Benchmark of `rpolars`.

polars_bench.R

install.packages(
  'tidypolars', 
  repos = c('https://etiennebacher.r-universe.dev', getOption("repos"))
)

library(tidypolars)
library(polars)
library(collapse, warn.conflicts = FALSE)
library(dplyr, warn.conflicts = FALSE)
library(DBI)
# library(bench)
# library(data.table)
# library(duckdb)

db <- dbConnect(duckdb::duckdb())

large_iris <- data.table::rbindlist(rep(list(iris), 100000))
large_iris_pl <- as_polars_lf(large_iris)
large_iris_pl$sink_parquet("large_iris.parquet")

format(nrow(large_iris), big.mark = ",")

res <-
  bench::mark(
  polars = {
    pl$scan_parquet("large_iris.parquet")$
      select(c("Sepal.Length", "Sepal.Width", "Petal.Length", "Petal.Width"))$
      with_columns(
        pl$when(
          (pl$col("Petal.Length") / pl$col("Petal.Width") > 3)
        )$then(pl$lit("long"))$
          otherwise(pl$lit("large"))$
          alias("petal_type")
      )$
      filter(pl$col("Sepal.Length")$is_between(4.5, 5.5)) |>
      collect()
  },
  tidypolars = {
    pl$scan_parquet("large_iris.parquet") |>
      select(starts_with(c("Sep", "Pet"))) |>
      mutate(
        petal_type = ifelse((Petal.Length / Petal.Width) > 3, "long", "large")
      ) |> 
      filter(between(Sepal.Length, 4.5, 5.5)) |>
      collect()
  },
  dplyr = {
    arrow::read_parquet("large_iris.parquet") |>
      select(starts_with(c("Sep", "Pet"))) |>
      mutate(
        petal_type = ifelse((Petal.Length / Petal.Width) > 3, "long", "large")
      ) |>
      filter(between(Sepal.Length, 4.5, 5.5))
  },
  `DuckDB/dbplyr` = {
    tbl(db, "read_parquet('large_iris.parquet')",
        check_from = FALSE) |>
      select(starts_with(c("Sep", "Pet"))) |>
      mutate(
        petal_type = if_else((Petal.Length / Petal.Width) > 3, "long", "large")
      ) |>
      filter(between(Sepal.Length, 4.5, 5.5)) |>
      collect()
  },
  collapse = {
    arrow::read_parquet("large_iris.parquet") |>
      fselect(c("Sepal.Length", "Sepal.Width", "Petal.Length", "Petal.Width")) |>
      fmutate(
        petal_type = data.table::fifelse((Petal.Length / Petal.Width) > 3, "long", "large")
      ) |>
      fsubset(Sepal.Length >= 4.5 & Sepal.Length <= 5.5)
  },
  check = FALSE,
  iterations = 40
)

# NOTE: do NOT take the "mem_alloc" results into account.
# `bench::mark()` doesn't report the accurate memory usage for packages calling
# Rust code.

res |>
  select(expression, median, total_time)