Feature Selection via Exhaustive Search
FSelectorExhaustiveSearch class that implements an Exhaustive Search.
In order to support general termination criteria and parallelization, feature sets are evaluated in batches. The size of the feature sets is increased by 1 in each batch.
This FSelector can be instantiated via the dictionary
mlr_fselectors or with the associated sugar function fs():
mlr_fselectors$get("exhaustive_search")
fs("exhaustive_search")max_featuresinteger(1)
Maximum number of features. By default, number of features in mlr3::Task.
mlr3fselect::FSelector -> FSelectorExhaustiveSearch
new()
Creates a new instance of this R6 class.
FSelectorExhaustiveSearch$new()
clone()
The objects of this class are cloneable with this method.
FSelectorExhaustiveSearch$clone(deep = FALSE)
deepWhether to make a deep clone.
library(mlr3)
terminator = trm("evals", n_evals = 5)
instance = FSelectInstanceSingleCrit$new(
task = tsk("iris"),
learner = lrn("classif.rpart"),
resampling = rsmp("holdout"),
measure = msr("classif.ce"),
terminator = terminator
)
fselector = fs("exhaustive_search")
# Modifies the instance by reference
fselector$optimize(instance)
# Returns best scoring evaluation
instance$result
# Allows access of data.table of full path of all evaluations
as.data.table(instance$archive)Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.