [[4]]
## [1] "2"# 提取所有匹配模式的字符串，结果返回一个矩阵，通过simplify = TRUE设置
str_extract_all(string = shopping_list, pattern = "\\b[a-z]+\\b", simplify = TRUE)## [,1] [,2] [,3]
## [1,] "apples" "" ""
## [2,] "bag" "of" "flour"
## [3,] "bag" "of" "sugar"
## [4,] "milk" "" ""str_extract_all(string = shopping_list, pattern = "\\d", simplify = TRUE)## [,1] [,2]
## [1,] "4" "4"
## [2,] "" ""
## [3,] "" ""
## [4,] "2" ""str_length(string)
str_length(letters)## [1] 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1str_length(NA)## [1] NAstr_length(factor("abc"))## [1] 3str_length(c("i", "like", "programming", NA))## [1] 1 4 11 NA# Two ways of representing a u with an umlaut
u1 <- "ü"
u2 <- stringi::stri_trans_nfd(u1)
# The print the same:
u1## [1] "ü"u2## [1] "u<U+0308>"# But have a different length
str_length(u1)## [1] 1str_length(u2)## [1] 2# Even though they have the same number of characters
str_count(u1)## [1] 1str_count(u2)## [1] 1str_locate(string, pattern)：返回匹配的第一个字符串的位置
str_locate_all(string, pattern)：返回匹配的所有位置
fruit <- c("apple", "banana", "pear", "pineapple")
# 返回匹配的第一个字符串的位置：
str_locate(string = fruit, pattern = "a")## start end
## [1,] 1 1
## [2,] 2 2
## [3,] 3 3
## [4,] 5 5str_locate(string = fruit, pattern = "ap")## start end
## [1,] 1 2
## [2,] NA NA
## [3,] NA NA
## [4,] 5 6str_locate(string = fruit, pattern = c("a", "b", "p", "p"))## start end
## [1,] 1 1
## [2,] 1 1
## [3,] 1 1
## [4,] 1 1# 返回匹配的所有位置：
str_locate_all(string = fruit, pattern = "a")## [[1]]
## start end
## [1,] 1 1
##
## [[2]]
## start end
## [1,] 2 2
## [2,] 4 4
## [3,] 6 6
##
## [[3]]
## start end
## [1,] 3 3
##
## [[4]]
## start end
## [1,] 5 5str_locate_all(string = fruit, pattern = "e")## [[1]]
## start end
## [1,] 5 5
##
## [[2]]
## start end
##
## [[3]]
## start end
## [1,] 2 2
##
## [[4]]
## start end
## [1,] 4 4
## [2,] 9 9str_locate_all(string = fruit, pattern = c("a", "b", "p", "p"))## [[1]]
## start end
## [1,] 1 1
##
## [[2]]
## start end
## [1,] 1 1
##
## [[3]]
## start end
## [1,] 1 1
##
## [[4]]
## start end
## [1,] 1 1
## [2,] 6 6
## [3,] 7 7# 查找每个字符的位置
str_locate_all(string = fruit, pattern = "")## [[1]]
## start end
## [1,] 1 1
## [2,] 2 2
## [3,] 3 3
## [4,] 4 4
## [5,] 5 5
##
## [[2]]
## start end
## [1,] 1 1
## [2,] 2 2
## [3,] 3 3
## [4,] 4 4
## [5,] 5 5
## [6,] 6 6
##
## [[3]]
## start end
## [1,] 1 1
## [2,] 2 2
## [3,] 3 3
## [4,] 4 4
##
## [[4]]
## start end
## [1,] 1 1
## [2,] 2 2
## [3,] 3 3
## [4,] 4 4
## [5,] 5 5
## [6,] 6 6
## [7,] 7 7
## [8,] 8 8
## [9,] 9 9str_match(string, pattern) 提取匹配的第一个字符串
str_match_all(string, pattern) 提取匹配的所有字符串
strings <- c(" 219 733 8965", "329-293-8753 ", "banana", "595 794 7569", "387 287 6718",
"apple", "233.398.9187 ", "482 952 3315", "239 923 8115 and 842 566 4692",
"Work: 579-499-7527", "$1000", "Home: 543.355.3679")
phone <- "([2-9][0-9]{2})[- .]([0-9]{3})[- .]([0-9]{4})"
str_extract(string = strings, pattern = phone) #返回匹配的最长字符串## [1] "219 733 8965" "329-293-8753" NA "595 794 7569"
