hw06_data_wrangling

14.2.5 Exercises

3. Use str_length() and str_sub() to extract the middle character from a string. What will you do if the string has an even number of characters?

library(tidyverse)
library(stringr)

string1 <- "abc"
string2 <- "abcd"

str_sub(string1, floor((str_length(string1)+1)/2), ceiling((str_length(string1)+1)/2))

## [1] "b"

str_sub(string2, floor((str_length(string2)+1)/2), ceiling((str_length(string2)+1)/2)) #returns the two middle characters as the string has an even number. 

## [1] "bc"

I chose to extract both of the middle characters when having an even number, but I could also extract only one arbitrarily:

str_sub(string2, ceiling(str_length(string2)/2), ceiling(str_length(string2)/2))

## [1] "b"

This way, I extract only one of the middle characters.

6. Write a function that turns (e.g.) a vector c(“a”, “b”, “c”) into the string a, b, and c. Think carefully about what it should do if given a vector of length 0, 1, or 2.

st_comma <- function (x, delim = ",") {
  num <- length(x)
  if(num == 0) {
   stop("vector length = 0") #error message when trying with a length 0 vector
  } else if(num == 1) {
    x
  } else if(num == 2) {
    str_c(x[[1]], "and", x[[2]], sep = " ")
  } else {
   str_1 <- str_c(x[seq_len(num - 1)], delim) #all but the last
   str_2 <- str_c("and", x[[num]], sep = " ")
   str_c(c(str_1, str_2), collapse = " ")
  }
}

#st_comma(c()) # as vector is length 0, the function throws an error message "vector length = 0"
st_comma("a") 

## [1] "a"

st_comma(c("a", "b"))

## [1] "a and b"

st_comma(c("a", "b", "c"))

## [1] "a, b, and c"

14.3.1.1 Basic matches

2. How would you match the sequence "'\?

str_view("\"'\\", "\"'\\\\")

3. What patterns will the regular expression \..\..\.. match? How would you represent it as a string?

str_view("w.x.y.z", "\\..\\..\\..")

It matches patterns with a dot followed by a character that repeats three times.

14.3.2.1 Anchors

1. How would you match the literal string "$^$" ?

str_view("$^$", "^\\$\\^\\$")

2. Given the corpus of common words in stringr::words, create regular expressions that find all words that:

• Start with “y”.
• End with “x”
• Are exactly three letters long. (Don’t cheat by using str_length()!)
• Have seven letters or more.

Since the list is long, I used a match argument to show only the matching words. When the output is too long, I use str_subset instead of str_view to have a more compact output.

str_view_match <- function(words, pattern) {
    str_view(words, pattern, match=TRUE)
} #function to only show matches

# start with y
str_view_match(words, "^y") 

# end with x
str_view_match(words, "x$")

# have exactly three letters
str_subset(words, "^...$")

##   [1] "act" "add" "age" "ago" "air" "all" "and" "any" "arm" "art" "ask"
##  [12] "bad" "bag" "bar" "bed" "bet" "big" "bit" "box" "boy" "bus" "but"
##  [23] "buy" "can" "car" "cat" "cup" "cut" "dad" "day" "die" "dog" "dry"
##  [34] "due" "eat" "egg" "end" "eye" "far" "few" "fit" "fly" "for" "fun"
##  [45] "gas" "get" "god" "guy" "hit" "hot" "how" "job" "key" "kid" "lad"
##  [56] "law" "lay" "leg" "let" "lie" "lot" "low" "man" "may" "mrs" "new"
##  [67] "non" "not" "now" "odd" "off" "old" "one" "out" "own" "pay" "per"
##  [78] "put" "red" "rid" "run" "say" "see" "set" "sex" "she" "sir" "sit"
##  [89] "six" "son" "sun" "tax" "tea" "ten" "the" "tie" "too" "top" "try"
## [100] "two" "use" "war" "way" "wee" "who" "why" "win" "yes" "yet" "you"

