# Prevent dropping from non-occuring levels using dplyr

``library(tidyverse)  # data wrangling``

# 2 Problem

Consider the following situation:

``````mtcars |>
group_by(high_hp = hp > 1000) |>
count(high_hp)
#> # A tibble: 1 × 2
#> # Groups:   high_hp [1]
#>   high_hp     n
#>   <lgl>   <int>
#> 1 FALSE      32``````

The summary table does not show the level `TRUE`, as it is not occuring in the data. This can be problematic: If the data is unknown before summarizing and you would expect that both/all levels (TRUE, FALSE) occur. Just imagine that a subsequent function will count the level `TRUE` and the level `FALSE`. If one level is missing, your system may brake down.

# 3 Solution

Using dplyr and `count` or `summarize`, one solution is to turn the grouping variable in a factor, and then using the parameter `.drop = FALSE` in `count` or `summarise`.

Here’s an example for `count`:

``````mtcars |>
group_by(high_hp = hp > 1000) |>
mutate(high_hp = factor(high_hp, levels = c(FALSE, TRUE))) |>
count(high_hp, .drop = FALSE)
#> # A tibble: 2 × 2
#> # Groups:   high_hp [2]
#>   high_hp     n
#>   <fct>   <int>
#> 1 FALSE      32
#> 2 TRUE        0``````

And here a similar one for `summarise`:

``````mtcars %>%
group_by(hp_over_1000 = factor(hp > 1000, levels = c(FALSE, TRUE)), .drop = FALSE) %>%
summarise(mean_hp = mean(hp))
#> # A tibble: 2 × 2
#>   hp_over_1000 mean_hp
#>   <fct>          <dbl>
#> 1 FALSE           147.
#> 2 TRUE            NaN``````

If we would like to make sure that the resulting variable is not `NaN`, then we could use `complete`:

``````mtcars %>%
group_by(hp_over_1000 = factor(hp > 1000, levels = c(FALSE, TRUE)), .drop = FALSE) %>%
summarise(mean_hp = mean(hp)) %>%
complete(hp_over_1000, fill = list(mean_hp = NA))
#> # A tibble: 2 × 2
#>   hp_over_1000 mean_hp
#>   <fct>          <dbl>
#> 1 FALSE           147.
#> 2 TRUE             NA``````