## [5] "387 287 6718" NA "233.398.9187" "482 952 3315"
## [9] "239 923 8115" "579-499-7527" NA "543.355.3679"str_match(string = strings, pattern = phone) #返回匹配的最长字符串，同时返回最长字符串中的子字符串## [,1] [,2] [,3] [,4]
## [1,] "219 733 8965" "219" "733" "8965"
## [2,] "329-293-8753" "329" "293" "8753"
## [3,] NA NA NA NA
## [4,] "595 794 7569" "595" "794" "7569"
## [5,] "387 287 6718" "387" "287" "6718"
## [6,] NA NA NA NA
## [7,] "233.398.9187" "233" "398" "9187"
## [8,] "482 952 3315" "482" "952" "3315"
## [9,] "239 923 8115" "239" "923" "8115"
## [10,] "579-499-7527" "579" "499" "7527"
## [11,] NA NA NA NA
## [12,] "543.355.3679" "543" "355" "3679"# Extract/match all
str_extract_all(string = strings, pattern = phone)## [[1]]
## [1] "219 733 8965"
##
## [[2]]
## [1] "329-293-8753"
##
## [[3]]
## character(0)
##
## [[4]]
## [1] "595 794 7569"
##
## [[5]]
## [1] "387 287 6718"
##
## [[6]]
## character(0)
##
## [[7]]
## [1] "233.398.9187"
##
## [[8]]
## [1] "482 952 3315"
##
## [[9]]
## [1] "239 923 8115" "842 566 4692"
##
## [[10]]
## [1] "579-499-7527"
##
## [[11]]
## character(0)
##
## [[12]]
## [1] "543.355.3679"str_match_all(string = strings, pattern = phone)## [[1]]
## [,1] [,2] [,3] [,4]
## [1,] "219 733 8965" "219" "733" "8965"
##
## [[2]]
## [,1] [,2] [,3] [,4]
## [1,] "329-293-8753" "329" "293" "8753"
##
## [[3]]
## [,1] [,2] [,3] [,4]
##
## [[4]]
## [,1] [,2] [,3] [,4]
## [1,] "595 794 7569" "595" "794" "7569"
##
## [[5]]
## [,1] [,2] [,3] [,4]
## [1,] "387 287 6718" "387" "287" "6718"
##
## [[6]]
## [,1] [,2] [,3] [,4]
##
## [[7]]
## [,1] [,2] [,3] [,4]
## [1,] "233.398.9187" "233" "398" "9187"
##
## [[8]]
## [,1] [,2] [,3] [,4]
## [1,] "482 952 3315" "482" "952" "3315"
##
## [[9]]
## [,1] [,2] [,3] [,4]
## [1,] "239 923 8115" "239" "923" "8115"
## [2,] "842 566 4692" "842" "566" "4692"
##
## [[10]]
## [,1] [,2] [,3] [,4]
## [1,] "579-499-7527" "579" "499" "7527"
##
## [[11]]
## [,1] [,2] [,3] [,4]
##
## [[12]]
## [,1] [,2] [,3] [,4]
## [1,] "543.355.3679" "543" "355" "3679"str_order(x, decreasing = FALSE, na_last = TRUE, locale = “”, …)
str_sort(x, decreasing = FALSE, na_last = TRUE, locale = “”, …)
str_order(x = letters, locale = "en")## [1] 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23
## [24] 24 25 26str_sort(x = letters, locale = "en")## [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q"
## [18] "r" "s" "t" "u" "v" "w" "x" "y" "z"str_order(x = letters, locale = "haw")## [1] 1 5 9 15 21 2 3 4 6 7 8 10 11 12 13 14 16 17 18 19 20 22 23
## [24] 24 25 26str_sort(x = letters, locale = "haw")## [1] "a" "e" "i" "o" "u" "b" "c" "d" "f" "g" "h" "j" "k" "l" "m" "n" "p"
## [18] "q" "r" "s" "t" "v" "w" "x" "y" "z"str_pad(string, width, side = c(“left”, “right”, “both”), pad = " “)
rbind(str_pad("hadley", 30, "left"), str_pad("hadley", 30, "right"), str_pad("hadley",
30, "both"))## [,1]
