Testing readr::read_csv(), data.table::fread() and vroom::vroom()

test-readr-datatable-vroom.R

# Test done to check/answer the question at https://stackoverflow.com/questions/68211842/why-is-vroom-so-slow
# Downloaded CSV file on 2021-07-01 from:
# https://www.datosabiertos.gob.pe/dataset/vacunaci%C3%B3n-contra-covid-19-ministerio-de-salud-minsa
# and then compressed it with gzip
# $ zcat vacunas_covid.csv.gz | wc -l
# 7311644

library(readr)
library(vroom)
library(data.table)
library(microbenchmark)
csv_file <- "vacunas_covid.csv.gz"
microbenchmark(
  readr={
    t <- read_csv(csv_file, col_types=cols())
    write_csv(t, csv_file)
  },data.table={
    t <- fread(csv_file)
    fwrite(t, csv_file, sep=",")
  },vroom={
    t <- vroom(csv_file, delim=",", show_col_types = F)
    vroom_write(t, csv_file, delim=",")
  },
  times=5
)

test-readr-datatable-vroom.Rout

R version 4.1.0 (2021-05-18) -- "Camp Pontanezen"
Copyright (C) 2021 The R Foundation for Statistical Computing
Platform: x86_64-pc-linux-gnu (64-bit)

R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.

  Natural language support but running in an English locale

R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.

Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for an HTML browser interface to help.
Type 'q()' to quit R.

> # Test done to check/answer the question at https://stackoverflow.com/questions/68211842/why-is-vroom-so-slow
> # Downloaded CSV file on 2021-07-01 from:
> # https://www.datosabiertos.gob.pe/dataset/vacunaci%C3%B3n-contra-covid-19-ministerio-de-salud-minsa
> # and then compressed it with gzip
> 
> library(readr)
> library(vroom)
> library(data.table)
> library(microbenchmark)
> csv_file <- "vacunas_covid.csv.gz"
> microbenchmark(
+   readr={
+     t <- read_csv(csv_file, col_types=cols())
+     write_csv(t, csv_file)
+   },data.table={
+     t <- fread(csv_file)
+     fwrite(t, csv_file, sep=",")
+   },vroom={
+     t <- vroom(csv_file, delim=",", show_col_types = F)
+     vroom_write(t, csv_file, delim=",")
+   },
+   times=5
+ )
Unit: seconds
       expr       min        lq      mean    median        uq       max neval  cld
      readr 101.72094 105.75384 109.16869 106.08111 108.06967 124.21788     5    c
 data.table  28.18751  30.32570  31.06592  30.44838  33.12746  33.24055     5  a
      vroom  48.65399  51.52445  55.78264  52.89823  53.83582  72.00071     5   b
> 
> 
> 
> proc.time()
    user   system  elapsed 
1065.499   39.475  990.722