This lecture note is based on Dr. Hua Zhou’s 2018 Winter Statistical Computing course notes available at http://hua-zhou.github.io/teaching/biostatm280-2018winter/index.html.
stringr pacakge, by Hadley Wickham, provides utilities for handling strings.
Included in tidyverse.
library("tidyverse")Strings are enclosed by double quotes orx single quotes:
string1 <- "This is a string"
string2 <- 'If I want to include a "quote" inside a string, I use single quotes'Literal single or double quote:
double_quote <- "\"" # or '"'
single_quote <- '\'' # or "'"Printed representation:
x <- c("\"", "\\")
x## [1] "\"" "\\"vs writeLines():
writeLines(x)## "
## \Other special characters: "\n" (new line), "\t" (tab), … Check
?"'"for a complete list.
Unicode
x <- "\u00b5"
x## [1] "µ"Character vector (vector of strings):
c("one", "two", "three")## [1] "one" "two" "three"Length of a single string:
str_length("R for data science")## [1] 18Lengths of a character vector:
str_length(c("a", "R for data science", NA))## [1] 1 18 NACombine two or more strings
str_c("x", "y")## [1] "xy"str_c("x", "y", "z")## [1] "xyz"Separator:
str_c("x", "y", sep = ", ")## [1] "x, y"str_c() is vectorised:
str_c("prefix-", c("a", "b", "c"), "-suffix")## [1] "prefix-a-suffix" "prefix-b-suffix" "prefix-c-suffix"Objects of length 0 are silently dropped:
name <- "Hadley"
time_of_day <- "morning"
birthday <- FALSE
str_c(
"Good ", time_of_day, " ", name,
if (birthday) " and HAPPY BIRTHDAY",
"."
)## [1] "Good morning Hadley."Combine a vector of strings:
str_c(c("x", "y", "z"))## [1] "x" "y" "z"str_c(c("x", "y", "z"), collapse = ", ")## [1] "x, y, z"By position:
str_sub("Apple", 1, 3)## [1] "App"x <- c("Apple", "Banana", "Pear")
str_sub(x, 1, 3)## [1] "App" "Ban" "Pea"Negative numbers count backwards from end:
str_sub(x, -3, -1)## [1] "ple" "ana" "ear"Out of range:
str_sub("a", 1, 5)## [1] "a"str_sub("a", 2, 5)## [1] ""Assignment to a substring:
str_sub(x, 1, 1) <- str_to_lower(str_sub(x, 1, 1))
x## [1] "apple" "banana" "pear"str_view() shows the first match;
str_view_all() shows all matches.
Match exact strings:
x <- c("apple", "banana", "pear")
str_view(x, "an")str_view_all(x, "an"). matches any character apart from a newline:
str_view(x, ".a.")To match a literal .:
str_view(c("abc", "a.c", "bef"), "a\\.c")To match a literal \:
str_view("a\\b", "\\\\")^ matches the start of the string:
x <- c("apple", "banana", "pear")
str_view(x, "^a")$ matches the end of the string:
str_view(x, "a$")To force a regular expression to only match a complete string:
x <- c("apple pie", "apple", "apple cake")
str_view(x, "^apple$")Other special matches:
\d: matches any digit.
\s: matches any whitespace (e.g. space, tab, newline).
[abc]: matches a, b, or c.
[^abc]: matches anything except a, b, or c.
alternation
str_view(c("grey", "gray"), "gr(e|a)y")str_view(c("grey", "gray"), "gr[ea]y")?: 0 or 1
+: 1 or more
*: 0 or more
x <- "1888 is the longest year in Roman numerals: MDCCCLXXXVIII"
str_view(x, "CC?")# greedy matches
str_view(x, "CC+")# greedy matches
str_view(x, 'C[LX]+')Specify number of matches:
{n}: exactly n
{n,}: n or more
{,m}: at most m
{n,m}: between n and m
str_view(x, "C{2}")# greedy matches
str_view(x, "C{2,}")# greedy matches
str_view(x, "C{2,3}")Greedy (default) vs lazy (put ? after repetition):
# lazy matches
str_view(x, 'C{2,3}?')# lazy matches
str_view(x, 'C[LX]+?')Parentheses define groups, which can be back-referenced as \1, \2, …
str_view(fruit, "(..)\\1", match = TRUE)x <- c("apple", "banana", "pear")
str_detect(x, "e")## [1] TRUE FALSE TRUEVector words contains 1000 commonly used words:
length(words)## [1] 980head(words)## [1] "a" "able" "about" "absolute" "accept" "account"# How many common words start with t?
sum(str_detect(words, "^t"))## [1] 65# What proportion of common words end with a vowel?
mean(str_detect(words, "[aeiou]$"))## [1] 0.2765306Find workds that end with x:
words[str_detect(words, "x$")]## [1] "box" "sex" "six" "tax"same as
str_subset(words, "x$")## [1] "box" "sex" "six" "tax"Filter a data frame:
df <- tibble(
word = words,
i = seq_along(word)
)
df %>%
filter(str_detect(words, "x$"))## # A tibble: 4 x 2
## word i
## <chr> <int>
## 1 box 108
## 2 sex 747
## 3 six 772
## 4 tax 841str_count() tells how many matches are found:
x <- c("apple", "banana", "pear")
str_count(x, "a")## [1] 1 3 1# On average, how many vowels per word?
mean(str_count(words, "[aeiou]"))## [1] 1.991837Matches never overlap:
str_count("abababa", "aba")## [1] 2str_view_all("abababa", "aba")Mutate a data frame:
df %>%
mutate(
vowels = str_count(word, "[aeiou]"),
consonants = str_count(word, "[^aeiou]")
)## # A tibble: 980 x 4
## word i vowels consonants
## <chr> <int> <int> <int>
## 1 a 1 1 0
## 2 able 2 2 2
## 3 about 3 3 2
## 4 absolute 4 4 4
## 5 accept 5 2 4
## 6 account 6 3 4
## 7 achieve 7 4 3
## 8 across 8 2 4
## 9 act 9 1 2
## 10 active 10 3 3
## # ... with 970 more rowssentences is a collection of 720 phrases:
length(sentences)## [1] 720head(sentences)## [1] "The birch canoe slid on the smooth planks."
## [2] "Glue the sheet to the dark blue background."
## [3] "It's easy to tell the depth of a well."
## [4] "These days a chicken leg is a rare dish."
## [5] "Rice is often served in round bowls."
## [6] "The juice of lemons makes fine punch."Suppose we want to find all sentences that contain a colour.
Create a collection of colours:
colours <- c("red", "orange", "yellow", "green", "blue", "purple")
colour_match <- str_c(colours, collapse = "|")
colour_match## [1] "red|orange|yellow|green|blue|purple"Select the sentences that contain a colour, and then extract the colour to figure out which one it is:
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() only extracts the first match.
more <- sentences[str_count(sentences, colour_match) > 1]
str_view_all(more, colour_match)str_extract_all() extracts all matches:
str_extract_all(more, colour_match)## [[1]]
## [1] "blue" "red"
##
## [[2]]
## [1] "green" "red"
##
## [[3]]
## [1] "orange" "red"Setting simplify = TRUE in str_extract_all() will return a matrix with short matches expanded to the same length as the longest:
str_extract_all(more, colour_match, simplify = TRUE)## [,1] [,2]
## [1,] "blue" "red"
## [2,] "green" "red"
## [3,] "orange" "red"x <- c("a", "a b", "a b c")
str_extract_all(x, "[a-z]", simplify = TRUE)## [,1] [,2] [,3]
## [1,] "a" "" ""
## [2,] "a" "b" ""
## [3,] "a" "b" "c"str_extract() gives us the complete match:
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() gives each individual component:
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"tidyr::extract() works with tibble:
tibble(sentence = sentences) %>%
tidyr::extract(
sentence, c("article", "noun"), "(a|the) ([^ ]+)",
remove = FALSE
)## # 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 rowsReplace the first match:
x <- c("apple", "pear", "banana")
str_replace(x, "[aeiou]", "-")## [1] "-pple" "p-ar" "b-nana"Replace all matches:
str_replace_all(x, "[aeiou]", "-")## [1] "-ppl-" "p--r" "b-n-n-"Multiple replacement:
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"Back-reference:
# flip the order of the second and third words
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."Split a string up into pieces:
sentences %>%
head(5) %>%
str_split(" ")## [[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."Use simplify = TRUE to return a matrix:
sentences %>%
head(5) %>%
str_split(" ", simplify = TRUE)## [,1] [,2] [,3] [,4] [,5] [,6] [,7]
## [1,] "The" "birch" "canoe" "slid" "on" "the" "smooth"
## [2,] "Glue" "the" "sheet" "to" "the" "dark" "blue"
## [3,] "It's" "easy" "to" "tell" "the" "depth" "of"
## [4,] "These" "days" "a" "chicken" "leg" "is" "a"
## [5,] "Rice" "is" "often" "served" "in" "round" "bowls."
## [,8] [,9]
## [1,] "planks." ""
## [2,] "background." ""
## [3,] "a" "well."
## [4,] "rare" "dish."
## [5,] "" ""