SHOGUN  4.1.0
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Macros Modules Pages
List of all members | Public Types | Public Member Functions | Public Attributes | Static Public Attributes | Protected Member Functions | Protected Attributes
CRandomCARTree Class Reference

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:
Inheritance graph
[legend]

Public Types

typedef CTreeMachineNode
< CARTreeNodeData
node_t
 
typedef CBinaryTreeMachineNode
< CARTreeNodeData
bnode_t
 

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 CMulticlassLabelsapply_multiclass (CFeatures *data=NULL)
 
virtual CRegressionLabelsapply_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_tget_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 ()
 
void unset_cv_pruning ()
 
float64_t get_label_epsilon ()
 
void set_label_epsilon (float64_t epsilon)
 
void set_root (CTreeMachineNode< CARTreeNodeData > *root)
 
CTreeMachineNode
< CARTreeNodeData > * 
get_root ()
 
CTreeMachineclone_tree ()
 
int32_t get_num_machines () const
 
virtual bool train (CFeatures *data=NULL)
 
virtual CLabelsapply (CFeatures *data=NULL)
 
virtual CBinaryLabelsapply_binary (CFeatures *data=NULL)
 
virtual CStructuredLabelsapply_structured (CFeatures *data=NULL)
 
virtual CLatentLabelsapply_latent (CFeatures *data=NULL)
 
virtual CLabelsget_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 CLabelsapply_locked (SGVector< index_t > indices)
 
virtual CBinaryLabelsapply_locked_binary (SGVector< index_t > indices)
 
virtual CRegressionLabelsapply_locked_regression (SGVector< index_t > indices)
 
virtual CMulticlassLabelsapply_locked_multiclass (SGVector< index_t > indices)
 
virtual CStructuredLabelsapply_locked_structured (SGVector< index_t > indices)
 
virtual CLatentLabelsapply_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
 
virtual CSGObjectshallow_copy () const
 
virtual CSGObjectdeep_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)
 
SGIOget_global_io ()
 
void set_global_parallel (Parallel *parallel)
 
Parallelget_global_parallel ()
 
void set_global_version (Version *version)
 
Versionget_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)
 
virtual void update_parameter_hash ()
 
virtual bool parameter_hash_changed ()
 
virtual bool equals (CSGObject *other, float64_t accuracy=0.0, bool tolerant=false)
 
virtual CSGObjectclone ()
 

Public Attributes

SGIOio
 
Parallelparallel
 
Versionversion
 
Parameterm_parameters
 
Parameterm_model_selection_parameters
 
Parameterm_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 (SGMatrix< float64_t > mat, SGVector< float64_t > weights, SGVector< float64_t > labels_vec, 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)
 
virtual bool train_machine (CFeatures *data=NULL)
 
virtual CBinaryTreeMachineNode
< CARTreeNodeData > * 
CARTtrain (CFeatures *data, SGVector< float64_t > weights, CLabels *labels, int32_t level)
 
SGVector< float64_tget_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 (SGVector< float64_t > wleft, SGVector< float64_t > wright, SGVector< float64_t > wtotal)
 
float64_t gini_impurity_index (SGVector< float64_t > weighted_lab_classes, float64_t &total_weight)
 
float64_t least_squares_deviation (SGVector< float64_t > labels, SGVector< float64_t > weights, float64_t &total_weight)
 
CLabelsapply_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)
 
CDynamicObjectArrayprune_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
 
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)
 

Protected Attributes

float64_t m_label_epsilon
 
SGVector< bool > m_nominal
 
SGVector< float64_tm_weights
 
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
 
CDynamicObjectArraym_machines
 
float64_t m_max_train_time
 
CLabelsm_labels
 
ESolverType m_solver_type
 
bool m_store_model_features
 
bool m_data_locked
 

Member Typedef Documentation

bnode_t type- Tree node with max 2 possible children

Definition at line 55 of file TreeMachine.h.

node_t type- Tree node with many possible children

Definition at line 52 of file TreeMachine.h.

Constructor & Destructor Documentation

constructor

Definition at line 36 of file RandomCARTree.cpp.

~CRandomCARTree ( )
virtual

destructor

Definition at line 42 of file RandomCARTree.cpp.

Member Function Documentation

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 152 of file Machine.cpp.