## [1,] " hadley"
## [2,] "hadley "
## [3,] " hadley "str_pad(string = c("a", "abc", "abcdef"), width = 10)## [1] " a" " abc" " abcdef"str_pad(string = "a", width = c(5, 10, 20))## [1] " a" " a" " a"str_pad(string = "a", width = 10, pad = c("-", "_", "+"))## [1] "---------a" "_________a" "+++++++++a"# 当设置width小于string的长度时，结果返回原string
str_pad(string = "hadley", width = 3, pad = "-")## [1] "hadley"str_pad("hadley", width = 8, side = "left", pad = "-")## [1] "--hadley"str_pad("hadley", width = 8, side = "right", pad = "-")## [1] "hadley--"str_pad("hadley", width = 8, side = "both", pad = "-")## [1] "-hadley-"str_replace(string, pattern, replacement)
str_replace_all(string, pattern, replacement)
fruits <- c("one apple", "two pears", "three bananas")
str_replace(string = fruits, pattern = "[aeiou]", replacement = "-") #替换第一个匹配的字符## [1] "-ne apple" "tw- pears" "thr-e bananas"str_replace_all(string = fruits, pattern = "[aeiou]", replacement = "-") #替换所有匹配的字符## [1] "-n- -ppl-" "tw- p--rs" "thr-- b-n-n-s"str_replace(string = fruits, pattern = "([aeiou])", replacement = "")## [1] "ne apple" "tw pears" "thre bananas"str_replace(string = fruits, pattern = "([aeiou])", replacement = "\\1\\1")## [1] "oone apple" "twoo pears" "threee bananas"str_replace(string = fruits, pattern = "[aeiou]", replacement = c("1", "2",
"3"))## [1] "1ne apple" "tw2 pears" "thr3e bananas"str_replace(string = fruits, pattern = c("a", "e", "i"), replacement = "-")## [1] "one -pple" "two p-ars" "three bananas"fruits <- c("one apple", "two pears", "three bananas")
str_replace(string = fruits, pattern = "[aeiou]", replacement = "-")## [1] "-ne apple" "tw- pears" "thr-e bananas"str_replace_all(string = fruits, pattern = "[aeiou]", replacement = "-")## [1] "-n- -ppl-" "tw- p--rs" "thr-- b-n-n-s"str_replace_all(string = fruits, pattern = "([aeiou])", replacement = "")## [1] "n ppl" "tw prs" "thr bnns"str_replace_all(string = fruits, pattern = "([aeiou])", replacement = "\\1\\1")## [1] "oonee aapplee" "twoo peeaars" "threeee baanaanaas"str_replace_all(string = fruits, pattern = "[aeiou]", replacement = c("1", "2",
"3"))## [1] "1n1 1ppl1" "tw2 p22rs" "thr33 b3n3n3s"str_replace_all(string = fruits, pattern = c("a", "e", "i"), replacement = "-")## [1] "one -pple" "two p-ars" "three bananas"# 对一个字符串同时应用多个指定规则进行替换：
strings1 <- str_c(fruits, collapse = "---")
strings1## [1] "one apple---two pears---three bananas"str_replace_all(string = strings1, pattern = c(one = 1, two = 2, three = 3))## [1] "1 apple---2 pears---3 bananas"str_replace_na(string, replacement = “NA”)
str_replace_na(c(NA, "abc", "def"))## [1] "NA" "abc" "def"str_split(string, pattern, n = Inf)#结果返回列表
str_split_fixed(string, pattern, n)#必须设置n，结果返回矩阵
fruits <- c("apples and oranges and pears and bananas", "pineapples and mangos and guavas")
str_split(string = fruits, pattern = " and ")## [[1]]
## [1] "apples" "oranges" "pears" "bananas"
##
## [[2]]
## [1] "pineapples" "mangos" "guavas"str_split_fixed(string = fruits, pattern = " and ", n = 4)## [,1] [,2] [,3] [,4]
## [1,] "apples" "oranges" "pears" "bananas"
## [2,] "pineapples" "mangos" "guavas" ""# 通过设置n，指定分割成n块
str_split(string = fruits, pattern = " and ", n = 3) #将字符串分割成3部分## [[1]]
