/
FilterCorrelation.R
81 lines (76 loc) · 2.43 KB
/
FilterCorrelation.R
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
#' @title Correlation Filter
#'
#' @name mlr_filters_correlation
#'
#' @description
#' Simple correlation filter calling [stats::cor()].
#' The filter score is the absolute value of the correlation.
#'
#' @family Filter
#' @template seealso_filter
#' @export
#' @examples
#' ## Pearson (default)
#' task = mlr3::tsk("mtcars")
#' filter = flt("correlation")
#' filter$calculate(task)
#' as.data.table(filter)
#'
#' ## Spearman
#' filter = FilterCorrelation$new()
#' filter$param_set$values = list("method" = "spearman")
#' filter$calculate(task)
#' as.data.table(filter)
FilterCorrelation = R6Class("FilterCorrelation", inherit = Filter,
public = list(
#' @description Create a FilterCorrelation object.
#' @param id (`character(1)`)\cr
#' Identifier for the filter.
#' @param task_type (`character()`)\cr
#' Types of the task the filter can operator on. E.g., `"classif"` or
#' `"regr"`.
#' @param param_set ([paradox::ParamSet])\cr
#' Set of hyperparameters.
#' @param feature_types (`character()`)\cr
#' Feature types the filter operates on.
#' Must be a subset of
#' [`mlr_reflections$task_feature_types`][mlr3::mlr_reflections].
#' @param packages (`character()`)\cr
#' Set of required packages.
#' Note that these packages will be loaded via [requireNamespace()], and
#' are not attached.
initialize = function(id = "correlation",
task_type = "regr",
param_set = ParamSet$new(list(
ParamFct$new("use", default = "everything",
levels = c("everything", "all.obs", "complete.obs", "na.or.complete",
"pairwise.complete.obs")),
ParamFct$new("method", default = "pearson",
levels = c("pearson", "kendall", "spearman"))
)),
packages = "stats",
feature_types = c("integer", "numeric")) {
super$initialize(
id = id,
task_type = task_type,
param_set = param_set,
feature_types = feature_types,
packages = packages,
man = "mlr3filters::mlr_filters_correlation"
)
}
),
private = list(
.calculate = function(task, nfeat) {
fn = task$feature_names
pv = self$param_set$values
score = invoke(stats::cor,
x = as.matrix(task$data(cols = fn)),
y = as.matrix(task$truth()),
.args = pv)[, 1L]
set_names(abs(score), fn)
}
)
)
#' @include mlr_filters.R
mlr_filters$add("correlation", FilterCorrelation)