mlr-org · pat-s · Oct 6, 2021 · Oct 3, 2021 · Oct 6, 2021 · Oct 6, 2021
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -54,7 +54,7 @@ Config/testthat/parallel: true
 Encoding: UTF-8
 NeedsCompilation: no
 Roxygen: list(markdown = TRUE, r6 = TRUE)
-RoxygenNote: 7.1.1
+RoxygenNote: 7.1.2
 Collate:
     'Filter.R'
     'mlr_filters.R'
@@ -78,6 +78,7 @@ Collate:
     'FilterRelief.R'
     'FilterSelectedFeatures.R'
     'FilterVariance.R'
+    'bibentries.R'
     'flt.R'
     'helper.R'
     'reexports.R'

diff --git a/NAMESPACE b/NAMESPACE
@@ -38,4 +38,5 @@ importFrom(stats,aov)
 importFrom(stats,kruskal.test)
 importFrom(stats,runif)
 importFrom(stats,var)
+importFrom(utils,bibentry)
 importFrom(utils,head)
diff --git a/R/FilterAUC.R b/R/FilterAUC.R
@@ -9,6 +9,11 @@
 #' (random classifier). The absolute value of the difference between the AUC and
 #' 0.5 is used as final filter value.
 #'
+#' @references
+#' For a benchmark of filter methods:
+#'
+#' `r format_bib("bommert_2020")`
+#'
 #' @family Filter
 #' @template seealso_filter
 #' @export

diff --git a/R/FilterAnova.R b/R/FilterAnova.R
@@ -9,6 +9,11 @@
 #' transformation is necessary to ensure numerical stability for very small
 #' \eqn{p}-values.
 #'
+#' @references
+#' For a benchmark of filter methods:
+#'
+#' `r format_bib("bommert_2020")`
+#'
 #' @family Filter
 #' @importFrom stats aov
 #' @template seealso_filter

diff --git a/R/FilterCMIM.R b/R/FilterCMIM.R
@@ -7,6 +7,13 @@
 #'
 #' This filter supports partial scoring (see [Filter]).
 #'
+#' @references
+#' `r format_bib("kursa_2021")`
+#'
+#' For a benchmark of filter methods:
+#'
+#' `r format_bib("bommert_2020")`
+#'
 #' @template details_praznik
 #' @family Filter
 #' @template seealso_filter

diff --git a/R/FilterCarScore.R b/R/FilterCarScore.R
@@ -2,7 +2,7 @@
 #'
 #' @name mlr_filters_carscore
 #'
-#' @description Calculates the Correlation-Adjusted (marginal) coRelation scores
+#' @description Calculates the Correlation-Adjusted (marginal) coRrelation scores
 #' (short CAR scores) implemented in [care::carscore()] in package
 #' \CRANpkg{care}. The CAR scores for a set of features are defined as the
 #' correlations between the target and the decorrelated features. The filter

diff --git a/R/FilterCorrelation.R b/R/FilterCorrelation.R
@@ -6,6 +6,11 @@
 #' Simple correlation filter calling [stats::cor()].
 #' The filter score is the absolute value of the correlation.
 #'
+#' @references
+#' For a benchmark of filter methods:
+#'
+#' `r format_bib("bommert_2020")`
+#'
 #' @family Filter
 #' @template seealso_filter
 #' @export

diff --git a/R/FilterDISR.R b/R/FilterDISR.R
@@ -7,6 +7,13 @@
 #'
 #' This filter supports partial scoring (see [Filter]).
 #'
+#' @references
+#' `r format_bib("kursa_2021")`
+#'
+#' For a benchmark of filter methods:
+#'
+#' `r format_bib("bommert_2020")`
+#'
 #' @template details_praznik
 #' @family Filter
 #' @template seealso_filter

diff --git a/R/FilterJMI.R b/R/FilterJMI.R
@@ -7,6 +7,14 @@
 #'
 #' This filter supports partial scoring (see [Filter]).
 #'
+#' @references
+#' `r format_bib("kursa_2021")`
+#'
+#' For a benchmark of filter methods:
+#'
+#' `r format_bib("bommert_2020")`
+#'
+#'
 #' @template details_praznik
 #' @family Filter
 #' @template seealso_filter

diff --git a/R/FilterJMIM.R b/R/FilterJMIM.R
@@ -7,6 +7,13 @@
 #'
 #' This filter supports partial scoring (see [Filter]).
 #'
+#' @references
+#' `r format_bib("kursa_2021")`
+#'
+#' For a benchmark of filter methods:
+#'
+#' `r format_bib("bommert_2020")`
+#'
 #' @template details_praznik
 #' @family Filter
 #' @template seealso_filter

