A lazy data.table captures the intent of dplyr verbs, only actually
performing computation when requested (with collect()
, pull()
,
as.data.frame()
, data.table::as.data.table()
, or tibble::as_tibble()
).
This allows dtplyr to convert dplyr verbs into as few data.table expressions
as possible, which leads to a high performance translation.
See vignette("translation")
for the details of the translation.
Arguments
- x
A data table (or something can can be coerced to a data table).
- name
Optionally, supply a name to be used in generated expressions. For expert use only.
- immutable
If
TRUE
,x
is treated as immutable and will never be modified by any code generated by dtplyr. Alternatively, you can setimmutable = FALSE
to allow dtplyr to modify the input object.- key_by
Set keys for data frame, using
select()
semantics (e.g.key_by = c(key1, key2)
.This uses
data.table::setkey()
to sort the table and build an index. This will considerably improve performance for subsets, summaries, and joins that use the keys.See
vignette("datatable-keys-fast-subset")
for more details.
Examples
library(dplyr, warn.conflicts = FALSE)
mtcars2 <- lazy_dt(mtcars)
mtcars2
#> Source: local data table [32 x 11]
#> Call: `_DT20`
#>
#> 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
#> 6 18.1 6 225 105 2.76 3.46 20.2 1 0 3 1
#> # ℹ 26 more rows
#>
#> # Use as.data.table()/as.data.frame()/as_tibble() to access results
mtcars2 %>% select(mpg:cyl)
#> Source: local data table [32 x 2]
#> Call: `_DT20`[, .(mpg, cyl)]
#>
#> mpg cyl
#> <dbl> <dbl>
#> 1 21 6
#> 2 21 6
#> 3 22.8 4
#> 4 21.4 6
#> 5 18.7 8
#> 6 18.1 6
#> # ℹ 26 more rows
#>
#> # Use as.data.table()/as.data.frame()/as_tibble() to access results
mtcars2 %>% select(x = mpg, y = cyl)
#> Source: local data table [32 x 2]
#> Call: `_DT20`[, .(x = mpg, y = cyl)]
#>
#> x y
#> <dbl> <dbl>
#> 1 21 6
#> 2 21 6
#> 3 22.8 4
#> 4 21.4 6
#> 5 18.7 8
#> 6 18.1 6
#> # ℹ 26 more rows
#>
#> # Use as.data.table()/as.data.frame()/as_tibble() to access results
mtcars2 %>% filter(cyl == 4) %>% select(mpg)
#> Source: local data table [11 x 1]
#> Call: `_DT20`[cyl == 4, .(mpg)]
#>
#> mpg
#> <dbl>
#> 1 22.8
#> 2 24.4
#> 3 22.8
#> 4 32.4
#> 5 30.4
#> 6 33.9
#> # ℹ 5 more rows
#>
#> # Use as.data.table()/as.data.frame()/as_tibble() to access results
mtcars2 %>% select(mpg, cyl) %>% filter(cyl == 4)
#> Source: local data table [11 x 2]
#> Call: `_DT20`[, .(mpg, cyl)][cyl == 4]
#>
#> mpg cyl
#> <dbl> <dbl>
#> 1 22.8 4
#> 2 24.4 4
#> 3 22.8 4
#> 4 32.4 4
#> 5 30.4 4
#> 6 33.9 4
#> # ℹ 5 more rows
#>
#> # Use as.data.table()/as.data.frame()/as_tibble() to access results
mtcars2 %>% mutate(cyl2 = cyl * 2, cyl4 = cyl2 * 2)
#> Source: local data table [32 x 13]
#> Call: copy(`_DT20`)[, `:=`(c("cyl2", "cyl4"), {