CBinaryLabels * apply_binary ( CFeatures data = NULL)
virtualinherited

apply machine to data in means of binary classification problem

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

Definition at line 208 of file Machine.cpp.

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

uses current subtree to classify/regress data

Parameters
featsdata to be classified/regressed
currentroot of current subtree
Returns
classification/regression labels of input data

Definition at line 976 of file CARTree.cpp.

CLatentLabels * apply_latent ( CFeatures data = NULL)
virtualinherited

apply machine to data in means of latent problem

Reimplemented in CLinearLatentMachine.

Definition at line 232 of file Machine.cpp.

CLabels * apply_locked ( SGVector< index_t indices)
virtualinherited

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

Parameters
indicesindex vector (of locked features) that is predicted

Definition at line 187 of file Machine.cpp.

CBinaryLabels * apply_locked_binary ( SGVector< index_t indices)
virtualinherited

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

Reimplemented in CKernelMachine, and CMultitaskLinearMachine.

Definition at line 238 of file Machine.cpp.

CLatentLabels * apply_locked_latent ( SGVector< index_t indices)
virtualinherited

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

Definition at line 266 of file Machine.cpp.

CMulticlassLabels * apply_locked_multiclass ( SGVector< index_t indices)
virtualinherited

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

Definition at line 252 of file Machine.cpp.

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 245 of file Machine.cpp.

CStructuredLabels * apply_locked_structured ( SGVector< index_t indices)
virtualinherited

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

Definition at line 259 of file Machine.cpp.

CMulticlassLabels * apply_multiclass ( CFeatures data = NULL)
virtualinherited

classify data using Classification Tree

Parameters
datadata to be classified
Returns
MulticlassLabels corresponding to labels of various test vectors

Reimplemented from CMachine.

Definition at line 99 of file CARTree.cpp.

virtual float64_t apply_one ( int32_t  i)
virtualinherited
CRegressionLabels * apply_regression ( CFeatures data = NULL)
virtualinherited

Get regression labels using Regression Tree

Parameters
datadata whose regression output is needed
Returns
Regression output for various test vectors

Reimplemented from CMachine.

Definition at line 111 of file CARTree.cpp.

CStructuredLabels * apply_structured ( CFeatures data = NULL)
virtualinherited

apply machine to data in means of SO classification problem

Reimplemented in CLinearStructuredOutputMachine.

Definition at line 226 of file Machine.cpp.

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
dictdictionary of parameters to be built.

Definition at line 597 of file SGObject.cpp.

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

CARTtrain - recursive CART training method

Parameters
datatraining data
weightsvector of weights of data points
labelslabels of data points
levelcurrent tree depth
Returns
pointer to the root of the CART subtree

Definition at line 285 of file CARTree.cpp.

void clear_feature_types ( )
inherited

clear feature types of various features

Definition at line 197 of file CARTree.cpp.

void clear_weights ( )
inherited

clear weights of data points

Definition at line 180 of file CARTree.cpp.

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

Definition at line 714 of file SGObject.cpp.

CTreeMachine* clone_tree ( )
inherited

clone tree

Returns
clone of entire tree

Definition at line 97 of file TreeMachine.h.

int32_t compute_best_attribute ( SGMatrix< float64_t mat,
SGVector< float64_t weights,
SGVector< float64_t labels_vec,
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 
)
protectedvirtual

computes best attribute for CARTtrain

Parameters
matdata matrix
weightsdata weights
labels_vecdata labels
leftstores feature values for left transition
rightstores feature values for right transition
is_left_finalstores which feature vectors go to the left child
num_missingnumber of missing attributes
count_leftstores number of feature values for left transition
count_rightstores number of feature values for right transition
Returns
index to the best attribute

Reimplemented from CCARTree.

Definition at line 52 of file RandomCARTree.cpp.

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
labelsthe labels whose error needs to be calculated
referenceactual labels against which test labels are compared
weightsweights associated with the labels
Returns
error evaluated

Definition at line 1198 of file CARTree.cpp.

void cut_weakest_link ( bnode_t node,
float64_t  alpha 
)
protectedinherited

recursively cuts weakest link(s) in a tree

Parameters
nodethe root of subtree whose weakest link it cuts
alphaalpha value corresponding to weakest link

Definition at line 1305 of file CARTree.cpp.

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
labslabels used for locking
featuresfeatures used for locking

Reimplemented in CKernelMachine.