## [1] "apples" "oranges" "pears and bananas"
##
## [[2]]
## [1] "pineapples" "mangos" "guavas"str_split(string = fruits, pattern = " and ", n = 2) #将字符串分割成2部分## [[1]]
## [1] "apples" "oranges and pears and bananas"
##
## [[2]]
## [1] "pineapples" "mangos and guavas"str_split(string = fruits, pattern = " and ", n = 5) #将字符串分割成5部分## [[1]]
## [1] "apples" "oranges" "pears" "bananas"
##
## [[2]]
## [1] "pineapples" "mangos" "guavas"str_split_fixed(string = fruits, pattern = " and ", n = 3)## [,1] [,2] [,3]
## [1,] "apples" "oranges" "pears and bananas"
## [2,] "pineapples" "mangos" "guavas"str_split_fixed(string = fruits, pattern = " and ", n = 4)## [,1] [,2] [,3] [,4]
## [1,] "apples" "oranges" "pears" "bananas"
## [2,] "pineapples" "mangos" "guavas" ""str_split_fixed(string = fruits, pattern = " and ", n = 6)## [,1] [,2] [,3] [,4] [,5] [,6]
## [1,] "apples" "oranges" "pears" "bananas" "" ""
## [2,] "pineapples" "mangos" "guavas" "" "" ""str_sub(string, start = 1L, end = -1L) 提取子字符串
str_sub(string, start = 1L, end = -1L) <- value 替换子字符串
hw <- "Hadley Wickham"
str_sub(string = hw, start = 1, end = 6)## [1] "Hadley"str_sub(string = hw, end = 6)## [1] "Hadley"str_sub(string = hw, start = 8, end = 14)## [1] "Wickham"str_sub(string = hw, start = 8)## [1] "Wickham"str_sub(string = hw, start = c(1, 8), end = c(6, 14))## [1] "Hadley" "Wickham"# 使用负值索引
str_sub(string = hw, start = -1)## [1] "m"str_sub(string = hw, start = -7)## [1] "Wickham"str_sub(string = hw, end = -7)## [1] "Hadley W"# 从函数str_locate_all的结果传入位置参数
pos <- str_locate_all(hw, "[aeio]")[[1]]
pos## start end
## [1,] 2 2
## [2,] 5 5
## [3,] 9 9
## [4,] 13 13str_sub(string = hw, pos)## [1] "a" "e" "i" "a"str_sub(string = hw, start = pos[, 1], end = pos[, 2])## [1] "a" "e" "i" "a"# 向量化
str_sub(hw, start = seq_len(str_length(hw)))## [1] "Hadley Wickham" "adley Wickham" "dley Wickham" "ley Wickham"
## [5] "ey Wickham" "y Wickham" " Wickham" "Wickham"
## [9] "ickham" "ckham" "kham" "ham"
## [13] "am" "m"str_sub(hw, end = seq_len(str_length(hw)))## [1] "H" "Ha" "Had" "Hadl"
## [5] "Hadle" "Hadley" "Hadley " "Hadley W"
## [9] "Hadley Wi" "Hadley Wic" "Hadley Wick" "Hadley Wickh"
## [13] "Hadley Wickha" "Hadley Wickham"# 替换
x <- "BBCDEF"
str_sub(x, 1, 1) <- "A"
x## [1] "ABCDEF"str_sub(x, -1, -1) <- "K"
x## [1] "ABCDEK"str_sub(x, -2, -2) <- "GHIJ"
x## [1] "ABCDGHIJK"str_sub(x, 2, -2) <- ""
x## [1] "AK"str_subset(string, pattern)
fruit <- c("apple", "banana", "pear", "pinapple")
str_subset(string = fruit, pattern = "a")## [1] "apple" "banana" "pear" "pinapple"str_subset(string = fruit, pattern = "ap")## [1] "apple" "pinapple"str_subset(string = fruit, pattern = "^a")## [1] "apple"str_subset(string = fruit, pattern = "a$")## [1] "banana"str_subset(string = fruit, pattern = "[aeiou]")## [1] "apple" "banana" "pear" "pinapple"# 有缺失值时
str_subset(string = c("a", NA, "b"), pattern = ".")## [1] "a" "b"str_trim(string, side = c(“both”, “left”, “right”))