#> cyl2 <- cyl * 2
#> cyl4 <- cyl2 * 2
#> .(cyl2, cyl4)
#> })]
#>
#> mpg cyl disp hp drat wt qsec vs am gear carb cyl2
#> <dbl> <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 12
#> 2 21 6 160 110 3.9 2.88 17.0 0 1 4 4 12
#> 3 22.8 4 108 93 3.85 2.32 18.6 1 1 4 1 8
#> 4 21.4 6 258 110 3.08 3.22 19.4 1 0 3 1 12
#> 5 18.7 8 360 175 3.15 3.44 17.0 0 0 3 2 16
#> 6 18.1 6 225 105 2.76 3.46 20.2 1 0 3 1 12
#> # ℹ 26 more rows
#> # ℹ 1 more variable: cyl4 <dbl>
#>
#> # Use as.data.table()/as.data.frame()/as_tibble() to access results
mtcars2 %>% transmute(cyl2 = cyl * 2, vs2 = vs * 2)
#> Source: local data table [32 x 2]
#> Call: `_DT20`[, .(cyl2 = cyl * 2, vs2 = vs * 2)]
#>
#> cyl2 vs2
#> <dbl> <dbl>
#> 1 12 0
#> 2 12 0
#> 3 8 2
#> 4 12 2
#> 5 16 0
#> 6 12 2
#> # ℹ 26 more rows
#>
#> # Use as.data.table()/as.data.frame()/as_tibble() to access results
mtcars2 %>% filter(cyl == 8) %>% mutate(cyl2 = cyl * 2)
#> Source: local data table [14 x 12]
#> Call: `_DT20`[cyl == 8][, `:=`(cyl2 = cyl * 2)]
#>
#> mpg cyl disp hp drat wt qsec vs am gear carb cyl2
#> <dbl> <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 16
#> 2 14.3 8 360 245 3.21 3.57 15.8 0 0 3 4 16
#> 3 16.4 8 276. 180 3.07 4.07 17.4 0 0 3 3 16
#> 4 17.3 8 276. 180 3.07 3.73 17.6 0 0 3 3 16
#> 5 15.2 8 276. 180 3.07 3.78 18 0 0 3 3 16
#> 6 10.4 8 472 205 2.93 5.25 18.0 0 0 3 4 16
#> # ℹ 8 more rows
#>
#> # Use as.data.table()/as.data.frame()/as_tibble() to access results
# Learn more about translation in vignette("translation")
by_cyl <- mtcars2 %>% group_by(cyl)
by_cyl %>% summarise(mpg = mean(mpg))
#> Source: local data table [3 x 2]
#> Call: `_DT20`[, .(mpg = mean(mpg)), keyby = .(cyl)]
#>
#> cyl mpg
#> <dbl> <dbl>
#> 1 4 26.7
#> 2 6 19.7
#> 3 8 15.1
#>
#> # Use as.data.table()/as.data.frame()/as_tibble() to access results
by_cyl %>% mutate(mpg = mean(mpg))
#> Source: local data table [32 x 11]
#> Groups: cyl
#> Call: copy(`_DT20`)[, `:=`(mpg = mean(mpg)), by = .(cyl)]
#>
#> mpg cyl disp hp drat wt qsec vs am gear carb
#> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 19.7 6 160 110 3.9 2.62 16.5 0 1 4 4
#> 2 19.7 6 160 110 3.9 2.88 17.0 0 1 4 4
#> 3 26.7 4 108 93 3.85 2.32 18.6 1 1 4 1
#> 4 19.7 6 258 110 3.08 3.22 19.4 1 0 3 1
#> 5 15.1 8 360 175 3.15 3.44 17.0 0 0 3 2
#> 6 19.7 6 225 105 2.76 3.46 20.2 1 0 3 1
#> # ℹ 26 more rows
#>
#> # Use as.data.table()/as.data.frame()/as_tibble() to access results
by_cyl %>%
filter(mpg < mean(mpg)) %>%
summarise(hp = mean(hp))
#> Source: local data table [3 x 2]
#> Call: `_DT20`[`_DT20`[, .I[mpg < mean(mpg)], by = .(cyl)]$V1, .(hp = mean(hp)),
#> keyby = .(cyl)]
#>
#> cyl hp
#> <dbl> <dbl>
#> 1 4 91.2
#> 2 6 132.
#> 3 8 246.
#>
#> # Use as.data.table()/as.data.frame()/as_tibble() to access results