chunk_df.R

``` r
library(dplyr)

# vector operation
chunk_vec <- function(chunk_size){
  ceiling(seq_along(row_number())/chunk_size)
}

# operate on dataframe
chunk_df <- function(.data, chunk_size) {
  
  mutate(.data, chunk = chunk_vec(chunk_size)) %>%
    group_by(chunk) %>%
    group_split()
  
}

mtcars |> 
  chunk_df(12)
#> <list_of<
#>   tbl_df<
#>     mpg  : double
#>     cyl  : double
#>     disp : double
#>     hp   : double
#>     drat : double
#>     wt   : double
#>     qsec : double
#>     vs   : double
#>     am   : double
#>     gear : double
#>     carb : double
#>     chunk: double
#>   >
#> >[3]>
#> [[1]]
#> # A tibble: 12 × 12
#>      mpg   cyl  disp    hp  drat    wt  qsec    vs    am  gear  carb chunk
#>    <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#>  1  21       6  160    110  3.9   2.62  16.5     0     1     4     4     1
#>  2  21       6  160    110  3.9   2.88  17.0     0     1     4     4     1
#>  3  22.8     4  108     93  3.85  2.32  18.6     1     1     4     1     1
#>  4  21.4     6  258    110  3.08  3.22  19.4     1     0     3     1     1
#>  5  18.7     8  360    175  3.15  3.44  17.0     0     0     3     2     1
#>  6  18.1     6  225    105  2.76  3.46  20.2     1     0     3     1     1
#>  7  14.3     8  360    245  3.21  3.57  15.8     0     0     3     4     1
#>  8  24.4     4  147.    62  3.69  3.19  20       1     0     4     2     1
#>  9  22.8     4  141.    95  3.92  3.15  22.9     1     0     4     2     1
#> 10  19.2     6  168.   123  3.92  3.44  18.3     1     0     4     4     1
#> 11  17.8     6  168.   123  3.92  3.44  18.9     1     0     4     4     1
#> 12  16.4     8  276.   180  3.07  4.07  17.4     0     0     3     3     1
#> 
#> [[2]]
#> # A tibble: 12 × 12
#>      mpg   cyl  disp    hp  drat    wt  qsec    vs    am  gear  carb chunk
#>    <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#>  1  17.3     8 276.    180  3.07  3.73  17.6     0     0     3     3     2
#>  2  15.2     8 276.    180  3.07  3.78  18       0     0     3     3     2
#>  3  10.4     8 472     205  2.93  5.25  18.0     0     0     3     4     2
#>  4  10.4     8 460     215  3     5.42  17.8     0     0     3     4     2
#>  5  14.7     8 440     230  3.23  5.34  17.4     0     0     3     4     2
#>  6  32.4     4  78.7    66  4.08  2.2   19.5     1     1     4     1     2
#>  7  30.4     4  75.7    52  4.93  1.62  18.5     1     1     4     2     2
#>  8  33.9     4  71.1    65  4.22  1.84  19.9     1     1     4     1     2
#>  9  21.5     4 120.     97  3.7   2.46  20.0     1     0     3     1     2
#> 10  15.5     8 318     150  2.76  3.52  16.9     0     0     3     2     2
#> 11  15.2     8 304     150  3.15  3.44  17.3     0     0     3     2     2
#> 12  13.3     8 350     245  3.73  3.84  15.4     0     0     3     4     2
#> 
#> [[3]]
#> # A tibble: 8 × 12
#>     mpg   cyl  disp    hp  drat    wt  qsec    vs    am  gear  carb chunk
#>   <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1  19.2     8 400     175  3.08  3.84  17.0     0     0     3     2     3
#> 2  27.3     4  79      66  4.08  1.94  18.9     1     1     4     1     3
#> 3  26       4 120.     91  4.43  2.14  16.7     0     1     5     2     3
#> 4  30.4     4  95.1   113  3.77  1.51  16.9     1     1     5     2     3
#> 5  15.8     8 351     264  4.22  3.17  14.5     0     1     5     4     3
#> 6  19.7     6 145     175  3.62  2.77  15.5     0     1     5     6     3
#> 7  15       8 301     335  3.54  3.57  14.6     0     1     5     8     3
#> 8  21.4     4 121     109  4.11  2.78  18.6     1     1     4     2     3
```

<sup>Created on 2023-10-13 by the [reprex package](https://reprex.tidyverse.org) (v2.0.1)</sup>

An alternate take on the problem is to find the indices of each chunk outside of the context of dplyr.
This returns a list with start and end which contains the start and end indices of each chunk.

#' Get chunk indices
#' 
#' For a given number of items and a chunk size, determine the start and end
#' positions of each chunk.
#' 
#' @param n the number of rows
#' @param m the chunk size
chunk_indices <- function(n, m) {
  n_chunks <- ceiling(n/m) 
  chunk_starts <- seq(1, n, by = m) 
  chunk_ends <- seq_len(n_chunks) * m
  chunk_ends[n_chunks] <- n
  list(start = chunk_starts, end = chunk_ends)
}