Benchmarking
Benchmarking.RmdTimings hydrorecipes vs recipes
Timings for the hydrorecipes package are prefaced with an “h”. The first few comparisons include the R6 interface in hydrorecipes to check if there is a loss of speed compared to the standard API. Most users are likely to use the standard API so the remaining benchmarks only present that. Typical speed improvements are between 2-10x and memory consumption is typically half of the recipes package.
creating a recipe
relative <- FALSE
n <- c(1e2, 1e4, 5e6)
formula <- as.formula(y~x)
results <- bench::press(
rows = n,
{
dat <- data.frame(x = rnorm(rows),
y = 1:rows)
bench::mark(
hrec1 = hydrorecipes:::Recipe$new(formula = formula, data = dat),
hrec2 = recipe(formula = formula, data = dat),
rec = recipes::recipe(formula = formula, data = dat),
check = FALSE
)
}
)
#> Running with:
#> rows
#> 1 100
#> 2 10000
#> 3 5000000
results
#> # A tibble: 9 × 7
#> expression rows min median `itr/sec` mem_alloc `gc/sec`
#> <bch:expr> <dbl> <bch:tm> <bch:tm> <dbl> <bch:byt> <dbl>
#> 1 hrec1 100 643.63µs 665.39µs 1477. 1.87MB 6.19
#> 2 hrec2 100 642.95µs 664.15µs 1488. 3.66KB 6.95
#> 3 rec 100 2.91ms 2.99ms 327. 84.14MB 4.09
#> 4 hrec1 10000 640.57µs 661.19µs 1497. 544B 4.07
#> 5 hrec2 10000 643.59µs 661.88µs 1499. 544B 6.16
#> 6 rec 10000 2.91ms 2.97ms 336. 42.63KB 6.25
#> 7 hrec1 5000000 640.35µs 662.02µs 1497. 544B 6.48
#> 8 hrec2 5000000 640.65µs 657.96µs 1505. 544B 4.07
#> 9 rec 5000000 2.91ms 2.96ms 336. 19.08MB 6.23add a step
results <- bench::press(
rows = n,
{
dat <- data.frame(x = rnorm(rows),
y = 1:rows)
bench::mark(
hrec1 = hydrorecipes:::Recipe$new(formula = formula, data = dat)$
add_step(hydrorecipes:::StepCenter$new(x)),
hrec2 = recipe(formula = formula, data = dat) |>
step_center(x),
rec = {recipes::recipe(formula = formula, data = dat) |>
recipes::step_center(x)},
check = FALSE,
relative = relative
)
}
)
#> Running with:
#> rows
#> 1 100
#> 2 10000
#> 3 5000000
results
#> # A tibble: 9 × 7
#> expression rows min median `itr/sec` mem_alloc `gc/sec`
#> <bch:expr> <dbl> <bch:tm> <bch:tm> <dbl> <bch:byt> <dbl>
#> 1 hrec1 100 868.55µs 892.43µs 1104. 531.23KB 6.18
#> 2 hrec2 100 891.83µs 925.42µs 1069. 6.57KB 6.30
#> 3 rec 100 3.03ms 3.12ms 318. 102.48KB 4.10
#> 4 hrec1 10000 868.75µs 901.76µs 1103. 1.06KB 6.18
#> 5 hrec2 10000 888.89µs 919.56µs 1082. 1.06KB 6.21
#> 6 rec 10000 3.03ms 3.12ms 320. 43.16KB 4.10
#> 7 hrec1 5000000 870.86µs 891.51µs 1114. 1.06KB 4.08
#> 8 hrec2 5000000 886.83µs 912.45µs 1089. 1.06KB 6.19
#> 9 rec 5000000 3.04ms 3.09ms 322. 19.08MB 6.35step_center prep
results <- bench::press(
rows = n,
{
dat <- data.frame(x = rnorm(rows),
y = 1:rows)
hrec1 = hydrorecipes:::Recipe$new(formula = formula, data = dat)$
add_step(hydrorecipes:::StepCenter$new(x))
hrec2 = recipe(formula = formula, data = dat) |>
step_center(x)
rec = recipes::recipe(formula = formula, data = dat) |>
recipes::step_center(x)
bench::mark(
hrec1$prep(),
hrec2 |> prep(),
rec |> recipes::prep(),
check = FALSE,
min_iterations = 10,
relative = relative
)
}
)
#> Running with:
#> rows
#> 1 100
#> 2 10000
#> 3 5000000
results
#> # A tibble: 9 × 7
#> expression rows min median `itr/sec` mem_alloc `gc/sec`
#> <bch:expr> <dbl> <bch:tm> <bch:tm> <dbl> <bch:byt> <dbl>
#> 1 hrec1$prep() 100 181.91µs 188.72µs 5238. 80.73KB 6.18
#> 2 prep(hrec2) 100 182.44µs 189.4µs 5173. 2.69KB 6.17
#> 3 recipes::prep(rec) 100 13.72ms 13.91ms 71.6 4.06MB 6.71
#> 4 hrec1$prep() 10000 190.77µs 198.63µs 4932. 0B 6.17
#> 5 prep(hrec2) 10000 193.3µs 200.07µs 4943. 0B 6.18
#> 6 recipes::prep(rec) 10000 13.82ms 14.04ms 70.7 224.78KB 6.63
#> 7 hrec1$prep() 5000000 4.99ms 5.08ms 196. 0B 0
#> 8 prep(hrec2) 5000000 5.05ms 5.08ms 197. 0B 0
#> 9 recipes::prep(rec) 5000000 101.8ms 106.78ms 6.47 95.4MB 10.4step_center prep and bake
results <- bench::press(
rows = n,
{
dat <- data.frame(x = rnorm(rows),
y = 1:rows)
hrec1 = hydrorecipes:::Recipe$new(formula = formula, data = dat)$
add_step(hydrorecipes:::StepCenter$new(x))
hrec2 = recipe(formula = formula, data = dat) |>
step_center(x)
rec = recipes::recipe(formula = formula, data = dat) |>
recipes::step_center(x)
bench::mark(
hrec1$prep()$bake(),
hrec2 |> prep() |> bake(),
rec |> recipes::prep() |> recipes::bake(new_data = NULL),
check = FALSE,
min_iterations = 10,
relative = relative
)
}
)
#> Running with:
