Introduction

String Basics

chac_data <- "I'm 'very' hungry."

chac_data <- 'I am "very" hunrgy.'

stringr::str_length("I am hungry.")
## [1] 12
stringr::str_c("I", " am")
## [1] "I am"
stringr::str_c("I", " am", sep = " ;")
## [1] "I ; am"
stringr::str_c(c("I", " am"), collapse = "")
## [1] "I am"
x <- c("Apple", "Banana", "Pear")
stringr::str_sub(x, 1, 3)
## [1] "App" "Ban" "Pea"
str_to_upper(c("i", "ı"))
## [1] "I" "I"
str_to_upper(c("i", "ı"), locale = "tr")
## [1] "İ" "I"
str_sort(c("John", "Mary", "Aaron"))
## [1] "Aaron" "John"  "Mary"

Matching Patterns with Regular Expressions

flights %>% glimpse()
## Rows: 336,776
## Columns: 19
## $ year           <int> 2013, 2013, 2013, 2013, 2013, 2013, 2013, 2013, 2013, 2…
## $ month          <int> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1…
## $ day            <int> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1…
## $ dep_time       <int> 517, 533, 542, 544, 554, 554, 555, 557, 557, 558, 558, …
## $ sched_dep_time <int> 515, 529, 540, 545, 600, 558, 600, 600, 600, 600, 600, …
## $ dep_delay      <dbl> 2, 4, 2, -1, -6, -4, -5, -3, -3, -2, -2, -2, -2, -2, -1…
## $ arr_time       <int> 830, 850, 923, 1004, 812, 740, 913, 709, 838, 753, 849,…
## $ sched_arr_time <int> 819, 830, 850, 1022, 837, 728, 854, 723, 846, 745, 851,…
## $ arr_delay      <dbl> 11, 20, 33, -18, -25, 12, 19, -14, -8, 8, -2, -3, 7, -1…
## $ carrier        <chr> "UA", "UA", "AA", "B6", "DL", "UA", "B6", "EV", "B6", "…
## $ flight         <int> 1545, 1714, 1141, 725, 461, 1696, 507, 5708, 79, 301, 4…
## $ tailnum        <chr> "N14228", "N24211", "N619AA", "N804JB", "N668DN", "N394…
## $ origin         <chr> "EWR", "LGA", "JFK", "JFK", "LGA", "EWR", "EWR", "LGA",…
## $ dest           <chr> "IAH", "IAH", "MIA", "BQN", "ATL", "ORD", "FLL", "IAD",…
## $ air_time       <dbl> 227, 227, 160, 183, 116, 150, 158, 53, 140, 138, 149, 1…
## $ distance       <dbl> 1400, 1416, 1089, 1576, 762, 719, 1065, 229, 944, 733, …
## $ hour           <dbl> 5, 5, 5, 5, 6, 5, 6, 6, 6, 6, 6, 6, 6, 6, 6, 5, 6, 6, 6…
## $ minute         <dbl> 15, 29, 40, 45, 0, 58, 0, 0, 0, 0, 0, 0, 0, 0, 0, 59, 0…
## $ time_hour      <dttm> 2013-01-01 05:00:00, 2013-01-01 05:00:00, 2013-01-01 0…
flights %>% select(where(is.character)) %>% head(n = 10)
## # A tibble: 10 × 4
##    carrier tailnum origin dest 
##    <chr>   <chr>   <chr>  <chr>
##  1 UA      N14228  EWR    IAH  
##  2 UA      N24211  LGA    IAH  
##  3 AA      N619AA  JFK    MIA  
##  4 B6      N804JB  JFK    BQN  
##  5 DL      N668DN  LGA    ATL  
##  6 UA      N39463  EWR    ORD  
##  7 B6      N516JB  EWR    FLL  
##  8 EV      N829AS  LGA    IAD  
##  9 B6      N593JB  JFK    MCO  
## 10 AA      N3ALAA  LGA    ORD
flights_small <- flights %>% select(where(is.character)) %>% head(n = 10)

