Detailed Description

This class implements randomized CART algorithm used in the tree growing process of candidate trees in Random Forests algorithm. The tree growing process is different from the original CART algorithm because of the input attributes which are considered for each node split. In randomized CART, a few (fixed number) attributes are randomly chosen from all available attributes while deciding the best split. This is unlike the original CART where all available attributes are considered while deciding the best split.

Definition at line 48 of file RandomCARTree.h.

Inheritance diagram for CRandomCARTree:

[legend]

Public Types
typedef CTreeMachineNode< CARTreeNodeData >	node_t

typedef CBinaryTreeMachineNode< CARTreeNodeData >	bnode_t

typedef rxcpp::subjects::subject< ObservedValue >	SGSubject

typedef rxcpp::observable< ObservedValue, rxcpp::dynamic_observable< ObservedValue > >	SGObservable

typedef rxcpp::subscriber< ObservedValue, rxcpp::observer< ObservedValue, void, void, void, void > >	SGSubscriber

Public Member Functions
	CRandomCARTree ()

virtual	~CRandomCARTree ()

virtual const char *	get_name () const

void	set_feature_subset_size (int32_t size)

int32_t	get_feature_subset_size () const

virtual void	set_labels (CLabels *lab)

virtual EProblemType	get_machine_problem_type () const

void	set_machine_problem_type (EProblemType mode)

virtual bool	is_label_valid (CLabels *lab) const

virtual CMulticlassLabels *	apply_multiclass (CFeatures *data=NULL)

virtual CRegressionLabels *	apply_regression (CFeatures *data=NULL)

void	prune_using_test_dataset (CDenseFeatures< float64_t > feats, CLabels gnd_truth, SGVector< float64_t > weights=SGVector< float64_t >())

void	set_weights (SGVector< float64_t > w)

SGVector< float64_t >	get_weights () const

void	clear_weights ()

void	set_feature_types (SGVector< bool > ft)

SGVector< bool >	get_feature_types () const

void	clear_feature_types ()

int32_t	get_num_folds () const

void	set_num_folds (int32_t folds)

int32_t	get_max_depth () const

void	set_max_depth (int32_t depth)

int32_t	get_min_node_size () const

void	set_min_node_size (int32_t nsize)

void	set_cv_pruning (bool cv_pruning)

float64_t	get_label_epsilon ()

void	set_label_epsilon (float64_t epsilon)

void	pre_sort_features (CFeatures *data, SGMatrix< float64_t > &sorted_feats, SGMatrix< index_t > &sorted_indices)

void	set_sorted_features (SGMatrix< float64_t > &sorted_feats, SGMatrix< index_t > &sorted_indices)

void	set_root (CTreeMachineNode< CARTreeNodeData > *root)

CTreeMachineNode< CARTreeNodeData > *	get_root ()

CTreeMachine *	clone_tree ()

int32_t	get_num_machines () const

virtual bool	train (CFeatures *data=NULL)

virtual CLabels *	apply (CFeatures *data=NULL)

virtual CBinaryLabels *	apply_binary (CFeatures *data=NULL)

virtual CStructuredLabels *	apply_structured (CFeatures *data=NULL)

virtual CLatentLabels *	apply_latent (CFeatures *data=NULL)

virtual CLabels *	get_labels ()

void	set_max_train_time (float64_t t)

float64_t	get_max_train_time ()

virtual EMachineType	get_classifier_type ()

void	set_solver_type (ESolverType st)

ESolverType	get_solver_type ()

virtual void	set_store_model_features (bool store_model)

virtual bool	train_locked (SGVector< index_t > indices)

virtual float64_t	apply_one (int32_t i)

virtual CLabels *	apply_locked (SGVector< index_t > indices)

virtual CBinaryLabels *	apply_locked_binary (SGVector< index_t > indices)

virtual CRegressionLabels *	apply_locked_regression (SGVector< index_t > indices)

virtual CMulticlassLabels *	apply_locked_multiclass (SGVector< index_t > indices)

virtual CStructuredLabels *	apply_locked_structured (SGVector< index_t > indices)

virtual CLatentLabels *	apply_locked_latent (SGVector< index_t > indices)

virtual void	data_lock (CLabels labs, CFeatures features)

virtual void	post_lock (CLabels labs, CFeatures features)

virtual void	data_unlock ()

virtual bool	supports_locking () const

bool	is_data_locked () const

SG_FORCED_INLINE bool	cancel_computation () const

SG_FORCED_INLINE void	pause_computation ()

SG_FORCED_INLINE void	resume_computation ()

int32_t	ref ()

int32_t	ref_count ()

int32_t	unref ()

virtual CSGObject *	shallow_copy () const

virtual CSGObject *	deep_copy () const

virtual bool	is_generic (EPrimitiveType *generic) const

template<class T >
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

void	unset_generic ()

virtual void	print_serializable (const char *prefix="")

virtual bool	save_serializable (CSerializableFile file, const char prefix="")

virtual bool	load_serializable (CSerializableFile file, const char prefix="")

void	set_global_io (SGIO *io)

SGIO *	get_global_io ()

void	set_global_parallel (Parallel *parallel)

Parallel *	get_global_parallel ()

void	set_global_version (Version *version)

Version *	get_global_version ()

SGStringList< char >	get_modelsel_names ()

void	print_modsel_params ()

char *	get_modsel_param_descr (const char *param_name)

index_t	get_modsel_param_index (const char *param_name)

void	build_gradient_parameter_dictionary (CMap< TParameter , CSGObject > *dict)

bool	has (const std::string &name) const

template<typename T >
bool	has (const Tag< T > &tag) const

template<typename T , typename U = void>
bool	has (const std::string &name) const

template<typename T >
void	set (const Tag< T > &_tag, const T &value)

template<typename T , typename U = void>
void	set (const std::string &name, const T &value)

template<typename T >
T	get (const Tag< T > &_tag) const

template<typename T , typename U = void>
T	get (const std::string &name) const

SGObservable *	get_parameters_observable ()

void	subscribe_to_parameters (ParameterObserverInterface *obs)

void	list_observable_parameters ()

virtual void	update_parameter_hash ()

virtual bool	parameter_hash_changed ()

virtual bool	equals (CSGObject *other, float64_t accuracy=0.0, bool tolerant=false)

virtual CSGObject *	clone ()

Public Attributes
SGIO *	io

Parallel *	parallel

Version *	version

Parameter *	m_parameters

Parameter *	m_model_selection_parameters

Parameter *	m_gradient_parameters

uint32_t	m_hash

Static Public Attributes
static const float64_t	MISSING =CMath::MAX_REAL_NUMBER

static const float64_t	MIN_SPLIT_GAIN =1e-7

static const float64_t	EQ_DELTA =1e-7

Protected Member Functions
virtual int32_t	compute_best_attribute (const SGMatrix< float64_t > &mat, const SGVector< float64_t > &weights, CLabels *labels, SGVector< float64_t > &left, SGVector< float64_t > &right, SGVector< bool > &is_left_final, int32_t &num_missing, int32_t &count_left, int32_t &count_right, int32_t subset_size=0, const SGVector< int32_t > &active_indices=SGVector< index_t >())

virtual bool	train_machine (CFeatures *data=NULL)

virtual CBinaryTreeMachineNode< CARTreeNodeData > *	CARTtrain (CFeatures data, SGVector< float64_t > weights, CLabels labels, int32_t level)