#> rows
#> 1 100
#> 2 10000
#> 3 5000000
results
#> # A tibble: 9 × 7
#> expression rows min median `itr/sec` mem_alloc `gc/sec`
#> <bch:expr> <dbl> <bch:t> <bch:t> <dbl> <bch:byt> <dbl>
#> 1 hrec1$prep()$bake() 1e2 260.9µs 270.3µs 3605. 382.14KB 6.17
#> 2 bake(prep(hrec2)) 1e2 260.7µs 271.7µs 3640. 3.56KB 6.17
#> 3 recipes::bake(recipes::pre… 1e2 14.4ms 14.7ms 67.6 161.56KB 4.22
#> 4 hrec1$prep()$bake() 1e4 280.3µs 291.8µs 3389. 78.17KB 4.13
#> 5 bake(prep(hrec2)) 1e4 280.6µs 291.4µs 3353. 78.17KB 6.18
#> 6 recipes::bake(recipes::pre… 1e4 14.6ms 14.8ms 67.0 229.11KB 6.70
#> 7 hrec1$prep()$bake() 5e6 12.4ms 12.4ms 80.2 38.15MB 80.2
#> 8 bake(prep(hrec2)) 5e6 12.2ms 12.4ms 78.4 38.15MB 39.2
#> 9 recipes::bake(recipes::pre… 5e6 100.7ms 101.7ms 9.84 95.4MB 44.3step_center
formula <- as.formula(y~x+z)
results <- bench::press(
rows = n,
{
dat <- data.frame(x = rnorm(rows),
y = 1:rows,
z = rnorm(rows))
bench::mark(
hrec = (recipe(formula = formula, data = dat) |>
step_center(x) |>
plate())[["x"]],
rec = (recipes::recipe(formula = formula, data = dat) |>
recipes::step_center(x) |>
recipes::prep() |>
recipes::bake(new_data = NULL))[["x"]],
check = TRUE,
min_iterations = 10,
relative = relative
)
}
)
#> Running with:
#> rows
#> 1 100
#> 2 10000
#> 3 5000000
results
#> # A tibble: 6 × 7
#> expression rows min median `itr/sec` mem_alloc `gc/sec`
#> <bch:expr> <dbl> <bch:tm> <bch:tm> <dbl> <bch:byt> <dbl>
#> 1 hrec 100 1.26ms 1.31ms 759. 97.5KB 6.26
#> 2 rec 100 17.77ms 18.08ms 55.0 40.2KB 4.23
#> 3 hrec 10000 1.28ms 1.32ms 751. 80.9KB 6.22
#> 4 rec 10000 18ms 18.23ms 54.5 272.3KB 4.36
#> 5 hrec 5000000 10.08ms 13.68ms 74.4 38.1MB 47.8
#> 6 rec 5000000 110.8ms 110.8ms 9.03 114.5MB 81.2step_scale
formula <- as.formula(y~x)
results <- bench::press(
rows = n,
{
dat <- data.frame(x = rnorm(rows),
y = 1:rows,
z = rnorm(rows))
bench::mark(
hrec = (recipe(formula = formula, data = dat) |>
step_scale(x, fun = fsd, n_sd = 2L) |>
plate("tbl"))[["x"]],
rec = (recipes::recipe(formula = formula, data = dat) |>
recipes::step_scale(x, factor = 2L) |>
recipes::prep() |>
recipes::bake(new_data = NULL))[["x"]],
check = TRUE,
relative = relative,
min_iterations = 5
)
}
)
#> Running with:
#> rows
#> 1 100
#> 2 10000
#> 3 5000000
results
#> # A tibble: 6 × 7
#> expression rows min median `itr/sec` mem_alloc `gc/sec`
#> <bch:expr> <dbl> <bch:tm> <bch:tm> <dbl> <bch:byt> <dbl>
#> 1 hrec 100 1.27ms 1.31ms 756. 594.8KB 6.22
#> 2 rec 100 17.65ms 17.99ms 54.2 133.2KB 4.34
#> 3 hrec 10000 1.31ms 1.35ms 728. 79.2KB 6.20
#> 4 rec 10000 17.83ms 18.08ms 54.8 233.2KB 4.39
#> 5 hrec 5000000 20.82ms 24.55ms 41.6 38.1MB 17.8
#> 6 rec 5000000 131.12ms 131.27ms 7.62 95.4MB 11.4step_intercept
formula <- as.formula(y~x)
results <- bench::press(
rows = n,
{
dat <- data.frame(x = rnorm(rows),
y = rnorm(rows))
bench::mark(
hrec = (recipe(formula = formula, data = dat) |>
step_intercept() |>
plate("tbl"))[["intercept"]],
rec = (recipes::recipe(formula = formula, data = dat) |>
recipes::step_intercept() |>
recipes::prep() |>
recipes::bake(new_data = NULL))[["intercept"]],
check = TRUE,
relative = relative,
min_iterations = 2
)
}
)
#> Running with:
#> rows
#> 1 100
#> 2 10000
#> 3 5000000
results
#> # A tibble: 6 × 7
#> expression rows min median `itr/sec` mem_alloc `gc/sec`
#> <bch:expr> <dbl> <bch:tm> <bch:tm> <dbl> <bch:byt> <dbl>
#> 1 hrec 100 1.24ms 1.28ms 774. 527.7KB 6.23
#> 2 rec 100 16.64ms 16.9ms 58.9 116.3KB 4.36
#> 3 hrec 10000 1.24ms 1.29ms 764. 79.2KB 6.21
#> 4 rec 10000 16.79ms 17.04ms 58.3 112.1KB 6.73
#> 5 hrec 5000000 10.65ms 10.93ms 91.5 38.1MB 25.0
#> 6 rec 5000000 48.75ms 50.15ms 20.0 38.2MB 8.55step_normalize
formula <- as.formula(y~x+z)
results <- bench::press(
rows = n,
{
dat <- data.frame(x = rnorm(rows),
y = rnorm(rows),
z = rnorm(rows))
bench::mark(
hrec1 = (recipe(formula = formula, data = dat) |>
step_normalize(c(x, y, z)) |>
plate("tbl"))[, c("x", "z", "y")],
hrec2 = (recipe(formula = formula, data = dat) |>
step_center(c(x, y, z)) |>
step_scale(c(x, y, z)) |>
plate("tbl"))[, c("x", "z", "y")],
rec = recipes::recipe(formula = formula, data = dat) |>
recipes::step_normalize(x, y, z) |>
recipes::prep() |>
recipes::bake(new_data = NULL),
relative = relative,
min_iterations = 2,
check = TRUE
)
}
)
#> Running with:
#> rows
#> 1 100
#> 2 10000
#> 3 5000000
results
#> # A tibble: 9 × 7
#> expression rows min median `itr/sec` mem_alloc `gc/sec`
#> <bch:expr> <dbl> <bch:tm> <bch:tm> <dbl> <bch:byt> <dbl>
#> 1 hrec1 100 1.34ms 1.38ms 719. 541.98KB 6.24
#> 2 hrec2 100 1.7ms 1.75ms 568. 6.56KB 6.26
#> 3 rec 100 18.23ms 18.61ms 52.9 88.22KB 4.24
#> 4 hrec1 10000 1.51ms 1.55ms 642. 235.58KB 6.23
#> 5 hrec2 10000 1.88ms 1.94ms 514. 470.62KB 4.11
#> 6 rec 10000 18.69ms 19ms 52.3 663.09KB 6.82
#> 7 hrec1 5000000 83.16ms 90.09ms 11.2 114.44MB 5.59
#> 8 hrec2 5000000 99.27ms 101.64ms 9.86 228.88MB 9.86
#> 9 rec 5000000 273.57ms 273.77ms 3.65 305.21MB 3.65step_lag
formula <- as.formula(y~x)
results <- bench::press(
rows = n,
{
dat <- data.frame(x = rnorm(rows),
y = 1:rows,
z = rnorm(rows))
bench::mark(
hrec1 = unname(recipe(formula = formula, data = dat) |>
step_lead_lag(x, lag = 1:30) |>
plate("tbl")),
rec = unname(recipes::recipe(formula = formula, data = dat) |>
recipes::step_lag(x, lag = 1:30) |>
recipes::prep() |>
recipes::bake(new_data = NULL)),
check = TRUE,
relative = relative,
min_iterations = 10
)
}
)
#> Running with:
#> rows
#> 1 100
#> 2 10000
#> 3 5000000
results
#> # A tibble: 6 × 7
#> expression rows min median `itr/sec` mem_alloc `gc/sec`
#> <bch:expr> <dbl> <bch:tm> <bch:tm> <dbl> <bch:byt> <dbl>
#> 1 hrec1 100 2.83ms 2.9ms 340. 799.77KB 6.29
#> 2 rec 100 22.44ms 22.88ms 43.7 281.48KB 4.37
#> 3 hrec1 10000 2.98ms 3.06ms 317. 2.3MB 4.12
#> 4 rec 10000 23.64ms 23.93ms 41.6 5.9MB 6.93
#> 5 hrec1 5000000 179.61ms 196.59ms 3.95 1.12GB 3.95
#> 6 rec 5000000 660.25ms 722.94ms 1.29 2.83GB 2.19step_distributed_lag
formula <- as.formula(y~x)
results <- bench::press(
rows = c(5e5, 5e6, 1e7),
{
dat <- data.frame(x = rnorm(rows),
y = 1:rows,
z = rnorm(rows))
bench::mark(
hrec = recipe(formula = formula, data = dat) |>
step_distributed_lag(x, knots = log_lags_arma(5, 86401)) |>
plate(),
check = FALSE,
relative = relative,
min_iterations = 2
)
}
)
#> Running with:
#> rows
#> 1 500000
#> 2 5000000
#> 3 10000000
results
#> # A tibble: 3 × 7
#> expression rows min median `itr/sec` mem_alloc `gc/sec`
#> <bch:expr> <dbl> <bch:tm> <bch:tm> <dbl> <bch:byt> <dbl>
#> 1 hrec 500000 65.8ms 69.7ms 14.4 19.1MB 0
#> 2 hrec 5000000 450.2ms 450.2ms 2.22 155.9MB 2.22
#> 3 hrec 10000000 904.9ms 904.9ms 1.11 308.5MB 1.11step_harmonic
formula <- as.formula(y~x)
results <- bench::press(
rows = n,
{
dat <- data.frame(x = rnorm(rows),
y = 1:rows,
z = rnorm(rows))
bench::mark(
hrec = recipe(formula = formula, data = dat) |>
step_harmonic(x,
frequency = c(1.0, 2.0, 3.0),
cycle_size = 0.1,
starting_value = 0.0) |>
plate("tbl"),
rec = recipes::recipe(formula = formula, data = dat) |>
recipes::step_harmonic(x,
frequency = c(1.0, 2.0, 3.0),
cycle_size = 0.1,
starting_val = 0.0,
keep_original_cols = TRUE) |>
recipes::prep() |>
recipes::bake(new_data = NULL),
# sin and cos terms order is different
check = FALSE,
relative = relative,
min_iterations = 10
)
}
)
#> Running with:
#> rows
#> 1 100
#> 2 10000
#> 3 5000000
results
#> # A tibble: 6 × 7
#> expression rows min median `itr/sec` mem_alloc `gc/sec`
#> <bch:expr> <dbl> <bch:tm> <bch:tm> <dbl> <bch:byt> <dbl>
#> 1 hrec 100 1.41ms 1.46ms 680. 565.88KB 6.22
#> 2 rec 100 18.57ms 18.87ms 52.7 176.72KB 4.39
#> 3 hrec 10000 2.67ms 2.7ms 369. 548.27KB 4.10
#> 4 rec 10000 20.28ms 20.5ms 48.4 1.91MB 4.40
#> 5 hrec 5000000 596.49ms 618.41ms 1.63 267.03MB 0.181
#> 6 rec 5000000 775.4ms 782.13ms 1.25 934.64MB 0.535step_pca
set.seed(1)
formula <- as.formula(x~a + b + c + d + e + f + g + h + i + j + k + l)
results <- bench::press(
rows = n,
{
dat <- data.frame(x = rnorm(rows),
a = rnorm(rows),
b = rnorm(rows),
c = rnorm(rows),
d = rnorm(rows),
e = rnorm(rows),
f = rnorm(rows),
g = rnorm(rows),
h = rnorm(rows),
i = rnorm(rows),
j = rnorm(rows),
k = rnorm(rows),
l = rnorm(rows)
)
bench::mark(
hrec1 = recipe(formula = formula, data = dat)|>
step_pca(all_predictor(), n_comp = 10L) |>
plate(),
hrec2 = recipe(formula = formula, data = dat)|>
step_pca(all_predictor(), n_comp = 5L) |>
plate(),
hrec3 = recipe(formula = formula, data = dat)|>
step_pca(all_predictor(),
n_comp = 10L,
center = FALSE,
scale = FALSE) |>
plate(),
hrec4 = recipe(formula = formula, data = dat)|>
step_pca(all_predictor(),
n_comp = 5L,
center = FALSE,
scale = FALSE) |>
plate(),
rec1 = recipes::recipe(formula = formula, data = dat) |>