diff --git a/R/FilterKruskalTest.R b/R/FilterKruskalTest.R
@@ -2,13 +2,17 @@
 #'
 #' @name mlr_filters_kruskal_test
 #'
-#' @description Kruskal-Wallis rank sum test filter calling
-#'   [stats::kruskal.test()].
+#' @description Kruskal-Wallis rank sum test filter calling [stats::kruskal.test()].
 #'
 #' The filter value is `-log10(p)` where `p` is the \eqn{p}-value. This
 #' transformation is necessary to ensure numerical stability for very small
 #' \eqn{p}-values.
 #'
+#' @references
+#' For a benchmark of filter methods:
+#'
+#' `r format_bib("bommert_2020")`
+#'
 #' @family Filter
 #' @importFrom stats kruskal.test
 #' @template seealso_filter

diff --git a/R/FilterMIM.R b/R/FilterMIM.R
@@ -7,6 +7,13 @@
 #'
 #' This filter supports partial scoring (see [Filter]).
 #'
+#' @references
+#' `r format_bib("kursa_2021")`
+#'
+#' For a benchmark of filter methods:
+#'
+#' `r format_bib("bommert_2020")`
+#'
 #' @template details_praznik
 #' @family Filter
 #' @template seealso_filter

diff --git a/R/FilterMRMR.R b/R/FilterMRMR.R
@@ -7,6 +7,13 @@
 #'
 #' This filter supports partial scoring (see [Filter]).
 #'
+#' @references
+#' `r format_bib("kursa_2021")`
+#'
+#' For a benchmark of filter methods:
+#'
+#' `r format_bib("bommert_2020")`
+#'
 #' @template details_praznik
 #' @family Filter
 #' @template seealso_filter

diff --git a/R/FilterNJMIM.R b/R/FilterNJMIM.R
@@ -7,6 +7,13 @@
 #'
 #' This filter supports partial scoring (see [Filter]).
 #'
+#' @references
+#' `r format_bib("kursa_2021")`
+#'
+#' For a benchmark of filter methods:
+#'
+#' `r format_bib("bommert_2020")`
+#'
 #' @template details_praznik
 #' @family Filter
 #' @template seealso_filter

diff --git a/R/FilterVariance.R b/R/FilterVariance.R
@@ -6,6 +6,11 @@
 #'
 #' Argument `na.rm` defaults to `TRUE` here.
 #'
+#' @references
+#' For a benchmark of filter methods:
+#'
+#' `r format_bib("bommert_2020")`
+#'
 #' @family Filter
 #' @importFrom stats var
 #' @template seealso_filter

diff --git a/R/bibentries.R b/R/bibentries.R
@@ -0,0 +1,26 @@
+#' @importFrom utils bibentry
+bibentries     = c(
+  bommert_2020 = bibentry("article",
+    doi        = "10.1016/j.csda.2019.106839",
+    year       = "2020",
+    month      = "3",
+    publisher  = "Elsevier {BV}",
+    volume     = "143",
+    pages      = "106839",
+    author     = "Andrea Bommert and Xudong Sun and Bernd Bischl and J\u00f6rg Rahnenf\u00fchrer and Michel Lang",
+    title      = "Benchmark for filter methods for feature selection in high-dimensional classification data",
+    journal    = "Computational Statistics & Data Analysis"
+  ),
+
+ kursa_2021    = bibentry("article",
+    doi        = "10.1016/j.softx.2021.100819",
+    year       = "2021",
+    month      = "12",
+    publisher  = "Elsevier {BV}",
+    volume     = "16",
+    pages      = "100819",
+    author     = "Miron B. Kursa",
+    title      = "Praznik: High performance information-based feature selection",
+    journal    = "{SoftwareX}"
+  )
+)
diff --git a/man/mlr3filters-package.Rd b/man/mlr3filters-package.Rd
diff --git a/man/mlr_filters_anova.Rd b/man/mlr_filters_anova.Rd
diff --git a/man/mlr_filters_auc.Rd b/man/mlr_filters_auc.Rd
diff --git a/man/mlr_filters_carscore.Rd b/man/mlr_filters_carscore.Rd
diff --git a/man/mlr_filters_cmim.Rd b/man/mlr_filters_cmim.Rd
diff --git a/man/mlr_filters_correlation.Rd b/man/mlr_filters_correlation.Rd
diff --git a/man/mlr_filters_disr.Rd b/man/mlr_filters_disr.Rd
diff --git a/man/mlr_filters_jmi.Rd b/man/mlr_filters_jmi.Rd
diff --git a/man/mlr_filters_jmim.Rd b/man/mlr_filters_jmim.Rd
diff --git a/man/mlr_filters_kruskal_test.Rd b/man/mlr_filters_kruskal_test.Rd