-
-
Save knbknb/e113b12d852f0f65f5ee282af49c8210 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# benchmarking the new parsnip release 1.0.3 vs previous 1.0.2 | |
# | |
# forked from: @simonpcouch | |
# https://gist.github.com/simonpcouch/651d0ea4d968b455ded8194578dabf52 | |
# gist name:simonpcouch/parsnip_speedup.R | |
# 2022-11-22 | |
# | |
library(tidymodels) | |
# with v1.0.2 ------------------------------------------------------------ | |
pak::pkg_install("tidymodels/parsnip@v1.0.2") | |
num_samples <- 10^(3:7) | |
num_resamples <- c(5, 10, 20) | |
nrow <- length(num_samples) * length(num_resamples) | |
res_v102 <- | |
tibble( | |
version = character(nrow), | |
num_samples = numeric(nrow), | |
num_resamples = numeric(nrow), | |
time_to_fit = numeric(nrow) | |
) | |
set.seed(1) | |
for (i in seq_along(num_samples)) { | |
dat <- tibble(x = rnorm(num_samples[i]), y = x + rnorm(num_samples[i], sd = .2)) | |
for (j in seq_along(num_resamples)) { | |
folds <- vfold_cv(dat, v = num_resamples[j]) | |
timing <- | |
system.time({ | |
fit_resamples(linear_reg(), y ~ x, folds) | |
}) | |
idx <- (length(num_samples) * (j - 1)) + i | |
res_v102[idx,] <- list("v1.0.2", num_samples[i], num_resamples[j], timing[["elapsed"]]) | |
} | |
} | |
# with v1.0.3 ------------------------------------------------------------ | |
pak::pkg_install("tidymodels/parsnip@v1.0.3") | |
res_v103 <- | |
tibble( | |
version = character(nrow), | |
num_samples = numeric(nrow), | |
num_resamples = numeric(nrow), | |
time_to_fit = numeric(nrow) | |
) | |
set.seed(1) | |
for (i in seq_along(num_samples)) { | |
dat <- tibble(x = rnorm(num_samples[i]), y = x + rnorm(num_samples[i], sd = .2)) | |
for (j in seq_along(num_resamples)) { | |
folds <- vfold_cv(dat, v = num_resamples[j]) | |
timing <- | |
system.time({ | |
fit_resamples(linear_reg(), y ~ x, folds) | |
}) | |
idx <- (length(num_samples) * (j - 1)) + i | |
res_v103[idx,] <- list("v1.0.3", num_samples[i], num_resamples[j], timing[["elapsed"]]) | |
} | |
} | |
# plotting --------------------------------------------------------------- | |
res <- bind_rows(res_v102, res_v103) | |
res_plot <- | |
res %>% | |
pivot_wider( | |
id_cols = c(num_samples, num_resamples), | |
names_from = version, | |
values_from = time_to_fit | |
) %>% | |
mutate(speedup = `v1.0.2` / `v1.0.3`) %>% | |
select(-starts_with("v")) %>% | |
mutate(num_resamples = factor(num_resamples, levels = c("20", "10", "5"), ordered = TRUE)) %>% | |
ggplot() + | |
aes(x = num_samples, y = speedup, col = num_resamples) + | |
geom_line() + | |
scale_x_log10() + | |
labs( | |
x = "Number of Rows in Training Data", | |
y = "Speedup (v1.0.2 / v1.0.3)", | |
col = "Number \nof Folds", | |
title = "The 'parsnip' R Package got a bit faster", | |
subtitle = "The new release of parsnip contributed speedup for model fitting." | |
) + | |
scale_color_viridis_d(end = .8) + | |
theme(plot.subtitle = element_text(face = "italic")) | |
res_plot | |
ggsave("parsnip-102vs103-speedup.svg", res_plot, width = 6, height = 4, dpi = 400) | |
ggsave("parsnip-102vs103-speedup.png", res_plot, width = 6, height = 4, dpi = 400) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
This is the speedup I got on my machine. R 4.2.2, i686 Haswell i4770K from 2012, 16 GB RAM,