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

Detailed Description

This class implements the Random Forests algorithm. In Random Forests algorithm, we train a number of randomized CART trees (see class CRandomCARTree) using the supplied training data. The number of trees to be trained is a parameter (called number of bags) controlled by the user. Test feature vectors are classified/regressed by combining the outputs of all these trained candidate trees using a combination rule (see class CCombinationRule). The feature for calculating out-of-box error is also provided to help determine the appropriate number of bags. The evaluatin criteria for calculating this out-of-box error is specified by the user (see class CEvaluation).

Definition at line 46 of file RandomForest.h.

Inheritance diagram for CRandomForest:
Inheritance graph
[legend]

Public Member Functions

 CRandomForest ()
 
 CRandomForest (int32_t num_rand_feats, int32_t num_bags=10)
 
 CRandomForest (CFeatures *features, CLabels *labels, int32_t num_bags=10, int32_t num_rand_feats=0)
 
 CRandomForest (CFeatures *features, CLabels *labels, SGVector< float64_t > weights, int32_t num_bags=10, int32_t num_rand_feats=0)
 
virtual ~CRandomForest ()
 
virtual const char * get_name () const
 
virtual void set_machine (CMachine *machine)
 
void set_weights (SGVector< float64_t > weights)
 
SGVector< float64_t > get_weights () const
 
void set_feature_types (SGVector< bool > ft)
 
SGVector< bool > get_feature_types () const
 
virtual EProblemType get_machine_problem_type () const
 
void set_machine_problem_type (EProblemType mode)
 
void set_num_random_features (int32_t rand_featsize)
 
int32_t get_num_random_features () const
 
virtual CBinaryLabels * apply_binary (CFeatures *data=NULL)
 
virtual CMulticlassLabels * apply_multiclass (CFeatures *data=NULL)
 
virtual CRegressionLabels * apply_regression (CFeatures *data=NULL)
 
void set_num_bags (int32_t num_bags)
 
int32_t get_num_bags () const
 
virtual void set_bag_size (int32_t bag_size)
 
virtual int32_t get_bag_size () const
 
CMachine * get_machine () const
 
void set_combination_rule (CCombinationRule *rule)
 
CCombinationRule * get_combination_rule () const
 
virtual EMachineType get_classifier_type ()
 
float64_t get_oob_error (CEvaluation *eval) const
 
virtual bool train (CFeatures *data=NULL)
 
virtual CLabels * apply (CFeatures *data=NULL)
 
virtual CStructuredLabels * apply_structured (CFeatures *data=NULL)
 
virtual CLatentLabels * apply_latent (CFeatures *data=NULL)
 
virtual void set_labels (CLabels *lab)
 
virtual CLabels * get_labels ()
 
void set_max_train_time (float64_t t)
 
float64_t get_max_train_time ()
 
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
 
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)
 
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
 

Protected Member Functions

virtual void set_machine_parameters (CMachine *m, SGVector< index_t > idx)
 
virtual bool train_machine (CFeatures *data=NULL)
 
SGVector< float64_t > apply_get_outputs (CFeatures *data)
 
void register_parameters ()
 
CDynamicArray< index_t > * get_oob_indices (const SGVector< index_t > &in_bag)
 
virtual void store_model_features ()
 
virtual bool is_label_valid (CLabels *lab) const
 
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

CDynamicObjectArray * m_bags
 
CFeatures * m_features
 
CMachine * m_machine
 
int32_t m_num_bags
 
int32_t m_bag_size
 
CCombinationRule * m_combination_rule
 
SGVector< bool > m_all_oob_idx
 
CDynamicObjectArray * m_oob_indices
 
float64_t m_max_train_time
 
CLabels * m_labels
 
ESolverType m_solver_type
 
bool m_store_model_features
 
bool m_data_locked
 

Constructor & Destructor Documentation

CRandomForest ( )

constructor

Definition at line 36 of file RandomForest.cpp.

CRandomForest ( int32_t  num_rand_feats,
int32_t  num_bags = 10 
)

constructor

Parameters
num_rand_featsnumber of attributes chosen randomly during node split in candidate trees
num_bagsnumber of trees in forest

Definition at line 42 of file RandomForest.cpp.

CRandomForest ( CFeatures *  features,
CLabels *  labels,
int32_t  num_bags = 10,
int32_t  num_rand_feats = 0 
)

constructor

Parameters
featurestraining features
labelstraining labels
num_bagsnumber of trees in forest
num_rand_featsnumber of attributes chosen randomly during node split in candidate trees

Definition at line 54 of file RandomForest.cpp.

CRandomForest ( CFeatures *  features,
CLabels *  labels,
SGVector< float64_t >  weights,
int32_t  num_bags = 10,
int32_t  num_rand_feats = 0 
)

constructor

Parameters
featurestraining features
labelstraining labels
weightsweights of training feature vectors
num_bagsnumber of trees in forest
num_rand_featsnumber of attributes chosen randomly during node split in candidate trees

Definition at line 69 of file RandomForest.cpp.