Definition at line 112 of file Machine.cpp.

void data_unlock ( )
virtualinherited

Unlocks a locked machine and restores previous state

Reimplemented in CKernelMachine.

Definition at line 143 of file Machine.cpp.

CSGObject * deep_copy ( ) const
virtualinherited

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

Definition at line 198 of file SGObject.cpp.

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
otherobject to compare with
accuracyaccuracy to use for comparison (optional)
tolerantallows linient check on float equality (within accuracy)
Returns
true if all parameters were equal, false if not

Definition at line 618 of file SGObject.cpp.

float64_t find_weakest_alpha ( bnode_t node)
protectedinherited

recursively finds alpha corresponding to weakest link(s)

Parameters
nodethe root of subtree whose weakest link it finds
Returns
alpha value corresponding to the weakest link in subtree

Definition at line 1284 of file CARTree.cpp.

void form_t1 ( bnode_t node)
protectedinherited

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

Parameters
nodethe root of current subtree

Definition at line 1335 of file CARTree.cpp.

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
wleftleft child weight distribution
wrightright child weights distribution
wtotalweight distribution in current node
labelsregression labels
Returns
least squared deviation gain achieved after spliting the node

Definition at line 918 of file CARTree.cpp.

float64_t gain ( SGVector< float64_t wleft,
SGVector< float64_t wright,
SGVector< float64_t wtotal 
)
protectedinherited

returns gain in Gini impurity measure

Parameters
wleftleft child label distribution
wrightright child label distribution
wtotallabel distribution in current node
Returns
Gini gain achieved after spliting the node

Definition at line 932 of file CARTree.cpp.

EMachineType get_classifier_type ( )
virtualinherited
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.

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 192 of file CARTree.cpp.

SGIO * get_global_io ( )
inherited

get the io object

Returns
io object

Definition at line 235 of file SGObject.cpp.

Parallel * get_global_parallel ( )
inherited

get the parallel object

Returns
parallel object

Definition at line 277 of file SGObject.cpp.

Version * get_global_version ( )
inherited

get the version object

Returns
version object

Definition at line 290 of file SGObject.cpp.

float64_t get_label_epsilon ( )
inherited

get label epsilon

Returns
equality range for regression labels

Definition at line 220 of file CARTree.h.

CLabels * get_labels ( )
virtualinherited

get labels

Returns
labels

Definition at line 76 of file Machine.cpp.

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.

int32_t get_max_depth ( ) const
inherited

get max allowed tree depth

Returns
max allowed tree depth

Definition at line 214 of file CARTree.cpp.

float64_t get_max_train_time ( )
inherited

get maximum training time

Returns
maximum training time

Definition at line 87 of file Machine.cpp.

int32_t get_min_node_size ( ) const
inherited

get min allowed node size

Returns
min allowed node size

Definition at line 225 of file CARTree.cpp.

SGStringList< char > get_modelsel_names ( )
inherited
Returns
vector of names of all parameters which are registered for model selection

Definition at line 498 of file SGObject.cpp.

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_namename of the parameter
Returns
description of the parameter

Definition at line 522 of file SGObject.cpp.

index_t get_modsel_param_index ( const char *  param_name)
inherited

Returns index of model selection parameter with provided index

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

Definition at line 535 of file SGObject.cpp.

virtual const char* get_name ( ) const
virtual

get name

Returns
class name CARTree

Reimplemented from CCARTree.

Definition at line 60 of file RandomCARTree.h.

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 203 of file CARTree.cpp.

int32_t get_num_machines ( ) const
inherited

get number of machines

Returns
number of machines

Definition at line 27 of file BaseMulticlassMachine.cpp.

CTreeMachineNode<CARTreeNodeData >* get_root ( )
inherited

get root

Returns
root the root node of the tree

Definition at line 88 of file TreeMachine.h.

ESolverType get_solver_type ( )
inherited

get solver type

Returns
solver

Definition at line 102 of file Machine.cpp.

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

modify labels for compute_best_attribute

Parameters
labels_veclabels vector
n_ulabelsstores number of unique labels
Returns
unique labels

Definition at line 462 of file CARTree.cpp.

SGVector< float64_t > get_weights ( ) const
inherited

get weights of data points

Returns
vector of weights

Definition at line 175 of file CARTree.cpp.

float64_t gini_impurity_index ( SGVector< float64_t weighted_lab_classes,
float64_t total_weight 
)
protectedinherited

returns Gini impurity of a node

Parameters
weighted_lab_classesvector of weights associated with various labels
total_weightstores the total weight of all classes
Returns
Gini index of the node

Definition at line 944 of file CARTree.cpp.