SGVector< float64_t >	get_unique_labels (SGVector< float64_t > labels_vec, int32_t &n_ulabels)

SGVector< bool >	surrogate_split (SGMatrix< float64_t > data, SGVector< float64_t > weights, SGVector< bool > nm_left, int32_t attr)

void	handle_missing_vecs_for_continuous_surrogate (SGMatrix< float64_t > m, CDynamicArray< int32_t > missing_vecs, CDynamicArray< float64_t > association_index, CDynamicArray< int32_t > *intersect_vecs, SGVector< bool > is_left, SGVector< float64_t > weights, float64_t p, int32_t attr)

void	handle_missing_vecs_for_nominal_surrogate (SGMatrix< float64_t > m, CDynamicArray< int32_t > missing_vecs, CDynamicArray< float64_t > association_index, CDynamicArray< int32_t > *intersect_vecs, SGVector< bool > is_left, SGVector< float64_t > weights, float64_t p, int32_t attr)

float64_t	gain (SGVector< float64_t > wleft, SGVector< float64_t > wright, SGVector< float64_t > wtotal, SGVector< float64_t > labels)

float64_t	gain (const SGVector< float64_t > &wleft, const SGVector< float64_t > &wright, const SGVector< float64_t > &wtotal)

float64_t	gini_impurity_index (const SGVector< float64_t > &weighted_lab_classes, float64_t &total_weight)

float64_t	least_squares_deviation (const SGVector< float64_t > &labels, const SGVector< float64_t > &weights, float64_t &total_weight)

CLabels *	apply_from_current_node (CDenseFeatures< float64_t > feats, bnode_t current)

void	prune_by_cross_validation (CDenseFeatures< float64_t > *data, int32_t folds)

float64_t	compute_error (CLabels labels, CLabels reference, SGVector< float64_t > weights)

CDynamicObjectArray *	prune_tree (CTreeMachine< CARTreeNodeData > *tree)

float64_t	find_weakest_alpha (bnode_t *node)

void	cut_weakest_link (bnode_t *node, float64_t alpha)

void	form_t1 (bnode_t *node)

virtual void	store_model_features ()

virtual bool	train_require_labels () const

rxcpp::subscription	connect_to_signal_handler ()

void	reset_computation_variables ()

virtual void	on_next ()

virtual void	on_pause ()

virtual void	on_complete ()

virtual void	load_serializable_pre () throw (ShogunException)

virtual void	load_serializable_post () throw (ShogunException)

virtual void	save_serializable_pre () throw (ShogunException)

virtual void	save_serializable_post () throw (ShogunException)

template<typename T >
void	register_param (Tag< T > &_tag, const T &value)

template<typename T >
void	register_param (const std::string &name, const T &value)

bool	clone_parameters (CSGObject *other)

void	observe (const ObservedValue value)

void	register_observable_param (const std::string &name, const SG_OBS_VALUE_TYPE type, const std::string &description)

Protected Attributes
float64_t	m_label_epsilon

SGVector< bool >	m_nominal

SGVector< float64_t >	m_weights

SGMatrix< float64_t >	m_sorted_features

SGMatrix< index_t >	m_sorted_indices

bool	m_pre_sort

bool	m_types_set

bool	m_weights_set

bool	m_apply_cv_pruning

int32_t	m_folds

EProblemType	m_mode

CDynamicArray< float64_t > *	m_alphas

int32_t	m_max_depth

int32_t	m_min_node_size

CTreeMachineNode< CARTreeNodeData > *	m_root

CDynamicObjectArray *	m_machines

float64_t	m_max_train_time

CLabels *	m_labels

ESolverType	m_solver_type

bool	m_store_model_features

bool	m_data_locked

std::atomic< bool >	m_cancel_computation

std::atomic< bool >	m_pause_computation_flag

std::condition_variable	m_pause_computation

std::mutex	m_mutex

Member Typedef Documentation

◆ bnode_t

typedef CBinaryTreeMachineNode<CARTreeNodeData > bnode_t

inherited

bnode_t type- Tree node with max 2 possible children

Definition at line 55 of file TreeMachine.h.

◆ node_t

typedef CTreeMachineNode<CARTreeNodeData > node_t

inherited

node_t type- Tree node with many possible children

Definition at line 52 of file TreeMachine.h.

◆ SGObservable

typedef rxcpp::observable<ObservedValue, rxcpp::dynamic_observable<ObservedValue> > SGObservable

inherited

Definition at line 130 of file SGObject.h.

◆ SGSubject

typedef rxcpp::subjects::subject<ObservedValue> SGSubject

inherited

Definition at line 127 of file SGObject.h.

◆ SGSubscriber

typedef rxcpp::subscriber< ObservedValue, rxcpp::observer<ObservedValue, void, void, void, void> > SGSubscriber

inherited

Definition at line 133 of file SGObject.h.

Constructor & Destructor Documentation

◆ CRandomCARTree()

CRandomCARTree ( )

constructor

Definition at line 36 of file RandomCARTree.cpp.

◆ ~CRandomCARTree()

~CRandomCARTree ( )

virtual

destructor

Definition at line 42 of file RandomCARTree.cpp.

Member Function Documentation

◆ apply()

CLabels * apply ( CFeatures * data = NULL )

virtualinherited

apply machine to data if data is not specified apply to the current features

Parameters

data	(test)data to be classified

Returns: classified labels

Definition at line 159 of file Machine.cpp.

◆ apply_binary()

CBinaryLabels * apply_binary ( CFeatures * data = NULL )

virtualinherited

apply machine to data in means of binary classification problem

Reimplemented in CKernelMachine, CNeuralNetwork, COnlineLinearMachine, CLinearMachine, CGaussianProcessClassification, CDomainAdaptationSVMLinear, CDomainAdaptationSVM, CPluginEstimate, and CBaggingMachine.

Definition at line 215 of file Machine.cpp.

◆ apply_from_current_node()

CLabels * apply_from_current_node	(	CDenseFeatures< float64_t > *	feats,
		bnode_t *	current
	)

protectedinherited

uses current subtree to classify/regress data

Parameters

feats	data to be classified/regressed
current	root of current subtree

Returns: classification/regression labels of input data

Definition at line 1104 of file CARTree.cpp.

◆ apply_latent()

CLatentLabels * apply_latent ( CFeatures * data = NULL )

virtualinherited

apply machine to data in means of latent problem

Reimplemented in CLinearLatentMachine.

Definition at line 239 of file Machine.cpp.

◆ apply_locked()

CLabels * apply_locked ( SGVector< index_t > indices )

virtualinherited

Applies a locked machine on a set of indices. Error if machine is not locked

Parameters

indices index vector (of locked features) that is predicted

Definition at line 194 of file Machine.cpp.

◆ apply_locked_binary()

CBinaryLabels * apply_locked_binary ( SGVector< index_t > indices )

virtualinherited

applies a locked machine on a set of indices for binary problems

Reimplemented in CKernelMachine.

Definition at line 245 of file Machine.cpp.

◆ apply_locked_latent()

CLatentLabels * apply_locked_latent ( SGVector< index_t > indices )

virtualinherited

applies a locked machine on a set of indices for latent problems

Definition at line 273 of file Machine.cpp.

◆ apply_locked_multiclass()

CMulticlassLabels * apply_locked_multiclass ( SGVector< index_t > indices )

virtualinherited

applies a locked machine on a set of indices for multiclass problems

Definition at line 259 of file Machine.cpp.