str_trim(" String with trailing and leading white space\t")## [1] "String with trailing and leading white space"str_trim("\n\nString with trailing and leading white space\n\n")## [1] "String with trailing and leading white space"str_wrap(string, width = 80, indent = 0, exdent = 0)
thanks_path <- file.path(R.home("doc"), "THANKS")
thanks <- str_c(readLines(thanks_path), collapse = "\n")
thanks <- word(thanks, 1, 3, fixed("\n\n"))
cat(str_wrap(thanks), "\n")## R would not be what it is today without the invaluable help of these people,
## who contributed by donating code, bug fixes and documentation: Valerio Aimale,
## Thomas Baier, Henrik Bengtsson, Roger Bivand, Ben Bolker, David Brahm, Goran
## Brostrom, Patrick Burns, Vince Carey, Saikat DebRoy, Brian D'Urso, Lyndon
## Drake, Dirk Eddelbuettel, Claus Ekstrom, Sebastian Fischmeister, John Fox,
## Paul Gilbert, Yu Gong, Gabor Grothendieck, Frank E Harrell Jr, Torsten Hothorn,
## Robert King, Kjetil Kjernsmo, Roger Koenker, Philippe Lambert, Jan de Leeuw,
## Jim Lindsey, Patrick Lindsey, Catherine Loader, Gordon Maclean, John Maindonald,
## David Meyer, Ei-ji Nakama, Jens Oehlschaegel, Steve Oncley, Richard O'Keefe,
## Hubert Palme, Roger D. Peng, Jose' C. Pinheiro, Tony Plate, Anthony Rossini,
## Jonathan Rougier, Petr Savicky, Guenther Sawitzki, Marc Schwartz, Detlef Steuer,
## Bill Simpson, Gordon Smyth, Adrian Trapletti, Terry Therneau, Rolf Turner,
## Bill Venables, Gregory R. Warnes, Andreas Weingessel, Morten Welinder, James
## Wettenhall, Simon Wood and Achim Zeileis. Others have written code that has been
## adopted by R and is acknowledged in the code files, includingcat(str_wrap(string = thanks, width = 70), "\n")## R would not be what it is today without the invaluable help of these
## people, who contributed by donating code, bug fixes and documentation:
## Valerio Aimale, Thomas Baier, Henrik Bengtsson, Roger Bivand, Ben
## Bolker, David Brahm, Goran Brostrom, Patrick Burns, Vince Carey,
## Saikat DebRoy, Brian D'Urso, Lyndon Drake, Dirk Eddelbuettel, Claus
## Ekstrom, Sebastian Fischmeister, John Fox, Paul Gilbert, Yu Gong,
## Gabor Grothendieck, Frank E Harrell Jr, Torsten Hothorn, Robert King,
## Kjetil Kjernsmo, Roger Koenker, Philippe Lambert, Jan de Leeuw, Jim
## Lindsey, Patrick Lindsey, Catherine Loader, Gordon Maclean, John
## Maindonald, David Meyer, Ei-ji Nakama, Jens Oehlschaegel, Steve
## Oncley, Richard O'Keefe, Hubert Palme, Roger D. Peng, Jose' C.
## Pinheiro, Tony Plate, Anthony Rossini, Jonathan Rougier, Petr Savicky,
## Guenther Sawitzki, Marc Schwartz, Detlef Steuer, Bill Simpson,
## Gordon Smyth, Adrian Trapletti, Terry Therneau, Rolf Turner, Bill
## Venables, Gregory R. Warnes, Andreas Weingessel, Morten Welinder,
## James Wettenhall, Simon Wood and Achim Zeileis. Others have written
## code that has been adopted by R and is acknowledged in the code files,
## includingcat(str_wrap(string = thanks, width = 60, indent = 6), "\n")## R would not be what it is today without the invaluable help
