这篇笔记记录一下在 R 中 如何处理字符串，虽然对我个人来说更加习惯 perl ，但是不想 R、perl 来回切换，所以还是在 R 中学习一下，stringr 这个包很强大
library(tidyverse)## ─ Attaching packages ─────────────────────── tidyverse 1.2.1 ─## ✔ ggplot2 3.2.0 ✔ purrr 0.3.2
## ✔ tibble 2.1.3 ✔ dplyr 0.8.3
## ✔ tidyr 0.8.3 ✔ stringr 1.4.0
## ✔ readr 1.3.1 ✔ forcats 0.4.0## ─ Conflicts ──────────────────────── tidyverse_conflicts() ─
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()library(stringr)你可以使用 “” 创建一个字符串
string1 <- "this is a string"
string1## [1] "this is a string"string2 <- 'a "quote" inside a string'
string2## [1] "a \"quote\" inside a string"如果你想在字符串中包含 双引号和单引号，可以使用 进行转义
double_quote <- "\"" # or '"'
double_quote## [1] "\""single_quote <- '\'' # or "'"
single_quote## [1] "'"如果你想创建带有 的字符串，同样需要转义
slash <- "\\"
slash## [1] "\\"R 基础函数有许多对字符串处理的函数，但建议避免使用它们，因为你很难记住它们，然而在 stringr 包中可以很好的对这些函数进行记忆
str_length(c("a", "R for data science", NA))## [1] 1 18 NAstr_order() 返回排序后的索引
str_sort() 返回排序后的实际值
x <- c("ab","ac","ba")
str_order(x)## [1] 1 2 3str_sort(x)## [1] "ab" "ac" "ba"合并多个字符串为一个字符串
str_c("x","y")## [1] "xy"str_c("x","y","z")## [1] "xyz"指定 sep 参数定义分隔符
str_c("x","y",sep = ", ")## [1] "x, y"指定 collapse 把向量参数合并成一个大的字符串
str_c(head(letters),collapse = ",")## [1] "a,b,c,d,e,f"# collapse 对多个字符串没有效果
str_c(c('a','a1'),c('b','b1'),collapse='-')## [1] "ab-a1b1"str_c() 是一个向量化函数，可以对长度短的字符向量进行再循环
str_c("prefix-",c('a','b','c'),"-suffix")## [1] "prefix-a-suffix" "prefix-b-suffix" "prefix-c-suffix"将一个字符向量合并成一个字符串，使用 collapse 参数
str_c(c("x","y","z"),collapse = ",") ## [1] "x,y,z"提取字符串子集
x <- c("apple","banana","pear")
str_sub(x,1,3) # 从第一个字符开始提取到第三个字符结束## [1] "app" "ban" "pea"负数表示从后往前区子集，最后一个位置为 -1
str_sub(x,-3,-1)## [1] "ple" "ana" "ear"str_trim(" abc ")## [1] "abc"# 也可以指定去除哪端的空格
str_trim(" abc ",side = "left")## [1] "abc "str_pad("abc",5,side = "both") # 5 表示填充后的长度为 5## [1] " abc "# pad 参数可以指定用什么字符填充
str_pad("abc",5,side = "both",pad = "*")## [1] "*abc*"结合 Purrr 包 函数式编程可以向量化去除空格和添加空格
x <- c("x","y","z")
library(purrr)
map_chr(x,str_pad,5,side = "left")## [1] " x" " y" " z"str_c(x[seq_len(3) - 1],collapse = ",")## [1] "x,y"R 中的正则表达式和 perl 中有点不一样,基本语法类似
str_view() 和 str_view_all() 这两个函数是用来学习正则表达式的
library(htmlwidgets)
x <- c("apple","banana","pear")
str_view(x,"an")" . " 可以表示任意字符，除了换行符
str_view(x,".a.")如果你要匹配 “.” 号，你需要进行转义(告诉 R 只想对 " . “进行匹配，消除”." 的匹配特性)
str_view(c("abc","a.c","bef"),"a\\.c") # 由于在 R 中 转义字符为 "\\" # 如果要匹配 \,需要用 \\\\ 来匹配
str_view(c("a\\c","abc"),"\\\\")^ 匹配字符开头
$ 匹配字符结尾
x <- c("apple","banana")
str_view(x,"^a")str_view(x,"a$") 若想匹配一个完整的字符，同时使用 ^ 和 $
x <- c("apple pie", "apple", "apple cake")
str_view(x,"^apple$")和其他语言的正则表达式一样，在使用上不同的地方在于需要使用两个斜杠
x <- c("1","a1w")
str_view(x,"^\\d$")和其他语言的正则表达式一样(略)
和其他语言的正则表达式一样(略) ，注意使用 双斜杠 反向引用
x <- c("abab","abba")
str_view(x,"(..)\\1")以上就是 R 中正则表达式的基础部分，后面将学习如何使用它们解决实际问题，stringr 包实现的功能有
检查一个字符向量是否匹配一个模式，返回的是一个逻辑向量
x <- c("apple","banana","pear")
str_detect(x,"e")## [1] TRUE FALSE TRUE一个常见的应用就是，用得到的逻辑向量去获取匹配的子元素
x[str_detect(x,"e")]## [1] "apple" "pear"# 可以使用 str_subset 替代上式
str_subset(x,"e")## [1] "apple" "pear"实际应用场景更多的是，query 字符向量作为数据框的列向量
df <- tibble(word = x,
i = 1:3)
df %>% filter(str_detect(word,"e"))## # A tibble: 2 x 2
## word i
## <chr> <int>
## 1 apple 1
## 2 pear 3另一个有用的函数是 str_count(),将返回每一个字符串中能匹配的个数
x <- c("apple", "banana", "pear")