◆ apply_locked_regression()

CRegressionLabels * apply_locked_regression ( SGVector< index_t > indices )

virtualinherited

applies a locked machine on a set of indices for regression problems

Reimplemented in CKernelMachine.

Definition at line 252 of file Machine.cpp.

◆ apply_locked_structured()

CStructuredLabels * apply_locked_structured ( SGVector< index_t > indices )

virtualinherited

applies a locked machine on a set of indices for structured problems

Definition at line 266 of file Machine.cpp.

◆ apply_multiclass()

CMulticlassLabels * apply_multiclass ( CFeatures * data = NULL )

virtualinherited

classify data using Classification Tree

Parameters

data	data to be classified

Returns: MulticlassLabels corresponding to labels of various test vectors

Reimplemented from CMachine.

Definition at line 101 of file CARTree.cpp.

◆ apply_one()

virtual float64_t apply_one ( int32_t i )

virtualinherited

applies to one vector

Reimplemented in CKernelMachine, CRelaxedTree, COnlineLinearMachine, CLinearMachine, CKNN, CMulticlassMachine, CDistanceMachine, CScatterSVM, CGaussianNaiveBayes, and CPluginEstimate.

Definition at line 257 of file Machine.h.

◆ apply_regression()

CRegressionLabels * apply_regression ( CFeatures * data = NULL )

virtualinherited

Get regression labels using Regression Tree

Parameters

data	data whose regression output is needed

Returns: Regression output for various test vectors

Reimplemented from CMachine.

Definition at line 115 of file CARTree.cpp.

◆ apply_structured()

CStructuredLabels * apply_structured ( CFeatures * data = NULL )

virtualinherited

apply machine to data in means of SO classification problem

Reimplemented in CLinearStructuredOutputMachine.

Definition at line 233 of file Machine.cpp.

◆ build_gradient_parameter_dictionary()

void build_gradient_parameter_dictionary ( CMap< TParameter *, CSGObject *> * dict )

inherited

Builds a dictionary of all parameters in SGObject as well of those of SGObjects that are parameters of this object. Dictionary maps parameters to the objects that own them.

Parameters

dict	dictionary of parameters to be built.

Definition at line 635 of file SGObject.cpp.

◆ cancel_computation()

SG_FORCED_INLINE bool cancel_computation ( ) const

inherited

Returns: whether the algorithm needs to be stopped

Definition at line 319 of file Machine.h.

◆ CARTtrain()

CBinaryTreeMachineNode< CARTreeNodeData > * CARTtrain	(	CFeatures *	data,
		SGVector< float64_t >	weights,
		CLabels *	labels,
		int32_t	level
	)

protectedvirtualinherited

CARTtrain - recursive CART training method

Parameters

data	training data
weights	vector of weights of data points
labels	labels of data points
level	current tree depth

Returns: pointer to the root of the CART subtree

Definition at line 316 of file CARTree.cpp.

◆ clear_feature_types()

void clear_feature_types ( )

inherited

clear feature types of various features

Definition at line 201 of file CARTree.cpp.

◆ clear_weights()

void clear_weights ( )

inherited

clear weights of data points

Definition at line 184 of file CARTree.cpp.

◆ clone()

CSGObject * clone ( )

virtualinherited

Creates a clone of the current object. This is done via recursively traversing all parameters, which corresponds to a deep copy. Calling equals on the cloned object always returns true although none of the memory of both objects overlaps.

Returns: an identical copy of the given object, which is disjoint in memory. NULL if the clone fails. Note that the returned object is SG_REF'ed

Reimplemented in CDynamicArray< T >, CDynamicArray< float64_t >, CDynamicArray< float32_t >, CDynamicArray< int32_t >, CDynamicArray< char >, CDynamicArray< bool >, CDynamicObjectArray, CAlphabet, and CMKL.

Definition at line 734 of file SGObject.cpp.

◆ clone_parameters()

bool clone_parameters ( CSGObject * other )

protectedinherited

Definition at line 759 of file SGObject.cpp.

◆ clone_tree()

CTreeMachine* clone_tree ( )

inherited

clone tree

Returns: clone of entire tree

Definition at line 97 of file TreeMachine.h.

◆ compute_best_attribute()

int32_t compute_best_attribute	(	const SGMatrix< float64_t > &	mat,
		const SGVector< float64_t > &	weights,
		CLabels *	labels,
		SGVector< float64_t > &	left,
		SGVector< float64_t > &	right,
		SGVector< bool > &	is_left_final,
		int32_t &	num_missing,
		int32_t &	count_left,
		int32_t &	count_right,
		int32_t	subset_size = `0`,
		const SGVector< int32_t > &	active_indices = `SGVector<index_t>()`
	)

protectedvirtual

computes best attribute for CARTtrain

Parameters

mat	data matrix
weights	data weights
labels_vec	data labels
left	stores feature values for left transition
right	stores feature values for right transition
is_left_final	stores which feature vectors go to the left child
num_missing	number of missing attributes
count_left	stores number of feature values for left transition
count_right	stores number of feature values for right transition

Returns: index to the best attribute

Reimplemented from CCARTree.

Definition at line 52 of file RandomCARTree.cpp.

◆ compute_error()

float64_t compute_error	(	CLabels *	labels,
		CLabels *	reference,
		SGVector< float64_t >	weights
	)

protectedinherited

computes error in classification/regression for classification it eveluates weight_missclassified/total_weight for regression it evaluates weighted sum of squared error/total_weight

Parameters

labels	the labels whose error needs to be calculated
reference	actual labels against which test labels are compared
weights	weights associated with the labels

Returns: error evaluated

Definition at line 1328 of file CARTree.cpp.

◆ connect_to_signal_handler()

rxcpp::subscription connect_to_signal_handler ( )

protectedinherited

connect the machine instance to the signal handler

Definition at line 280 of file Machine.cpp.

◆ cut_weakest_link()

void cut_weakest_link	(	bnode_t *	node,
		float64_t	alpha
	)

protectedinherited

recursively cuts weakest link(s) in a tree

Parameters

node	the root of subtree whose weakest link it cuts
alpha	alpha value corresponding to weakest link

Definition at line 1437 of file CARTree.cpp.

◆ data_lock()

void data_lock	(	CLabels *	labs,
		CFeatures *	features
	)

virtualinherited

Locks the machine on given labels and data. After this call, only train_locked and apply_locked may be called

Only possible if supports_locking() returns true

Parameters

labs	labels used for locking
features	features used for locking

Reimplemented in CKernelMachine.

Definition at line 119 of file Machine.cpp.

◆ data_unlock()

void data_unlock ( )

virtualinherited

Unlocks a locked machine and restores previous state

Reimplemented in CKernelMachine.

Definition at line 150 of file Machine.cpp.

◆ deep_copy()

CSGObject * deep_copy ( ) const

virtualinherited

A deep copy. All the instance variables will also be copied.

Definition at line 232 of file SGObject.cpp.

◆ equals()

bool equals	(	CSGObject *	other,
		float64_t	accuracy = `0.0`,
		bool	tolerant = `false`
	)

virtualinherited

Recursively compares the current SGObject to another one. Compares all registered numerical parameters, recursion upon complex (SGObject) parameters. Does not compare pointers!

May be overwritten but please do with care! Should not be necessary in most cases.

Parameters

other	object to compare with
accuracy	accuracy to use for comparison (optional)
tolerant	allows linient check on float equality (within accuracy)

Returns: true if all parameters were equal, false if not

Definition at line 656 of file SGObject.cpp.