## of these people, who contributed by donating code, bug fixes
## and documentation: Valerio Aimale, Thomas Baier, Henrik
## Bengtsson, Roger Bivand, Ben Bolker, David Brahm, Goran
## Brostrom, Patrick Burns, Vince Carey, Saikat DebRoy, Brian
## D'Urso, Lyndon Drake, Dirk Eddelbuettel, Claus Ekstrom,
## Sebastian Fischmeister, John Fox, Paul Gilbert, Yu Gong,
## Gabor Grothendieck, Frank E Harrell Jr, Torsten Hothorn,
## Robert King, Kjetil Kjernsmo, Roger Koenker, Philippe
## Lambert, Jan de Leeuw, Jim Lindsey, Patrick Lindsey,
## Catherine Loader, Gordon Maclean, John Maindonald, David
## Meyer, Ei-ji Nakama, Jens Oehlschaegel, Steve Oncley,
## Richard O'Keefe, Hubert Palme, Roger D. Peng, Jose' C.
## Pinheiro, Tony Plate, Anthony Rossini, Jonathan Rougier,
## Petr Savicky, Guenther Sawitzki, Marc Schwartz, Detlef
## Steuer, Bill Simpson, Gordon Smyth, Adrian Trapletti, Terry
## Therneau, Rolf Turner, Bill Venables, Gregory R. Warnes,
## Andreas Weingessel, Morten Welinder, James Wettenhall, Simon
## Wood and Achim Zeileis. Others have written code that has
## been adopted by R and is acknowledged in the code files,
## includingcat(str_wrap(string = thanks, width = 80, indent = 6, exdent = 2), "\n")## R would not be what it is today without the invaluable help of these people,
## who contributed by donating code, bug fixes and documentation: Valerio Aimale,
## Thomas Baier, Henrik Bengtsson, Roger Bivand, Ben Bolker, David Brahm, Goran
## Brostrom, Patrick Burns, Vince Carey, Saikat DebRoy, Brian D'Urso, Lyndon
## Drake, Dirk Eddelbuettel, Claus Ekstrom, Sebastian Fischmeister, John Fox,
## Paul Gilbert, Yu Gong, Gabor Grothendieck, Frank E Harrell Jr, Torsten Hothorn,
## Robert King, Kjetil Kjernsmo, Roger Koenker, Philippe Lambert, Jan de Leeuw,
## Jim Lindsey, Patrick Lindsey, Catherine Loader, Gordon Maclean, John Maindonald,
## David Meyer, Ei-ji Nakama, Jens Oehlschaegel, Steve Oncley, Richard O'Keefe,
## Hubert Palme, Roger D. Peng, Jose' C. Pinheiro, Tony Plate, Anthony Rossini,
## Jonathan Rougier, Petr Savicky, Guenther Sawitzki, Marc Schwartz, Detlef Steuer,
## Bill Simpson, Gordon Smyth, Adrian Trapletti, Terry Therneau, Rolf Turner,
## Bill Venables, Gregory R. Warnes, Andreas Weingessel, Morten Welinder, James
## Wettenhall, Simon Wood and Achim Zeileis. Others have written code that has been
## adopted by R and is acknowledged in the code files, includingword(string, start = 1L, end = start, sep = fixed(" “))
sentences <- c("Jane saw a cat", "Jane sat down")
word(string = sentences, start = 1) #提取第一个单词## [1] "Jane" "Jane"word(string = sentences, start = 2) #提取第二个单词## [1] "saw" "sat"word(string = sentences, start = -1) #提取句子的最后一个单词## [1] "cat" "down"word(string = sentences, start = 2, end = -1) #提取第二个单词到最后一个单词## [1] "saw a cat" "sat down"# 向量化：
word(string = sentences[1], start = 1:3, end = -1)## [1] "Jane saw a cat" "saw a cat" "a cat"word(string = sentences[1], start = 1, end = 1:4)## [1] "Jane" "Jane saw" "Jane saw a" "Jane saw a cat"# 通过参数sep指定分隔符
str <- "abc.def..123.4568.999"
word(string = str, start = 1, sep = fixed(".."))## [1] "abc.def"word(string = str, start = 2, sep = fixed(".."))## [1] "123.4568.999"paste(…, sep = " “, collapse = NULL)
