daltoolbox (version 1.3.727)

feature_selection_relief: Feature selection by RELIEF

Description

Rank and select features using a simplified RELIEF algorithm.

Usage

feature_selection_relief(
  attribute,
  features = NULL,
  top = NULL,
  cutoff = NULL,
  m = 50,
  seed = 1
)

Value

returns an object of class feature_selection_relief

Arguments

attribute

target attribute name

features

optional vector of feature names (default: all columns except attribute)

top

optional number of top features to keep

cutoff

optional minimum RELIEF weight to keep a feature

m

number of sampled instances for RELIEF updates

seed

random seed for sampling

Details

For each sampled instance, the algorithm compares nearest hit/miss neighbors and updates feature weights.

Examples

data(iris)
fg <- feature_generation(
 IsVersicolor = ifelse(Species == "versicolor", "versicolor", "not_versicolor")
)
iris_bin <- transform(fg, iris)
iris_bin$IsVersicolor <- factor(iris_bin$IsVersicolor)
fs <- feature_selection_relief("IsVersicolor", top = 2, m = 50)
fs <- fit(fs, iris_bin)
fs$selected
transform(fs, iris_bin) |> names()