◆ find_weakest_alpha()

float64_t find_weakest_alpha ( bnode_t * node )

protectedinherited

recursively finds alpha corresponding to weakest link(s)

Parameters

node	the root of subtree whose weakest link it finds

Returns: alpha value corresponding to the weakest link in subtree

Definition at line 1416 of file CARTree.cpp.

◆ form_t1()

void form_t1 ( bnode_t * node )

protectedinherited

recursively forms base case $ft_1$f tree from $ft_max$f during pruning

Parameters

node	the root of current subtree

Definition at line 1467 of file CARTree.cpp.

◆ gain() [1/2]

float64_t gain	(	SGVector< float64_t >	wleft,
		SGVector< float64_t >	wright,
		SGVector< float64_t >	wtotal,
		SGVector< float64_t >	labels
	)

protectedinherited

returns gain in regression case

Parameters

wleft	left child weight distribution
wright	right child weights distribution
wtotal	weight distribution in current node
labels	regression labels

Returns: least squared deviation gain achieved after spliting the node

Definition at line 1052 of file CARTree.cpp.

◆ gain() [2/2]

float64_t gain	(	const SGVector< float64_t > &	wleft,
		const SGVector< float64_t > &	wright,
		const SGVector< float64_t > &	wtotal
	)

protectedinherited

returns gain in Gini impurity measure

Parameters

wleft	left child label distribution
wright	right child label distribution
wtotal	label distribution in current node

Returns: Gini gain achieved after spliting the node

Definition at line 1066 of file CARTree.cpp.

◆ get() [1/2]

T get ( const Tag< T > & _tag ) const

inherited

Getter for a class parameter, identified by a Tag. Throws an exception if the class does not have such a parameter.

Parameters

_tag	name and type information of parameter

Returns: value of the parameter identified by the input tag

Definition at line 381 of file SGObject.h.

◆ get() [2/2]

T get ( const std::string & name ) const

inherited

Getter for a class parameter, identified by a name. Throws an exception if the class does not have such a parameter.

Parameters

name	name of the parameter

Returns: value of the parameter corresponding to the input name and type

Definition at line 404 of file SGObject.h.

◆ get_classifier_type()

EMachineType get_classifier_type ( )

virtualinherited

get classifier type

Returns: classifier type NONE

Reimplemented in CLaRank, CSVMLight, CNeuralNetwork, CCCSOSVM, CLeastAngleRegression, CLDA, CQDA, CLibLinearMTL, CBaggingMachine, CLibLinear, CGaussianProcessClassification, CKernelRidgeRegression, CKNN, CLibSVR, CGaussianNaiveBayes, CSVRLight, CMCLDA, CLinearRidgeRegression, CScatterSVM, CGaussianProcessRegression, CSGDQN, CSVMSGD, CMKLClassification, COnlineSVMSGD, CLeastSquaresRegression, CMKLRegression, CDomainAdaptationSVMLinear, CMKLMulticlass, CKMeansBase, CHierarchical, CMKLOneClass, CLibSVM, CStochasticSOSVM, CDomainAdaptationSVM, CLPBoost, CPerceptron, CAveragedPerceptron, CFWSOSVM, CNewtonSVM, CLPM, CGMNPSVM, CSVMLightOneClass, CMulticlassLibSVM, CLibSVMOneClass, CMPDSVM, CGNPPSVM, and CCPLEXSVM.

Definition at line 99 of file Machine.cpp.

◆ get_feature_subset_size()

int32_t get_feature_subset_size ( ) const

get number of random features to choose in each node split

Returns: size subset size

Definition at line 72 of file RandomCARTree.h.

◆ get_feature_types()

SGVector< bool > get_feature_types ( ) const

inherited

set feature types of various features

Returns: bool vector - true for nominal feature false for continuous feature type

Definition at line 196 of file CARTree.cpp.

◆ get_global_io()

SGIO * get_global_io ( )

inherited

get the io object

Returns: io object

Definition at line 269 of file SGObject.cpp.

◆ get_global_parallel()

Parallel * get_global_parallel ( )

inherited

get the parallel object

Returns: parallel object

Definition at line 311 of file SGObject.cpp.

◆ get_global_version()

Version * get_global_version ( )

inherited

get the version object

Returns: version object

Definition at line 324 of file SGObject.cpp.

◆ get_label_epsilon()

float64_t get_label_epsilon ( )

inherited

get label epsilon

Returns: equality range for regression labels

Definition at line 223 of file CARTree.h.

◆ get_labels()

CLabels * get_labels ( )

virtualinherited

get labels

Returns: labels

Definition at line 83 of file Machine.cpp.

◆ get_machine_problem_type()

virtual EProblemType get_machine_problem_type ( ) const

virtualinherited

get problem type - multiclass classification or regression

Returns: PT_MULTICLASS or PT_REGRESSION

Reimplemented from CBaseMulticlassMachine.

Definition at line 115 of file CARTree.h.

◆ get_max_depth()

int32_t get_max_depth ( ) const

inherited

get max allowed tree depth

Returns: max allowed tree depth

Definition at line 218 of file CARTree.cpp.

◆ get_max_train_time()

float64_t get_max_train_time ( )

inherited

get maximum training time

Returns: maximum training time

Definition at line 94 of file Machine.cpp.

◆ get_min_node_size()

int32_t get_min_node_size ( ) const

inherited

get min allowed node size

Returns: min allowed node size

Definition at line 229 of file CARTree.cpp.

◆ get_modelsel_names()

SGStringList< char > get_modelsel_names ( )

inherited

Returns: vector of names of all parameters which are registered for model selection

Definition at line 536 of file SGObject.cpp.

◆ get_modsel_param_descr()

char * get_modsel_param_descr ( const char * param_name )

inherited

Returns description of a given parameter string, if it exists. SG_ERROR otherwise

Parameters

param_name name of the parameter

Returns: description of the parameter

Definition at line 560 of file SGObject.cpp.

◆ get_modsel_param_index()

index_t get_modsel_param_index ( const char * param_name )

inherited

Returns index of model selection parameter with provided index

Parameters

param_name name of model selection parameter

Returns: index of model selection parameter with provided name, -1 if there is no such

Definition at line 573 of file SGObject.cpp.

◆ get_name()

virtual const char* get_name ( ) const

virtual

get name

Returns: class name CARTree

Reimplemented from CCARTree.

Definition at line 60 of file RandomCARTree.h.

◆ get_num_folds()

int32_t get_num_folds ( ) const

inherited

get number of subsets used for cross validation

Returns: number of folds used in cross validation

Definition at line 207 of file CARTree.cpp.

◆ get_num_machines()

int32_t get_num_machines ( ) const

inherited

get number of machines

Returns: number of machines

Definition at line 27 of file BaseMulticlassMachine.cpp.

◆ get_parameters_observable()

SGObservable* get_parameters_observable ( )

inherited

Get parameters observable

Returns: RxCpp observable

Definition at line 415 of file SGObject.h.

◆ get_root()

CTreeMachineNode<CARTreeNodeData >* get_root ( )

inherited

get root

Returns: root the root node of the tree

Definition at line 88 of file TreeMachine.h.

◆ get_solver_type()

ESolverType get_solver_type ( )

inherited

get solver type

Returns: solver

Definition at line 109 of file Machine.cpp.