paste("A", 1:6, sep = "")## [1] "A1" "A2" "A3" "A4" "A5" "A6"paste("A", 1:6, sep = "", collapse = "-") #设置collapse时，将连成一个字符串## [1] "A1-A2-A3-A4-A5-A6"paste(1:6, collapse = "")## [1] "123456"paste(1:6, collapse = "-")## [1] "1-2-3-4-5-6"paste("Today is", date())## [1] "Today is Sat Jun 18 16:29:34 2016"strsplit(x, split, fixed = FALSE, perl = FALSE, useBytes = FALSE)
x <- c(as = "asfef", qu = "qwerty", "yuiop[", "b", "stuff.blah.yech")
strsplit(x = x, split = "e")## $as
## [1] "asf" "f"
##
## $qu
## [1] "qw" "rty"
##
## [[3]]
## [1] "yuiop["
##
## [[4]]
## [1] "b"
##
## [[5]]
## [1] "stuff.blah.y" "ch"unlist(strsplit(x = "a.b.c", split = "."))## [1] "" "" "" "" ""unlist(strsplit(x = "a.b.c", split = "[.]")) #使用‘.’为分割符## [1] "a" "b" "c"# 或者：
unlist(strsplit(x = "a.b.c", split = ".", fixed = TRUE))## [1] "a" "b" "c"x <- "ascd123afrwf34535ddggh454fgf5e4"
strsplit(x = x, split = "[0-9]+", perl = TRUE) #以数字为分割符## [[1]]
## [1] "ascd" "afrwf" "ddggh" "fgf" "e"unlist(strsplit(x = x, split = "[a-z]+")) #以字母为分割符## [1] "" "123" "34535" "454" "5" "4"nchar(x, type = “chars”, allowNA = FALSE)
x <- c("asfef", "qwerty", "yuiop[", "b", "stuff.blah.yech")
nchar(x) #结果返回向量x的每个元素的字符个数## [1] 5 6 6 1 15(1)substr(x, start, stop)
(2)substring(text, first, last = 1000000L)
(3)substr(x, start, stop) <- value
(4)substring(text, first, last = 1000000L) <- value
# 对于单个字符串：
substr(x = "abcdef", start = 2, stop = 4)## [1] "bcd"substring(text = "abcdef", first = 2, last = 4)## [1] "bcd"substring(text = "abcdef", first = 1:6, last = 1:6)## [1] "a" "b" "c" "d" "e" "f"substr(x = rep("abcdef", 4), start = 1:4, stop = 4:5)## [1] "abcd" "bcde" "cd" "de"# 对于字符串向量：
x <- c("asfef", "qwerty", "yuiop[", "b", "stuff.blah.yech")
substr(x = x, start = 2, stop = 5) #对向量x每个元素截取子字符串## [1] "sfef" "wert" "uiop" "" "tuff"substring(text = x, first = 2, last = 4:6)## [1] "sfe" "wert" "uiop[" "" "tuff"substring(text = x, first = 2) <- c("..", "+++") #以赋值的方式进行替换
x## [1] "a..ef" "q+++ty" "y..op[" "b"
## [5] "s..ff.blah.yech"chartr(old, new, x) tolower(x) toupper(x) casefold(x, upper = FALSE)
x <- "MiXeD cAsE 123"
chartr("iXs", "why", x) #i:w,X:h,s:y，单个字符对应替换## [1] "MwheD cAyE 123"chartr("a-cX", "D-Fw", x)## [1] "MiweD FAsE 123"tolower(x) #转换成小写## [1] "mixed case 123"toupper(x) #转换成大写## [1] "MIXED CASE 123"casefold(x, upper = FALSE)## [1] "mixed case 123"casefold(x, upper = TRUE)## [1] "MIXED CASE 123"txt <- c("10arm03", "Foot 12", " 678-lefroo.345", "__.bafoobar90..")
grep(pattern = "foo", x = txt, value = FALSE) #区分大小写，结果返回匹配的元素索引## [1] 4grep(pattern = "foo", x = txt, value = TRUE) #区分大小写，结果返回匹配的元素值## [1] "__.bafoobar90.."grep(pattern = "foo", x = txt, ignore.case = TRUE) #忽略大小写，结果返回匹配的元素索引## [1] 2 4grep(pattern = "foo", x = txt, ignore.case = TRUE, value = TRUE) #忽略大小写，结果返回匹配的元素值## [1] "Foot 12" "__.bafoobar90.."grep(pattern = "foo", x = txt, ignore.case = TRUE, value = TRUE, invert = TRUE) #忽略大小写，结果返回不匹配的元素值## [1] "10arm03" " 678-lefroo.345"grep(pattern = "^[0-9]+", x = txt, perl = TRUE) #返回以数字开头的元素索引## [1] 1grep(pattern = "[0-9]+$", x = txt, perl = TRUE, value = TRUE) #返回以数字结尾的元素## [1] "10arm03" "Foot 12" " 678-lefroo.345"grep(pattern = "\\d$", x = txt, perl = TRUE, value = TRUE) #返回以数字结尾的元素## [1] "10arm03" "Foot 12" " 678-lefroo.345"txt <- c("10arm03", "Foot 12", " 678-lefroo.345", "__.bafoobar90..")
