Map & Walk
Here, we will use a simple example to illustrate the performance
difference of lstrrr.
files <- list.files(all.files = TRUE, recursive = TRUE)
files_list <- dir_listwise(files)
slow_string_op <- function(x, n = 10) {
stopifnot(is.character(x))
out <- x
for (i in seq_len(n)) {
out <- paste0(
rev(strsplit(out, "", fixed = TRUE)[[1]]),
collapse = ""
)
out <- toupper(out)
out <- tolower(out)
}
out
}
set.seed(123)
bench_map <- microbenchmark::microbenchmark(
purrr_10 = {
purrr::walk(files, \(x) slow_string_op(x))
},
lstrrr_10 = {
list_walk(files_list, \(x) slow_string_op(x))
},
purrr_50 = {
purrr::walk(files, \(x) slow_string_op(x, n = 50))
},
lstrrr_50 = {
list_walk(files_list, \(x) slow_string_op(x, n = 50))
},
purrr_100 = {
purrr::walk(files, \(x) slow_string_op(x, n = 100))
},
lstrrr_100 = {
list_walk(files_list, \(x) slow_string_op(x, n = 100))
}
)
print(bench_map)
#> Unit: milliseconds
#> expr min lq mean median uq max neval
#> purrr_10 3.410271 3.545301 4.297314 3.605756 3.669977 53.54569 100
#> lstrrr_10 3.362640 3.458302 3.745305 3.517645 3.576458 8.76341 100
#> purrr_50 16.314968 16.993607 18.035075 17.201381 17.527140 22.46480 100
#> lstrrr_50 15.859661 16.865977 17.834599 17.047002 17.291966 25.91676 100
#> purrr_100 32.662474 34.014725 36.356021 34.439687 38.208565 92.70551 100
#> lstrrr_100 32.849042 33.870586 35.940210 34.406588 38.078162 46.77079 100
ggplot2::autoplot(bench_map) +
ggplot2::theme(axis.text = ggplot2::element_text(size = 12))
#> Warning: `aes_string()` was deprecated in ggplot2 3.0.0.
#> ℹ Please use tidy evaluation idioms with `aes()`.
#> ℹ See also `vignette("ggplot2-in-packages")` for more information.
#> ℹ The deprecated feature was likely used in the microbenchmark package.
#> Please report the issue at
#> <https://github.com/joshuaulrich/microbenchmark/issues/>.
#> This warning is displayed once per session.
#> Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
#> generated.
Detect Depth
set.seed(124)
bench_depth <- microbenchmark::microbenchmark(
purrr = {
purrr::pluck_depth(sputnik_1)
},
lstrrr = {
list_depth(sputnik_1)
}
)
print(bench_depth)
#> Unit: microseconds
#> expr min lq mean median uq max neval
#> purrr 3803.545 3911.0955 4241.79746 4036.647 4126.601 7117.593 100
#> lstrrr 1.973 2.1985 4.79397 4.722 5.809 37.466 100
ggplot2::autoplot(bench_depth) +
ggplot2::theme(axis.text = ggplot2::element_text(size = 12))
Assignment
set.seed(125)
bench_assign <- microbenchmark::microbenchmark(
purrr = {
purrr::list_assign(sputnik_1, z = list(a = 1:5))
},
lstrrr = {
list_set(sputnik_1, c("z"), list(a = 1:5))
}
)
print(bench_assign)
#> Unit: microseconds
#> expr min lq mean median uq max neval
#> purrr 14.772 15.0575 19.00410 15.378 15.899 332.064 100
#> lstrrr 1.462 1.6080 1.96052 1.722 1.857 22.904 100
ggplot2::autoplot(bench_assign) +
ggplot2::theme(axis.text = ggplot2::element_text(size = 12))
Modification
set.seed(126)
bench_modify <- microbenchmark::microbenchmark(
purrr = {
purrr::list_modify(sputnik_1, test_branches = list(null_leaf = 1:5))
},
lstrrr = {
list_set(sputnik_1, c("test_branches", "null_leaf"), 1:5)
}
)
print(bench_modify)
#> Unit: microseconds
#> expr min lq mean median uq max neval
#> purrr 25.568 26.4195 28.87368 26.8300 27.5010 177.634 100
#> lstrrr 1.372 1.5020 1.77978 1.5675 1.7625 16.534 100
ggplot2::autoplot(bench_modify) +
ggplot2::theme(axis.text = ggplot2::element_text(size = 12))
Flatten
set.seed(127)
bench_flatten <- microbenchmark::microbenchmark(
purrr = {
purrr::list_flatten(sputnik_1)
},
lstrrr = {
list_flatten(sputnik_1)
}
)
print(bench_flatten)
#> Unit: microseconds
#> expr min lq mean median uq max neval
#> purrr 864.655 891.926 972.54582 922.4765 967.9045 3706.761 100
#> lstrrr 24.977 29.644 33.35854 31.4470 35.6530 91.887 100
ggplot2::autoplot(bench_flatten) +
ggplot2::theme(axis.text = ggplot2::element_text(size = 12))
modifyList
set.seed(128)
foo <- sputnik_1
foo$test_branches$empty_branch$score <- 1e-256
bench_modify_list <- microbenchmark::microbenchmark(
utils = {
utils::modifyList(sputnik_1, foo)
},
lstrrr = {
modify_list(sputnik_1, foo)
}
)
print(bench_modify_list)
#> Unit: microseconds
#> expr min lq mean median uq max neval
#> utils 589.677 599.5165 645.96378 610.533 625.7655 3431.082 100
#> lstrrr 12.659 13.5500 15.17506 14.161 15.0720 84.285 100
ggplot2::autoplot(bench_modify_list) +
ggplot2::theme(axis.text = ggplot2::element_text(size = 12))
Parallel Computation
Most of logic is in C implementation, so the acceleration is not that obvious.
set.seed(129)
mirai::daemons(3L)
crate <- purrr::in_parallel(
\(x) {
slow_string_op(x, n = 10)
},
slow_string_op = slow_string_op
)
fn <- function(x) {
slow_string_op(x, n = 10)
}
bench_parallel <- microbenchmark::microbenchmark(
lstrrr_parallel = {
list_map(files_list, crate)
},
lstrrr = {
list_map(files_list, fn)
},
purrr = {
purrr::map(files, fn)
},
purrr_parallel = {
purrr::map(files, crate)
}
)
mirai::daemons(0L)
print(bench_parallel)
#> Unit: milliseconds
#> expr min lq mean median uq max neval
#> lstrrr_parallel 3.543438 3.600383 3.887280 3.643948 3.707522 12.08487 100
#> lstrrr 3.339055 3.392650 3.521817 3.426360 3.472002 10.98174 100
#> purrr 3.372594 3.443064 3.799679 3.480295 3.556849 13.29755 100
#> purrr_parallel 8.411927 8.887134 9.381990 9.181231 9.453261 12.97562 100
ggplot2::autoplot(bench_parallel) +
ggplot2::theme(axis.text = ggplot2::element_text(size = 12))