gbt.importance: Importance of features in a model.

In agtboost: Adaptive and Automatic Gradient Boosting Computations

Description

gbt.importance creates a data.frame of feature importance in a model

Usage

gbt.importance(feature_names, object)

Arguments

feature_names	character vector of feature names
object	object or pointer to object of class ENSEMBLE

Details

Sums up "expected reduction" in generalization loss (scaled using learning_rate) at each node for each tree in the model, and attributes it to the feature the node is split on. Returns result in terms of percents.

Value

data.frame with percentwise reduction in loss of total attributed to each feature.

Examples

## Load data
data(caravan.train, package = "agtboost")
train <- caravan.train
mod <- gbt.train(train$y, train$x, loss_function = "logloss", verbose=10)
feature_names <- colnames(train$x)
imp <- gbt.importance(feature_names, mod)
imp

agtboost documentation built on Nov. 24, 2021, 1:16 a.m.