# 4 Reproducibility

``````#> ─ Session info ───────────────────────────────────────────────────────────────────────────────────────────────────────
#>  setting  value
#>  version  R version 4.2.1 (2022-06-23)
#>  os       macOS Big Sur ... 10.16
#>  system   x86_64, darwin17.0
#>  ui       X11
#>  language (EN)
#>  collate  en_US.UTF-8
#>  ctype    en_US.UTF-8
#>  tz       Europe/Berlin
#>  date     2024-01-30
#>  pandoc   3.1.1 @ /Applications/RStudio.app/Contents/Resources/app/quarto/bin/tools/ (via rmarkdown)
#>
#> ─ Packages ───────────────────────────────────────────────────────────────────────────────────────────────────────────
#>  package     * version date (UTC) lib source
#>  blogdown      1.18    2023-06-19 [1] CRAN (R 4.2.0)
#>  bookdown      0.36    2023-10-16 [1] CRAN (R 4.2.0)
#>  bslib         0.5.1   2023-08-11 [1] CRAN (R 4.2.0)
#>  cachem        1.0.8   2023-05-01 [1] CRAN (R 4.2.0)
#>  callr         3.7.3   2022-11-02 [1] CRAN (R 4.2.0)
#>  cli           3.6.1   2023-03-23 [1] CRAN (R 4.2.0)
#>  codetools     0.2-19  2023-02-01 [1] CRAN (R 4.2.0)
#>  colorout    * 1.3-0   2023-11-08 [1] Github (jalvesaq/colorout@8384882)
#>  colorspace    2.1-0   2023-01-23 [1] CRAN (R 4.2.0)
#>  crayon        1.5.2   2022-09-29 [1] CRAN (R 4.2.1)
#>  devtools      2.4.5   2022-10-11 [1] CRAN (R 4.2.1)
#>  digest        0.6.33  2023-07-07 [1] CRAN (R 4.2.0)
#>  dplyr       * 1.1.3   2023-09-03 [1] CRAN (R 4.2.0)
#>  ellipsis      0.3.2   2021-04-29 [1] CRAN (R 4.2.0)
#>  evaluate      0.21    2023-05-05 [1] CRAN (R 4.2.0)
#>  fansi         1.0.5   2023-10-08 [1] CRAN (R 4.2.0)
#>  fastmap       1.1.1   2023-02-24 [1] CRAN (R 4.2.0)
#>  forcats     * 1.0.0   2023-01-29 [1] CRAN (R 4.2.0)
#>  fs            1.6.3   2023-07-20 [1] CRAN (R 4.2.0)
#>  generics      0.1.3   2022-07-05 [1] CRAN (R 4.2.0)
#>  ggplot2     * 3.4.4   2023-10-12 [1] CRAN (R 4.2.0)
#>  glue          1.6.2   2022-02-24 [1] CRAN (R 4.2.0)
#>  gtable        0.3.4   2023-08-21 [1] CRAN (R 4.2.0)
#>  hms           1.1.3   2023-03-21 [1] CRAN (R 4.2.0)
#>  htmltools     0.5.6.1 2023-10-06 [1] CRAN (R 4.2.0)
#>  htmlwidgets   1.6.2   2023-03-17 [1] CRAN (R 4.2.0)
#>  httpuv        1.6.11  2023-05-11 [1] CRAN (R 4.2.0)
#>  jquerylib     0.1.4   2021-04-26 [1] CRAN (R 4.2.0)
#>  jsonlite      1.8.7   2023-06-29 [1] CRAN (R 4.2.0)
#>  knitr         1.45    2023-10-30 [1] CRAN (R 4.2.1)
#>  later         1.3.1   2023-05-02 [1] CRAN (R 4.2.0)
#>  lifecycle     1.0.4   2023-11-07 [1] CRAN (R 4.2.1)
#>  lubridate   * 1.9.3   2023-09-27 [1] CRAN (R 4.2.0)
#>  magrittr      2.0.3   2022-03-30 [1] CRAN (R 4.2.0)
#>  memoise       2.0.1   2021-11-26 [1] CRAN (R 4.2.0)
#>  mime          0.12    2021-09-28 [1] CRAN (R 4.2.0)
#>  miniUI        0.1.1.1 2018-05-18 [1] CRAN (R 4.2.0)
#>  munsell       0.5.0   2018-06-12 [1] CRAN (R 4.2.0)
#>  pillar        1.9.0   2023-03-22 [1] CRAN (R 4.2.0)
#>  pkgbuild      1.4.0   2022-11-27 [1] CRAN (R 4.2.0)
#>  pkgconfig     2.0.3   2019-09-22 [1] CRAN (R 4.2.0)
#>  pkgload       1.3.2.1 2023-07-08 [1] CRAN (R 4.2.0)
#>  prettyunits   1.1.1   2020-01-24 [1] CRAN (R 4.2.0)
#>  processx      3.8.2   2023-06-30 [1] CRAN (R 4.2.0)
#>  profvis       0.3.8   2023-05-02 [1] CRAN (R 4.2.0)
#>  promises      1.2.1   2023-08-10 [1] CRAN (R 4.2.0)
#>  ps            1.7.5   2023-04-18 [1] CRAN (R 4.2.0)
#>  purrr       * 1.0.2   2023-08-10 [1] CRAN (R 4.2.0)
#>  R6            2.5.1   2021-08-19 [1] CRAN (R 4.2.0)
#>  Rcpp          1.0.11  2023-07-06 [1] CRAN (R 4.2.0)
#>  readr       * 2.1.4   2023-02-10 [1] CRAN (R 4.2.0)
#>  remotes       2.4.2.1 2023-07-18 [1] CRAN (R 4.2.0)
#>  rlang         1.1.1   2023-04-28 [1] CRAN (R 4.2.0)
#>  rmarkdown     2.25    2023-09-18 [1] CRAN (R 4.2.0)
#>  rstudioapi    0.15.0  2023-07-07 [1] CRAN (R 4.2.0)
#>  sass          0.4.7   2023-07-15 [1] CRAN (R 4.2.0)
#>  scales        1.2.1   2022-08-20 [1] CRAN (R 4.2.0)
#>  sessioninfo   1.2.2   2021-12-06 [1] CRAN (R 4.2.0)
#>  shiny         1.8.0   2023-11-17 [1] CRAN (R 4.2.1)
#>  stringi       1.7.12  2023-01-11 [1] CRAN (R 4.2.0)
#>  stringr     * 1.5.1   2023-11-14 [1] CRAN (R 4.2.1)
#>  tibble      * 3.2.1   2023-03-20 [1] CRAN (R 4.2.0)
#>  tidyr       * 1.3.0   2023-01-24 [1] CRAN (R 4.2.0)
#>  tidyselect    1.2.0   2022-10-10 [1] CRAN (R 4.2.0)
#>  tidyverse   * 2.0.0   2023-02-22 [1] CRAN (R 4.2.0)
#>  timechange    0.2.0   2023-01-11 [1] CRAN (R 4.2.0)
#>  tzdb          0.4.0   2023-05-12 [1] CRAN (R 4.2.0)
#>  urlchecker    1.0.1   2021-11-30 [1] CRAN (R 4.2.0)
#>  usethis       2.2.2   2023-07-06 [1] CRAN (R 4.2.0)
#>  utf8          1.2.3   2023-01-31 [1] CRAN (R 4.2.0)
#>  vctrs         0.6.4   2023-10-12 [1] CRAN (R 4.2.0)
#>  withr         2.5.2   2023-10-30 [1] CRAN (R 4.2.1)
#>  xfun          0.40    2023-08-09 [1] CRAN (R 4.2.0)
#>  xtable        1.8-4   2019-04-21 [1] CRAN (R 4.2.0)
#>  yaml          2.3.7   2023-01-23 [1] CRAN (R 4.2.0)
#>
#>  [1] /Users/sebastiansaueruser/Rlibs
#>  [2] /Library/Frameworks/R.framework/Versions/4.2/Resources/library
#>
#> ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────``````