most_important: Most Important Variables.

In flashlight: Shed Light on Black Box Machine Learning Models

Most Important Variables.

Description

Returns the most important variable names sorted descendingly.

Usage

most_important(x, top_m = Inf)

## Default S3 method:
most_important(x, top_m = Inf)

## S3 method for class 'light_importance'
most_important(x, top_m = Inf)

Arguments

x	An object of class "light_importance".
top_m	Maximum number of important variables to be returned. Defaults to Inf, i.e., return all variables in descending order of importance.

Value

A character vector of variable names sorted in descending order by importance.

Methods (by class)

• most_important(default): Default method not implemented yet.

• most_important(light_importance): Extracts most important variables from an object of class "light_importance".

See Also

light_importance()

Examples

fit <- lm(Sepal.Length ~ ., data = iris)
fl <- flashlight(model = fit, label = "ols", data = iris, y = "Sepal.Length")
(imp <- light_importance(fl, seed = 4))
most_important(imp)
most_important(imp, 2)

flashlight documentation built on May 31, 2023, 6:19 p.m.