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
mtraining data matrix
missing_vecscolumn indices of vectors with missing attribute in data matrix
association_indexstores the final lambda values used to address members of missing_vecs
intersect_vecscolumn indices of vectors with known values for the best attribute as well as the chosen surrogate
is_leftwhether a vector goes into left child
weightsweights of training data vectors
pmin(p_l,p_r) in the lambda formula
attrsurrogate 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 781 of file CARTree.cpp.

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
mtraining data matrix
missing_vecscolumn indices of vectors with missing attribute in data matrix
association_indexstores the final lambda values used to address members of missing_vecs
intersect_vecscolumn indices of vectors with known values for the best attribute as well as the chosen surrogate
is_leftwhether a vector goes into left child
weightsweights of training data vectors
pmin(p_l,p_r) in the lambda formula
attrsurrogate 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 838 of file CARTree.cpp.

bool is_data_locked ( ) const
inherited
Returns
whether this machine is locked

Definition at line 296 of file Machine.h.

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
genericset to the type of the generic if returning TRUE
Returns
TRUE if a class template.

Definition at line 296 of file SGObject.cpp.

bool is_label_valid ( CLabels lab) const
virtualinherited

whether labels supplied are valid for current problem type

Parameters
lablabels supplied
Returns
true for valid labels, false for invalid labels

Reimplemented from CBaseMulticlassMachine.

Definition at line 89 of file CARTree.cpp.

float64_t least_squares_deviation ( SGVector< float64_t labels,
SGVector< float64_t weights,
float64_t total_weight 
)
protectedinherited

returns least squares deviation

Parameters
labelsregression labels
weightsweights of regression data points
total_weightstores sum of weights in weights vector
Returns
least squares deviation of the data

Definition at line 958 of file CARTree.cpp.

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
filewhere to load from
prefixprefix for members
Returns
TRUE if done, otherwise FALSE

Definition at line 369 of file SGObject.cpp.

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
ShogunExceptionwill be thrown if an error occurs.

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

Definition at line 426 of file SGObject.cpp.

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
ShogunExceptionwill 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 421 of file SGObject.cpp.

bool parameter_hash_changed ( )
virtualinherited
Returns
whether parameter combination has changed since last update

Definition at line 262 of file SGObject.cpp.

virtual void post_lock ( CLabels labs,
CFeatures features 
)
virtualinherited

post lock

Reimplemented in CMultitaskLinearMachine.

Definition at line 287 of file Machine.h.

void print_modsel_params ( )
inherited

prints all parameter registered for model selection and their type

Definition at line 474 of file SGObject.cpp.

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

prints registered parameters out

Parameters
prefixprefix for members

Definition at line 308 of file SGObject.cpp.

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

prune by cross validation

Parameters
datatraining data
foldsthe integer V for V-fold cross validation

Definition at line 1059 of file CARTree.cpp.

CDynamicObjectArray * prune_tree ( CTreeMachine< CARTreeNodeData > *  tree)
protectedinherited

cost-complexity pruning

Parameters
treethe tree to be pruned
Returns
CDynamicObjectArray of pruned trees

Definition at line 1236 of file CARTree.cpp.

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
featstest data to be used
gnd_truthtest labels
weightsweights of data points

Definition at line 123 of file CARTree.cpp.

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

Save this object to file.

Parameters
filewhere to save the object; will be closed during returning if PREFIX is an empty string.
prefixprefix for members
Returns
TRUE if done, otherwise FALSE

Definition at line 314 of file SGObject.cpp.

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
ShogunExceptionwill be thrown if an error occurs.

Reimplemented in CKernel.

Definition at line 436 of file SGObject.cpp.

