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: 9.
#> → 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()`.


dd <- tibble(x=1:100, y=rep(LETTERS[1:20], 5))


write_csv(dd, "test.csv")


## open file without reading it into memory and perform aggregations

df <- duck_file("test.csv", "read_csv")

df_stat <- df |>
    group_by(y) |>
    summarise(total=sum(x))
#> Error: Materialization is disabled, use collect() or as_tibble() to materialize
    ungroup()
#> Error in UseMethod("ungroup"): no applicable method for 'ungroup' applied to an object of class "NULL"


df_stat2 <- df |>
    collect() |>
    group_by(y) |>
    summarise(total=sum(x))
    ungroup()
#> Error in UseMethod("ungroup"): no applicable method for 'ungroup' applied to an object of class "NULL"

df_stat2
#> # A tibble: 20 × 2
#>    y     total
#>    <chr> <dbl>
#>  1 A       205
#>  2 B       210
#>  3 C       215
#>  4 D       220
#>  5 E       225
#>  6 F       230
#>  7 G       235
#>  8 H       240
#>  9 I       245
#> 10 J       250
#> 11 K       255
#> 12 L       260
#> 13 M       265
#> 14 N       270
#> 15 O       275
#> 16 P       280
#> 17 Q       285
#> 18 R       290
#> 19 S       295
#> 20 T       300

sessionInfo()
#> R version 4.4.2 (2024-10-31)
#> Platform: x86_64-pc-linux-gnu
#> Running under: Debian GNU/Linux 12 (bookworm)
#>
#> Matrix products: default
#> BLAS:   /usr/lib/x86_64-linux-gnu/blas/libblas.so.3.11.0
#> LAPACK: /usr/lib/x86_64-linux-gnu/lapack/liblapack.so.3.11.0
#>
#> locale:
#>  [1] LC_CTYPE=en_GB.UTF-8       LC_NUMERIC=C
#>  [3] LC_TIME=en_GB.UTF-8        LC_COLLATE=en_GB.UTF-8
#>  [5] LC_MONETARY=en_GB.UTF-8    LC_MESSAGES=en_GB.UTF-8
#>  [7] LC_PAPER=en_GB.UTF-8       LC_NAME=C
#>  [9] LC_ADDRESS=C               LC_TELEPHONE=C
#> [11] LC_MEASUREMENT=en_GB.UTF-8 LC_IDENTIFICATION=C
#>
#> time zone: Europe/Brussels
#> tzcode source: system (glibc)
#>
#> attached base packages:
#> [1] stats     graphics  grDevices utils     datasets  methods   base
#>
#> other attached packages:
#>  [1] duckplyr_0.99.99.9910 lubridate_1.9.3       forcats_1.0.0
#>  [4] stringr_1.5.1         dplyr_1.1.4           purrr_1.0.2
#>  [7] readr_2.1.5           tidyr_1.3.1           tibble_3.2.1
#> [10] ggplot2_3.5.1         tidyverse_2.0.0
#>
#> loaded via a namespace (and not attached):
#>  [1] styler_1.10.3      utf8_1.2.4         generics_0.1.3     stringi_1.8.4
#>  [5] hms_1.1.3          digest_0.6.35      magrittr_2.0.3     evaluate_0.23
#>  [9] grid_4.4.2         timechange_0.3.0   fastmap_1.1.1      jsonlite_1.8.8
#> [13] R.oo_1.26.0        R.cache_0.16.0     R.utils_2.12.3     DBI_1.2.2
#> [17] scales_1.3.0       collections_0.3.7  duckdb_1.1.3-1     cli_3.6.3
#> [21] rlang_1.1.4        crayon_1.5.2       R.methodsS3_1.8.2  bit64_4.0.5
#> [25] munsell_0.5.1      reprex_2.1.0       withr_3.0.0        cachem_1.0.8
#> [29] yaml_2.3.8         tools_4.4.2        parallel_4.4.2     tzdb_0.4.0
#> [33] memoise_2.0.1      colorspace_2.1-0   vctrs_0.6.5        R6_2.5.1
#> [37] lifecycle_1.0.4    fs_1.6.4           bit_4.0.5          vroom_1.6.5
#> [41] pkgconfig_2.0.3    pillar_1.10.1.9000 gtable_0.3.5       glue_1.7.0
#> [45] xfun_0.43          tidyselect_1.2.1   knitr_1.46         htmltools_0.5.8.1
#> [49] rmarkdown_2.26     compiler_4.4.2
Created on 2024-12-31 with reprex v2.1.0