recipes::step_pca(recipes::all_predictors(),
num_comp = 10L,
options = list(center = TRUE, scale. = TRUE))|>
recipes::prep() |>
recipes::bake(new_data = NULL),
rec2 = recipes::recipe(formula = formula, data = dat) |>
recipes::step_pca(recipes::all_predictors(),
num_comp = 5L,
options = list(center = TRUE, scale. = TRUE)) |>
recipes::prep() |>
recipes::bake(new_data = NULL),
rec3 = recipes::recipe(formula = formula, data = dat) |>
recipes::step_pca(recipes::all_predictors(),
num_comp = 10L) |>
recipes::prep() |>
recipes::bake(new_data = NULL),
rec4 = recipes::recipe(formula = formula, data = dat) |>
recipes::step_pca(recipes::all_predictors(),
num_comp = 5L) |>
recipes::prep() |>
recipes::bake(new_data = NULL),
check = FALSE,
relative = relative,
min_iterations = 2
)
}
)
#> Running with:
#> rows
#> 1 100
#> 2 10000
#> 3 5000000
print(results, n = 100)
#> # A tibble: 24 × 14
#> expression rows min median `itr/sec` mem_alloc `gc/sec` n_itr n_gc
#> <bch:expr> <dbl> <bch:tm> <bch:tm> <dbl> <bch:byt> <dbl> <int> <dbl>
#> 1 hrec1 100 1.63ms 1.68ms 594. 706.11KB 6.25 285 3
#> 2 hrec2 100 1.63ms 1.68ms 594. 34.89KB 4.11 289 2
#> 3 hrec3 100 1.56ms 1.61ms 621. 34.02KB 6.24 299 3
#> 4 hrec4 100 1.56ms 1.6ms 621. 24.95KB 6.23 299 3
#> 5 rec1 100 21.69ms 22.21ms 44.7 661.98KB 4.47 20 2
#> 6 rec2 100 21.14ms 21.49ms 46.5 277.84KB 6.97 20 3
#> 7 rec3 100 21.28ms 21.59ms 46.2 154.4KB 6.93 20 3
#> 8 rec4 100 20.77ms 21.08ms 47.3 136.89KB 4.30 22 2
#> 9 hrec1 10000 4.24ms 4.28ms 224. 3.37MB 2.03 110 1
#> 10 hrec2 10000 4.15ms 4.2ms 238. 2.6MB 4.17 114 2
#> 11 hrec3 10000 3.17ms 3.22ms 299. 2.45MB 2.03 147 1
#> 12 hrec4 10000 3.1ms 3.15ms 317. 1.69MB 2.03 156 1
#> 13 rec1 10000 41.54ms 41.82ms 23.8 21.17MB 4.76 10 2
#> 14 rec2 10000 40.52ms 41.01ms 24.3 20.02MB 2.03 12 1
#> 15 rec3 10000 34.57ms 34.99ms 28.4 7.89MB 4.73 12 2
#> 16 rec4 10000 33.78ms 34.03ms 29.3 6.74MB 4.51 13 2
#> 17 hrec1 5000000 782.28ms 807.83ms 1.24 1.64GB 0.619 2 1
#> 18 hrec2 5000000 730.48ms 767.09ms 1.30 1.27GB 0.652 2 1
#> 19 hrec3 5000000 391.58ms 409.78ms 2.44 1.19GB 2.44 2 2
#> 20 hrec4 5000000 318.48ms 361.1ms 2.77 839.24MB 0 2 0
#> 21 rec1 5000000 4.14s 4.2s 0.238 10.3GB 1.43 2 12
#> 22 rec2 5000000 4.01s 4.33s 0.231 9.74GB 2.08 2 18
#> 23 rec3 5000000 2.01s 2.07s 0.483 3.82GB 1.21 2 5
#> 24 rec4 5000000 1.69s 1.73s 0.577 3.26GB 1.44 2 5
#> # ℹ 5 more variables: total_time <bch:tm>, result <list>, memory <list>,
#> # time <list>, gc <list>step_dummy
formula <- as.formula(y~x)
results <- bench::press(
rows = n,
{
dat <- data.frame(x = rnorm(rows),
y = qF(sample(1:10, rows, replace = TRUE)),
z = rnorm(rows))
bench::mark(
hrec = unname(recipe(formula = formula, data = dat) |>
step_dummy(y) |>
plate("tbl")),
rec = unname(recipes::recipe(formula = formula, data = dat) |>
recipes::step_dummy(y, keep_original_cols = TRUE) |>
recipes::prep() |>
recipes::bake(new_data = NULL)),
check = TRUE,
relative = FALSE,
min_iterations = 1
)
}
)
#> Running with:
#> rows
#> 1 100
#> 2 10000
#> 3 5000000
results
#> # A tibble: 6 × 7
#> expression rows min median `itr/sec` mem_alloc `gc/sec`
#> <bch:expr> <dbl> <bch:tm> <bch:tm> <dbl> <bch:byt> <dbl>
#> 1 hrec 100 2.8ms 2.88ms 346. 559.23KB 6.36
#> 2 rec 100 21.2ms 21.6ms 46.3 487.89KB 4.41
#> 3 hrec 10000 2.9ms 2.97ms 333. 353.05KB 4.11
#> 4 rec 10000 38ms 38.45ms 25.9 6.09MB 4.70
#> 5 hrec 5000000 45.8ms 48.57ms 19.2 235.66MB 3.83
#> 6 rec 5000000 11.5s 11.48s 0.0871 2.98GB 0.261step_find_interval
- no direct comparison so compare to step_cut
formula <- as.formula(y~x)
results <- bench::press(
rows = n,
{
dat <- data.frame(x = rnorm(rows),
y = 1:rows,
z = rnorm(rows))
bench::mark(
hrec = recipe(formula = formula, data = dat) |>
step_find_interval(x, vec = c(-0.1, 0, 0.1)) |>
plate("tbl"),
rec = recipes::recipe(formula = formula, data = dat) |>
recipes::step_cut(x, breaks = c(-0.1, 0, 0.1)) |>
recipes::prep() |>
recipes::bake(new_data = NULL),
check = FALSE,
relative = relative,
min_iterations = 1
)
}
)
#> Running with:
#> rows
#> 1 100
#> 2 10000
#> 3 5000000
results
#> # A tibble: 6 × 7
#> expression rows min median `itr/sec` mem_alloc `gc/sec`
#> <bch:expr> <dbl> <bch:tm> <bch:tm> <dbl> <bch:byt> <dbl>
#> 1 hrec 100 1.39ms 1.43ms 692. 562.7KB 6.99
#> 2 rec 100 18.38ms 18.77ms 52.5 174.2KB 0
#> 3 hrec 10000 1.53ms 1.58ms 632. 157.5KB 0
#> 4 rec 10000 18.68ms 19.36ms 51.1 585.1KB 2.13
