SHOGUN  4.2.0
 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
CDependenceMaximization Class Referenceabstract

Detailed Description

Class CDependenceMaximization, base class for all feature selection preprocessors which select a subset of features that shows maximum dependence between the features and the labels. This is done via an implementation of CIndependenceTest, m_estimator inside compute_measures() (see class documentation of CFeatureSelection), which performs a statistical test for a given feature \(\mathbf{X}_i\) from the set of features \(\mathbf{X}\), and the labels \(\mathbf{Y}\). The test checks

\[ \textbf{H}_0 : P\left(\mathbf{X}\setminus \mathbf{X}_i, \mathbf{Y}\right) =P\left(\mathbf{X}\setminus \mathbf{X}_i\right)P\left(\mathbf{Y}\right) \]

The test statistic is then used as a measure which signifies the independence between the rest of the features and the labels - higher the value of the test statistic, greater the dependency between the rest of the features and the class labels, and therefore lesser significant the current feature becomes. Therefore, highest scoring features are removed. The removal policy thus can only be shogun::N_LARGEST and shogun::PERCENTILE_LARGEST and it can be set via set_policy() call. remove_feats() method handles the removal of features based on the specified policy.

The estimator cannot be set via user interface, rather its subclasses initialize this estimator with appropriate instances internally.

This class also overrides set_labels() method to create a feature object from the labels and sets this as features \(\mathbf{Y}\sim q\) to the estimator which is required to compute the measure.

Definition at line 70 of file DependenceMaximization.h.

Inheritance diagram for CDependenceMaximization:
[legend]

Public Member Functions

 CDependenceMaximization ()
 
virtual ~CDependenceMaximization ()
 
virtual float64_t compute_measures (CFeatures *features, index_t idx)
 
virtual CFeaturesremove_feats (CFeatures *features, SGVector< index_t > ranks)
 
virtual void set_policy (EFeatureRemovalPolicy policy)
 
virtual void set_algorithm (EFeatureSelectionAlgorithm algorithm)=0
 
virtual bool init (CFeatures *features)
 
virtual void set_labels (CLabels *labels)
 
virtual const char * get_name () const
 
virtual CFeaturesapply (CFeatures *features)
 
SGVector< index_tget_selected_feats ()
 
virtual EFeatureClass get_feature_class ()
 
virtual EFeatureType get_feature_type ()
 
virtual EPreprocessorType get_type () const
 
void set_target_dim (index_t target_dim)
 
index_t get_target_dim () const
 
EFeatureSelectionAlgorithm get_algorithm () const
 
EFeatureRemovalPolicy get_policy () const
 
void set_num_remove (index_t num_remove)
 
index_t get_num_remove () const
 
CLabelsget_labels () const
 
virtual void cleanup ()
 
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
 

Protected Member Functions

virtual CFeaturescreate_transformed_copy (CFeatures *features, index_t idx)
 
virtual CFeaturesapply_backward_elimination (CFeatures *features)
 
virtual void precompute ()
 
virtual void adapt_params (CFeatures *features)
 
index_t get_num_features (CFeatures *features) 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

CIndependenceTestm_estimator
 
CFeaturesm_labels_feats
 
index_t m_target_dim
 
EFeatureSelectionAlgorithm m_algorithm
 
EFeatureRemovalPolicy m_policy
 
index_t m_num_remove
 
CLabelsm_labels
 
CSubsetStackm_subset
 

Constructor & Destructor Documentation

Default constructor

Definition at line 40 of file DependenceMaximization.cpp.

Destructor

Definition at line 57 of file DependenceMaximization.cpp.

Member Function Documentation

virtual void adapt_params ( CFeatures features)
protectedvirtualinherited

Tunes the parameters which are required to compute the measure based on current features. Overridden in the subclasses. Here it does nothing.

Parameters
featuresthe features based on which parameters are needed to be tuned for computing measures
virtual CFeatures* apply ( CFeatures features)
virtualinherited

Generic interface for applying the feature selection preprocessor. Acts as a wrapper which decides which actual method to call based on the algorithm specified.

Parameters
featuresthe input features
Returns
the result feature object after applying the preprocessor

Implements CPreprocessor.

virtual CFeatures* apply_backward_elimination ( CFeatures features)
protectedvirtualinherited

Applies backward elimination algorithm for performing feature selection. After performing necessary precomputing (defined by subclasses), it iteratively eliminates a number of features based on a measure until target dimension is reached.

Parameters
featuresthe input features
Returns
the result feature object after applying the preprocessor
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.

virtual void cleanup ( )
virtualinherited

performs cleanup

Implements CPreprocessor.

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.

float64_t compute_measures ( CFeatures features,
index_t  idx 
)
virtual

Method that computes the measures using test statistic computed by an instance of CIndependenceTest wiht the provided features and the labels

Parameters
featuresthe features on which the measure has to be computed
idxthe index that decides which features should we compute the measure on
Returns
the measure based on which features are selected

Implements CFeatureSelection< float64_t >.

Definition at line 106 of file DependenceMaximization.cpp.

CFeatures * create_transformed_copy ( CFeatures features,
index_t  idx 
)
protectedvirtual

Helper method which removes the dimension specified via the index. It copies the rest of the features into a separate object via copy_dimension_subset() call.

Parameters
featuresthe features
idxindex of the dimension which is required to be removed
Returns
a new feature object with the specified dimension removed

Definition at line 78 of file DependenceMaximization.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.

