- Consistent naming for dummy feature encoding of variables with different levels count

[pat-s]

fix #2814

@mllg I don't see an immediate downside of this change and all tests seem to pass as well. OK to merge?

library(mlr)
#> Loading required package: ParamHelpers
#> Warning message: 'mlr' is in 'maintenance-only' mode since July 2019.
#> Future development will only happen in 'mlr3'
#> (<https://mlr3.mlr-org.com>). Due to the focus on 'mlr3' there might be
#> uncaught bugs meanwhile in {mlr} - please consider switching.
d <- structure(list(
  a = structure(c(2L, 1L, 1L, 1L, 3L, 2L), .Label = c("1", "2", "3"), class = "factor"),
  b = structure(c(2L, 1L, 1L, 1L, 1L, 2L), .Label = c("1", "2"), class = "factor"),
  target = structure(c(1L, 1L, 1L, 2L, 2L, 2L), .Label = c("zero", "one"), class = "factor")
),
row.names = c(NA, -6L),
class = "data.frame"
)

mlr::createDummyFeatures(d, "target", method = "reference")
#>   target a.2 a.3 b.2
#> 1   zero   1   0   1
#> 2   zero   0   0   0
#> 3   zero   0   0   0
#> 4    one   0   0   0
#> 5    one   0   1   0
#> 6    one   1   0   1

^{Created on 2022-08-14 by the reprex package (v2.0.1)}

Session info

sessioninfo::session_info()
#> ─ Session info ───────────────────────────────────────────────────────────────
#>  setting  value
#>  version  R version 4.2.1 (2022-06-23)
#>  os       macOS Monterey 12.5
#>  system   aarch64, darwin20
#>  ui       X11
#>  language (EN)
#>  collate  en_US.UTF-8
#>  ctype    en_US.UTF-8
#>  tz       Europe/Zurich
#>  date     2022-08-14
#>  pandoc   2.19 @ /opt/homebrew/bin/ (via rmarkdown)
#> 
#> ─ Packages ───────────────────────────────────────────────────────────────────
#>  package      * version     date (UTC) lib source
#>  assertthat     0.2.1       2019-03-21 [1] CRAN (R 4.2.0)
#>  backports      1.4.1       2021-12-13 [1] CRAN (R 4.2.0)
#>  BBmisc         1.12        2022-03-10 [1] CRAN (R 4.2.0)
#>  checkmate      2.1.0       2022-04-21 [1] CRAN (R 4.2.0)
#>  cli            3.3.0       2022-04-25 [1] CRAN (R 4.2.0)
#>  colorspace     2.0-3       2022-02-21 [1] CRAN (R 4.2.0)
#>  data.table     1.14.2      2021-09-27 [1] CRAN (R 4.2.0)
#>  DBI            1.1.3       2022-06-18 [1] CRAN (R 4.2.0)
#>  digest         0.6.29      2021-12-01 [1] CRAN (R 4.2.0)
#>  dplyr          1.0.9       2022-04-28 [1] CRAN (R 4.2.0)
#>  evaluate       0.16        2022-08-09 [1] CRAN (R 4.2.1)
#>  fansi          1.0.3       2022-03-24 [1] CRAN (R 4.2.0)
#>  fastmap        1.1.0       2021-01-25 [1] CRAN (R 4.2.0)
#>  fastmatch      1.1-3       2021-07-23 [1] CRAN (R 4.2.0)
#>  fs             1.5.2       2021-12-08 [1] CRAN (R 4.2.0)
#>  generics       0.1.3       2022-07-05 [1] CRAN (R 4.2.0)
#>  ggplot2        3.3.6       2022-05-03 [1] CRAN (R 4.2.0)
#>  glue           1.6.2       2022-02-24 [1] CRAN (R 4.2.0)
#>  gtable         0.3.0       2019-03-25 [1] CRAN (R 4.2.0)
#>  highr          0.9         2021-04-16 [1] CRAN (R 4.2.0)
#>  htmltools      0.5.3       2022-07-18 [1] CRAN (R 4.2.0)
#>  knitr          1.39        2022-04-26 [1] CRAN (R 4.2.0)
#>  lattice        0.20-45     2021-09-22 [1] CRAN (R 4.2.1)
#>  lifecycle      1.0.1       2021-09-24 [1] CRAN (R 4.2.0)
#>  magrittr       2.0.3       2022-03-30 [1] CRAN (R 4.2.0)
#>  Matrix         1.4-1       2022-03-23 [1] CRAN (R 4.2.0)
#>  mlr          * 2.19.0.9001 2022-08-14 [1] local
#>  munsell        0.5.0       2018-06-12 [1] CRAN (R 4.2.0)
#>  parallelMap    1.5.1       2021-06-28 [1] CRAN (R 4.2.0)
#>  ParamHelpers * 1.14.1      2022-07-04 [1] CRAN (R 4.2.0)
#>  pillar         1.8.0       2022-07-18 [1] CRAN (R 4.2.0)
#>  pkgconfig      2.0.3       2019-09-22 [1] CRAN (R 4.2.0)
#>  purrr          0.3.4       2020-04-17 [1] CRAN (R 4.2.0)
#>  R.cache        0.16.0      2022-07-21 [1] CRAN (R 4.2.0)
#>  R.methodsS3    1.8.2       2022-06-13 [1] CRAN (R 4.2.0)
#>  R.oo           1.25.0      2022-06-12 [1] CRAN (R 4.2.0)
#>  R.utils        2.12.0      2022-06-28 [1] CRAN (R 4.2.0)
#>  R6             2.5.1       2021-08-19 [1] CRAN (R 4.2.0)
#>  reprex         2.0.1       2021-08-05 [1] CRAN (R 4.2.0)
#>  rlang          1.0.4       2022-07-12 [1] CRAN (R 4.2.0)
#>  rmarkdown      2.14        2022-04-25 [1] CRAN (R 4.2.0)
#>  rstudioapi     0.13        2020-11-12 [1] CRAN (R 4.2.0)
#>  scales         1.2.0       2022-04-13 [1] CRAN (R 4.2.0)
#>  sessioninfo    1.2.2       2021-12-06 [1] CRAN (R 4.2.0)
#>  stringi        1.7.8       2022-07-11 [1] CRAN (R 4.2.0)
#>  stringr        1.4.0       2019-02-10 [1] CRAN (R 4.2.0)
#>  styler         1.7.0.9001  2022-08-08 [1] Github (r-lib/styler@a3b69e4)
#>  survival       3.3-1       2022-03-03 [1] CRAN (R 4.2.0)
#>  tibble         3.1.8       2022-07-22 [1] CRAN (R 4.2.0)
#>  tidyselect     1.1.2       2022-02-21 [1] CRAN (R 4.2.0)
#>  utf8           1.2.2       2021-07-24 [1] CRAN (R 4.2.0)
#>  vctrs          0.4.1       2022-04-13 [1] CRAN (R 4.2.0)
#>  withr          2.5.0       2022-03-03 [1] CRAN (R 4.2.0)
#>  xfun           0.32        2022-08-10 [1] CRAN (R 4.2.1)
#>  yaml           2.3.5       2022-02-21 [1] CRAN (R 4.2.0)
#> 
#>  [1] /Users/pjs/Library/R/arm64/4.2/library
#>  [2] /opt/R/4.2.1-arm64/Resources/site-library
#>  [3] /opt/R/4.2.1-arm64/Resources/library
#> 
#> ──────────────────────────────────────────────────────────────────────────────

[mllg]

LGTM