xgboost::tree::ColMaker Class Reference

column-wise update to construct a tree More...

Inheritance diagram for xgboost::tree::ColMaker:

Data Structures
class	Builder
struct	NodeEntry
struct	ThreadEntry
	per thread x per node entry to store tmp data More...

Public Member Functions
	ColMaker (Context const *ctx)
void	Configure (const Args &args) override
	Initialize the updater with given arguments.
void	LoadConfig (Json const &in) override
	Load configuration from JSON object.
void	SaveConfig (Json *p_out) const override
	Save configuration to JSON object.
char const *	Name () const override
void	LazyGetColumnDensity (DMatrix *dmat)
void	Update (TrainParam const *param, HostDeviceVector< GradientPair > *gpair, DMatrix *dmat, common::Span< HostDeviceVector< bst_node_t > >, const std::vector< RegTree * > &trees) override
	perform update to the tree models
Public Member Functions inherited from xgboost::TreeUpdater
	TreeUpdater (const Context *ctx)
	~TreeUpdater () override=default
	virtual destructor
virtual bool	CanModifyTree () const
	Whether this updater can be used for updating existing trees.
virtual bool	HasNodePosition () const
	Wether the out_position in Update is valid. This determines whether adaptive tree can be used.
virtual bool	UpdatePredictionCache (const DMatrix *, linalg::MatrixView< float >)
	determines whether updater has enough knowledge about a given dataset to quickly update prediction cache its training data and performs the update if possible.

Protected Attributes
ColMakerTrainParam	colmaker_param_
std::vector< float >	column_densities_
FeatureInteractionConstraintHost	interaction_constraints_
Protected Attributes inherited from xgboost::TreeUpdater
Context const *	ctx_ = nullptr

Additional Inherited Members
Static Public Member Functions inherited from xgboost::TreeUpdater
static TreeUpdater *	Create (const std::string &name, Context const *ctx, ObjInfo const *task)
	Create a tree updater given name.

Detailed Description

column-wise update to construct a tree

Member Function Documentation

Configure()

void xgboost::tree::ColMaker::Configure ( const Args &  args )

inlineoverridevirtual

Initialize the updater with given arguments.

Parameters

args	arguments to the objective function.

Implements xgboost::TreeUpdater.

LoadConfig()

void xgboost::tree::ColMaker::LoadConfig ( Json const &  in )

inlineoverridevirtual

Load configuration from JSON object.

Parameters

in	JSON object containing the configuration

Implements xgboost::Configurable.

Name()

char const * xgboost::tree::ColMaker::Name ( ) const

inlineoverridevirtual

Implements xgboost::TreeUpdater.

SaveConfig()

void xgboost::tree::ColMaker::SaveConfig ( Json *  out ) const

inlineoverridevirtual

Save configuration to JSON object.

Parameters

out	pointer to output JSON object

Implements xgboost::Configurable.

Update()

void xgboost::tree::ColMaker::Update ( TrainParam const *  param, HostDeviceVector< GradientPair > *  gpair, DMatrix *  data, common::Span< HostDeviceVector< bst_node_t > >  out_position, const std::vector< RegTree * > &  out_trees  )

inlineoverridevirtual

perform update to the tree models

Parameters

param	Hyper-parameter for constructing trees.
gpair	the gradient pair statistics of the data
data	The data matrix passed to the updater.
out_position	The leaf index for each row. The index is negated if that row is removed during sampling. So the 3th node is ~3.
out_trees	references the trees to be updated, updater will change the content of trees note: all the trees in the vector are updated, with the same statistics, but maybe different random seeds, usually one tree is passed in at a time, there can be multiple trees when we train random forest style model

Implements xgboost::TreeUpdater.

---

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

• External/xgboost/src/tree/updater_colmaker.cc