◆ get_unique_labels()

SGVector< float64_t > get_unique_labels	(	SGVector< float64_t >	labels_vec,
		int32_t &	n_ulabels
	)

protectedinherited

modify labels for compute_best_attribute

Parameters

labels_vec	labels vector
n_ulabels	stores number of unique labels

Returns: unique labels

Definition at line 506 of file CARTree.cpp.

◆ get_weights()

SGVector< float64_t > get_weights ( ) const

inherited

get weights of data points

Returns: vector of weights

Definition at line 179 of file CARTree.cpp.

◆ gini_impurity_index()

float64_t gini_impurity_index	(	const SGVector< float64_t > &	weighted_lab_classes,
		float64_t &	total_weight
	)

protectedinherited

returns Gini impurity of a node

Parameters

weighted_lab_classes	vector of weights associated with various labels
total_weight	stores the total weight of all classes

Returns: Gini index of the node

Definition at line 1078 of file CARTree.cpp.

◆ handle_missing_vecs_for_continuous_surrogate()

void handle_missing_vecs_for_continuous_surrogate	(	SGMatrix< float64_t >	m,
		CDynamicArray< int32_t > *	missing_vecs,
		CDynamicArray< float64_t > *	association_index,
		CDynamicArray< int32_t > *	intersect_vecs,
		SGVector< bool >	is_left,
		SGVector< float64_t >	weights,
		float64_t	p,
		int32_t	attr
	)

protectedinherited

handles missing values for a chosen continuous surrogate attribute

Parameters

m	training data matrix
missing_vecs	column indices of vectors with missing attribute in data matrix
association_index	stores the final lambda values used to address members of missing_vecs
intersect_vecs	column indices of vectors with known values for the best attribute as well as the chosen surrogate
is_left	whether a vector goes into left child
weights	weights of training data vectors
p	min(p_l,p_r) in the lambda formula
attr	surrogate attribute chosen for split

Returns: vector denoting whether a data point goes to left child for all data points including ones with missing attributes

Definition at line 915 of file CARTree.cpp.

◆ handle_missing_vecs_for_nominal_surrogate()

void handle_missing_vecs_for_nominal_surrogate	(	SGMatrix< float64_t >	m,
		CDynamicArray< int32_t > *	missing_vecs,
		CDynamicArray< float64_t > *	association_index,
		CDynamicArray< int32_t > *	intersect_vecs,
		SGVector< bool >	is_left,
		SGVector< float64_t >	weights,
		float64_t	p,
		int32_t	attr
	)

protectedinherited

handles missing values for a chosen nominal surrogate attribute

Parameters

m	training data matrix
missing_vecs	column indices of vectors with missing attribute in data matrix
association_index	stores the final lambda values used to address members of missing_vecs
intersect_vecs	column indices of vectors with known values for the best attribute as well as the chosen surrogate
is_left	whether a vector goes into left child
weights	weights of training data vectors
p	min(p_l,p_r) in the lambda formula
attr	surrogate attribute chosen for split

Returns: vector denoting whether a data point goes to left child for all data points including ones with missing attributes

Definition at line 972 of file CARTree.cpp.

◆ has() [1/3]

bool has ( const std::string & name ) const

inherited

Checks if object has a class parameter identified by a name.

Parameters

name	name of the parameter

Returns: true if the parameter exists with the input name

Definition at line 304 of file SGObject.h.

◆ has() [2/3]

bool has ( const Tag< T > & tag ) const

inherited

Checks if object has a class parameter identified by a Tag.

Parameters

tag	tag of the parameter containing name and type information

Returns: true if the parameter exists with the input tag

Definition at line 315 of file SGObject.h.

◆ has() [3/3]

bool has ( const std::string & name ) const

inherited

Checks if a type exists for a class parameter identified by a name.

Parameters

name	name of the parameter

Returns: true if the parameter exists with the input name and type

Definition at line 326 of file SGObject.h.

◆ is_data_locked()

bool is_data_locked ( ) const

inherited

Returns: whether this machine is locked

Definition at line 308 of file Machine.h.

◆ is_generic()

bool is_generic ( EPrimitiveType * generic ) const

virtualinherited

If the SGSerializable is a class template then TRUE will be returned and GENERIC is set to the type of the generic.

Parameters

generic set to the type of the generic if returning TRUE

Returns: TRUE if a class template.

Definition at line 330 of file SGObject.cpp.

◆ is_label_valid()

bool is_label_valid ( CLabels * lab ) const

virtualinherited

whether labels supplied are valid for current problem type

Parameters

lab	labels supplied

Returns: true for valid labels, false for invalid labels

Reimplemented from CBaseMulticlassMachine.

Definition at line 91 of file CARTree.cpp.

◆ least_squares_deviation()

float64_t least_squares_deviation	(	const SGVector< float64_t > &	labels,
		const SGVector< float64_t > &	weights,
		float64_t &	total_weight
	)

protectedinherited

returns least squares deviation

Parameters

labels	regression labels
weights	weights of regression data points
total_weight	stores sum of weights in weights vector

Returns: least squares deviation of the data

Definition at line 1088 of file CARTree.cpp.

◆ list_observable_parameters()

void list_observable_parameters ( )

inherited

Print to stdout a list of observable parameters

Definition at line 878 of file SGObject.cpp.

◆ load_serializable()

bool load_serializable	(	CSerializableFile *	file,
		const char *	prefix = `""`
	)

virtualinherited

Load this object from file. If it will fail (returning FALSE) then this object will contain inconsistent data and should not be used!

Parameters

file	where to load from
prefix	prefix for members

Returns: TRUE if done, otherwise FALSE

Definition at line 403 of file SGObject.cpp.

◆ load_serializable_post()

void load_serializable_post	(		)
throw	(	ShogunException
	)

protectedvirtualinherited

Can (optionally) be overridden to post-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::LOAD_SERIALIZABLE_POST is called.

Exceptions

ShogunException will be thrown if an error occurs.

Reimplemented in CKernel, CWeightedDegreePositionStringKernel, CList, CAlphabet, CLinearHMM, CGaussianKernel, CInverseMultiQuadricKernel, CCircularKernel, and CExponentialKernel.

Definition at line 460 of file SGObject.cpp.

◆ load_serializable_pre()

void load_serializable_pre	(		)
throw	(	ShogunException
	)

protectedvirtualinherited

Can (optionally) be overridden to pre-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::LOAD_SERIALIZABLE_PRE is called.

Exceptions

ShogunException will be thrown if an error occurs.

Reimplemented in CDynamicArray< T >, CDynamicArray< float64_t >, CDynamicArray< float32_t >, CDynamicArray< int32_t >, CDynamicArray< char >, CDynamicArray< bool >, and CDynamicObjectArray.

Definition at line 455 of file SGObject.cpp.

◆ observe()

void observe ( const ObservedValue value )

protectedinherited

Observe a parameter value and emit them to observer.

Parameters

value Observed parameter's value

Definition at line 828 of file SGObject.cpp.

◆ on_complete()

virtual void on_complete ( )

protectedvirtualinherited

The action which will be done when the user decides to return to prompt and terminate the program execution

Definition at line 427 of file Machine.h.

◆ on_next()

virtual void on_next ( )

protectedvirtualinherited

The action which will be done when the user decides to premature stop the CMachine execution

Definition at line 411 of file Machine.h.

◆ on_pause()

virtual void on_pause ( )

protectedvirtualinherited

The action which will be done when the user decides to pause the CMachine execution

Definition at line 418 of file Machine.h.

