getImpXgboost: Xgboost importance

In Boruta: Wrapper Algorithm for All Relevant Feature Selection

Xgboost importance

Description

This function is intended to be given to a getImp argument of Boruta function to be called by the Boruta algorithm as an importance source. This functionality is inspired by the Python package BoostARoota by Chase DeHan. In practice, due to the eager way XgBoost works, this adapter changes Boruta into minimal optimal method, hence I strongly recommend against using this.

Usage

getImpXgboost(x, y, nrounds = 5, verbose = 0, ...)

Arguments

x	data frame of predictors including shadows.
y	response vector.
nrounds	Number of rounds; passed to the underlying xgboost call.
verbose	Verbosity level of xgboost; either 0 (silent) or 1 (progress reports). Passed to the underlying xgboost call.
...	other parameters passed to the underlying xgboost call. Similarly as nrounds and verbose, they are relayed from ... of Boruta. For convenience, this function sets nrounds to 5 and verbose to 0, but this can be overridden.

Note

Only dense matrix interface is supported; all predictions given to Boruta call have to be numeric (not integer). Categorical features should be split into indicator attributes.

References

https://github.com/chasedehan/BoostARoota

Boruta documentation built on Nov. 12, 2022, 9:06 a.m.