Basic Matches

flights_small %>% filter(str_detect(dest, "AH"))
## # A tibble: 2 × 4
##   carrier tailnum origin dest 
##   <chr>   <chr>   <chr>  <chr>
## 1 UA      N14228  EWR    IAH  
## 2 UA      N24211  LGA    IAH
flights_small %>% filter(str_detect(dest, "M"))
## # A tibble: 2 × 4
##   carrier tailnum origin dest 
##   <chr>   <chr>   <chr>  <chr>
## 1 AA      N619AA  JFK    MIA  
## 2 B6      N593JB  JFK    MCO
flights_small %>% filter(str_detect(dest, "M."))
## # A tibble: 2 × 4
##   carrier tailnum origin dest 
##   <chr>   <chr>   <chr>  <chr>
## 1 AA      N619AA  JFK    MIA  
## 2 B6      N593JB  JFK    MCO
flights_small %>% filter(str_detect(dest, ".M"))
## # A tibble: 0 × 4
## # ℹ 4 variables: carrier <chr>, tailnum <chr>, origin <chr>, dest <chr>
flights_small %>% filter(str_detect(dest, "M\\."))
## # A tibble: 0 × 4
## # ℹ 4 variables: carrier <chr>, tailnum <chr>, origin <chr>, dest <chr>
flights_small %>% filter(str_detect(origin, "M"))
## # A tibble: 0 × 4
## # ℹ 4 variables: carrier <chr>, tailnum <chr>, origin <chr>, dest <chr>

Anchors

flights_small %>% filter(str_detect(origin, "^E"))
## # A tibble: 3 × 4
##   carrier tailnum origin dest 
##   <chr>   <chr>   <chr>  <chr>
## 1 UA      N14228  EWR    IAH  
## 2 UA      N39463  EWR    ORD  
## 3 B6      N516JB  EWR    FLL
flights_small %>% filter(str_detect(origin, "E$"))
## # A tibble: 0 × 4
## # ℹ 4 variables: carrier <chr>, tailnum <chr>, origin <chr>, dest <chr>
flights_small %>% filter(str_detect(origin, "A$"))
## # A tibble: 4 × 4
##   carrier tailnum origin dest 
##   <chr>   <chr>   <chr>  <chr>
## 1 UA      N24211  LGA    IAH  
## 2 DL      N668DN  LGA    ATL  
## 3 EV      N829AS  LGA    IAD  
## 4 AA      N3ALAA  LGA    ORD

Character Classes and Alternatives

flights_small %>% filter(str_detect(carrier, "\\d"))
## # A tibble: 3 × 4
##   carrier tailnum origin dest 
##   <chr>   <chr>   <chr>  <chr>
## 1 B6      N804JB  JFK    BQN  
## 2 B6      N516JB  EWR    FLL  
## 3 B6      N593JB  JFK    MCO
flights_small %>% filter(str_detect(carrier, "\\s"))
## # A tibble: 0 × 4
## # ℹ 4 variables: carrier <chr>, tailnum <chr>, origin <chr>, dest <chr>
flights_small %>% filter(str_detect(carrier, "[ABD]"))
## # A tibble: 9 × 4
##   carrier tailnum origin dest 
##   <chr>   <chr>   <chr>  <chr>
## 1 UA      N14228  EWR    IAH  
## 2 UA      N24211  LGA    IAH  
## 3 AA      N619AA  JFK    MIA  
## 4 B6      N804JB  JFK    BQN  
## 5 DL      N668DN  LGA    ATL  
## 6 UA      N39463  EWR    ORD  
## 7 B6      N516JB  EWR    FLL  
## 8 B6      N593JB  JFK    MCO  
## 9 AA      N3ALAA  LGA    ORD
flights_small %>% filter(str_detect(carrier, "[^ABD]"))
## # A tibble: 8 × 4
##   carrier tailnum origin dest 
##   <chr>   <chr>   <chr>  <chr>
## 1 UA      N14228  EWR    IAH  
## 2 UA      N24211  LGA    IAH  
## 3 B6      N804JB  JFK    BQN  
## 4 DL      N668DN  LGA    ATL  
## 5 UA      N39463  EWR    ORD  
## 6 B6      N516JB  EWR    FLL  
## 7 EV      N829AS  LGA    IAD  
## 8 B6      N593JB  JFK    MCO