grepl(pattern = "foo", x = txt)## [1] FALSE FALSE FALSE TRUEgrepl(pattern = "\\d$", x = txt, perl = TRUE)## [1] TRUE TRUE TRUE FALSEtxt <- c("10arm03", "Foot 12 foot", " 678-lefroo.345", "__.bafoobar90foobar..")
sub(pattern = "foo", replacement = "99", x = txt) #将元素中的第一个foo替换成99## [1] "10arm03" "Foot 12 99t" " 678-lefroo.345"
## [4] "__.ba99bar90foobar.."sub(pattern = "\\d+$", replacement = "+++", x = txt, perl = TRUE) #将结尾的数字替换成+++## [1] "10arm+++" "Foot 12 foot" " 678-lefroo.+++"
## [4] "__.bafoobar90foobar.."txt <- c("10arm03", "Foot 12 foot", " 678-lefroo.345", "__.bafoobar90foobar..")
gsub(pattern = "foo", replacement = "99", x = txt) #将所有的foo替换成99## [1] "10arm03" "Foot 12 99t" " 678-lefroo.345"
## [4] "__.ba99bar9099bar.."gsub(pattern = "\\d+", replacement = "+++", x = txt, perl = TRUE) #将所有数字替换成+++## [1] "+++arm+++" "Foot +++ foot"
## [3] " +++-lefroo.+++" "__.bafoobar+++foobar.."txt <- c("10arm03", "Foot 12 foot", " 678-lefroo.345", "__.bafoobar90foobar..")
regexpr(pattern = "foo", text = txt)## [1] -1 9 -1 6
## attr(,"match.length")
## [1] -1 3 -1 3
## attr(,"useBytes")
## [1] TRUEregexpr(pattern = "\\d+", text = txt)## [1] 1 6 2 12
## attr(,"match.length")
## [1] 2 2 3 2
## attr(,"useBytes")
## [1] TRUEtxt <- c("10arm03", "Foot 12 foot", " 678-lefroo.345", "__.bafoobar90foobar..")
gregexpr(pattern = "foo", text = txt)## [[1]]
## [1] -1
## attr(,"match.length")
## [1] -1
## attr(,"useBytes")
## [1] TRUE
##
## [[2]]
## [1] 9
## attr(,"match.length")
## [1] 3
## attr(,"useBytes")
## [1] TRUE
##
## [[3]]
## [1] -1
## attr(,"match.length")
## [1] -1
## attr(,"useBytes")
## [1] TRUE
##
## [[4]]
## [1] 6 14
## attr(,"match.length")
## [1] 3 3
## attr(,"useBytes")
## [1] TRUEgregexpr(pattern = "\\d+", text = txt)## [[1]]
## [1] 1 6
## attr(,"match.length")
## [1] 2 2
## attr(,"useBytes")
## [1] TRUE
##
## [[2]]
## [1] 6
## attr(,"match.length")
## [1] 2
## attr(,"useBytes")
## [1] TRUE
##
## [[3]]
## [1] 2 13
## attr(,"match.length")
## [1] 3 3
## attr(,"useBytes")
## [1] TRUE
##
## [[4]]
## [1] 12
## attr(,"match.length")
## [1] 2
## attr(,"useBytes")
## [1] TRUEtxt <- c(NA, "Foot 12 foot", " 678-lefroo.345", "__.bafoobar90foobar..")
regexec(pattern = "foo", text = txt)## [[1]]
## [1] NA
## attr(,"match.length")
## [1] NA
##
## [[2]]
## [1] 9
## attr(,"match.length")
## [1] 3
##
## [[3]]
## [1] -1
## attr(,"match.length")
## [1] -1
##
## [[4]]
## [1] 6
## attr(,"match.length")
## [1] 3regexec(pattern = "\\d+", text = txt)## [[1]]
## [1] NA
## attr(,"match.length")
## [1] NA
##
## [[2]]
## [1] 6
## attr(,"match.length")
## [1] 2
##
## [[3]]
## [1] 2
## attr(,"match.length")
## [1] 3
##
## [[4]]
## [1] 12
## attr(,"match.length")
## [1] 2