Last active
April 19, 2024 14:55
-
-
Save JosiahParry/841daaf9a0a9deca6b60d13e2aaa044b to your computer and use it in GitHub Desktop.
fast UUID replacement
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
FROM python:3.9-bookworm | |
ENV R_VERSION=4.3.3 | |
# Install from Posit binaries | |
# https://docs.posit.co/resources/install-r/#verify-r-installation | |
RUN apt-get update && \ | |
apt-get install -y gdebi-core curl && \ | |
curl -O https://cdn.rstudio.com/r/debian-12/pkgs/r-${R_VERSION}_1_amd64.deb && \ | |
gdebi -n r-${R_VERSION}_1_amd64.deb && \ | |
ln -s /opt/R/${R_VERSION}/bin/R /usr/local/bin/R && \ | |
ln -s /opt/R/${R_VERSION}/bin/Rscript /usr/local/bin/Rscript | |
RUN R -e "install.packages('https://josiahparry.r-universe.dev/bin/linux/jammy/4.3/src/contrib/uwu_0.0.0.9000.tar.gz')" | |
# install packages to create fake data | |
RUN R -e "install.packages(c('collapse', 'lorem', 'bench'), repos = 'https://p3m.dev/cran/__linux__/bookworm/latest')" | |
RUN echo "\ | |
words <- lorem::ipsum_words(1e6) |> strsplit(' ') |> unlist(); \ | |
df <- as.data.frame(replicate(10, sample(words))); \ | |
df <- collapse::na_insert(df, prop = 0.1); \ | |
bench::mark( \ | |
uwu = { \ | |
df_names <- colnames(df); \ | |
for (j in seq_along(df)) { \ | |
uwu::impute_uuid(df[[j]], paste0('NA_', df_names[j], '_')); \ | |
} \ | |
}, \ | |
iterations = 1 \ | |
) \ | |
" > /tmp/script.R | |
ENTRYPOINT ["Rscript", "/tmp/script.R"] |
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
library(data.table) | |
library(collapse) | |
words <- lorem::ipsum_words(1e6) |> | |
strsplit(" ") |> | |
unlist() | |
df <- as.data.frame(replicate(10, sample(words))) | |
df <- na_insert(df, prop = 0.1) | |
# create a data.table | |
dt <- df | |
setDT(dt) | |
# based on | |
# https://stackoverflow.com/questions/7235657/fastest-way-to-replace-nas-in-a-large-data-table | |
f_dowle3 = function(DT) { | |
dt_names <- colnames(DT) | |
for (j in seq_len(ncol(DT))) { | |
na_index <- which(is.na(DT[[j]])) | |
uuids <- uuid::UUIDgenerate(use.time = NA, n = length(na_index)) | |
to_fill_with <- paste0("NA_", dt_names[j], "_", uuids) | |
set(DT,na_index,j, to_fill_with) | |
} | |
} | |
f_dowle3(dt) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment