Separate

Code - R

~/code/R/

Table

df <- data.frame(x = c(NA, "a.b", "a.d", "b.c"))
df %>% 
  {if (is_html_output()) print_table(.) else .}

x
NA
a.b
a.d
b.c

Separate

df %>% 
  separate(x, c("A", "B")) %>%
  {if (is_html_output()) print_table(.) else .}

A	B
NA	NA
a	b
a	d
b	c

Just want the second variable

If you just want the second variable:

df %>% 
  separate(x, c(NA, "B")) %>%
  {if (is_html_output()) print_table(.) else .}

B
NA
b
d
c

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("a", "a b", "a b c", NA))
df %>% 
  separate(x, c("a", "b")) %>%
  {if (is_html_output()) print_table(.) else .}

a	b
a	NA
a	b
a	b
NA	NA

The same behaviour drops the c but no warnings

df %>% 
  separate(x, c("a", "b"), extra = "drop", fill = "right") %>%
  {if (is_html_output()) print_table(.) else .}

a	b
a	NA
a	b
a	b
NA	NA

Another option:

df %>% 
  separate(x, c("a", "b"), extra = "merge", fill = "left") %>%
  {if (is_html_output()) print_table(.) else .}

a	b
NA	a
a	b
a	b c
NA	NA

Or you can keep all three

df %>% 
  separate(x, c("a", "b", "c")) %>%
  {if (is_html_output()) print_table(.) else .}

a	b	c
a	NA	NA
a	b	NA
a	b	c
NA	NA	NA

If only want to split 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") %>%
  {if (is_html_output()) print_table(.) else .}

key	value
x	123
y	error: 7

Use regular expressions to separate on multiple characters:

df <- data.frame(x = c(NA, "a?b", "a.d", "b:c"))
df %>% 
  separate(x, c("A","B"), sep = "([\\.\\?\\:])") %>%
  {if (is_html_output()) print_table(.) else .}

A	B
NA	NA
a	b
a	d
b	c

convert = TRUE detects column classes

df <- data.frame(x = c("a:1", "a:2", "c:4", "d", NA))
df %>% 
  separate(x, c("key","value"), ":") %>% 
  str

# 'data.frame': 5 obs. of  2 variables:
#  $ key  : chr  "a" "a" "c" "d" ...
#  $ value: chr  "1" "2" "4" NA ...

df %>% 
  separate(x, c("key","value"), ":", convert = TRUE) %>% 
  str

# 'data.frame': 5 obs. of  2 variables:
#  $ key  : chr  "a" "a" "c" "d" ...
#  $ value: int  1 2 4 NA NA

Argument col can take quasiquotation to work with strings

var <- "x"
df %>% 
  separate(!!var, c("key","value"), ":") %>%
  {if (is_html_output()) print_table(.) else .}

key	value
a	1
a	2
c	4
d	NA
NA	NA