# ≥ 7 letters
str_subset(words, ".......")

##   [1] "absolute"    "account"     "achieve"     "address"     "advertise"  
##   [6] "afternoon"   "against"     "already"     "alright"     "although"   
##  [11] "america"     "another"     "apparent"    "appoint"     "approach"   
##  [16] "appropriate" "arrange"     "associate"   "authority"   "available"  
##  [21] "balance"     "because"     "believe"     "benefit"     "between"    
##  [26] "brilliant"   "britain"     "brother"     "business"    "certain"    
##  [31] "chairman"    "character"   "Christmas"   "colleague"   "collect"    
##  [36] "college"     "comment"     "committee"   "community"   "company"    
##  [41] "compare"     "complete"    "compute"     "concern"     "condition"  
##  [46] "consider"    "consult"     "contact"     "continue"    "contract"   
##  [51] "control"     "converse"    "correct"     "council"     "country"    
##  [56] "current"     "decision"    "definite"    "department"  "describe"   
##  [61] "develop"     "difference"  "difficult"   "discuss"     "district"   
##  [66] "document"    "economy"     "educate"     "electric"    "encourage"  
##  [71] "english"     "environment" "especial"    "evening"     "evidence"   
##  [76] "example"     "exercise"    "expense"     "experience"  "explain"    
##  [81] "express"     "finance"     "fortune"     "forward"     "function"   
##  [86] "further"     "general"     "germany"     "goodbye"     "history"    
##  [91] "holiday"     "hospital"    "however"     "hundred"     "husband"    
##  [96] "identify"    "imagine"     "important"   "improve"     "include"    
## [101] "increase"    "individual"  "industry"    "instead"     "interest"   
## [106] "introduce"   "involve"     "kitchen"     "language"    "machine"    
## [111] "meaning"     "measure"     "mention"     "million"     "minister"   
## [116] "morning"     "necessary"   "obvious"     "occasion"    "operate"    
## [121] "opportunity" "organize"    "original"    "otherwise"   "paragraph"  
## [126] "particular"  "pension"     "percent"     "perfect"     "perhaps"    
## [131] "photograph"  "picture"     "politic"     "position"    "positive"   
## [136] "possible"    "practise"    "prepare"     "present"     "pressure"   
## [141] "presume"     "previous"    "private"     "probable"    "problem"    
## [146] "proceed"     "process"     "produce"     "product"     "programme"  
## [151] "project"     "propose"     "protect"     "provide"     "purpose"    
## [156] "quality"     "quarter"     "question"    "realise"     "receive"    
## [161] "recognize"   "recommend"   "relation"    "remember"    "represent"  
## [166] "require"     "research"    "resource"    "respect"     "responsible"
## [171] "saturday"    "science"     "scotland"    "secretary"   "section"    
## [176] "separate"    "serious"     "service"     "similar"     "situate"    
## [181] "society"     "special"     "specific"    "standard"    "station"    
## [186] "straight"    "strategy"    "structure"   "student"     "subject"    
## [191] "succeed"     "suggest"     "support"     "suppose"     "surprise"   
## [196] "telephone"   "television"  "terrible"    "therefore"   "thirteen"   
## [201] "thousand"    "through"     "thursday"    "together"    "tomorrow"   
## [206] "tonight"     "traffic"     "transport"   "trouble"     "tuesday"    
## [211] "understand"  "university"  "various"     "village"     "wednesday"  
## [216] "welcome"     "whether"     "without"     "yesterday"

14.3.3.1 Character classes and alternatives

1. Create regular expressions to find all words that:

• Start with a vowel.
• That only contain consonants. (Hint: thinking about matching “not”-vowels.)
• End with ed, but not with eed.
• End with ing or ise.