Repitition

# ? 0 or 1
flights_small %>% filter(str_detect(carrier, "A?"))
## # A tibble: 10 × 4
##    carrier tailnum origin dest 
##    <chr>   <chr>   <chr>  <chr>
##  1 UA      N14228  EWR    IAH  
##  2 UA      N24211  LGA    IAH  
##  3 AA      N619AA  JFK    MIA  
##  4 B6      N804JB  JFK    BQN  
##  5 DL      N668DN  LGA    ATL  
##  6 UA      N39463  EWR    ORD  
##  7 B6      N516JB  EWR    FLL  
##  8 EV      N829AS  LGA    IAD  
##  9 B6      N593JB  JFK    MCO  
## 10 AA      N3ALAA  LGA    ORD
# + 1 or more 
flights_small %>% filter(str_detect(carrier, "A+"))
## # A tibble: 5 × 4
##   carrier tailnum origin dest 
##   <chr>   <chr>   <chr>  <chr>
## 1 UA      N14228  EWR    IAH  
## 2 UA      N24211  LGA    IAH  
## 3 AA      N619AA  JFK    MIA  
## 4 UA      N39463  EWR    ORD  
## 5 AA      N3ALAA  LGA    ORD
# * 0 or more
flights_small %>% filter(str_detect(carrier, "A*"))
## # A tibble: 10 × 4
##    carrier tailnum origin dest 
##    <chr>   <chr>   <chr>  <chr>
##  1 UA      N14228  EWR    IAH  
##  2 UA      N24211  LGA    IAH  
##  3 AA      N619AA  JFK    MIA  
##  4 B6      N804JB  JFK    BQN  
##  5 DL      N668DN  LGA    ATL  
##  6 UA      N39463  EWR    ORD  
##  7 B6      N516JB  EWR    FLL  
##  8 EV      N829AS  LGA    IAD  
##  9 B6      N593JB  JFK    MCO  
## 10 AA      N3ALAA  LGA    ORD

Grouping and Backreferences

# (..)\\1
flights_small %>% filter(str_detect(tailnum, "(\\d{2})\\1"))
## # A tibble: 0 × 4
## # ℹ 4 variables: carrier <chr>, tailnum <chr>, origin <chr>, dest <chr>
flights %>% select(where(is.character)) %>% filter(str_detect(tailnum, "(\\d{2})\\1"))
## # A tibble: 1,990 × 4
##    carrier tailnum origin dest 
##    <chr>   <chr>   <chr>  <chr>
##  1 EV      N15555  EWR    MKE  
##  2 EV      N11119  LGA    CLE  
##  3 UA      N14242  EWR    TPA  
##  4 EV      N14143  EWR    PIT  
##  5 EV      N15555  EWR    SAV  
##  6 UA      N12125  EWR    LAX  
##  7 EV      N15555  EWR    PWM  
##  8 EV      N15555  EWR    BUF  
##  9 EV      N15555  EWR    RIC  
## 10 EV      N13133  EWR    DTW  
## # ℹ 1,980 more rows

Tools

Detect Matches

flights_small %>% 
    summarise(sum(str_detect(tailnum, "8$")))
## # A tibble: 1 × 1
##   `sum(str_detect(tailnum, "8$"))`
##                              <int>
## 1                                1
str_detect(flights_small$tailnum, "8$")
##  [1]  TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
sum(str_detect(flights_small$tailnum, "8$"))
## [1] 1

