R/separate.R
separate.Rd
Given either a regular expression or a vector of character positions,
separate()
turns a single character column into multiple columns.
separate( data, col, into, sep = "[^[:alnum:]]+", remove = TRUE, convert = FALSE, extra = "warn", fill = "warn", ... )
data | A data frame. |
---|---|
col | Column name or position. This is passed to
This argument is passed by expression and supports quasiquotation (you can unquote column names or column positions). |
into | Names of new variables to create as character vector.
Use |
sep | Separator between columns. If character, If numeric, |
remove | If |
convert | If NB: this will cause string |
extra | If
|
fill | If
|
... | Additional arguments passed on to methods. |
library(dplyr) # If you want to split by any non-alphanumeric value (the default): df <- data.frame(x = c(NA, "x.y", "x.z", "y.z")) df %>% separate(x, c("A", "B"))#> A B #> 1 <NA> <NA> #> 2 x y #> 3 x z #> 4 y z#> B #> 1 <NA> #> 2 y #> 3 z #> 4 z# If every row doesn't split into the same number of pieces, use # the extra and fill arguments to control what happens: df <- data.frame(x = c("x", "x y", "x y z", NA)) df %>% separate(x, c("a", "b"))#> Warning: Expected 2 pieces. Additional pieces discarded in 1 rows [3].#> Warning: Expected 2 pieces. Missing pieces filled with `NA` in 1 rows [1].#> a b #> 1 x <NA> #> 2 x y #> 3 x y #> 4 <NA> <NA># The same behaviour as previous, but drops the c without warnings: df %>% separate(x, c("a", "b"), extra = "drop", fill = "right")#> a b #> 1 x <NA> #> 2 x y #> 3 x y #> 4 <NA> <NA># Opposite of previous, keeping the c and filling left: df %>% separate(x, c("a", "b"), extra = "merge", fill = "left")#> a b #> 1 <NA> x #> 2 x y #> 3 x y z #> 4 <NA> <NA>#> Warning: Expected 3 pieces. Missing pieces filled with `NA` in 2 rows [1, 2].#> a b c #> 1 x <NA> <NA> #> 2 x y <NA> #> 3 x y z #> 4 <NA> <NA> <NA># To only split a specified number of times use extra = "merge": df <- data.frame(x = c("x: 123", "y: error: 7")) df %>% separate(x, c("key", "value"), ": ", extra = "merge")#> key value #> 1 x 123 #> 2 y error: 7# Use regular expressions to separate on multiple characters: df <- data.frame(x = c(NA, "x?y", "x.z", "y:z")) df %>% separate(x, c("A","B"), sep = "([.?:])")#> A B #> 1 <NA> <NA> #> 2 x y #> 3 x z #> 4 y z# convert = TRUE detects column classes: df <- data.frame(x = c("x:1", "x:2", "y:4", "z", NA)) df %>% separate(x, c("key","value"), ":") %>% str#> Warning: Expected 2 pieces. Missing pieces filled with `NA` in 1 rows [4].#> 'data.frame': 5 obs. of 2 variables: #> $ key : chr "x" "x" "y" "z" ... #> $ value: chr "1" "2" "4" NA ...#> Warning: Expected 2 pieces. Missing pieces filled with `NA` in 1 rows [4].#> 'data.frame': 5 obs. of 2 variables: #> $ key : chr "x" "x" "y" "z" ... #> $ value: int 1 2 4 NA NA