#> 5 hrec 5000000 71.02ms 71.37ms 13.9 76.3MB 0
#> 6 rec 5000000 377.75ms 383.97ms 2.60 267.1MB 0step_varying
formula <- as.formula(y~x+z)
results <- bench::press(
rows = n,
{
dat <- data.frame(x = rep(1, rows),
y = 1:rows,
z = rnorm(rows))
bench::mark(
hrec = recipe(formula = formula, data = dat) |>
step_varying(c(x, y, z)) |>
plate("tbl"),
rec = recipes::recipe(formula = formula, data = dat) |>
recipes::step_zv(x, y, z) |>
recipes::prep() |>
recipes::bake(new_data = NULL),
check = TRUE,
relative = relative,
min_iterations = 1
)
}
)
#> Running with:
#> rows
#> 1 100
#> 2 10000
#> 3 5000000
results
#> # A tibble: 6 × 7
#> expression rows min median `itr/sec` mem_alloc `gc/sec`
#> <bch:expr> <dbl> <bch:tm> <bch:tm> <dbl> <bch:byt> <dbl>
#> 1 hrec 100 1.26ms 1.29ms 768. 583.33KB 2.08
#> 2 rec 100 17.88ms 18.4ms 53.9 93.13KB 2.07
#> 3 hrec 10000 1.25ms 1.29ms 760. 40.17KB 2.06
#> 4 rec 10000 18.51ms 18.61ms 53.4 1.33MB 0
#> 5 hrec 5000000 5.42ms 5.5ms 179. 19.07MB 0
#> 6 rec 5000000 628.34ms 628.34ms 1.59 649.8MB 0step_kernel_filter
formula <- as.formula(y~x+z)
results <- bench::press(
rows = c(2e4, 2e5),
{
dat <- data.frame(x = rep(1, rows),
y = 1:rows,
z = cumsum(rnorm(rows)))
bench::mark(
hrec = unname((recipe(formula = formula, data = dat) |>
step_kernel_filter(z, kernel = list(rep(1, 5001)/5001), align = "center") |>
plate("tbl"))[10000, "kernel_filter_z"]),
{rec = recipes::recipe(formula = formula, data = dat) |>
recipes::step_window(z, size = 5001, statistic = "mean") |>
recipes::prep() |>
recipes::bake(new_data = NULL)
unname(rec[10000, "z"])},
min_iterations = 1,
check = TRUE
)
}
)
#> Running with:
#> rows
#> 1 20000
#> 2 200000
results
#> # A tibble: 4 × 7
#> expression rows min median `itr/sec` mem_alloc `gc/sec`
#> <bch:expr> <dbl> <bch:tm> <bch:tm> <dbl> <bch:byt> <dbl>
#> 1 hrec 2e4 3.59ms 3.65ms 273. 750KB 2.07
#> 2 { rec = recipes::bake(re… 2e4 300.12ms 300.44ms 3.33 508.16KB 0
#> 3 hrec 2e5 5.82ms 5.92ms 167. 1.56MB 0
#> 4 { rec = recipes::bake(re… 2e5 3.64s 3.64s 0.275 3.11MB 0multiple steps
formula <- as.formula(y~x)
results <- bench::press(
rows = n,
{
dat <- data.frame(x = as.numeric(1:rows),
y = 1:rows)
bench::mark(
hrec = recipe(formula = formula, data = dat) |>
step_lead_lag(x, lag = 1:10) |>
step_harmonic(x,
frequency = c(1, 2, 3, 4, 5),
cycle_size = 0.1,
starting_value = 0) |>
step_center(x) |>
plate("tbl"),
rec = recipes::recipe(formula = formula, data = dat) |>
recipes::step_lag(x, lag = 1:10, keep_original_cols = TRUE) |>
recipes::step_harmonic(x,
frequency = c(1, 2, 3, 4, 5),
cycle_size = 0.1,
starting_val = 0,
keep_original_cols = TRUE) |>
recipes::step_center(x) |>
recipes::prep() |>
recipes::bake(new_data = NULL),
check = FALSE,
relative = relative,
min_iterations = 1
)
}
)
#> Running with:
#> rows
#> 1 100
#> 2 10000
#> 3 5000000
results
#> # A tibble: 6 × 7
#> expression rows min median `itr/sec` mem_alloc `gc/sec`
#> <bch:expr> <dbl> <bch:tm> <bch:tm> <dbl> <bch:byt> <dbl>
#> 1 hrec 100 2.24ms 2.29ms 436. 26.89KB 2.08
#> 2 rec 100 33.93ms 34.48ms 28.8 191.67KB 2.21
#> 3 hrec 10000 3.33ms 3.39ms 295. 1.76MB 2.05
#> 4 rec 10000 36.27ms 36.51ms 27.2 5.13MB 0
#> 5 hrec 5000000 2.03s 2.03s 0.493 877.39MB 0
#> 6 rec 5000000 2.78s 2.78s 0.360 2.44GB 1.08step_spline_b
formula <- as.formula(y~x)
results <- bench::press(
rows = n,
{
dat <- data.frame(x = rnorm(rows),
y = 1:rows)
bench::mark(
hrec = unname(recipe(formula = formula, data = dat) |>
step_spline_b(x, df = 13) |>
plate("tbl")),
rec = unname(recipes::recipe(formula = formula, data = dat) |>
recipes::step_spline_b(x, deg_free = 13, keep_original_cols = TRUE)|>
recipes::prep() |>
recipes::bake(new_data = NULL)),
check = TRUE,
relative = relative,
min_iterations = 10
)
}
)
#> Running with:
#> rows
#> 1 100
#> 2 10000
#> 3 5000000
results
#> # A tibble: 6 × 7
#> expression rows min median `itr/sec` mem_alloc `gc/sec`
#> <bch:expr> <dbl> <bch:tm> <bch:tm> <dbl> <bch:byt> <dbl>
#> 1 hrec 100 2.95ms 3.02ms 330. 583.65KB 0
#> 2 rec 100 21.59ms 21.91ms 45.4 365.84KB 2.16
#> 3 hrec 10000 3.81ms 3.9ms 255. 1.07MB 2.08
#> 4 rec 10000 23.9ms 24.26ms 40.6 4.55MB 2.14
#> 5 hrec 5000000 530.38ms 590.65ms 1.72 534.06MB 0.687
#> 6 rec 5000000 1.62s 1.66s 0.575 2.2GB 1.21step_aquifer_grf & step_aquifer_theis
The Theis solution is a subset of the grf solution.