EFeatureSelectionAlgorithm get_algorithm ( ) const
inherited
Returns
the feature removal algorithm being used
virtual EFeatureClass get_feature_class ( )
virtualinherited
Returns
the feature class, shogun::C_ANY

Implements CPreprocessor.

virtual EFeatureType get_feature_type ( )
virtualinherited
Returns
feature type

Implements CPreprocessor.

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 ( ) const
inherited
Returns
the labels
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
Returns
the class name

Reimplemented from CFeatureSelection< float64_t >.

Reimplemented in CBAHSIC, and CKernelDependenceMaximization.

Definition at line 136 of file DependenceMaximization.h.

index_t get_num_features ( CFeatures features) const
protectedinherited

Returns the number of features of the provided feature object. Since the number of features doesn't make sense for all types of features, this helper method checks whether obtaining a num_features is possible and then calls get_num_features() on those features after proper type-cast

Parameters
featuresthe feature object
Returns
the number of features
index_t get_num_remove ( ) const
inherited
Returns
number or percentage of features removed in each iteration
EFeatureRemovalPolicy get_policy ( ) const
inherited
Returns
the feature removal policy being used
SGVector<index_t> get_selected_feats ( )
inherited
Returns
indices of selected features
index_t get_target_dim ( ) const
inherited
Returns
the target dimension
virtual EPreprocessorType get_type ( ) const
virtualinherited
Returns
the preprocessor type

Implements CPreprocessor.

Reimplemented in CBAHSIC.

bool init ( CFeatures features)
virtual

Initialize preprocessor from features

Parameters
featuresthe features
Returns
true if init was successful

Implements CPreprocessor.

Definition at line 63 of file DependenceMaximization.cpp.

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 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 precompute ( )
protectedvirtualinherited

Performs the tasks which can be computed beforehand before the actual algorithm begins. This method is overridden in the subclasses. Here it does nothing.

Reimplemented in CKernelDependenceMaximization.

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.

CFeatures * remove_feats ( CFeatures features,
SGVector< index_t ranks 
)
virtual

Method which handles the removal of features based on removal policy. see documentation of CFeatureSelection. For dependence maximization approach, the highest scoring features are removed. Therefore, only m_policy can only be shogun::N_LARGEST, shogun::PERCENTILE_LARGEST. See set_policy() method for specifying the exact policy

Parameters
featuresthe features object from which specific features has to be removed
ranksthe ranks of the features based on their measures, 0 being the lowest rank which corresponds to smallest measure.
Returns
the feature object after removal of features based on the policy

Implements CFeatureSelection< float64_t >.

Definition at line 130 of file DependenceMaximization.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.

virtual void set_algorithm ( EFeatureSelectionAlgorithm  algorithm)
pure virtual

Abstract method which is overridden in the subclasses to set accepted feature selection algorithm

Parameters
algorithmthe feature selection algorithm to use

Implements CFeatureSelection< float64_t >.

Implemented in CKernelDependenceMaximization, and CBAHSIC.

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 labels)
virtual

Setter for labels. This method is overridden to internally convert the labels to a dense feature object and set this feature in the independence test estimator. These labels serve as samples \(\mathbf{Y}\sim q\) in the independence test

Parameters
labelsthe labels

Reimplemented from CFeatureSelection< float64_t >.

Definition at line 187 of file DependenceMaximization.cpp.

void set_num_remove ( index_t  num_remove)
inherited

Use this method to set the number or percentile of features to be removed in each iteration.

Parameters
num_removenumber or percentage of features to be removed in each iteration
void set_policy ( EFeatureRemovalPolicy  policy)
virtual
Parameters
policyfeature removal policy

Implements CFeatureSelection< float64_t >.

Definition at line 179 of file DependenceMaximization.cpp.

void set_target_dim ( index_t  target_dim)
inherited
Parameters
target_dimthe target dimension to achieve
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.

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.

EFeatureSelectionAlgorithm m_algorithm
protectedinherited

Wrapper algorithm for feature selection

Definition at line 302 of file FeatureSelection.h.

CIndependenceTest* m_estimator
protected

The estimator for performing statistical tests for independence which is used for computing measures

Definition at line 157 of file DependenceMaximization.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

The labels for the feature vectors

Definition at line 316 of file FeatureSelection.h.

CFeatures* m_labels_feats
protected

The feature for the labels

Definition at line 160 of file DependenceMaximization.h.

Parameter* m_model_selection_parameters
inherited

model selection parameters

Definition at line 381 of file SGObject.h.

index_t m_num_remove
protectedinherited

Number or percentage of features to be removed. When the policy is set as shogun::N_SMALLEST or shogun::N_LARGEST, this number decides how many features in an iteration. For shogun::PERCENTILE_SMALLEST or shogun::PERCENTILE_LARGEST, this decides the percentage of current number of features to be removed in each iteration

Definition at line 313 of file FeatureSelection.h.

Parameter* m_parameters
inherited

parameters

Definition at line 378 of file SGObject.h.

EFeatureRemovalPolicy m_policy
protectedinherited

Feature removal policy

Definition at line 305 of file FeatureSelection.h.

CSubsetStack* m_subset
protectedinherited

The indices of features that are selected

Definition at line 319 of file FeatureSelection.h.

index_t m_target_dim
protectedinherited

Target dimension

Definition at line 299 of file FeatureSelection.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