~CRandomForest ( )
virtual

destructor

Definition at line 85 of file RandomForest.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 from CMachine.

Definition at line 45 of file BaggingMachine.cpp.

SGVector< float64_t > apply_get_outputs ( CFeatures *  data)
protectedinherited

helper function for the apply_{regression,..} functions that computes the output

Parameters
datathe data to compute the output for
Returns
predictions

Definition at line 70 of file BaggingMachine.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

apply machine to data in means of multiclass classification problem

Reimplemented from CMachine.

Definition at line 53 of file BaggingMachine.cpp.

virtual float64_t apply_one ( int32_t  i)
virtualinherited

applies to one vector

Reimplemented in CKernelMachine, CRelaxedTree, CWDSVMOcas, COnlineLinearMachine, CLinearMachine, CMultitaskLinearMachine, CMulticlassMachine, CKNN, CDistanceMachine, CMultitaskLogisticRegression, CMultitaskLeastSquaresRegression, CScatterSVM, CGaussianNaiveBayes, CPluginEstimate, and CFeatureBlockLogisticRegression.

Definition at line 247 of file Machine.h.

CRegressionLabels * apply_regression ( CFeatures *  data = NULL)
virtualinherited

apply machine to data in means of regression problem

Reimplemented from CMachine.

Definition at line 61 of file BaggingMachine.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.

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.

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.

int32_t get_bag_size ( ) const
virtualinherited

Get number of feature vectors that are use for training each bag/machine

Returns
number of vectors used for training for each bag.

Definition at line 214 of file BaggingMachine.cpp.

virtual EMachineType get_classifier_type ( )
virtualinherited

get classifier type

Returns
classifier type CT_BAGGING

Reimplemented from CMachine.

Definition at line 110 of file BaggingMachine.h.

CCombinationRule * get_combination_rule ( ) const
inherited

Get the combination rule that is used for aggregating the results

Returns
CCombinationRule

Definition at line 252 of file BaggingMachine.cpp.

SGVector< bool > get_feature_types ( ) const

get feature types of various features

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

Definition at line 110 of file RandomForest.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.

CLabels * get_labels ( )
virtualinherited

get labels

Returns
labels

Definition at line 76 of file Machine.cpp.

CMachine * get_machine ( ) const
inherited

Get machine for bagging

Returns
machine that is being used in bagging

Definition at line 219 of file BaggingMachine.cpp.

EProblemType get_machine_problem_type ( ) const
virtual

get problem type - multiclass classification or regression

Returns
PT_MULTICLASS or PT_REGRESSION

Reimplemented from CMachine.

Definition at line 116 of file RandomForest.cpp.

float64_t get_max_train_time ( )
inherited

get maximum training time

Returns
maximum training time

Definition at line 87 of file Machine.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
RandomForest

Reimplemented from CBaggingMachine.

Definition at line 85 of file RandomForest.h.

int32_t get_num_bags ( ) const
inherited

Get number of bags/machines

Returns
number of bags

Definition at line 204 of file BaggingMachine.cpp.

int32_t get_num_random_features ( ) const

get number of random features to be chosen during node splits

Returns
number of randomly chosen features during each node split

Definition at line 136 of file RandomForest.cpp.

float64_t get_oob_error ( CEvaluation *  eval) const
inherited

get out-of-bag error CombinationRule is used for combining the predictions.

Parameters
evalEvaluation method to use for calculating the error
Returns
out-of-bag error.

Definition at line 258 of file BaggingMachine.cpp.

CDynamicArray< index_t > * get_oob_indices ( const SGVector< index_t > &  in_bag)
protectedinherited

get the vector of indices for feature vectors that are out of bag

Parameters
in_bagvector of indices that are in bag. NOTE: in_bag is a randomly generated with replacement
Returns
the vector of indices

Definition at line 338 of file BaggingMachine.cpp.

ESolverType get_solver_type ( )
inherited

get solver type

Returns
solver

Definition at line 102 of file Machine.cpp.

SGVector< float64_t > get_weights ( ) const

get weights

Returns
weights of training feature vectors

Definition at line 99 of file RandomForest.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.

virtual bool is_label_valid ( CLabels *  lab) const
protectedvirtualinherited

check whether the labels is valid.

Subclasses can override this to implement their check of label types.

Parameters
labthe labels being checked, guaranteed to be non-NULL

Reimplemented in CNeuralNetwork, CCARTree, CCHAIDTree, CGaussianProcessRegression, and CBaseMulticlassMachine.

Definition at line 348 of file Machine.h.