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
ShogunExceptionwill 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 431 of file SGObject.cpp.

void set_cv_pruning ( )
inherited

apply cross validation pruning

Definition at line 211 of file CARTree.h.

void set_feature_subset_size ( int32_t  size)

set number of random features to choose in each node split

Parameters
sizesubset size

Definition at line 46 of file RandomCARTree.cpp.

void set_feature_types ( SGVector< bool >  ft)
inherited

set feature types of various features

Parameters
ftbool vector true for nominal feature false for continuous feature type

Definition at line 186 of file CARTree.cpp.

void set_generic ( )
inherited

Definition at line 41 of file SGObject.cpp.

void set_generic ( )
inherited

Definition at line 46 of file SGObject.cpp.

void set_generic ( )
inherited

Definition at line 51 of file SGObject.cpp.

void set_generic ( )
inherited

Definition at line 56 of file SGObject.cpp.

void set_generic ( )
inherited

Definition at line 61 of file SGObject.cpp.

void set_generic ( )
inherited

Definition at line 66 of file SGObject.cpp.

void set_generic ( )
inherited

Definition at line 71 of file SGObject.cpp.

void set_generic ( )
inherited

Definition at line 76 of file SGObject.cpp.

void set_generic ( )
inherited

Definition at line 81 of file SGObject.cpp.

void set_generic ( )
inherited

Definition at line 86 of file SGObject.cpp.

void set_generic ( )
inherited

Definition at line 91 of file SGObject.cpp.

void set_generic ( )
inherited

Definition at line 96 of file SGObject.cpp.

void set_generic ( )
inherited

Definition at line 101 of file SGObject.cpp.

void set_generic ( )
inherited

Definition at line 106 of file SGObject.cpp.

void set_generic ( )
inherited

Definition at line 111 of file SGObject.cpp.

void set_generic ( )
inherited

set generic type to T

void set_global_io ( SGIO io)
inherited

set the io object

Parameters
ioio object to use

Definition at line 228 of file SGObject.cpp.

void set_global_parallel ( Parallel parallel)
inherited

set the parallel object

Parameters
parallelparallel object to use

Definition at line 241 of file SGObject.cpp.

void set_global_version ( Version version)
inherited

set the version object

Parameters
versionversion object to use

Definition at line 283 of file SGObject.cpp.

void set_label_epsilon ( float64_t  epsilon)
inherited

set label epsilon

Parameters
epsilonequality range for regression labels

Definition at line 236 of file CARTree.cpp.

void set_labels ( CLabels lab)
virtualinherited

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

Parameters
lablabels

Reimplemented from CMachine.

Definition at line 70 of file CARTree.cpp.

void set_machine_problem_type ( EProblemType  mode)
inherited

set problem type - multiclass classification or regression

Parameters
modeEProblemType PT_MULTICLASS or PT_REGRESSION

Definition at line 84 of file CARTree.cpp.

void set_max_depth ( int32_t  depth)
inherited

set max allowed tree depth

Parameters
depthmax allowed tree depth

Definition at line 219 of file CARTree.cpp.

void set_max_train_time ( float64_t  t)
inherited

set maximum training time

Parameters
tmaximimum training time

Definition at line 82 of file Machine.cpp.

void set_min_node_size ( int32_t  nsize)
inherited

set min allowed node size

Parameters
nsizemin allowed node size

Definition at line 230 of file CARTree.cpp.

void set_num_folds ( int32_t  folds)
inherited

set number of subsets for cross validation

Parameters
foldsnumber of folds used in cross validation

Definition at line 208 of file CARTree.cpp.

void set_root ( CTreeMachineNode< CARTreeNodeData > *  root)
inherited

set root

Parameters
rootthe root node of the tree

Definition at line 78 of file TreeMachine.h.

void set_solver_type ( ESolverType  st)
inherited

set solver type

Parameters
stsolver type

Definition at line 97 of file Machine.cpp.

void set_store_model_features ( bool  store_model)
virtualinherited

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

Parameters
store_modelwhether model should be stored after training

Definition at line 107 of file Machine.cpp.

void set_weights ( SGVector< float64_t w)
inherited

set weights of data points

Parameters
wvector of weights

Definition at line 169 of file CARTree.cpp.

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 192 of file SGObject.cpp.

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.

virtual bool supports_locking ( ) const
virtualinherited
Returns
whether this machine supports locking

Reimplemented in CKernelMachine, and CMultitaskLinearMachine.

Definition at line 293 of file Machine.h.

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
datatraining data matrix
weightsvector of weights of data points
nm_leftwhether a data point is put into left child (available for only data points with non-missing attribute attr)
attrbest 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 706 of file CARTree.cpp.

bool train ( CFeatures data = NULL)
virtualinherited

train machine

Parameters
datatraining 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, CSGDQN, and COnlineSVMSGD.

Definition at line 39 of file Machine.cpp.

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
indicesindex vector (of locked features) that is used for training
Returns
whether training was successful

Reimplemented in CKernelMachine, and CMultitaskLinearMachine.

Definition at line 239 of file Machine.h.

bool train_machine ( CFeatures data = NULL)
protectedvirtualinherited

train machine - build CART from training data

Parameters
datatraining data
Returns
true

Reimplemented from CMachine.

Definition at line 242 of file CARTree.cpp.

virtual bool train_require_labels ( ) const
protectedvirtualinherited

returns whether machine require labels for training

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

Definition at line 354 of file Machine.h.

void unset_cv_pruning ( )
inherited

do not apply cross validation pruning

Definition at line 214 of file CARTree.h.

void unset_generic ( )
inherited

unset generic type

this has to be called in classes specializing a template class

Definition at line 303 of file SGObject.cpp.

void update_parameter_hash ( )
virtualinherited

Updates the hash of current parameter combination

Definition at line 248 of file SGObject.cpp.

Member Data Documentation

const float64_t EQ_DELTA =1e-7
staticinherited

equality epsilon

Definition at line 415 of file CARTree.h.

SGIO* io
inherited

io

Definition at line 369 of file SGObject.h.

CDynamicArray<float64_t>* m_alphas
protectedinherited

stores \(\alpha_k\) values evaluated in cost-complexity pruning

Definition at line 443 of file CARTree.h.

bool m_apply_cv_pruning
protectedinherited

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

Definition at line 434 of file CARTree.h.

bool m_data_locked
protectedinherited

whether data is locked

Definition at line 370 of file Machine.h.

int32_t m_folds
protectedinherited

V in V-fold cross validation - 5 by default

Definition at line 437 of file CARTree.h.

Parameter* m_gradient_parameters
inherited

parameters wrt which we can compute gradients

Definition at line 384 of file SGObject.h.

uint32_t m_hash
inherited

Hash of parameter values

Definition at line 387 of file SGObject.h.

float64_t m_label_epsilon
protectedinherited

equality range for regression labels

Definition at line 419 of file CARTree.h.

CLabels* m_labels
protectedinherited

labels

Definition at line 361 of file Machine.h.

CDynamicObjectArray* m_machines
protectedinherited

machines

Definition at line 56 of file BaseMulticlassMachine.h.

int32_t m_max_depth
protectedinherited

max allowed depth of tree

Definition at line 446 of file CARTree.h.

float64_t m_max_train_time
protectedinherited

maximum training time

Definition at line 358 of file Machine.h.

int32_t m_min_node_size
protectedinherited

minimum number of feature vectors required in a node

Definition at line 449 of file CARTree.h.

EProblemType m_mode
protectedinherited

Problem type : PT_MULTICLASS or PT_REGRESSION

Definition at line 440 of file CARTree.h.

Parameter* m_model_selection_parameters
inherited

model selection parameters

Definition at line 381 of file SGObject.h.

SGVector<bool> m_nominal
protectedinherited

vector depicting whether various feature dimensions are nominal or not

Definition at line 422 of file CARTree.h.

Parameter* m_parameters
inherited

parameters

Definition at line 378 of file SGObject.h.

CTreeMachineNode<CARTreeNodeData >* m_root
protectedinherited

tree root

Definition at line 156 of file TreeMachine.h.

ESolverType m_solver_type
protectedinherited

solver type

Definition at line 364 of file Machine.h.

bool m_store_model_features
protectedinherited

whether model features should be stored after training

Definition at line 367 of file Machine.h.

bool m_types_set
protectedinherited

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

Definition at line 428 of file CARTree.h.

SGVector<float64_t> m_weights
protectedinherited

weights of samples in training set

Definition at line 425 of file CARTree.h.

bool m_weights_set
protectedinherited

flag storing whether weights of samples are specified using weights vector

Definition at line 431 of file CARTree.h.

const float64_t MIN_SPLIT_GAIN =1e-7
staticinherited

min gain for splitting to be allowed

Definition at line 412 of file CARTree.h.

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 409 of file CARTree.h.

Parallel* parallel
inherited

parallel

Definition at line 372 of file SGObject.h.

Version* version
inherited

version

Definition at line 375 of file SGObject.h.


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

SHOGUN Machine Learning Toolbox - Documentation