mlr3filters (version 0.3.0)

mlr_filters_cmim: Minimal Conditional Mutual Information Filter

Description

Minimal conditional mutual information maximisation filter calling praznik::CMIM() from package praznik.

This filter supports partial scoring (see Filter).

Super class

mlr3filters::Filter -> FilterCMIM

Methods

Public methods

• FilterCMIM$new()

• FilterCMIM$clone()

• mlr3filters::Filter$calculate()

• mlr3filters::Filter$format()

• mlr3filters::Filter$help()

• mlr3filters::Filter$print()

Method new()

Create a FilterCMIM object.

Usage

FilterCMIM$new(
  id = "cmim",
  task_type = c("classif", "regr"),
  param_set = ParamSet$new(list(ParamInt$new("threads", lower = 0L, default = 0L))),
  feature_types = c("integer", "numeric", "factor", "ordered"),
  packages = "praznik"
)

Arguments

id

(character(1)) Identifier for the filter.

task_type

(character()) Types of the task the filter can operator on. E.g., "classif" or "regr".

param_set

(paradox::ParamSet) Set of hyperparameters.

feature_types

(character()) Feature types the filter operates on. Must be a subset of mlr_reflections$task_feature_types.

packages

(character()) Set of required packages. Note that these packages will be loaded via requireNamespace(), and are not attached.

Method clone()

The objects of this class are cloneable with this method.

Usage

FilterCMIM$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

See Also

Dictionary of Filters: mlr_filters

Other Filter: Filter, mlr_filters_anova, mlr_filters_auc, mlr_filters_carscore, mlr_filters_correlation, mlr_filters_disr, mlr_filters_find_correlation, mlr_filters_importance, mlr_filters_information_gain, mlr_filters_jmim, mlr_filters_jmi, mlr_filters_kruskal_test, mlr_filters_mim, mlr_filters_mrmr, mlr_filters_njmim, mlr_filters_performance, mlr_filters_permutation, mlr_filters_variance, mlr_filters

Examples

# NOT RUN {
task = mlr3::tsk("iris")
filter = flt("cmim")
filter$calculate(task, nfeat = 2)
as.data.table(filter)
# }