formula <- as.formula(y~x)
results <- bench::press(
rows = n,
{
dat <- data.frame(x = as.numeric(1:rows),
y = rep(0.01, rows))
bench::mark(
hrec1 = recipe(formula = formula, data = dat) |>
step_aquifer_grf(time = x, flow_rate = y) |>
plate("dt"),
hrec2 = recipe(formula = formula, data = dat) |>
step_aquifer_theis(time = x, flow_rate = y) |>
plate("dt"),
check = TRUE,
relative = relative)
}
)
#> Running with:
#> rows
#> 1 100
#> 2 10000
#> 3 5000000
results
#> # A tibble: 6 × 7
#> expression rows min median `itr/sec` mem_alloc `gc/sec`
#> <bch:expr> <dbl> <bch:tm> <bch:tm> <dbl> <bch:byt> <dbl>
#> 1 hrec1 100 1.42ms 1.5ms 667. 555.2KB 0
#> 2 hrec2 100 1.5ms 1.54ms 628. 530.4KB 3.57
#> 3 hrec1 10000 2.34ms 2.38ms 419. 160.2KB 0
#> 4 hrec2 10000 2.43ms 2.48ms 402. 83.1KB 2.07
#> 5 hrec1 5000000 604.03ms 604.03ms 1.66 76.3MB 0
#> 6 hrec2 5000000 596.65ms 596.65ms 1.68 38.2MB 0step_aquifer_leaky
formula <- as.formula(y~x)
results <- bench::press(
rows = n,
{
dat <- data.frame(x = as.numeric(1:rows),
y = rep(0.01, rows))
bench::mark(
hrec1 = unname(recipe(formula = formula, data = dat) |>
step_aquifer_leaky(time = x,
flow_rate = y,
leakage = 100000000) |>
plate("dt")),
hrec2 = unname(recipe(formula = formula, data = dat) |>
step_aquifer_theis(time = x,
flow_rate = y) |>
plate("dt")),
check = TRUE,
relative = relative)
}
)
#> Running with:
#> rows
#> 1 100
#> 2 10000
#> 3 5000000
results
#> # A tibble: 6 × 7
#> expression rows min median `itr/sec` mem_alloc `gc/sec`
#> <bch:expr> <dbl> <bch:tm> <bch:tm> <dbl> <bch:byt> <dbl>
#> 1 hrec1 100 1.52ms 1.56ms 634. 615.1KB 2.07
#> 2 hrec2 100 1.6ms 1.64ms 606. 7.45KB 2.07
#> 3 hrec1 10000 3.27ms 3.3ms 298. 396.41KB 0
#> 4 hrec2 10000 2.54ms 2.58ms 387. 84.8KB 0
#> 5 hrec1 5000000 1.32s 1.32s 0.758 190.74MB 0
#> 6 hrec2 5000000 615.82ms 615.82ms 1.62 38.15MB 0step_aquifer_patch
formula <- as.formula(y~x)
results <- bench::press(
rows = c(1e5),
{
dat <- data.frame(x = as.numeric(1:rows),
y = rep(0.01, rows))
bench::mark(
hrec1 = (recipe(formula = formula, data = dat) |>
step_aquifer_grf(time = x, flow_rate = y) |>
plate("dt")),
hrec3 = (recipe(formula = formula, data = dat) |>
step_aquifer_patch(time = x,
flow_rate = 0.01,
thickness = 1.0,
radius = 100.0,
radius_patch = 200.0,
specific_storage_inner = 1e-6,
specific_storage_outer = 1e-6,
hydraulic_conductivity_inner = 1e-4,
hydraulic_conductivity_outer = 1e-4,
n_stehfest = 8L
) |>
plate("dt")),
check = FALSE,
relative = relative)
}
)
#> Running with:
#> rows
#> 1 100000
results
#> # A tibble: 2 × 7
#> expression rows min median `itr/sec` mem_alloc `gc/sec`
#> <bch:expr> <dbl> <bch:tm> <bch:tm> <dbl> <bch:byt> <dbl>
#> 1 hrec1 100000 9.88ms 10.1ms 98.4 1.53MB 0
#> 2 hrec3 100000 953.04ms 953ms 1.05 1.31MB 0step_vadose_weeks
formula <- as.formula(y~x)
results <- bench::press(
rows = n,
{
dat <- data.frame(x = as.numeric(1:rows),
y = as.numeric(1:rows))
bench::mark(
hrec1 = (recipe(formula = formula, data = dat) |>
step_vadose_weeks(time = x,
air_diffusivity = 0.8,
thickness = 5,
precision = 1e-12) |>
plate("dt")),
check = FALSE,
min_iterations = 10
)
}
)
#> Running with:
#> rows
#> 1 100
#> 2 10000
#> 3 5000000
results
#> # A tibble: 3 × 7
#> expression rows min median `itr/sec` mem_alloc `gc/sec`
#> <bch:expr> <dbl> <bch:tm> <bch:tm> <dbl> <bch:byt> <dbl>
#> 1 hrec1 100 1.27ms 1.31ms 760. 545.5KB 2.07
#> 2 hrec1 10000 1.46ms 1.49ms 669. 160.1KB 0
#> 3 hrec1 5000000 171.34ms 171.85ms 5.80 76.3MB 0step_transport_ogata_banks
formula <- as.formula(y~x)
results <- bench::press(
rows = n,
{
dat <- data.frame(expand.grid(as.numeric(1:rows), as.numeric(1:10)))
names(dat) <- c('x', 'y')
bench::mark(
hrec1 = (recipe(formula = formula, data = dat) |>
step_transport_ogata_banks(time = x,
distance = y) |>
plate("dt")),
check = FALSE,
min_iterations = 10
)
}
)
#> Running with:
#> rows
#> 1 100
#> 2 10000
#> 3 5000000
results
#> # A tibble: 3 × 7
#> expression rows min median `itr/sec` mem_alloc `gc/sec`
#> <bch:expr> <dbl> <bch:tm> <bch:tm> <dbl> <bch:byt> <dbl>
#> 1 hrec1 100 1.35ms 1.39ms 718. 559KB 2.07
#> 2 hrec1 10000 4.65ms 4.72ms 209. 785KB 2.09
#> 3 hrec1 5000000 1.47s 1.47s 0.680 381MB 1.02step_transport_fractures_solute
formula <- as.formula(~time+z+x)
dat <- setDT(expand.grid(10^(3:8),
seq(0.0, 10, 1),
c(0.0)))
names(dat) <- c("time", "z", "x")
results <-
bench::mark(
hrec1 = recipe(formula = formula, data = dat) |>
step_transport_fractures_solute(time = time,
distance_fracture = z,