str_count(x, "a")## [1] 1 3 1将 str_count() 和 mutate() 相结合将会很有用
df %>% mutate(a = str_count(word,"a"))## # A tibble: 3 x 3
## word i a
## <chr> <int> <int>
## 1 apple 1 1
## 2 banana 2 3
## 3 pear 3 1使用一个案例 Harvard sentences，假设我们想提取句子中带有颜色的词汇
colours <- c("red", "orange", "yellow", "green", "blue", "purple")
colour_match <- str_c(colours, collapse = "|")
colour_match## [1] "red|orange|yellow|green|blue|purple"has_colour <- str_subset(sentences, colour_match)
matches <- str_extract(has_colour, colour_match)
head(matches)## [1] "blue" "blue" "red" "red" "red" "blue"str_extract() 只提取第一个匹配，你能使用 str_extract_all() 提取所有匹配,结果以列表展示
str_extract_all(has_colour,colour_match) %>% head()## [[1]]
## [1] "blue"
##
## [[2]]
## [1] "blue"
##
## [[3]]
## [1] "red"
##
## [[4]]
## [1] "red"
##
## [[5]]
## [1] "red"
##
## [[6]]
## [1] "blue"simplify = TRUE 则返回一个矩阵
str_extract_all(has_colour,colour_match,simplify = T) %>% head()## [,1] [,2]
## [1,] "blue" ""
## [2,] "blue" ""
## [3,] "red" ""
## [4,] "red" ""
## [5,] "red" ""
## [6,] "blue" ""找出 sentences 中所有以 “a” 或 “the” 为量词的名词
noun <- "(a|the) ([^ ]+)"
has_noun <- sentences %>%
str_subset(noun) %>%
head(10)
has_noun %>%
str_extract(noun)## [1] "the smooth" "the sheet" "the depth" "a chicken" "the parked"
## [6] "the sun" "the huge" "the ball" "the woman" "a helps"str_match() 不同于 str_extract(),主要在于 str_match() 会返回每一个捕获的内容
noun <- "(a|the) ([^ ]+)"
has_noun <- sentences %>%
str_subset(noun) %>%
head(10)
has_noun %>%
str_match(noun)## [,1] [,2] [,3]
## [1,] "the smooth" "the" "smooth"
## [2,] "the sheet" "the" "sheet"
## [3,] "the depth" "the" "depth"
## [4,] "a chicken" "a" "chicken"
## [5,] "the parked" "the" "parked"
## [6,] "the sun" "the" "sun"
## [7,] "the huge" "the" "huge"
## [8,] "the ball" "the" "ball"
## [9,] "the woman" "the" "woman"
## [10,] "a helps" "a" "helps"如果你的数据是 tibble, 使用 tidyr::extract()会很方便，这个函数类似于 str_match(),需要你命名捕获，然后形成一个新的变量
tibble(sentence = sentences) %>%
tidyr::extract(
sentence, c("article", "noun"), "(a|the) ([^ ]+)",
remove = F
)## # A tibble: 720 x 3
## sentence article noun
## <chr> <chr> <chr>
## 1 The birch canoe slid on the smooth planks. the smooth
## 2 Glue the sheet to the dark blue background. the sheet
## 3 It's easy to tell the depth of a well. the depth
## 4 These days a chicken leg is a rare dish. a chicken
## 5 Rice is often served in round bowls. <NA> <NA>
## 6 The juice of lemons makes fine punch. <NA> <NA>
## 7 The box was thrown beside the parked truck. the parked
## 8 The hogs were fed chopped corn and garbage. <NA> <NA>
## 9 Four hours of steady work faced us. <NA> <NA>
## 10 Large size in stockings is hard to sell. <NA> <NA>
## # … with 710 more rowsstr_replace() 和 str_replace_all() 允许你替换匹配形成新的字符串
x <- c("apple", "pear", "banana")
str_replace(x, "[aeiou]", "-") ## [1] "-pple" "p-ar" "b-nana"str_replace_all(x, "[aeiou]", "-")## [1] "-ppl-" "p--r" "b-n-n-"使用 str_replace_all() 你也可以提供一个有 name 的 向量进行多处替换
x <- c("1 house", "2 cars", "3 people")
str_replace_all(x, c("1" = "one", "2" = "two", "3" = "three"))## [1] "one house" "two cars" "three people"在替换过程中，也可以结合反向引用
sentences %>%
str_replace("([^ ]+) ([^ ]+) ([^ ]+)", "\\1 \\3 \\2") %>%
head(5)## [1] "The canoe birch slid on the smooth planks."