# start with a vowel
str_subset(words, "^[aeiou]")

##   [1] "a"           "able"        "about"       "absolute"    "accept"     
##   [6] "account"     "achieve"     "across"      "act"         "active"     
##  [11] "actual"      "add"         "address"     "admit"       "advertise"  
##  [16] "affect"      "afford"      "after"       "afternoon"   "again"      
##  [21] "against"     "age"         "agent"       "ago"         "agree"      
##  [26] "air"         "all"         "allow"       "almost"      "along"      
##  [31] "already"     "alright"     "also"        "although"    "always"     
##  [36] "america"     "amount"      "and"         "another"     "answer"     
##  [41] "any"         "apart"       "apparent"    "appear"      "apply"      
##  [46] "appoint"     "approach"    "appropriate" "area"        "argue"      
##  [51] "arm"         "around"      "arrange"     "art"         "as"         
##  [56] "ask"         "associate"   "assume"      "at"          "attend"     
##  [61] "authority"   "available"   "aware"       "away"        "awful"      
##  [66] "each"        "early"       "east"        "easy"        "eat"        
##  [71] "economy"     "educate"     "effect"      "egg"         "eight"      
##  [76] "either"      "elect"       "electric"    "eleven"      "else"       
##  [81] "employ"      "encourage"   "end"         "engine"      "english"    
##  [86] "enjoy"       "enough"      "enter"       "environment" "equal"      
##  [91] "especial"    "europe"      "even"        "evening"     "ever"       
##  [96] "every"       "evidence"    "exact"       "example"     "except"     
## [101] "excuse"      "exercise"    "exist"       "expect"      "expense"    
## [106] "experience"  "explain"     "express"     "extra"       "eye"        
## [111] "idea"        "identify"    "if"          "imagine"     "important"  
## [116] "improve"     "in"          "include"     "income"      "increase"   
## [121] "indeed"      "individual"  "industry"    "inform"      "inside"     
## [126] "instead"     "insure"      "interest"    "into"        "introduce"  
## [131] "invest"      "involve"     "issue"       "it"          "item"       
## [136] "obvious"     "occasion"    "odd"         "of"          "off"        
## [141] "offer"       "office"      "often"       "okay"        "old"        
## [146] "on"          "once"        "one"         "only"        "open"       
## [151] "operate"     "opportunity" "oppose"      "or"          "order"      
## [156] "organize"    "original"    "other"       "otherwise"   "ought"      
## [161] "out"         "over"        "own"         "under"       "understand" 
## [166] "union"       "unit"        "unite"       "university"  "unless"     
## [171] "until"       "up"          "upon"        "use"         "usual"

# only consonants
str_view_match(words, "^[^aeiou]+$")

# end with ed, but not with eed
str_view_match(words, "^ed$|[^e]ed$")

# end with ing or ise
str_view_match(words, "ing$|ise$")

2. Empirically verify the rule “i before e except after c”.

str_view_match(words, "([^c]ie|cei)") #rule

str_view_match(words, "(cie)") #exceptions?

From the second output we can see there are some exceptions for this rule, such as the words science and society.

3. Is “q” always followed by a “u”?

str_view_match(words, "q[^u]")

There were no words in the output, so “q” is always followed by a “u”.

4. Write a regular expression that matches a word if it’s probably written in British English, not American English.

str_view_match(words, "ise$|our") #ise instead of ize and our instead of or

5. Create a regular expression that will match telephone numbers as commonly written in your country

phones <- c("(55)32498722", "(778)952-5873")
str_view(phones, "\\(\\d{2}\\)\\d{8}", match = T)

The output matches the telephone number as commonly written in Mexico.

14.3.4.1 Repetition

3. Create regular expressions to find all words that:

• Start with three consonants.
• Have three or more vowels in a row.
• Have two or more vowel-consonant pairs in a row.

# start with 3 consonants
str_view_match(words, "^[^aeiou]{3}")

# ≥ 3 vowels in a row
str_view_match(words, "[aeiou]{3,}")

# ≥ 2 vowel-consonant pairs in a row
str_subset(words, "([aeiou][^aeiou]){2,}")

##   [1] "absolute"    "agent"       "along"       "america"     "another"    
##   [6] "apart"       "apparent"    "authority"   "available"   "aware"      
##  [11] "away"        "balance"     "basis"       "become"      "before"     
##  [16] "begin"       "behind"      "benefit"     "business"    "character"  
##  [21] "closes"      "community"   "consider"    "cover"       "debate"     
##  [26] "decide"      "decision"    "definite"    "department"  "depend"     
##  [31] "design"      "develop"     "difference"  "difficult"   "direct"     
##  [36] "divide"      "document"    "during"      "economy"     "educate"    
##  [41] "elect"       "electric"    "eleven"      "encourage"   "environment"
##  [46] "europe"      "even"        "evening"     "ever"        "every"      
##  [51] "evidence"    "exact"       "example"     "exercise"    "exist"      
##  [56] "family"      "figure"      "final"       "finance"     "finish"     
##  [61] "friday"      "future"      "general"     "govern"      "holiday"    
##  [66] "honest"      "hospital"    "however"     "identify"    "imagine"    
##  [71] "individual"  "interest"    "introduce"   "item"        "jesus"      
##  [76] "level"       "likely"      "limit"       "local"       "major"      
##  [81] "manage"      "meaning"     "measure"     "minister"    "minus"      
##  [86] "minute"      "moment"      "money"       "music"       "nature"     
##  [91] "necessary"   "never"       "notice"      "okay"        "open"       
##  [96] "operate"     "opportunity" "organize"    "original"    "over"       
## [101] "paper"       "paragraph"   "parent"      "particular"  "photograph" 
## [106] "police"      "policy"      "politic"     "position"    "positive"   
## [111] "power"       "prepare"     "present"     "presume"     "private"    
## [116] "probable"    "process"     "produce"     "product"     "project"    
## [121] "proper"      "propose"     "protect"     "provide"     "quality"    
## [126] "realise"     "reason"      "recent"      "recognize"   "recommend"  
## [131] "record"      "reduce"      "refer"       "regard"      "relation"   
## [136] "remember"    "report"      "represent"   "result"      "return"     
## [141] "saturday"    "second"      "secretary"   "secure"      "separate"   
## [146] "seven"       "similar"     "specific"    "strategy"    "student"    
## [151] "stupid"      "telephone"   "television"  "therefore"   "thousand"   
## [156] "today"       "together"    "tomorrow"    "tonight"     "total"      
## [161] "toward"      "travel"      "unit"        "unite"       "university" 
## [166] "upon"        "visit"       "water"       "woman"