distance_matrix = x) |>
plate("dt"),
check = FALSE,
min_iterations = 10
)
results
#> # A tibble: 1 × 6
#> expression min median `itr/sec` mem_alloc `gc/sec`
#> <bch:expr> <bch:tm> <bch:tm> <dbl> <bch:byt> <dbl>
#> 1 hrec1 1.78ms 1.84ms 538. 580KB 0step_transport_fractures_heat
formula <- as.formula(~time+z+x)
dat <- setDT(expand.grid(10^(3:8),
seq(0.0, 100, 1),
c(0.0, 0.05)))
names(dat) <- c("time", "z", "x")
results <-
bench::mark(
hrec1 = recipe(formula = formula, data = dat) |>
step_transport_fractures_heat(time = time,
distance_fracture = z,
distance_matrix = x) |>
plate("dt"),
check = FALSE,
min_iterations = 10
)
results
#> # A tibble: 1 × 6
#> expression min median `itr/sec` mem_alloc `gc/sec`
#> <bch:expr> <bch:tm> <bch:tm> <dbl> <bch:byt> <dbl>
#> 1 hrec1 10.3ms 10.3ms 96.5 587KB 0step_pgram and step_welch
formula <- as.formula(y~x + z)
results <- bench::press(
rows = n,
{
dat <- data.frame(x = rnorm(rows), y = rnorm(rows), z = rnorm(rows),
q = rnorm(rows), r = rnorm(rows), s = rnorm(rows))
bench::mark(
hrec1 = recipe(formula = formula, data = dat) |>
step_fft_pgram(c(x, y),
3,
TRUE,
TRUE,
FALSE,
0.1) |>
plate(),
hrec2 = recipe(formula = formula, data = dat) |>
step_fft_pgram(c(x, y),
3,
TRUE,
TRUE,
TRUE,
0.1) |>
plate(),
hrec3 = recipe(formula = formula, data = dat) |>
step_fft_welch(c(x, y),
length_subset = nrow(dat) / 10,
overlap = 0.60,
window = window_nuttall(nrow(dat) / 10)) |>
plate(),
check = FALSE,
min_iterations = 3
)
}
)
#> Running with:
#> rows
#> 1 100
#> 2 10000
#> 3 5000000
results
#> # A tibble: 9 × 7
#> expression rows min median `itr/sec` mem_alloc `gc/sec`
#> <bch:expr> <dbl> <bch:tm> <bch:tm> <dbl> <bch:byt> <dbl>
#> 1 hrec1 100 1.65ms 1.7ms 586. 566.41KB 2.76
#> 2 hrec2 100 1.68ms 1.72ms 574. 18.21KB 0
#> 3 hrec3 100 1.48ms 1.54ms 647. 546.3KB 2.56
#> 4 hrec1 10000 2.39ms 2.43ms 410. 1.38MB 0
#> 5 hrec2 10000 2.25ms 2.38ms 421. 1.07MB 0
#> 6 hrec3 10000 2.71ms 2.8ms 356. 260.91KB 2.58
#> 7 hrec1 5000000 471.55ms 487.89ms 2.05 686.65MB 1.02
#> 8 hrec2 5000000 414.88ms 414.88ms 2.41 534.06MB 4.82
#> 9 hrec3 5000000 443.85ms 454.35ms 2.22 125.89MB 0step_transfer_welch and step_transfer_pgram
formula <- as.formula(y~x)
results <- bench::press(
rows = n,
{
dat <- data.frame(x = rnorm(rows), y = rnorm(rows))
bench::mark(
hrec1 = recipe(formula = formula, data = dat) |>
step_fft_transfer_pgram(c(x, y),
3,
TRUE,
TRUE,
0.1) |>
plate("dt"),
hrec2 = recipe(formula = formula, data = dat) |>
step_fft_transfer_welch(c(x, y),
length_subset = nrow(dat) / 10,
overlap = 0.60,
window = window_nuttall(nrow(dat) / 10)) |>
plate("dt"),
check = FALSE,
min_iterations = 2
)
}
)
#> Running with:
#> rows
#> 1 100
#> 2 10000
#> 3 5000000
results
#> # A tibble: 6 × 7
#> expression rows min median `itr/sec` mem_alloc `gc/sec`
#> <bch:expr> <dbl> <bch:tm> <bch:tm> <dbl> <bch:byt> <dbl>
#> 1 hrec1 100 1.65ms 1.72ms 572. 548.3KB 0
#> 2 hrec2 100 1.54ms 1.58ms 631. 542.9KB 0
#> 3 hrec1 10000 3.22ms 3.35ms 291. 471.7KB 0
#> 4 hrec2 10000 2.88ms 2.94ms 340. 198.3KB 0
#> 5 hrec1 5000000 949.08ms 949.08ms 1.05 229.1MB 1.05
#> 6 hrec2 5000000 489.63ms 494.47ms 2.02 95.4MB 0step_ols
formula <- as.formula(y~x+z)
results <- bench::press(
rows = n,
{
dat <- data.frame(x = rnorm(rows),
y = rnorm(rows),
z = rnorm(rows))
bench::mark(
hrec = recipe(formula = formula, data = dat) |>
step_center(x) |>
step_scale(z) |>
step_ols(formula = formula) |>
plate(),
check = FALSE,
relative = relative
)
}
)
#> Running with:
#> rows
#> 1 100
#> 2 10000
#> 3 5000000
results
#> # A tibble: 3 × 7
#> expression rows min median `itr/sec` mem_alloc `gc/sec`
#> <bch:expr> <dbl> <bch:tm> <bch:tm> <dbl> <bch:byt> <dbl>
#> 1 hrec 100 2.68ms 2.77ms 356. 812.21KB 0
#> 2 hrec 10000 4.63ms 4.66ms 214. 1.34MB 0
#> 3 hrec 5000000 208.04ms 212.5ms 4.71 667.58MB 2.35step_ols_gap_fill
set.seed(123)
n <- 100000
frm <- formula(x ~ y + z)
x <- cumsum(rnorm(n))
dat <- data.table(x = x, y = x, z = as.numeric(1:n))
dat[, x := x + c(rep(20, n/2), rep(0, n/2))]
dat[, x := x + 3.0 * sin(z * 1/n)]
tmp <- copy(dat$x)
# Set value to NA. These values will be estimated.
dat[60000:70000, x := NA_real_]
dat <- unclass(dat)
bench::mark(
{h = recipe(formula = frm, data = dat) |>
step_find_interval(z, vec = c(0, n/2, n)) |>
step_intercept() |>
step_spline_b(z, df = 4) |>
step_drop_columns(z)
hrec = recipe(formula = frm, data = dat) |>
step_ols_gap_fill(c(x, y, z), recipe = h) |>
plate()},
)
#> num [1:100000, 1:8] -0.56 -0.791 0.768 0.839 0.968 ...