Extract Matches

colours <- c("red", "orange", "yellow", "green", "blue", "purple")
colour_match <- str_c(colours, collapse = "|")
colour_match
## [1] "red|orange|yellow|green|blue|purple"
# Extract String with a Color
str_subset(sentences, colour_match)
##  [1] "Glue the sheet to the dark blue background."       
##  [2] "Two blue fish swam in the tank."                   
##  [3] "The colt reared and threw the tall rider."         
##  [4] "The wide road shimmered in the hot sun."           
##  [5] "See the cat glaring at the scared mouse."          
##  [6] "A wisp of cloud hung in the blue air."             
##  [7] "Leaves turn brown and yellow in the fall."         
##  [8] "He ordered peach pie with ice cream."              
##  [9] "Pure bred poodles have curls."                     
## [10] "The spot on the blotter was made by green ink."    
## [11] "Mud was spattered on the front of his white shirt."
## [12] "The sofa cushion is red and of light weight."      
## [13] "The sky that morning was clear and bright blue."   
## [14] "Torn scraps littered the stone floor."             
## [15] "The doctor cured him with these pills."            
## [16] "The new girl was fired today at noon."             
## [17] "The third act was dull and tired the players."     
## [18] "A blue crane is a tall wading bird."               
## [19] "Live wires should be kept covered."                
## [20] "It is hard to erase blue or red ink."              
## [21] "The wreck occurred by the bank on Main Street."    
## [22] "The lamp shone with a steady green flame."         
## [23] "The box is held by a bright red snapper."          
## [24] "The prince ordered his head chopped off."          
## [25] "The houses are built of red clay bricks."          
## [26] "The red tape bound the smuggled food."             
## [27] "Nine men were hired to dig the ruins."             
## [28] "The flint sputtered and lit a pine torch."         
## [29] "Hedge apples may stain your hands green."          
## [30] "The old pan was covered with hard fudge."          
## [31] "The plant grew large and green in the window."     
## [32] "The store walls were lined with colored frocks."   
## [33] "The purple tie was ten years old."                 
## [34] "Bathe and relax in the cool green grass."          
## [35] "The clan gathered on each dull night."             
## [36] "The lake sparkled in the red hot sun."             
## [37] "Mark the spot with a sign painted red."            
## [38] "Smoke poured out of every crack."                  
## [39] "Serve the hot rum to the tired heroes."            
## [40] "The couch cover and hall drapes were blue."        
## [41] "He offered proof in the form of a large chart."    
## [42] "A man in a blue sweater sat at the desk."          
## [43] "A sip of tea revives his tired friend."            
## [44] "The door was barred, locked, and bolted as well."  
## [45] "A thick coat of black paint covered all."          
## [46] "The small red neon lamp went out."                 
## [47] "Paint the sockets in the wall dull green."         
## [48] "Wake and rise, and step into the green outdoors."  
## [49] "The green light in the brown box flickered."       
## [50] "He put his last cartridge into the gun and fired." 
## [51] "The ram scared the school children off."           
## [52] "Tear a thin sheet from the yellow pad."            
## [53] "Dimes showered down from all sides."               
## [54] "The sky in the west is tinged with orange red."    
## [55] "The red paper brightened the dim stage."           
## [56] "The hail pattered on the burnt brown grass."       
## [57] "The big red apple fell to the ground."
has_colour <- str_subset(sentences, colour_match)

str_extract(has_colour, colour_match)
##  [1] "blue"   "blue"   "red"    "red"    "red"    "blue"   "yellow" "red"   
##  [9] "red"    "green"  "red"    "red"    "blue"   "red"    "red"    "red"   
## [17] "red"    "blue"   "red"    "blue"   "red"    "green"  "red"    "red"   
## [25] "red"    "red"    "red"    "red"    "green"  "red"    "green"  "red"   
## [33] "purple" "green"  "red"    "red"    "red"    "red"    "red"    "blue"  
## [41] "red"    "blue"   "red"    "red"    "red"    "red"    "green"  "green" 
## [49] "green"  "red"    "red"    "yellow" "red"    "orange" "red"    "red"   
## [57] "red"

