R tidyr separate_wider_delim 将字符串拆分为列

separate_wider_delim(
  data,
  cols,
  delim,
  ...,
  names = NULL,
  names_sep = NULL,
  names_repair = "check_unique",
  too_few = c("error", "debug", "align_start", "align_end"),
  too_many = c("error", "debug", "drop", "merge"),
  cols_remove = TRUE
)

separate_wider_position(
  data,
  cols,
  widths,
  ...,
  names_sep = NULL,
  names_repair = "check_unique",
  too_few = c("error", "debug", "align_start"),
  too_many = c("error", "debug", "drop"),
  cols_remove = TRUE
)

separate_wider_regex(
  data,
  cols,
  patterns,
  ...,
  names_sep = NULL,
  names_repair = "check_unique",
  too_few = c("error", "debug", "align_start"),
  cols_remove = TRUE
)

df <- tibble(id = 1:3, x = c("m-123", "f-455", "f-123"))
# There are three basic ways to split up a string into pieces:
# 1. with a delimiter
df %>% separate_wider_delim(x, delim = "-", names = c("gender", "unit"))
#> # A tibble: 3 × 3
#>      id gender unit 
#>   <int> <chr>  <chr>
#> 1     1 m      123  
#> 2     2 f      455  
#> 3     3 f      123  
# 2. by length
df %>% separate_wider_position(x, c(gender = 1, 1, unit = 3))
#> # A tibble: 3 × 3
#>      id gender unit 
#>   <int> <chr>  <chr>
#> 1     1 m      123  
#> 2     2 f      455  
#> 3     3 f      123  
# 3. defining each component with a regular expression
df %>% separate_wider_regex(x, c(gender = ".", ".", unit = "\\d+"))
#> # A tibble: 3 × 3
#>      id gender unit 
#>   <int> <chr>  <chr>
#> 1     1 m      123  
#> 2     2 f      455  
#> 3     3 f      123  

# Sometimes you split on the "last" delimiter
df <- tibble(var = c("race_1", "race_2", "age_bucket_1", "age_bucket_2"))
# _delim won't help because it always splits on the first delimiter
try(df %>% separate_wider_delim(var, "_", names = c("var1", "var2")))
#> Error in separate_wider_delim(., var, "_", names = c("var1", "var2")) : 
#>   Expected 2 pieces in each element of `var`.
#> ! 2 values were too long.
#> ℹ Use `too_many = "debug"` to diagnose the problem.
#> ℹ Use `too_many = "drop"/"merge"` to silence this message.
df %>% separate_wider_delim(var, "_", names = c("var1", "var2"), too_many = "merge")
#> # A tibble: 4 × 2
#>   var1  var2    
#>   <chr> <chr>   
#> 1 race  1       
#> 2 race  2       
#> 3 age   bucket_1
#> 4 age   bucket_2
# Instead, you can use _regex
df %>% separate_wider_regex(var, c(var1 = ".*", "_", var2 = ".*"))
#> # A tibble: 4 × 2
#>   var1       var2 
#>   <chr>      <chr>
#> 1 race       1    
#> 2 race       2    
#> 3 age_bucket 1    
#> 4 age_bucket 2    
# this works because * is greedy; you can mimic the _delim behaviour with .*?
df %>% separate_wider_regex(var, c(var1 = ".*?", "_", var2 = ".*"))
#> # A tibble: 4 × 2
#>   var1  var2    
#>   <chr> <chr>   
#> 1 race  1       
#> 2 race  2       
#> 3 age   bucket_1
#> 4 age   bucket_2

# If the number of components varies, it's most natural to split into rows
df <- tibble(id = 1:4, x = c("x", "x y", "x y z", NA))
df %>% separate_longer_delim(x, delim = " ")
#> # A tibble: 7 × 2
#>      id x    
#>   <int> <chr>
#> 1     1 x    
#> 2     2 x    
#> 3     2 y    
#> 4     3 x    
#> 5     3 y    
#> 6     3 z    
#> 7     4 NA   
# But separate_wider_delim() provides some tools to deal with the problem
# The default behaviour tells you that there's a problem
try(df %>% separate_wider_delim(x, delim = " ", names = c("a", "b")))
#> Error in separate_wider_delim(., x, delim = " ", names = c("a", "b")) : 
#>   Expected 2 pieces in each element of `x`.
#> ! 1 value was too short.
#> ℹ Use `too_few = "debug"` to diagnose the problem.
#> ℹ Use `too_few = "align_start"/"align_end"` to silence this message.
#> ! 1 value was too long.
#> ℹ Use `too_many = "debug"` to diagnose the problem.
#> ℹ Use `too_many = "drop"/"merge"` to silence this message.
# You can get additional insight by using the debug options
df %>%
  separate_wider_delim(
    x,
    delim = " ",
    names = c("a", "b"),
    too_few = "debug",
    too_many = "debug"
  )
#> Warning: Debug mode activated: adding variables `x_ok`, `x_pieces`, and
#> `x_remainder`.
#> # A tibble: 4 × 7
#>      id a     b     x     x_ok  x_pieces x_remainder
#>   <int> <chr> <chr> <chr> <lgl>    <int> <chr>      
#> 1     1 x     NA    x     FALSE        1 ""         
#> 2     2 x     y     x y   TRUE         2 ""         
#> 3     3 x     y     x y z FALSE        3 " z"       
#> 4     4 NA    NA    NA    TRUE        NA  NA        

# But you can suppress the warnings
df %>%
  separate_wider_delim(
    x,
    delim = " ",
    names = c("a", "b"),
    too_few = "align_start",
    too_many = "merge"
  )
#> # A tibble: 4 × 3
#>      id a     b    
#>   <int> <chr> <chr>
#> 1     1 x     NA   
#> 2     2 x     y    
#> 3     3 x     y z  
#> 4     4 NA    NA   

# Or choose to automatically name the columns, producing as many as needed
df %>% separate_wider_delim(x, delim = " ", names_sep = "", too_few = "align_start")
#> # A tibble: 4 × 4
#>      id x1    x2    x3   
#>   <int> <chr> <chr> <chr>
#> 1     1 x     NA    NA   
#> 2     2 x     y     NA   
#> 3     3 x     y     z    
#> 4     4 NA    NA    NA