#> - attr(*, "dimnames")=List of 2
#> ..$ : NULL
#> ..$ : chr [1:8] "y" "find_interval_z_1" "find_interval_z_2" "intercept" ...
#> NULL
#> num [1:100000, 1:8] -0.56 -0.791 0.768 0.839 0.968 ...
#> - attr(*, "dimnames")=List of 2
#> ..$ : NULL
#> ..$ : chr [1:8] "y" "find_interval_z_1" "find_interval_z_2" "intercept" ...
#> NULL
#> num [1:100000, 1:8] -0.56 -0.791 0.768 0.839 0.968 ...
#> - attr(*, "dimnames")=List of 2
#> ..$ : NULL
#> ..$ : chr [1:8] "y" "find_interval_z_1" "find_interval_z_2" "intercept" ...
#> NULL
#> num [1:100000, 1:8] -0.56 -0.791 0.768 0.839 0.968 ...
#> - attr(*, "dimnames")=List of 2
#> ..$ : NULL
#> ..$ : chr [1:8] "y" "find_interval_z_1" "find_interval_z_2" "intercept" ...
#> NULL
#> num [1:100000, 1:8] -0.56 -0.791 0.768 0.839 0.968 ...
#> - attr(*, "dimnames")=List of 2
#> ..$ : NULL
#> ..$ : chr [1:8] "y" "find_interval_z_1" "find_interval_z_2" "intercept" ...
#> NULL
#> num [1:100000, 1:8] -0.56 -0.791 0.768 0.839 0.968 ...
#> - attr(*, "dimnames")=List of 2
#> ..$ : NULL
#> ..$ : chr [1:8] "y" "find_interval_z_1" "find_interval_z_2" "intercept" ...
#> NULL
#> num [1:100000, 1:8] -0.56 -0.791 0.768 0.839 0.968 ...
#> - attr(*, "dimnames")=List of 2
#> ..$ : NULL
#> ..$ : chr [1:8] "y" "find_interval_z_1" "find_interval_z_2" "intercept" ...
#> NULL
#> num [1:100000, 1:8] -0.56 -0.791 0.768 0.839 0.968 ...
#> - attr(*, "dimnames")=List of 2
#> ..$ : NULL
#> ..$ : chr [1:8] "y" "find_interval_z_1" "find_interval_z_2" "intercept" ...
#> NULL
#> num [1:100000, 1:8] -0.56 -0.791 0.768 0.839 0.968 ...
#> - attr(*, "dimnames")=List of 2
#> ..$ : NULL
#> ..$ : chr [1:8] "y" "find_interval_z_1" "find_interval_z_2" "intercept" ...
#> NULL
#> num [1:100000, 1:8] -0.56 -0.791 0.768 0.839 0.968 ...
#> - attr(*, "dimnames")=List of 2
#> ..$ : NULL
#> ..$ : chr [1:8] "y" "find_interval_z_1" "find_interval_z_2" "intercept" ...
#> NULL
#> num [1:100000, 1:8] -0.56 -0.791 0.768 0.839 0.968 ...
#> - attr(*, "dimnames")=List of 2
#> ..$ : NULL
#> ..$ : chr [1:8] "y" "find_interval_z_1" "find_interval_z_2" "intercept" ...
#> NULL
#> num [1:100000, 1:8] -0.56 -0.791 0.768 0.839 0.968 ...
#> - attr(*, "dimnames")=List of 2
#> ..$ : NULL
#> ..$ : chr [1:8] "y" "find_interval_z_1" "find_interval_z_2" "intercept" ...
#> NULL
#> num [1:100000, 1:8] -0.56 -0.791 0.768 0.839 0.968 ...
#> - attr(*, "dimnames")=List of 2
#> ..$ : NULL
#> ..$ : chr [1:8] "y" "find_interval_z_1" "find_interval_z_2" "intercept" ...
#> NULL
#> num [1:100000, 1:8] -0.56 -0.791 0.768 0.839 0.968 ...
#> - attr(*, "dimnames")=List of 2
#> ..$ : NULL
#> ..$ : chr [1:8] "y" "find_interval_z_1" "find_interval_z_2" "intercept" ...
#> NULL
#> num [1:100000, 1:8] -0.56 -0.791 0.768 0.839 0.968 ...
#> - attr(*, "dimnames")=List of 2
#> ..$ : NULL
#> ..$ : chr [1:8] "y" "find_interval_z_1" "find_interval_z_2" "intercept" ...
#> NULL
#> num [1:100000, 1:8] -0.56 -0.791 0.768 0.839 0.968 ...
#> - attr(*, "dimnames")=List of 2
#> ..$ : NULL
#> ..$ : chr [1:8] "y" "find_interval_z_1" "find_interval_z_2" "intercept" ...
#> NULL
#> num [1:100000, 1:8] -0.56 -0.791 0.768 0.839 0.968 ...
#> - attr(*, "dimnames")=List of 2
#> ..$ : NULL
#> ..$ : chr [1:8] "y" "find_interval_z_1" "find_interval_z_2" "intercept" ...
#> NULL
#> num [1:100000, 1:8] -0.56 -0.791 0.768 0.839 0.968 ...
#> - attr(*, "dimnames")=List of 2
#> ..$ : NULL
#> ..$ : chr [1:8] "y" "find_interval_z_1" "find_interval_z_2" "intercept" ...
#> NULL
#> # A tibble: 1 × 6
#> expression min median `itr/sec` mem_alloc `gc/sec`
#> <bch:expr> <bch> <bch:> <dbl> <bch:byt> <dbl>
#> 1 { h = step_drop_columns(step_spline… 26ms 26.1ms 38.3 38.2MB 2.39check
step_check_spacing
formula <- as.formula(y~x)
results <- bench::press(
rows = n,
{
dat <- data.frame(x = rnorm(rows),
y = 1:rows)
dat[9, "x"] <- NA
dat[9, "y"] <- NA
bench::mark(
hrec1 = recipe(formula = formula, data = dat) |>
step_check_spacing(y) |>
step_check_na(y) |>
prep() |>
bake(),
hrec2 =recipe(formula = formula, data = dat) |>
step_check_spacing(x) |>
step_check_na(x) |>
prep() |>
bake(),
check = FALSE,
relative = relative,
min_iterations = 10
)
}
)
#> Running with:
#> rows
#> 1 100000
results
#> # A tibble: 2 × 7
#> expression rows min median `itr/sec` mem_alloc `gc/sec`
#> <bch:expr> <dbl> <bch:tm> <bch:tm> <dbl> <bch:byt> <dbl>
#> 1 hrec1 100000 1.89ms 1.93ms 510. 2.59MB 0
#> 2 hrec2 100000 2.32ms 2.36ms 422. 782.89KB 0