xgboost::linear::FeatureSelector Class Reference

Abstract class for stateful feature selection or ordering in coordinate descent algorithms. More...

#include <coordinate_common.h>

Inheritance diagram for xgboost::linear::FeatureSelector:

Public Member Functions
virtual	~FeatureSelector ()=default
	virtual destructor
virtual void	Setup (Context const *, const gbm::GBLinearModel &, const std::vector< GradientPair > &, DMatrix *, float, float, int)
	Setting up the selector state prior to looping through features.
virtual int	NextFeature (Context const *ctx, int iteration, const gbm::GBLinearModel &model, int group_idx, const std::vector< GradientPair > &gpair, DMatrix *p_fmat, float alpha, float lambda)=0
	Select next coordinate to update.

Static Public Member Functions
static FeatureSelector *	Create (int choice)
	factory method

Detailed Description

Abstract class for stateful feature selection or ordering in coordinate descent algorithms.

Member Function Documentation

NextFeature()

virtual int xgboost::linear::FeatureSelector::NextFeature ( Context const *  ctx, int  iteration, const gbm::GBLinearModel &  model, int  group_idx, const std::vector< GradientPair > &  gpair, DMatrix *  p_fmat, float  alpha, float  lambda  )

pure virtual

Select next coordinate to update.

Parameters

ctx	Booster context
iteration	The iteration in a loop through features
model	The model.
group_idx	Zero-based index of the group.
gpair	The gpair.
p_fmat	The feature matrix.
alpha	Regularisation alpha.
lambda	Regularisation lambda.

Returns

The index of the selected feature. -1 indicates none selected.

Implemented in xgboost::linear::CyclicFeatureSelector, xgboost::linear::ShuffleFeatureSelector, xgboost::linear::ThriftyFeatureSelector, xgboost::linear::RandomFeatureSelector, and xgboost::linear::GreedyFeatureSelector.

Setup()

virtual void xgboost::linear::FeatureSelector::Setup ( Context const *  , const gbm::GBLinearModel &  , const std::vector< GradientPair > &  , DMatrix *  , float  , float  , int    )

inlinevirtual

Setting up the selector state prior to looping through features.

Parameters

ctx	The booster context.
model	The model.
gpair	The gpair.
p_fmat	The feature matrix.
alpha	Regularisation alpha.
lambda	Regularisation lambda.
param	A parameter with algorithm-dependent use.

Reimplemented in xgboost::linear::GreedyFeatureSelector, xgboost::linear::ShuffleFeatureSelector, and xgboost::linear::ThriftyFeatureSelector.

---

The documentation for this class was generated from the following file:

• External/xgboost/src/linear/coordinate_common.h