◆ parameter_hash_changed()

bool parameter_hash_changed ( )

virtualinherited

Returns: whether parameter combination has changed since last update

Definition at line 296 of file SGObject.cpp.

◆ pause_computation()

SG_FORCED_INLINE void pause_computation ( )

inherited

Pause the algorithm if the flag is set

Definition at line 327 of file Machine.h.

◆ post_lock()

virtual void post_lock	(	CLabels *	labs,
		CFeatures *	features
	)

virtualinherited

post lock

Definition at line 299 of file Machine.h.

◆ pre_sort_features()

void pre_sort_features	(	CFeatures *	data,
		SGMatrix< float64_t > &	sorted_feats,
		SGMatrix< index_t > &	sorted_indices
	)

inherited

Definition at line 296 of file CARTree.cpp.

◆ print_modsel_params()

void print_modsel_params ( )

inherited

prints all parameter registered for model selection and their type

Definition at line 512 of file SGObject.cpp.

◆ print_serializable()

void print_serializable ( const char * prefix = "" )

virtualinherited

prints registered parameters out

Parameters

prefix prefix for members

Definition at line 342 of file SGObject.cpp.

◆ prune_by_cross_validation()

void prune_by_cross_validation	(	CDenseFeatures< float64_t > *	data,
		int32_t	folds
	)

protectedinherited

prune by cross validation

Parameters

data	training data
folds	the integer V for V-fold cross validation

Definition at line 1189 of file CARTree.cpp.

◆ prune_tree()

CDynamicObjectArray * prune_tree ( CTreeMachine< CARTreeNodeData > * tree )

protectedinherited

cost-complexity pruning

Parameters

tree	the tree to be pruned

Returns: CDynamicObjectArray of pruned trees

Definition at line 1366 of file CARTree.cpp.

◆ prune_using_test_dataset()

void prune_using_test_dataset	(	CDenseFeatures< float64_t > *	feats,
		CLabels *	gnd_truth,
		SGVector< float64_t >	weights = `SGVector<float64_t>()`
	)

inherited

uses test dataset to choose best pruned subtree

Parameters

feats	test data to be used
gnd_truth	test labels
weights	weights of data points

Definition at line 127 of file CARTree.cpp.

◆ ref()

int32_t ref ( )

inherited

increase reference counter

Returns: reference count

Definition at line 186 of file SGObject.cpp.

◆ ref_count()

int32_t ref_count ( )

inherited

display reference counter

Returns: reference count

Definition at line 193 of file SGObject.cpp.

◆ register_observable_param()

void register_observable_param	(	const std::string &	name,
		const SG_OBS_VALUE_TYPE	type,
		const std::string &	description
	)

protectedinherited

Register which params this object can emit.

Parameters

name	the param name
type	the param type
description	a user oriented description

Definition at line 871 of file SGObject.cpp.

◆ register_param() [1/2]

void register_param	(	Tag< T > &	_tag,
		const T &	value
	)

protectedinherited

Registers a class parameter which is identified by a tag. This enables the parameter to be modified by set() and retrieved by get(). Parameters can be registered in the constructor of the class.

Parameters

_tag	name and type information of parameter
value	value of the parameter

Definition at line 472 of file SGObject.h.

◆ register_param() [2/2]

void register_param	(	const std::string &	name,
		const T &	value
	)

protectedinherited

Registers a class parameter which is identified by a name. This enables the parameter to be modified by set() and retrieved by get(). Parameters can be registered in the constructor of the class.

Parameters

name	name of the parameter
value	value of the parameter along with type information

Definition at line 485 of file SGObject.h.

◆ reset_computation_variables()

void reset_computation_variables ( )

protectedinherited

reset the computation variables

Definition at line 403 of file Machine.h.

◆ resume_computation()

SG_FORCED_INLINE void resume_computation ( )

inherited

Resume current computation (sets the flag)

Definition at line 340 of file Machine.h.

◆ save_serializable()

bool save_serializable	(	CSerializableFile *	file,
		const char *	prefix = `""`
	)

virtualinherited

Save this object to file.

Parameters

file	where to save the object; will be closed during returning if PREFIX is an empty string.
prefix	prefix for members

Returns: TRUE if done, otherwise FALSE

Definition at line 348 of file SGObject.cpp.

◆ save_serializable_post()

void save_serializable_post	(		)
throw	(	ShogunException
	)

protectedvirtualinherited

Can (optionally) be overridden to post-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::SAVE_SERIALIZABLE_POST is called.

Exceptions

ShogunException will be thrown if an error occurs.

Reimplemented in CKernel.

Definition at line 470 of file SGObject.cpp.

◆ save_serializable_pre()

void save_serializable_pre	(		)
throw	(	ShogunException
	)

protectedvirtualinherited

Can (optionally) be overridden to pre-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::SAVE_SERIALIZABLE_PRE is called.

Exceptions

ShogunException will be thrown if an error occurs.

Reimplemented in CKernel, CDynamicArray< T >, CDynamicArray< float64_t >, CDynamicArray< float32_t >, CDynamicArray< int32_t >, CDynamicArray< char >, CDynamicArray< bool >, and CDynamicObjectArray.

Definition at line 465 of file SGObject.cpp.

◆ set() [1/2]

void set	(	const Tag< T > &	_tag,
		const T &	value
	)

inherited

Setter for a class parameter, identified by a Tag. Throws an exception if the class does not have such a parameter.

Parameters

_tag	name and type information of parameter
value	value of the parameter

Definition at line 342 of file SGObject.h.

◆ set() [2/2]

void set	(	const std::string &	name,
		const T &	value
	)

inherited

Setter for a class parameter, identified by a name. Throws an exception if the class does not have such a parameter.

Parameters

name	name of the parameter
value	value of the parameter along with type information

Definition at line 368 of file SGObject.h.

◆ set_cv_pruning()

void set_cv_pruning ( bool cv_pruning )

inherited

Set cross validation pruning parameter

Parameters

cv_pruning allow CV pruning

Definition at line 214 of file CARTree.h.

◆ set_feature_subset_size()

void set_feature_subset_size ( int32_t size )

set number of random features to choose in each node split

Parameters

size	subset size

Definition at line 46 of file RandomCARTree.cpp.

◆ set_feature_types()

void set_feature_types ( SGVector< bool > ft )

inherited

set feature types of various features

Parameters

ft	bool vector true for nominal feature false for continuous feature type

Definition at line 190 of file CARTree.cpp.

◆ set_generic() [1/16]

void set_generic ( )

inherited

Definition at line 73 of file SGObject.cpp.

◆ set_generic() [2/16]

void set_generic ( )

inherited

Definition at line 78 of file SGObject.cpp.

◆ set_generic() [3/16]

void set_generic ( )

inherited

Definition at line 83 of file SGObject.cpp.

◆ set_generic() [4/16]

void set_generic ( )

inherited

Definition at line 88 of file SGObject.cpp.

◆ set_generic() [5/16]

void set_generic ( )

inherited

Definition at line 93 of file SGObject.cpp.

◆ set_generic() [6/16]

void set_generic ( )

inherited

Definition at line 98 of file SGObject.cpp.

◆ set_generic() [7/16]

void set_generic ( )

inherited

Definition at line 103 of file SGObject.cpp.

◆ set_generic() [8/16]

void set_generic ( )

inherited

Definition at line 108 of file SGObject.cpp.