14.3.5.1 Grouping and backreferences

2. Construct regular expressions to match words that:

• Start and end with the same character.
• Contain a repeated pair of letters (e.g. “church” contains “ch” repeated twice.)
• Contain one letter repeated in at least three places (e.g. “eleven” contains three “e”s.)

#start + end same character
str_view_match(words, "^(.).*\\1$")

#repeated pair of letters
str_view_match(words, "(..).*\\1")

#repeated letters
str_view_match(words, "(.).*\\1.*\\1")

14.4.2 Detect matches

1. For each of the following challenges, try solving by using both a single regular expression, and a combination of multiple str_detect() calls.

• Find all words that start or end with x.
• Find all words that start with a vowel and end with a consonant.
• Are there any words that contain at least one of each different vowel?

# start or end with x 
str_view_match(words, "^x|x$") #single regex

# multiple str_detect() calls
start_x <- str_detect(words, "^x")
end_x <- str_detect(words, "x$")
words[start_x | end_x]

## [1] "box" "sex" "six" "tax"

#start with vowel end with consonant
str_subset(words, "^[aeiou].*[^aeiou]$") #single regex

##   [1] "about"       "accept"      "account"     "across"      "act"        
##   [6] "actual"      "add"         "address"     "admit"       "affect"     
##  [11] "afford"      "after"       "afternoon"   "again"       "against"    
##  [16] "agent"       "air"         "all"         "allow"       "almost"     
##  [21] "along"       "already"     "alright"     "although"    "always"     
##  [26] "amount"      "and"         "another"     "answer"      "any"        
##  [31] "apart"       "apparent"    "appear"      "apply"       "appoint"    
##  [36] "approach"    "arm"         "around"      "art"         "as"         
##  [41] "ask"         "at"          "attend"      "authority"   "away"       
##  [46] "awful"       "each"        "early"       "east"        "easy"       
##  [51] "eat"         "economy"     "effect"      "egg"         "eight"      
##  [56] "either"      "elect"       "electric"    "eleven"      "employ"     
##  [61] "end"         "english"     "enjoy"       "enough"      "enter"      
##  [66] "environment" "equal"       "especial"    "even"        "evening"    
##  [71] "ever"        "every"       "exact"       "except"      "exist"      
##  [76] "expect"      "explain"     "express"     "identify"    "if"         
##  [81] "important"   "in"          "indeed"      "individual"  "industry"   
##  [86] "inform"      "instead"     "interest"    "invest"      "it"         
##  [91] "item"        "obvious"     "occasion"    "odd"         "of"         
##  [96] "off"         "offer"       "often"       "okay"        "old"        
## [101] "on"          "only"        "open"        "opportunity" "or"         
## [106] "order"       "original"    "other"       "ought"       "out"        
## [111] "over"        "own"         "under"       "understand"  "union"      
## [116] "unit"        "university"  "unless"      "until"       "up"         
## [121] "upon"        "usual"

#multiple str_detect()
start_vowel <- str_detect(words, "^[aeiou]")
end_cons <- str_detect(words, "[^aeiou]$")
words[start_vowel & end_cons]

