This function allows you to vectorise multiple if_else()
statements. It is an R equivalent of the SQL CASE WHEN statement.
If no cases match, NA is returned.
case_when(...)
| ... | A sequence of two-sided formulas. The left hand side (LHS) determines which values match this case. The right hand side (RHS) provides the replacement value. The LHS must evaluate to a logical vector. The RHS does not need to be logical, but all RHSs must evaluate to the same type of vector. Both LHS and RHS may have the same length of either 1 or
These dots support tidy dots features. In
particular, if your patterns are stored in a list, you can
splice that in with |
|---|
A vector of length 1 or n, matching the length of the logical
input or output vectors, with the type (and attributes) of the first
RHS. Inconsistent lengths or types will generate an error.
x <- 1:50 case_when( x %% 35 == 0 ~ "fizz buzz", x %% 5 == 0 ~ "fizz", x %% 7 == 0 ~ "buzz", TRUE ~ as.character(x) )#> [1] "1" "2" "3" "4" "fizz" "6" #> [7] "buzz" "8" "9" "fizz" "11" "12" #> [13] "13" "buzz" "fizz" "16" "17" "18" #> [19] "19" "fizz" "buzz" "22" "23" "24" #> [25] "fizz" "26" "27" "buzz" "29" "fizz" #> [31] "31" "32" "33" "34" "fizz buzz" "36" #> [37] "37" "38" "39" "fizz" "41" "buzz" #> [43] "43" "44" "fizz" "46" "47" "48" #> [49] "buzz" "fizz"# Like an if statement, the arguments are evaluated in order, so you must # proceed from the most specific to the most general. This won't work: case_when( TRUE ~ as.character(x), x %% 5 == 0 ~ "fizz", x %% 7 == 0 ~ "buzz", x %% 35 == 0 ~ "fizz buzz" )#> [1] "1" "2" "3" "4" "5" "6" "7" "8" "9" "10" "11" "12" "13" "14" "15" #> [16] "16" "17" "18" "19" "20" "21" "22" "23" "24" "25" "26" "27" "28" "29" "30" #> [31] "31" "32" "33" "34" "35" "36" "37" "38" "39" "40" "41" "42" "43" "44" "45" #> [46] "46" "47" "48" "49" "50"# If none of the cases match, NA is used: case_when( x %% 5 == 0 ~ "fizz", x %% 7 == 0 ~ "buzz", x %% 35 == 0 ~ "fizz buzz" )#> [1] NA NA NA NA "fizz" NA "buzz" NA NA "fizz" #> [11] NA NA NA "buzz" "fizz" NA NA NA NA "fizz" #> [21] "buzz" NA NA NA "fizz" NA NA "buzz" NA "fizz" #> [31] NA NA NA NA "fizz" NA NA NA NA "fizz" #> [41] NA "buzz" NA NA "fizz" NA NA NA "buzz" "fizz"# Note that NA values in the vector x do not get special treatment. If you want # to explicitly handle NA values you can use the `is.na` function: x[2:4] <- NA_real_ case_when( x %% 35 == 0 ~ "fizz buzz", x %% 5 == 0 ~ "fizz", x %% 7 == 0 ~ "buzz", is.na(x) ~ "nope", TRUE ~ as.character(x) )#> [1] "1" "nope" "nope" "nope" "fizz" "6" #> [7] "buzz" "8" "9" "fizz" "11" "12" #> [13] "13" "buzz" "fizz" "16" "17" "18" #> [19] "19" "fizz" "buzz" "22" "23" "24" #> [25] "fizz" "26" "27" "buzz" "29" "fizz" #> [31] "31" "32" "33" "34" "fizz buzz" "36" #> [37] "37" "38" "39" "fizz" "41" "buzz" #> [43] "43" "44" "fizz" "46" "47" "48" #> [49] "buzz" "fizz"# All RHS values need to be of the same type. Inconsistent types will throw an error. # This applies also to NA values used in RHS: NA is logical, use # typed values like NA_real_, NA_complex, NA_character_, NA_integer_ as appropriate. case_when( x %% 35 == 0 ~ NA_character_, x %% 5 == 0 ~ "fizz", x %% 7 == 0 ~ "buzz", TRUE ~ as.character(x) )#> [1] "1" NA NA NA "fizz" "6" "buzz" "8" "9" "fizz" #> [11] "11" "12" "13" "buzz" "fizz" "16" "17" "18" "19" "fizz" #> [21] "buzz" "22" "23" "24" "fizz" "26" "27" "buzz" "29" "fizz" #> [31] "31" "32" "33" "34" NA "36" "37" "38" "39" "fizz" #> [41] "41" "buzz" "43" "44" "fizz" "46" "47" "48" "buzz" "fizz"case_when( x %% 35 == 0 ~ 35, x %% 5 == 0 ~ 5, x %% 7 == 0 ~ 7, TRUE ~ NA_real_ )#> [1] NA NA NA NA 5 NA 7 NA NA 5 NA NA NA 7 5 NA NA NA NA 5 7 NA NA NA 5 #> [26] NA NA 7 NA 5 NA NA NA NA 35 NA NA NA NA 5 NA 7 NA NA 5 NA NA NA 7 5# case_when() evaluates all RHS expressions, and then constructs its # result by extracting the selected (via