Introduction

String Basics

chac_data <- "I'm 'Very' Hungry"

stringr::str_length("I am Hungry.")
## [1] 12
stringr::str_c(c("I", "am"), collapse = "")
## [1] "Iam"
stringr::str_c("I","am", sep = ";")
## [1] "I;am"
str_sort(c("John", "Mary", "Aaron"))
## [1] "Aaron" "John"  "Mary"

Matching Patterns

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_small <- flights %>% select(where(is.character)) %>% head(n = 10)

Basic Matches

flights_small %>% filter(str_detect(origin, "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>
flights_small %>% filter(str_detect(origin, "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>

Grouping and Backing References

# (..)\\1

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

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"

Other Types of pattern

flights_small %>% filter(str_detect(origin, regex("^e", ignore_case = TRUE)))
## # 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