##   [1] "about"       "accept"      "account"     "across"      "act"        
##   [6] "actual"      "add"         "address"     "admit"       "affect"     
##  [11] "afford"      "after"       "afternoon"   "again"       "against"    
##  [16] "agent"       "air"         "all"         "allow"       "almost"     
##  [21] "along"       "already"     "alright"     "although"    "always"     
##  [26] "amount"      "and"         "another"     "answer"      "any"        
##  [31] "apart"       "apparent"    "appear"      "apply"       "appoint"    
##  [36] "approach"    "arm"         "around"      "art"         "as"         
##  [41] "ask"         "at"          "attend"      "authority"   "away"       
##  [46] "awful"       "each"        "early"       "east"        "easy"       
##  [51] "eat"         "economy"     "effect"      "egg"         "eight"      
##  [56] "either"      "elect"       "electric"    "eleven"      "employ"     
##  [61] "end"         "english"     "enjoy"       "enough"      "enter"      
##  [66] "environment" "equal"       "especial"    "even"        "evening"    
##  [71] "ever"        "every"       "exact"       "except"      "exist"      
##  [76] "expect"      "explain"     "express"     "identify"    "if"         
##  [81] "important"   "in"          "indeed"      "individual"  "industry"   
##  [86] "inform"      "instead"     "interest"    "invest"      "it"         
##  [91] "item"        "obvious"     "occasion"    "odd"         "of"         
##  [96] "off"         "offer"       "often"       "okay"        "old"        
## [101] "on"          "only"        "open"        "opportunity" "or"         
## [106] "order"       "original"    "other"       "ought"       "out"        
## [111] "over"        "own"         "under"       "understand"  "union"      
## [116] "unit"        "university"  "unless"      "until"       "up"         
## [121] "upon"        "usual"

#one of each vowel
allv <- c("aeioux", "aei") #to check it works
str_subset(allv, "a.*e.*i.*o.*u")

## [1] "aeioux"

str_subset(words, "a.*e.*i.*o.*u")

## character(0)

# multiple str_detect()
words[str_detect(words, "a") & str_detect(words, "e") &
        str_detect(words, "i") & str_detect(words, "o") &
        str_detect(words, "u")]

## character(0)

There are no words in stringr::words that contain all the vowels.

2. What word has the highest number of vowels? What word has the highest proportion of vowels?

#highest number of vowels
num_v <- str_count(words, "[aeiou]")
max_v <- max(num_v)
words[num_v == max_v]

## [1] "appropriate" "associate"   "available"   "colleague"   "encourage"  
## [6] "experience"  "individual"  "television"

#highest proportion of vowels
prop_v <- str_count(words, "[aeiou]") / str_length(words)
max_p <- max(prop_v)
words[prop_v == max_p]

## [1] "a"

8 words have 5 vowels, which is the maximum number of values among these words.

The word a has the highest proportion since length = 1 and num_v = 1.

14.4.3.1 Extract matches

2. From the Harvard sentences data, extract:

• The first word from each sentence.
• All words ending in ing.
• All plurals.

#first word
str_extract(sentences, "[^ ]+") %>% head()

## [1] "The"   "Glue"  "It's"  "These" "Rice"  "The"

sentences %>% head() #to check it worked

## [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."

#words ending in ing
pat_ing <- "[A-Za-z]+ing" #define pattern
ing <- str_detect(sentences, pat_ing)
str_extract_all(sentences[ing], pat_ing) %>%
  unlist() %>%
  unique() #don't show repeated words

##  [1] "stocking"  "spring"    "evening"   "morning"   "winding"  
##  [6] "living"    "king"      "Adding"    "making"    "raging"   
## [11] "playing"   "sleeping"  "ring"      "glaring"   "sinking"  
## [16] "thing"     "dying"     "Bring"     "lodging"   "filing"   
## [21] "wearing"   "wading"    "swing"     "nothing"   "Whiting"  
## [26] "sing"      "bring"     "painting"  "walking"   "ling"     
## [31] "shipping"  "hing"      "puzzling"  "landing"   "waiting"  
## [36] "whistling" "timing"    "ting"      "changing"  "drenching"
## [41] "moving"    "working"

#plurals
str_extract_all(sentences, "[A-Za-z]{3,}s") %>%
  unlist() %>%
  unique() %>%
  head()

## [1] "planks" "Thes"   "days"   "bowls"  "lemons" "makes"

14.4.4.1 Grouped matches

1. Find all words that come after a “number” like “one”, “two”, “three” etc. Pull out both the number and the word.

pat_num <- "(one|two|three|four|five|six|seven|eight|nine|ten) ([^ ]+)"
sen_num <- sentences %>% str_subset(pat_num)
sen_num %>% str_match(pat_num)