◆ set_generic() [9/16]

void set_generic ( )

inherited

Definition at line 113 of file SGObject.cpp.

◆ set_generic() [10/16]

void set_generic ( )

inherited

Definition at line 118 of file SGObject.cpp.

◆ set_generic() [11/16]

void set_generic ( )

inherited

Definition at line 123 of file SGObject.cpp.

◆ set_generic() [12/16]

void set_generic ( )

inherited

Definition at line 128 of file SGObject.cpp.

◆ set_generic() [13/16]

void set_generic ( )

inherited

Definition at line 133 of file SGObject.cpp.

◆ set_generic() [14/16]

void set_generic ( )

inherited

Definition at line 138 of file SGObject.cpp.

◆ set_generic() [15/16]

void set_generic ( )

inherited

Definition at line 143 of file SGObject.cpp.

◆ set_generic() [16/16]

void set_generic ( )

inherited

set generic type to T

◆ set_global_io()

void set_global_io ( SGIO * io )

inherited

set the io object

Parameters

io	io object to use

Definition at line 262 of file SGObject.cpp.

◆ set_global_parallel()

void set_global_parallel ( Parallel * parallel )

inherited

set the parallel object

Parameters

parallel parallel object to use

Definition at line 275 of file SGObject.cpp.

◆ set_global_version()

void set_global_version ( Version * version )

inherited

set the version object

Parameters

version version object to use

Definition at line 317 of file SGObject.cpp.

◆ set_label_epsilon()

void set_label_epsilon ( float64_t epsilon )

inherited

set label epsilon

Parameters

epsilon equality range for regression labels

Definition at line 240 of file CARTree.cpp.

◆ set_labels()

void set_labels ( CLabels * lab )

virtualinherited

set labels - automagically switch machine problem type based on type of labels supplied

Parameters

lab labels

Reimplemented from CMachine.

Definition at line 72 of file CARTree.cpp.

◆ set_machine_problem_type()

void set_machine_problem_type ( EProblemType mode )

inherited

set problem type - multiclass classification or regression

Parameters

mode	EProblemType PT_MULTICLASS or PT_REGRESSION

Definition at line 86 of file CARTree.cpp.

◆ set_max_depth()

void set_max_depth ( int32_t depth )

inherited

set max allowed tree depth

Parameters

depth max allowed tree depth

Definition at line 223 of file CARTree.cpp.

◆ set_max_train_time()

void set_max_train_time ( float64_t t )

inherited

set maximum training time

Parameters

t	maximimum training time

Definition at line 89 of file Machine.cpp.

◆ set_min_node_size()

void set_min_node_size ( int32_t nsize )

inherited

set min allowed node size

Parameters

nsize min allowed node size

Definition at line 234 of file CARTree.cpp.

◆ set_num_folds()

void set_num_folds ( int32_t folds )

inherited

set number of subsets for cross validation

Parameters

folds number of folds used in cross validation

Definition at line 212 of file CARTree.cpp.

◆ set_root()

void set_root ( CTreeMachineNode< CARTreeNodeData > * root )

inherited

set root

Parameters

root	the root node of the tree

Definition at line 78 of file TreeMachine.h.

◆ set_solver_type()

void set_solver_type ( ESolverType st )

inherited

set solver type

Parameters

st	solver type

Definition at line 104 of file Machine.cpp.

◆ set_sorted_features()

void set_sorted_features	(	SGMatrix< float64_t > &	sorted_feats,
		SGMatrix< index_t > &	sorted_indices
	)

inherited

Definition at line 289 of file CARTree.cpp.

◆ set_store_model_features()

void set_store_model_features ( bool store_model )

virtualinherited

Setter for store-model-features-after-training flag

Parameters

store_model whether model should be stored after training

Definition at line 114 of file Machine.cpp.

◆ set_weights()

void set_weights ( SGVector< float64_t > w )

inherited

set weights of data points

Parameters

w	vector of weights

Definition at line 173 of file CARTree.cpp.

◆ shallow_copy()

CSGObject * shallow_copy ( ) const

virtualinherited

A shallow copy. All the SGObject instance variables will be simply assigned and SG_REF-ed.

Reimplemented in CGaussianKernel.

Definition at line 226 of file SGObject.cpp.

◆ store_model_features()

virtual void store_model_features ( )

protectedvirtualinherited

enable unlocked cross-validation - no model features to store

Reimplemented from CMachine.

Definition at line 152 of file TreeMachine.h.

◆ subscribe_to_parameters()

void subscribe_to_parameters ( ParameterObserverInterface * obs )

inherited

Subscribe a parameter observer to watch over params

Definition at line 811 of file SGObject.cpp.

◆ supports_locking()

virtual bool supports_locking ( ) const

virtualinherited

Returns: whether this machine supports locking

Reimplemented in CKernelMachine.

Definition at line 305 of file Machine.h.

◆ surrogate_split()

SGVector< bool > surrogate_split	(	SGMatrix< float64_t >	data,
		SGVector< float64_t >	weights,
		SGVector< bool >	nm_left,
		int32_t	attr
	)

protectedinherited

handles missing values through surrogate splits

Parameters

data	training data matrix
weights	vector of weights of data points
nm_left	whether a data point is put into left child (available for only data points with non-missing attribute attr)
attr	best attribute chosen for split

Returns: vector denoting whether a data point goes to left child for all data points including ones with missing attributes

Definition at line 840 of file CARTree.cpp.

◆ train()

bool train ( CFeatures * data = NULL )

virtualinherited

train machine

Parameters

data	training data (parameter can be avoided if distance or kernel-based classifiers are used and distance/kernels are initialized with train data). If flag is set, model features will be stored after training.

Returns: whether training was successful

Reimplemented in CRelaxedTree, CAutoencoder, CLinearMachine, CSGDQN, and COnlineSVMSGD.

Definition at line 43 of file Machine.cpp.

◆ train_locked()

virtual bool train_locked ( SGVector< index_t > indices )

virtualinherited

Trains a locked machine on a set of indices. Error if machine is not locked

NOT IMPLEMENTED

Parameters

indices index vector (of locked features) that is used for training

Returns: whether training was successful

Reimplemented in CKernelMachine.

Definition at line 248 of file Machine.h.

◆ train_machine()

bool train_machine ( CFeatures * data = NULL )

protectedvirtualinherited

train machine - build CART from training data

Parameters

data	training data

Returns: true

Reimplemented from CMachine.

Definition at line 246 of file CARTree.cpp.

◆ train_require_labels()

virtual bool train_require_labels ( ) const

protectedvirtualinherited

returns whether machine require labels for training

Reimplemented in COnlineLinearMachine, CKMeansBase, CHierarchical, CLinearLatentMachine, CVwConditionalProbabilityTree, CConditionalProbabilityTree, and CLibSVMOneClass.

Definition at line 397 of file Machine.h.

◆ unref()

int32_t unref ( )

inherited

decrement reference counter and deallocate object if refcount is zero before or after decrementing it

Returns: reference count

Definition at line 200 of file SGObject.cpp.

◆ unset_generic()

void unset_generic ( )

inherited

unset generic type

this has to be called in classes specializing a template class

Definition at line 337 of file SGObject.cpp.

◆ update_parameter_hash()

void update_parameter_hash ( )

virtualinherited

Updates the hash of current parameter combination

Definition at line 282 of file SGObject.cpp.