the LHS expressions) parts. # In particular NaN are produced in this case: y <- seq(-2, 2, by = .5) case_when( y >= 0 ~ sqrt(y), TRUE ~ y )#> Warning: NaNs produced#> [1] -2.0000000 -1.5000000 -1.0000000 -0.5000000 0.0000000 0.7071068 1.0000000 #> [8] 1.2247449 1.4142136# This throws an error as NA is logical not numeric if (FALSE) { case_when( x %% 35 == 0 ~ 35, x %% 5 == 0 ~ 5, x %% 7 == 0 ~ 7, TRUE ~ NA ) } # case_when is particularly useful inside mutate when you want to # create a new variable that relies on a complex combination of existing # variables starwars %>% select(name:mass, gender, species) %>% mutate( type = case_when( height > 200 | mass > 200 ~ "large", species == "Droid" ~ "robot", TRUE ~ "other" ) )#> # A tibble: 87 x 6 #> name height mass gender species type #> <chr> <int> <dbl> <chr> <chr> <chr> #> 1 Luke Skywalker 172 77 male Human other #> 2 C-3PO 167 75 <NA> Droid robot #> 3 R2-D2 96 32 <NA> Droid robot #> 4 Darth Vader 202 136 male Human large #> 5 Leia Organa 150 49 female Human other #> 6 Owen Lars 178 120 male Human other #> 7 Beru Whitesun lars 165 75 female Human other #> 8 R5-D4 97 32 <NA> Droid robot #> 9 Biggs Darklighter 183 84 male Human other #> 10 Obi-Wan Kenobi 182 77 male Human other #> # … with 77 more rows# `case_when()` is not a tidy eval function. If you'd like to reuse # the same patterns, extract the `case_when()` call in a normal # function: case_character_type <- function(height, mass, species) { case_when( height > 200 | mass > 200 ~ "large", species == "Droid" ~ "robot", TRUE ~ "other" ) } case_character_type(150, 250, "Droid")#> [1] "large"case_character_type(150, 150, "Droid")#> [1] "robot"# Such functions can be used inside `mutate()` as well: starwars %>% mutate(type = case_character_type(height, mass, species)) %>% pull(type)#> [1] "other" "robot" "robot" "large" "other" "other" "other" "robot" "other" #> [10] "other" "other" "other" "large" "other" "other" "large" "other" "other" #> [19] "other" "other" "other" "robot" "other" "other" "other" "other" "other" #> [28] "other" "other" "other" "other" "other" "other" "other" "large" "large" #> [37] "other" "other" "other" "other" "other" "other" "other" "other" "other" #> [46] "other" "other" "other" "other" "other" "other" "other" "other" "large" #> [55] "other" "other" "other" "other" "other" "other" "other" "other" "other" #> [64] "other" "other" "other" "other" "other" "large" "large" "other" "other" #> [73] "other" "other" "other" "other" "large" "large" "other" "other" "large" #> [82] "other" "other" "other" "robot" "other" "other"# `case_when()` ignores `NULL` inputs. This is useful when you'd # like to use a pattern only under certain conditions. Here we'll # take advantage of the fact that `if` returns `NULL` when there is # no `else` clause: case_character_type <- function(height, mass, species, robots = TRUE) { case_when( height > 200 | mass > 200 ~ "large", if (robots) species == "Droid" ~ "robot", TRUE ~ "other" ) } starwars %>% mutate(type = case_character_type(height, mass, species, robots = FALSE)) %>% pull(type)#> [1] "other" "other" "other" "large" "other" "other" "other" "other" "other" #> [10] "other" "other" "other" "large" "other" "other" "large" "other" "other" #> [19] "other" "other" "other" "other" "other" "other" "other" "other" "other" #> [28] "other" "other" "other" "other" "other" "other" "other" "large" "large" #> [37] "other" "other" "other" "other" "other" "other" "other" "other" "other" #> [46] "other" "other" "other" "other" "other" "other" "other" "other" "large" #> [55] "other" "other" "other" "other" "other" "other" "other" "other" "other" #> [64] "other" "other" "other" "other" "other" "large" "large" "other" "other" #> [73] "other" "other" "other" "other" "large" "large" "other" "other" "large" #> [82] "other" "other" "other" "other" "other" "other"