##       [,1]            [,2]    [,3]      
##  [1,] "ten served"    "ten"   "served"  
##  [2,] "one over"      "one"   "over"    
##  [3,] "seven books"   "seven" "books"   
##  [4,] "two met"       "two"   "met"     
##  [5,] "two factors"   "two"   "factors" 
##  [6,] "one and"       "one"   "and"     
##  [7,] "three lists"   "three" "lists"   
##  [8,] "seven is"      "seven" "is"      
##  [9,] "two when"      "two"   "when"    
## [10,] "one floor."    "one"   "floor."  
## [11,] "ten inches."   "ten"   "inches." 
## [12,] "one with"      "one"   "with"    
## [13,] "one war"       "one"   "war"     
## [14,] "one button"    "one"   "button"  
## [15,] "six minutes."  "six"   "minutes."
## [16,] "ten years"     "ten"   "years"   
## [17,] "one in"        "one"   "in"      
## [18,] "ten chased"    "ten"   "chased"  
## [19,] "one like"      "one"   "like"    
## [20,] "two shares"    "two"   "shares"  
## [21,] "two distinct"  "two"   "distinct"
## [22,] "one costs"     "one"   "costs"   
## [23,] "ten two"       "ten"   "two"     
## [24,] "five robins."  "five"  "robins." 
## [25,] "four kinds"    "four"  "kinds"   
## [26,] "one rang"      "one"   "rang"    
## [27,] "ten him."      "ten"   "him."    
## [28,] "three story"   "three" "story"   
## [29,] "ten by"        "ten"   "by"      
## [30,] "one wall."     "one"   "wall."   
## [31,] "three inches"  "three" "inches"  
## [32,] "ten your"      "ten"   "your"    
## [33,] "six comes"     "six"   "comes"   
## [34,] "one before"    "one"   "before"  
## [35,] "three batches" "three" "batches" 
## [36,] "two leaves."   "two"   "leaves."

2. Find all contractions. Separate out the pieces before and after the apostrophe.

cont <- "([A-Za-z]+)'([A-Za-z]+)"
sen_cont <- sentences %>% str_subset(cont)
sen_cont %>% str_match(cont)

##       [,1]         [,2]       [,3]
##  [1,] "It's"       "It"       "s" 
##  [2,] "man's"      "man"      "s" 
##  [3,] "don't"      "don"      "t" 
##  [4,] "store's"    "store"    "s" 
##  [5,] "workmen's"  "workmen"  "s" 
##  [6,] "Let's"      "Let"      "s" 
##  [7,] "sun's"      "sun"      "s" 
##  [8,] "child's"    "child"    "s" 
##  [9,] "king's"     "king"     "s" 
## [10,] "It's"       "It"       "s" 
## [11,] "don't"      "don"      "t" 
## [12,] "queen's"    "queen"    "s" 
## [13,] "don't"      "don"      "t" 
## [14,] "pirate's"   "pirate"   "s" 
## [15,] "neighbor's" "neighbor" "s"

14.4.5.1 Replacing matches

1. Replace all forward slashes in a string with backslashes.

for_slash <- ("one/two/three")
str_replace_all(for_slash, "/", "\\\\") %>% writeLines()

## one\two\three

2. Implement a simple version of str_to_lower() using replace_all().

caps <- ("ABCDE")
str_replace_all(caps, "([A-Z])", tolower)

## [1] "abcde"

14.4.6.1 Splitting

1. Split up a string like “apples, pears, and bananas” into individual components.

fruity <- ("apples, pears, and bananas")
str_split(fruity, ", and |,")

## [[1]]
## [1] "apples"  " pears"  "bananas"

2. Why is it better to split up by boundary("word") than " "?

fruity2 <- ("fruit: apples, pears, (bananas), and oranges")
str_split(fruity2, " ")

## [[1]]
## [1] "fruit:"     "apples,"    "pears,"     "(bananas)," "and"       
## [6] "oranges"

str_split(fruity2, boundary("word"))

## [[1]]
## [1] "fruit"   "apples"  "pears"   "bananas" "and"     "oranges"

Splitting up with boundary("word") is better so I don’t have to specify each special punctuation character to keep out like : , or ().