These are methods for the dplyr slice(), slice_head(), slice_tail(),
slice_min(), slice_max() and slice_sample() generics. They are
translated to the i argument of [.data.table.
Unlike dplyr, slice() (and slice() alone) returns the same number of
rows per group, regardless of whether or not the indices appear in each
group.
Usage
# S3 method for dtplyr_step
slice(.data, ...)
# S3 method for dtplyr_step
slice_head(.data, ..., n, prop)
# S3 method for dtplyr_step
slice_tail(.data, ..., n, prop)
# S3 method for dtplyr_step
slice_min(.data, order_by, ..., n, prop, with_ties = TRUE)
# S3 method for dtplyr_step
slice_max(.data, order_by, ..., n, prop, with_ties = TRUE)Arguments
- .data
A
lazy_dt().- ...
Positive integers giving rows to select, or negative integers giving rows to drop.
- n, prop
Provide either
n, the number of rows, orprop, the proportion of rows to select. If neither are supplied,n = 1will be used.If a negative value of
norpropis provided, the specified number or proportion of rows will be removed.If
nis greater than the number of rows in the group (orprop > 1), the result will be silently truncated to the group size. If theproportion of a group size does not yield an integer number of rows, the absolute value ofprop*n()is rounded down.- order_by
Variable or function of variables to order by.
- with_ties
Should ties be kept together? The default,
TRUE, may return more rows than you request. UseFALSEto ignore ties, and return the firstnrows.
Examples
library(dplyr, warn.conflicts = FALSE)
dt <- lazy_dt(mtcars)
dt %>% slice(1, 5, 10)
#> Source: local data table [3 x 11]
#> Call: `_DT36`[c(1, 5, 10)[between(c(1, 5, 10), -.N, .N)]]
#>
#> mpg cyl disp hp drat wt qsec vs am gear carb
#> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 21 6 160 110 3.9 2.62 16.5 0 1 4 4
#> 2 18.7 8 360 175 3.15 3.44 17.0 0 0 3 2
#> 3 19.2 6 168. 123 3.92 3.44 18.3 1 0 4 4
#>
#> # Use as.data.table()/as.data.frame()/as_tibble() to access results
dt %>% slice(-(1:4))
#> Source: local data table [28 x 11]
#> Call: `_DT36`[(-(1:4))[between(-(1:4), -.N, .N)]]
#>
#> mpg cyl disp hp drat wt qsec vs am gear carb
#> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 18.7 8 360 175 3.15 3.44 17.0 0 0 3 2
#> 2 18.1 6 225 105 2.76 3.46 20.2 1 0 3 1
#> 3 14.3 8 360 245 3.21 3.57 15.8 0 0 3 4
#> 4 24.4 4 147. 62 3.69 3.19 20 1 0 4 2
#> 5 22.8 4 141. 95 3.92 3.15 22.9 1 0 4 2
#> 6 19.2 6 168. 123 3.92 3.44 18.3 1 0 4 4
#> # … with 22 more rows
#>
#> # Use as.data.table()/as.data.frame()/as_tibble() to access results
# First and last rows based on existing order
dt %>% slice_head(n = 5)
#> Source: local data table [5 x 11]
#> Call: `_DT36`[rlang::seq2(1L, min(5L, .N))]
#>
#> mpg cyl disp hp drat wt qsec vs am gear carb
#> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 21 6 160 110 3.9 2.62 16.5 0 1 4 4
#> 2 21 6 160 110 3.9 2.88 17.0 0 1 4 4
#> 3 22.8 4 108 93 3.85 2.32 18.6 1 1 4 1
#> 4 21.4 6 258 110 3.08 3.22 19.4 1 0 3 1
#> 5 18.7 8 360 175 3.15 3.44 17.0 0 0 3 2
#>
#> # Use as.data.table()/as.data.frame()/as_tibble() to access results
dt %>% slice_tail(n = 5)
#> Source: local data table [5 x 11]
#> Call: `_DT36`[rlang::seq2(.N - min(5L, .N) + 1L, .N)]
#>
#> mpg cyl disp hp drat wt qsec vs am gear carb
#> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 30.4 4 95.1 113 3.77 1.51 16.9 1 1 5 2
#> 2 15.8 8 351 264 4.22 3.17 14.5 0 1 5 4
#> 3 19.7 6 145 175 3.62 2.77 15.5 0 1 5 6
#> 4 15 8 301 335 3.54 3.57 14.6 0 1 5 8
#> 5 21.4 4 121 109 4.11 2.78 18.6 1 1 4 2
#>
#> # Use as.data.table()/as.data.frame()/as_tibble() to access results
# Rows with minimum and maximum values of a variable
dt %>% slice_min(mpg, n = 5)
#> Source: local data table [5 x 11]
#> Call: `_DT36`[rank(mpg, ties.method = "min", na.last = "keep") <= min(5L,
#> .N)][order(mpg)]
#>
#> mpg cyl disp hp drat wt qsec vs am gear carb
#> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 10.4 8 472 205 2.93 5.25 18.0 0 0 3 4
#> 2 10.4 8 460 215 3 5.42 17.8 0 0 3 4
#> 3 13.3 8 350 245 3.73 3.84 15.4 0 0 3 4
#> 4 14.3 8 360 245 3.21 3.57 15.8 0 0 3 4
#> 5 14.7 8 440 230 3.23 5.34 17.4 0 0 3 4
#>
#> # Use as.data.table()/as.data.frame()/as_tibble() to access results
dt %>% slice_max(mpg, n = 5)
#> Source: local data table [5 x 11]
#> Call: `_DT36`[rank(desc(mpg), ties.method = "min", na.last = "keep") <=
#> min(5L, .N)][order(-mpg)]
#>
#> mpg cyl disp hp drat wt qsec vs am gear carb
#> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 33.9 4 71.1 65 4.22 1.84 19.9 1 1 4 1
#> 2 32.4 4 78.7 66 4.08 2.2 19.5 1 1 4 1
#> 3 30.4 4 75.7 52 4.93 1.62 18.5 1 1 4 2
#> 4 30.4 4 95.1 113 3.77 1.51 16.9 1 1 5 2
#> 5 27.3 4 79 66 4.08 1.94 18.9 1 1 4 1
#>
#> # Use as.data.table()/as.data.frame()/as_tibble() to access results
# slice_min() and slice_max() may return more rows than requested
# in the presence of ties. Use with_ties = FALSE to suppress
dt %>% slice_min(cyl, n = 1)
#> Source: local data table [11 x 11]
#> Call: `_DT36`[rank(cyl, ties.method = "min", na.last = "keep") <= min(1L,
#> .N)][order(cyl)]
#>
#> mpg cyl disp hp drat wt qsec vs am gear carb
#> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 22.8 4 108 93 3.85 2.32 18.6 1 1 4 1
#> 2 24.4 4 147. 62 3.69 3.19 20 1 0 4 2
#> 3 22.8 4 141. 95 3.92 3.15 22.9 1 0 4 2
#> 4 32.4 4 78.7 66 4.08 2.2 19.5 1 1 4 1
#> 5 30.4 4 75.7 52 4.93 1.62 18.5 1 1 4 2
#> 6 33.9 4 71.1 65 4.22 1.84 19.9 1 1 4 1
#> # … with 5 more rows
#>
#> # Use as.data.table()/as.data.frame()/as_tibble() to access results
dt %>% slice_min(cyl, n = 1, with_ties = FALSE)
#> Source: local data table [1 x 11]
#> Call: `_DT36`[rank(cyl, ties.method = "first", na.last = "keep") <=
#> min(1L, .N)][order(cyl)]
#>
#> mpg cyl disp hp drat wt qsec vs am gear carb
#> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 22.8 4 108 93 3.85 2.32 18.6 1 1 4 1
#>
#> # Use as.data.table()/as.data.frame()/as_tibble() to access results
# slice_sample() allows you to random select with or without replacement
dt %>% slice_sample(n = 5)
#> Source: local data table [5 x 11]
#> Call: `_DT36`[sample.int(.N, min(min(5L, .N), .N))]
#>
#> mpg cyl disp hp drat wt qsec vs am gear carb
#> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 19.2 8 400 175 3.08 3.84 17.0 0 0 3 2
#> 2 19.2 6 168. 123 3.92 3.44 18.3 1 0 4 4
#> 3 22.8 4 108 93 3.85 2.32 18.6 1 1 4 1
#> 4 21.4 6 258 110 3.08 3.22 19.4 1 0 3 1
#> 5 21 6 160 110 3.9 2.62 16.5 0 1 4 4
#>
#> # Use as.data.table()/as.data.frame()/as_tibble() to access results
dt %>% slice_sample(n = 5, replace = TRUE)
#> Source: local data table [5 x 11]
#> Call: `_DT36`[sample.int(.N, min(5L, .N), replace = TRUE)]
#>
#> mpg cyl disp hp drat wt qsec vs am gear carb
#> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 21 6 160 110 3.9 2.62 16.5 0 1 4 4
#> 2 13.3 8 350 245 3.73 3.84 15.4 0 0 3 4
#> 3 15.5 8 318 150 2.76 3.52 16.9 0 0 3 2
#> 4 27.3 4 79 66 4.08 1.94 18.9 1 1 4 1
#> 5 15.5 8 318 150 2.76 3.52 16.9 0 0 3 2
#>
#> # Use as.data.table()/as.data.frame()/as_tibble() to access results
# you can optionally weight by a variable - this code weights by the
# physical weight of the cars, so heavy cars are more likely to get
# selected
dt %>% slice_sample(weight_by = wt, n = 5)
#> Source: local data table [5 x 11]
#> Call: `_DT36`[sample.int(.N, min(min(5L, .N), .N), prob = wt)]
#>
#> mpg cyl disp hp drat wt qsec vs am gear carb
#> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 17.8 6 168. 123 3.92 3.44 18.9 1 0 4 4
#> 2 19.7 6 145 175 3.62 2.77 15.5 0 1 5 6
#> 3 15.5 8 318 150 2.76 3.52 16.9 0 0 3 2
#> 4 10.4 8 472 205 2.93 5.25 18.0 0 0 3 4
#> 5 21.4 4 121 109 4.11 2.78 18.6 1 1 4 2
#>
#> # Use as.data.table()/as.data.frame()/as_tibble() to access results