Member Data Documentation

◆ EQ_DELTA

const float64_t EQ_DELTA =1e-7

staticinherited

equality epsilon

Definition at line 422 of file CARTree.h.

◆ io

SGIO* io

inherited

io

Definition at line 600 of file SGObject.h.

◆ m_alphas

CDynamicArray<float64_t>* m_alphas

protectedinherited

stores $\alpha_k$ values evaluated in cost-complexity pruning

Definition at line 459 of file CARTree.h.

◆ m_apply_cv_pruning

bool m_apply_cv_pruning

protectedinherited

flag indicating whether cross validation pruning has to be applied or not - false by default

Definition at line 450 of file CARTree.h.

◆ m_cancel_computation

std::atomic<bool> m_cancel_computation

protectedinherited

Cancel computation

Definition at line 448 of file Machine.h.

◆ m_data_locked

bool m_data_locked

protectedinherited

whether data is locked

Definition at line 445 of file Machine.h.

◆ m_folds

int32_t m_folds

protectedinherited

V in V-fold cross validation - 5 by default

Definition at line 453 of file CARTree.h.

◆ m_gradient_parameters

Parameter* m_gradient_parameters

inherited

parameters wrt which we can compute gradients

Definition at line 615 of file SGObject.h.

◆ m_hash

uint32_t m_hash

inherited

Hash of parameter values

Definition at line 618 of file SGObject.h.

◆ m_label_epsilon

float64_t m_label_epsilon

protectedinherited

equality range for regression labels

Definition at line 426 of file CARTree.h.

◆ m_labels

CLabels* m_labels

protectedinherited

labels

Definition at line 436 of file Machine.h.

◆ m_machines

CDynamicObjectArray* m_machines

protectedinherited

machines

Definition at line 56 of file BaseMulticlassMachine.h.

◆ m_max_depth

int32_t m_max_depth

protectedinherited

max allowed depth of tree

Definition at line 462 of file CARTree.h.

◆ m_max_train_time

float64_t m_max_train_time

protectedinherited

maximum training time

Definition at line 433 of file Machine.h.

◆ m_min_node_size

int32_t m_min_node_size

protectedinherited

minimum number of feature vectors required in a node

Definition at line 465 of file CARTree.h.

◆ m_mode

EProblemType m_mode

protectedinherited

Problem type : PT_MULTICLASS or PT_REGRESSION

Definition at line 456 of file CARTree.h.

◆ m_model_selection_parameters

Parameter* m_model_selection_parameters

inherited

model selection parameters

Definition at line 612 of file SGObject.h.

◆ m_mutex

std::mutex m_mutex

protectedinherited

Mutex used to pause threads

Definition at line 457 of file Machine.h.

◆ m_nominal

SGVector<bool> m_nominal

protectedinherited

vector depicting whether various feature dimensions are nominal or not

Definition at line 429 of file CARTree.h.

◆ m_parameters

Parameter* m_parameters

inherited

parameters

Definition at line 609 of file SGObject.h.

◆ m_pause_computation

std::condition_variable m_pause_computation

protectedinherited

Conditional variable to make threads wait

Definition at line 454 of file Machine.h.

◆ m_pause_computation_flag

std::atomic<bool> m_pause_computation_flag

protectedinherited

Pause computation flag

Definition at line 451 of file Machine.h.

◆ m_pre_sort

bool m_pre_sort

protectedinherited

If pre sorted features are used in train

Definition at line 441 of file CARTree.h.

◆ m_root

CTreeMachineNode<CARTreeNodeData >* m_root

protectedinherited

tree root

Definition at line 156 of file TreeMachine.h.

◆ m_solver_type

ESolverType m_solver_type

protectedinherited

solver type

Definition at line 439 of file Machine.h.

◆ m_sorted_features

SGMatrix<float64_t> m_sorted_features

protectedinherited

sorted transposed features

Definition at line 435 of file CARTree.h.

◆ m_sorted_indices

SGMatrix<index_t> m_sorted_indices

protectedinherited

sorted indices

Definition at line 438 of file CARTree.h.

◆ m_store_model_features

bool m_store_model_features

protectedinherited

whether model features should be stored after training

Definition at line 442 of file Machine.h.

◆ m_types_set

bool m_types_set

protectedinherited

flag storing whether the type of various feature dimensions are specified using is_nominal_feature

Definition at line 444 of file CARTree.h.

◆ m_weights

SGVector<float64_t> m_weights

protectedinherited

weights of samples in training set

Definition at line 432 of file CARTree.h.

◆ m_weights_set

bool m_weights_set

protectedinherited

flag storing whether weights of samples are specified using weights vector

Definition at line 447 of file CARTree.h.

◆ MIN_SPLIT_GAIN

const float64_t MIN_SPLIT_GAIN =1e-7

staticinherited

min gain for splitting to be allowed

Definition at line 419 of file CARTree.h.

◆ MISSING

const float64_t MISSING =CMath::MAX_REAL_NUMBER

staticinherited

denotes that a feature in a vector is missing MISSING = NOT_A_NUMBER

Definition at line 416 of file CARTree.h.

◆ parallel

Parallel* parallel

inherited

parallel

Definition at line 603 of file SGObject.h.

◆ version

Version* version

inherited

version

Definition at line 606 of file SGObject.h.

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

Detailed Description

Public Types

Public Member Functions

Public Attributes

Static Public Attributes

Protected Member Functions

Protected Attributes

Member Typedef Documentation

◆ bnode_t

◆ node_t

◆ SGObservable

◆ SGSubject

◆ SGSubscriber

Constructor & Destructor Documentation

◆ CRandomCARTree()

◆ ~CRandomCARTree()

Member Function Documentation

◆ apply()

◆ apply_binary()

◆ apply_from_current_node()

◆ apply_latent()

◆ apply_locked()

◆ apply_locked_binary()

◆ apply_locked_latent()

◆ apply_locked_multiclass()

◆ apply_locked_regression()

◆ apply_locked_structured()

◆ apply_multiclass()

◆ apply_one()

◆ apply_regression()

◆ apply_structured()

◆ build_gradient_parameter_dictionary()

◆ cancel_computation()

◆ CARTtrain()

◆ clear_feature_types()

◆ clear_weights()

◆ clone()

◆ clone_parameters()

◆ clone_tree()

◆ compute_best_attribute()

◆ compute_error()

◆ connect_to_signal_handler()

◆ cut_weakest_link()

◆ data_lock()

◆ data_unlock()

◆ deep_copy()

◆ equals()

◆ find_weakest_alpha()

◆ form_t1()

◆ gain() [1/2]

◆ gain() [2/2]

◆ get() [1/2]

◆ get() [2/2]

◆ get_classifier_type()

◆ get_feature_subset_size()

◆ get_feature_types()

◆ get_global_io()

◆ get_global_parallel()

◆ get_global_version()

◆ get_label_epsilon()

◆ get_labels()

◆ get_machine_problem_type()

◆ get_max_depth()

◆ get_max_train_time()

◆ get_min_node_size()

◆ get_modelsel_names()

◆ get_modsel_param_descr()

◆ get_modsel_param_index()

◆ get_name()

◆ get_num_folds()

◆ get_num_machines()

◆ get_parameters_observable()

◆ get_root()

◆ get_solver_type()

◆ get_unique_labels()

◆ get_weights()

◆ gini_impurity_index()

◆ handle_missing_vecs_for_continuous_surrogate()

◆ handle_missing_vecs_for_nominal_surrogate()

◆ has() [1/3]