chac_data<-"Im 'very' hungry"
stringr::str_length("I am hungry")## [1] 11stringr::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 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_small<-flights %>% select(where(is.character)) %>% head(n=10)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>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(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 MCOflights_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 ORDflights_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# ? 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# (..)\\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 rowsflights_small %>%
summarise(sum(str_detect(tailnum,"8$")))## # A tibble: 1 × 1
## `sum(str_detect(tailnum, "8$"))`
## <int>
## 1 1str_detect(flights_small$tailnum,"8$")## [1] TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSEsum(str_detect(flights_small$tailnum,"8$"))## [1] 1mean(str_detect(flights_small$tailnum,"8$"))## [1] 0.1colours<-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"# Extract strings with a noun
noun<-"(a|the)([^ ]+)"
had_nouns<-str_subset(sentences,noun)%>% head(10)
had_nouns %>% str_extract(noun)## [1] "anoe" "ark" "asy" "ays" "akes" "as" "and" "ady" "arge" "as"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 -3ALAAflights_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----sentences[1] %>% str_split("",n=3,simplify = TRUE)## [,1] [,2] [,3]
## [1,] "T" "h" "e birch canoe slid on the smooth planks."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