## [2] "Glue sheet the to the dark blue background."
## [3] "It's to easy tell the depth of a well."
## [4] "These a days chicken leg is a rare dish."
## [5] "Rice often is served in round bowls."使用 str_split() 分解字符串成多个部分，返回一个列表，同样可以指定 simplify = TRUE,返回矩阵
sentences %>%
head(5) %>%
str_split(" ") # 使用空格分解## [[1]]
## [1] "The" "birch" "canoe" "slid" "on" "the" "smooth"
## [8] "planks."
##
## [[2]]
## [1] "Glue" "the" "sheet" "to" "the"
## [6] "dark" "blue" "background."
##
## [[3]]
## [1] "It's" "easy" "to" "tell" "the" "depth" "of" "a" "well."
##
## [[4]]
## [1] "These" "days" "a" "chicken" "leg" "is" "a"
## [8] "rare" "dish."
##
## [[5]]
## [1] "Rice" "is" "often" "served" "in" "round" "bowls."fields <- c("Name: Hadley", "Country: NZ", "Age: 35")
fields %>% str_split(": ", n = 2, simplify = TRUE)## [,1] [,2]
## [1,] "Name" "Hadley"
## [2,] "Country" "NZ"
## [3,] "Age" "35"可以直接用 str_split_fixed() 返回矩阵格式
fields %>% str_split_fixed(": ",n = 2)## [,1] [,2]
## [1,] "Name" "Hadley"
## [2,] "Country" "NZ"
## [3,] "Age" "35"str_sub("abcdef",1,3)## [1] "abc"当你用一个字符串作为匹配模式模式时，将自动执行 regex() ,因此，你可以使用 regex() 去设置更多的匹配细节
str_view(c("apple","banana"),"nana")# 等价于
str_view(c("apple","banana"),regex("nana"))通过设置 regex() 其他的参数，可以实现更加强大的正则匹配
忽略大小写
ignore_case = TRUE， 默认为 false
bananas <- c("banana", "Banana", "BANANA")
str_view(bananas, "banana")str_view(bananas,regex("banana",ignore_case = T))多行匹配
multiline = TRUE 这种情况下， ^ 和 $ 则是匹配行的开头和结尾，而不是字符的开头为结尾
x <- "Line 1\nLine 2\nLine 3"
str_extract_all(x,"^Line")[[1]]## [1] "Line"str_extract_all(x,regex("^Line",multiline = T))[[1]]## [1] "Line" "Line" "Line"允许正则表达式中出现空格
comments = TRUE 为了让代码可读性大大增强，尤其是对于复杂的正则表达式
phone <- regex("
\\(? # optional opening parens
(\\d{3}) # area code
[) -]? # optional closing parens, space, or dash
(\\d{3}) # another three numbers
[ -]? # optional space or dash
(\\d{3}) # three more numbers
",
comments = T)
str_match("514-791-8141",phone)## [,1] [,2] [,3] [,4]
## [1,] "514-791-814" "514" "791" "814"允许点号匹配一切字符，包括换行符
dotall = TRUE
x <- "string\nabcd"
str_view(x,regex("g.*b",dotall = T))str_locate() 返回匹配对象的首末位置，一般与 str_sub函数搭配使用
fruit <- c("apple", "banana", "pear")
str_locate_all(fruit,'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大小写转换 str_to_upper / lower()
str_to_upper("apple")## [1] "APPLE"将首字母变换为大写
str_to_title()
str_to_title("apple")## [1] "Apple"