``` r
rm(list=ls())
library(tidyverse)
library(duckplyr)
#> The duckplyr package is configured to fall back to dplyr when it encounters an
#> incompatibility. Fallback events can be collected and uploaded for analysis to
#> guide future development. By default, data will be collected but no data will
#> be uploaded.
#> ℹ Automatic fallback uploading is not controlled and therefore disabled, see
#>   `?duckplyr::fallback()`.
#> ✔ Number of reports ready for upload: 11.
#> → Review with `duckplyr::fallback_review()`, upload with
#>   `duckplyr::fallback_upload()`.
#> ℹ Configure automatic uploading with `duckplyr::fallback_config()`.
#> ✔ Overwriting dplyr methods with duckplyr methods.
#> ℹ Turn off with `duckplyr::methods_restore()`.
library(tictoc)
library(arrow)
#>
#> Attaching package: 'arrow'
#> The following object is masked from 'package:lubridate':
#>
#>     duration
#> The following object is masked from 'package:utils':
#>
#>     timestamp


# Increased the size of data
## dd <- tibble(x=1:100000000, y=rep(LETTERS[1:20], 5000000))


## write_csv(dd, "test.csv")


df <- duck_csv("test.csv")

system.time({
df_stat <- df |>
    summarise(total=sum(x), .by = y) |>
    collect() |>
    as_tibble()

})
#>    user  system elapsed
#>  28.368   0.437   7.866


df2  <- open_dataset("test.csv",
  format = "csv",
  skip_rows = 0)

system.time({
    df_stat2 <- df2 |>
    group_by(y) |>
    summarise(total=sum(x)) |>
    ungroup() |>
    collect()

})
#>    user  system elapsed
#>  12.319   0.352   7.477


print("So far so good")
#> [1] "So far so good"
```

<sup>Created on 2024-12-31 with [reprex v2.1.0](https://reprex.tidyverse.org)</sup>