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 register_parameters ( )
protectedinherited

Register paramaters

Definition at line 184 of file BaggingMachine.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_bag_size ( int32_t  bag_size)
virtualinherited

Set number of feature vectors to use for each bag/machine

Parameters
bag_sizenumber of vectors to use for a bag

Definition at line 209 of file BaggingMachine.cpp.

void set_combination_rule ( CCombinationRule *  rule)
inherited

Set the combination rule to use for aggregating the classification results

Parameters
rulecombination rule

Definition at line 245 of file BaggingMachine.cpp.

void set_feature_types ( SGVector< bool >  ft)

set feature types of various features

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

Definition at line 104 of file RandomForest.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_labels ( CLabels *  lab)
virtualinherited

set labels

Parameters
lablabels

Reimplemented in CNeuralNetwork, CGaussianProcessMachine, CCARTree, CStructuredOutputMachine, CRelaxedTree, and CMulticlassMachine.

Definition at line 65 of file Machine.cpp.

void set_machine ( CMachine *  machine)
virtual

machine is set to modified CART(RandomCART) and cannot be changed

Parameters
machinethe machine to use for bagging

Reimplemented from CBaggingMachine.

Definition at line 89 of file RandomForest.cpp.

void set_machine_parameters ( CMachine *  m,
SGVector< index_t >  idx 
)
protectedvirtual

sets parameters of CARTree - sets machine labels and weights here

Parameters
mmachine
idxindices of training vectors chosen in current bag

Reimplemented from CBaggingMachine.

Definition at line 142 of file RandomForest.cpp.

void set_machine_problem_type ( EProblemType  mode)

set problem type - multiclass classification or regression

Parameters
modeEProblemType PT_MULTICLASS or PT_REGRESSION

Definition at line 122 of file RandomForest.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_num_bags ( int32_t  num_bags)
inherited

Set number of bags/machine to create

Parameters
num_bagsnumber of bags

Definition at line 199 of file BaggingMachine.cpp.

void set_num_random_features ( int32_t  rand_featsize)

set number of random features to be chosen during node splits

Parameters
rand_featsizenumber of randomly chosen features during each node split

Definition at line 128 of file RandomForest.cpp.

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 >  weights)

set weights

Parameters
weightsof training feature vectors

Definition at line 94 of file RandomForest.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

Stores feature data of underlying model. After this method has been called, it is possible to change the machine's feature data and call apply(), which is then performed on the training feature data that is part of the machine's model.

Base method, has to be implemented in order to allow cross-validation and model selection.

NOT IMPLEMENTED! Has to be done in subclasses

Reimplemented in CKernelMachine, CKNN, CLinearMulticlassMachine, CTreeMachine< T >, CTreeMachine< ConditionalProbabilityTreeNodeData >, CTreeMachine< RelaxedTreeNodeData >, CTreeMachine< id3TreeNodeData >, CTreeMachine< VwConditionalProbabilityTreeNodeData >, CTreeMachine< CARTreeNodeData >, CTreeMachine< C45TreeNodeData >, CTreeMachine< CHAIDTreeNodeData >, CTreeMachine< NbodyTreeNodeData >, CLinearMachine, CGaussianProcessMachine, CHierarchical, CDistanceMachine, CKernelMulticlassMachine, and CLinearStructuredOutputMachine.

Definition at line 335 of file Machine.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.

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

Parameters
datatraining data (parameter can be avoided if distance or kernel-based classifiers are used and distance/kernels are initialized with train data)

NOT IMPLEMENTED!

Returns
whether training was successful

Reimplemented from CMachine.

Definition at line 104 of file BaggingMachine.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_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

SGIO* io
inherited

io

Definition at line 369 of file SGObject.h.

SGVector<bool> m_all_oob_idx
protectedinherited

indices of all feature vectors that are out of bag

Definition at line 177 of file BaggingMachine.h.

int32_t m_bag_size
protectedinherited

number of vectors to use from the training features

Definition at line 171 of file BaggingMachine.h.

CDynamicObjectArray* m_bags
protectedinherited

bags array

Definition at line 159 of file BaggingMachine.h.

CCombinationRule* m_combination_rule
protectedinherited

combination rule to use

Definition at line 174 of file BaggingMachine.h.

bool m_data_locked
protectedinherited

whether data is locked

Definition at line 370 of file Machine.h.

CFeatures* m_features
protectedinherited

features to train on

Definition at line 162 of file BaggingMachine.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.

CLabels* m_labels
protectedinherited

labels

Definition at line 361 of file Machine.h.

CMachine* m_machine
protectedinherited

machine to use for bagging

Definition at line 165 of file BaggingMachine.h.

float64_t m_max_train_time
protectedinherited

maximum training time

Definition at line 358 of file Machine.h.

Parameter* m_model_selection_parameters
inherited

model selection parameters

Definition at line 381 of file SGObject.h.

int32_t m_num_bags
protectedinherited

number of bags to create

Definition at line 168 of file BaggingMachine.h.

CDynamicObjectArray* m_oob_indices
protectedinherited

array of oob indices

Definition at line 180 of file BaggingMachine.h.

Parameter* m_parameters
inherited

parameters

Definition at line 378 of file SGObject.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.

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