Grouped Matches

# Extract Strings with a noun
noun <-"(a|the) ([^ ]+)"
str_subset(sentences, noun) %>% head(10)
##  [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] "The box was thrown beside the parked truck."      
##  [6] "The boy was there when the sun rose."             
##  [7] "The source of the huge river is the clear spring."
##  [8] "Kick the ball straight and follow through."       
##  [9] "Help the woman get back to her feet."             
## [10] "A pot of tea helps to pass the evening."
has_noun <- str_subset(sentences, 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"

Replacing Matches

flights_small %>% mutate(tailnum_rev = tailnum %>% str_replace("^[A-Z]", "-"))
## # A tibble: 10 × 5
##    carrier tailnum origin dest  tailnum_rev
##    <chr>   <chr>   <chr>  <chr> <chr>      
##  1 UA      N14228  EWR    IAH   -14228     
##  2 UA      N24211  LGA    IAH   -24211     
##  3 AA      N619AA  JFK    MIA   -619AA     
##  4 B6      N804JB  JFK    BQN   -804JB     
##  5 DL      N668DN  LGA    ATL   -668DN     
##  6 UA      N39463  EWR    ORD   -39463     
##  7 B6      N516JB  EWR    FLL   -516JB     
##  8 EV      N829AS  LGA    IAD   -829AS     
##  9 B6      N593JB  JFK    MCO   -593JB     
## 10 AA      N3ALAA  LGA    ORD   -3ALAA
flights_small %>% mutate(tailnum_rev = tailnum %>% str_replace_all("[A-Z]", "-"))
## # A tibble: 10 × 5
##    carrier tailnum origin dest  tailnum_rev
##    <chr>   <chr>   <chr>  <chr> <chr>      
##  1 UA      N14228  EWR    IAH   -14228     
##  2 UA      N24211  LGA    IAH   -24211     
##  3 AA      N619AA  JFK    MIA   -619--     
##  4 B6      N804JB  JFK    BQN   -804--     
##  5 DL      N668DN  LGA    ATL   -668--     
##  6 UA      N39463  EWR    ORD   -39463     
##  7 B6      N516JB  EWR    FLL   -516--     
##  8 EV      N829AS  LGA    IAD   -829--     
##  9 B6      N593JB  JFK    MCO   -593--     
## 10 AA      N3ALAA  LGA    ORD   -3----

Splitting

sentences[1] %>% str_split(" ", n = 3, simplify = TRUE)
##      [,1]  [,2]    [,3]                              
## [1,] "The" "birch" "canoe slid on the smooth planks."

Other Types of Pattern

flights_small %>% filter(str_detect(tailnum, "^n"))
## # A tibble: 0 × 4
## # ℹ 4 variables: carrier <chr>, tailnum <chr>, origin <chr>, dest <chr>
flights_small %>% filter(str_detect(tailnum, regex("^n", ignore_case = TRUE)))
## # A tibble: 10 × 4
##    carrier tailnum origin dest 
##    <chr>   <chr>   <chr>  <chr>
##  1 UA      N14228  EWR    IAH  
##  2 UA      N24211  LGA    IAH  
##  3 AA      N619AA  JFK    MIA  
##  4 B6      N804JB  JFK    BQN  
##  5 DL      N668DN  LGA    ATL  
##  6 UA      N39463  EWR    ORD  
##  7 B6      N516JB  EWR    FLL  
##  8 EV      N829AS  LGA    IAD  
##  9 B6      N593JB  JFK    MCO  
## 10 AA      N3ALAA  LGA    ORD
flights_small %>% filter(str_detect(tailnum, regex("^e", ignore_case = TRUE)))
## # A tibble: 0 × 4
## # ℹ 4 variables: carrier <chr>, tailnum <chr>, origin <chr>, dest <chr>