Select distinct/unique rows

Retain only unique/distinct rows from an input tbl. This is similar to unique.data.frame(), but considerably faster.

distinct(.data, ..., .keep_all = FALSE)

Arguments

.data	a tbl
...	Optional variables to use when determining uniqueness. If there are multiple rows for a given combination of inputs, only the first row will be preserved. If omitted, will use all variables.
.keep_all	If TRUE, keep all variables in .data. If a combination of ... is not distinct, this keeps the first row of values.

Examples

df <- tibble(
  x = sample(10, 100, rep = TRUE),
  y = sample(10, 100, rep = TRUE)
)
nrow(df)
#> [1] 100
nrow(distinct(df))
#> [1] 66
nrow(distinct(df, x, y))
#> [1] 66

distinct(df, x)
#> # A tibble: 10 × 1
#>        x
#>    <int>
#>  1     8
#>  2     7
#>  3    10
#>  4     5
#>  5     6
#>  6     2
#>  7     9
#>  8     4
#>  9     1
#> 10     3
distinct(df, y)
#> # A tibble: 10 × 1
#>        y
#>    <int>
#>  1     9
#>  2     8
#>  3     4
#>  4     6
#>  5     5
#>  6     1
#>  7     7
#>  8     2
#>  9     3
#> 10    10

# Can choose to keep all other variables as well
distinct(df, x, .keep_all = TRUE)
#> # A tibble: 10 × 2
#>        x     y
#>    <int> <int>
#>  1     8     9
#>  2     7     9
#>  3    10     8
#>  4     5     4
#>  5     6     6
#>  6     2     5
#>  7     9     6
#>  8     4     3
#>  9     1     1
#> 10     3     9
distinct(df, y, .keep_all = TRUE)
#> # A tibble: 10 × 2
#>        x     y
#>    <int> <int>
#>  1     8     9
#>  2    10     8
#>  3     5     4
#>  4     6     6
#>  5     2     5
#>  6     6     1
#>  7     6     7
#>  8     8     2
#>  9     4     3
#> 10     9    10

# You can also use distinct on computed variables
distinct(df, diff = abs(x - y))
#> # A tibble: 10 × 1
#>     diff
#>    <int>
#>  1     1
#>  2     2
#>  3     0
#>  4     3
#>  5     5
#>  6     6
#>  7     4
#>  8     9
#>  9     7
#> 10     8

# The same behaviour applies for grouped data frames
# except that the grouping variables are always included
df <- tibble(
  g = c(1, 1, 2, 2),
  x = c(1, 1, 2, 1)
) %>% group_by(g)
df %>% distinct()
#> # A tibble: 3 × 2
#> # Groups: g [2]
#>       g     x
#>   <dbl> <dbl>
#> 1     1     1
#> 2     2     2
#> 3     2     1
df %>% distinct(x)
#> # A tibble: 3 × 2
#> # Groups: g [2]
#>       g     x
#>   <dbl> <dbl>
#> 1     1     1
#> 2     2     2
#> 3     2     1