Week 10: Code Along 9

# Load package
library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.4.4     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(nycflights13)

Introduction

String Bascis

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

stringr::str_length("I am hungry.")

## [1] 12

stringr::str_c(c("I", "am"), collapse = " ")

## [1] "I am"

stringr::str_c("x", "y", sep = ":")

## [1] "x:y"

x <- c("Apple", "Banana", "Pear")
stringr:: str_sub(x, 1, 3)

## [1] "App" "Ban" "Pea"

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(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>

Anchors

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

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>

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

Repetition

# ? 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 %>% 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

mean(str_detect(flights_small$tailnum, "8$"))

## [1] 0.1

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 strings with a color
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) ([^ ]+)"
had_noun <- str_subset(sentences, noun) %>% head(10)
had_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(" ")

## [[1]]
## [1] "The"     "birch"   "canoe"   "slid"    "on"      "the"     "smooth" 
## [8] "planks."

sentences[1] %>% str_split(" ", n = 1)

## [[1]]
## [1] "The birch canoe slid on the smooth planks."

sentences[1] %>% str_split(" ", n = 3)

## [[1]]
## [1] "The"                              "birch"                           
## [3] "canoe slid on the smooth planks."

sentences[1] %>% str_split(" ", n = 3, simplify = TRUE)

##      [,1]  [,2]    [,3]                              
## [1,] "The" "birch" "canoe slid on the smooth planks."

flights_small %>% mutate(new_col = str_split(tailnum, "\\d", n = 2, simplify = TRUE))

## # A tibble: 10 × 5
##    carrier tailnum origin dest  new_col[,1] [,2] 
##    <chr>   <chr>   <chr>  <chr> <chr>       <chr>
##  1 UA      N14228  EWR    IAH   N           4228 
##  2 UA      N24211  LGA    IAH   N           4211 
##  3 AA      N619AA  JFK    MIA   N           19AA 
##  4 B6      N804JB  JFK    BQN   N           04JB 
##  5 DL      N668DN  LGA    ATL   N           68DN 
##  6 UA      N39463  EWR    ORD   N           9463 
##  7 B6      N516JB  EWR    FLL   N           16JB 
##  8 EV      N829AS  LGA    IAD   N           29AS 
##  9 B6      N593JB  JFK    MCO   N           93JB 
## 10 AA      N3ALAA  LGA    ORD   N           ALAA

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 %>% mutate(tailnum_numOnly = str_extract(tailnum, "\\d+"))

## # A tibble: 10 × 5
##    carrier tailnum origin dest  tailnum_numOnly
##    <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

Other types of patterns

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

Week 10: Code Along 9

R for Data Science: Chapter 14

Jordan Lanowy

Introduction

String Bascis

Matching Patterns

Basic matches

Anchors

Character classes and alternatives

Repetition

Grouping and backreferences

Tools

Detect Matches

Extract matches

Grouped matches

Replacing matches

Splitting

Other types of patterns