SHOGUN
4.2.0
|
Class CBAHSIC, that extends CKernelDependenceMaximization and uses HSIC [1] to compute dependence measures for feature selection using a backward elimination approach as described in [1]. This class serves as a convenience class that initializes the CDependenceMaximization::m_estimator with an instance of CHSIC and allows only shogun::BACKWARD_ELIMINATION algorithm to use which is set internally. Therefore, trying to use other algorithms by set_algorithm() will not work. Plese see the class documentation of CHSIC and [2] for more details on mathematical description of HSIC.
Refrences: [1] Song, Le and Bedo, Justin and Borgwardt, Karsten M. and Gretton, Arthur and Smola, Alex. (2007). Gene Selection via the BAHSIC Family of Algorithms. Journal Bioinformatics. Volume 23 Issue Pages i490-i498. Oxford University Press Oxford, UK [2]: Gretton, A., Fukumizu, K., Teo, C., & Song, L. (2008). A kernel statistical test of independence. Advances in Neural Information Processing Systems, 1-8.
Public Member Functions | |
CBAHSIC () | |
virtual | ~CBAHSIC () |
virtual void | set_algorithm (EFeatureSelectionAlgorithm algorithm) |
virtual EPreprocessorType | get_type () const |
virtual const char * | get_name () const |
void | set_kernel_features (CKernel *kernel) |
CKernel * | get_kernel_features () const |
void | set_kernel_labels (CKernel *kernel) |
CKernel * | get_kernel_labels () const |
virtual float64_t | compute_measures (CFeatures *features, index_t idx) |
virtual CFeatures * | remove_feats (CFeatures *features, SGVector< index_t > ranks) |
virtual void | set_policy (EFeatureRemovalPolicy policy) |
virtual bool | init (CFeatures *features) |
virtual void | set_labels (CLabels *labels) |
virtual CFeatures * | apply (CFeatures *features) |
SGVector< index_t > | get_selected_feats () |
virtual EFeatureClass | get_feature_class () |
virtual EFeatureType | get_feature_type () |
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 |
CLabels * | get_labels () const |
virtual void | cleanup () |
virtual CSGObject * | shallow_copy () const |
virtual CSGObject * | deep_copy () const |
virtual bool | is_generic (EPrimitiveType *generic) const |
template<class T > | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
void | unset_generic () |
virtual void | print_serializable (const char *prefix="") |
virtual bool | save_serializable (CSerializableFile *file, const char *prefix="") |
virtual bool | load_serializable (CSerializableFile *file, const char *prefix="") |
void | set_global_io (SGIO *io) |
SGIO * | get_global_io () |
void | set_global_parallel (Parallel *parallel) |
Parallel * | get_global_parallel () |
void | set_global_version (Version *version) |
Version * | get_global_version () |
SGStringList< char > | get_modelsel_names () |
void | print_modsel_params () |
char * | get_modsel_param_descr (const char *param_name) |
index_t | get_modsel_param_index (const char *param_name) |
void | build_gradient_parameter_dictionary (CMap< TParameter *, CSGObject * > *dict) |
bool | has (const std::string &name) const |
template<typename T > | |
bool | has (const Tag< T > &tag) const |
template<typename T , typename U = void> | |
bool | has (const std::string &name) const |
template<typename T > | |
void | set (const Tag< T > &_tag, const T &value) |
template<typename T , typename U = void> | |
void | set (const std::string &name, const T &value) |
template<typename T > | |
T | get (const Tag< T > &_tag) const |
template<typename T , typename U = void> | |
T | get (const std::string &name) const |
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 | precompute () |
virtual CFeatures * | create_transformed_copy (CFeatures *features, index_t idx) |
virtual CFeatures * | apply_backward_elimination (CFeatures *features) |
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) |
template<typename T > | |
void | register_param (Tag< T > &_tag, const T &value) |
template<typename T > | |
void | register_param (const std::string &name, const T &value) |
CBAHSIC | ( | ) |
Default constructor
Definition at line 36 of file BAHSIC.cpp.
|
virtual |
Destructor
Definition at line 48 of file BAHSIC.cpp.
|
protectedvirtualinherited |
Tunes the parameters which are required to compute the measure based on current features. Overridden in the subclasses. Here it does nothing.
features | the features based on which parameters are needed to be tuned for computing measures |
Generic interface for applying the feature selection preprocessor. Acts as a wrapper which decides which actual method to call based on the algorithm specified.
features | the input features |
Implements CPreprocessor.
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.
features | the input features |
|
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.
dict | dictionary of parameters to be built. |
Definition at line 630 of file SGObject.cpp.
|
virtualinherited |
performs cleanup
Implements CPreprocessor.
|
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.
Definition at line 747 of file SGObject.cpp.
Method that computes the measures using test statistic computed by an instance of CIndependenceTest wiht the provided features and the labels
features | the features on which the measure has to be computed |
idx | the index that decides which features should we compute the measure on |
Implements CFeatureSelection< float64_t >.
Definition at line 106 of file DependenceMaximization.cpp.
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.
features | the features |
idx | index of the dimension which is required to be removed |
Definition at line 78 of file DependenceMaximization.cpp.
|
virtualinherited |
A deep copy. All the instance variables will also be copied.
Definition at line 231 of file SGObject.cpp.
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.
other | object to compare with |
accuracy | accuracy to use for comparison (optional) |
tolerant | allows linient check on float equality (within accuracy) |
Definition at line 651 of file SGObject.cpp.
|
inherited |
Getter for a class parameter, identified by a Tag. Throws an exception if the class does not have such a parameter.
_tag | name and type information of parameter |
Definition at line 367 of file SGObject.h.
|
inherited |
Getter for a class parameter, identified by a name. Throws an exception if the class does not have such a parameter.
name | name of the parameter |
Definition at line 388 of file SGObject.h.
|
inherited |
|
virtualinherited |
Implements CPreprocessor.
|
virtualinherited |
Implements CPreprocessor.
|
inherited |
|
inherited |
|
inherited |
|
inherited |
Definition at line 131 of file KernelDependenceMaximization.cpp.
|
inherited |
Definition at line 137 of file KernelDependenceMaximization.cpp.
|
inherited |
|
inherited |
Definition at line 531 of file SGObject.cpp.
|
inherited |
Returns description of a given parameter string, if it exists. SG_ERROR otherwise
param_name | name of the parameter |
Definition at line 555 of file SGObject.cpp.
|
inherited |
Returns index of model selection parameter with provided index
param_name | name of model selection parameter |
Definition at line 568 of file SGObject.cpp.
|
virtual |
Reimplemented from CKernelDependenceMaximization.
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
features | the feature object |
|
inherited |
|
inherited |
|
inherited |
|
virtual |
Reimplemented from CFeatureSelection< float64_t >.
Definition at line 59 of file BAHSIC.cpp.
|
inherited |
Checks if object has a class parameter identified by a name.
name | name of the parameter |
Definition at line 289 of file SGObject.h.
|
inherited |
Checks if object has a class parameter identified by a Tag.
tag | tag of the parameter containing name and type information |
Definition at line 301 of file SGObject.h.
|
inherited |
Checks if a type exists for a class parameter identified by a name.
name | name of the parameter |
Definition at line 312 of file SGObject.h.
|
virtualinherited |
Initialize preprocessor from features
features | the features |
Implements CPreprocessor.
Definition at line 63 of file DependenceMaximization.cpp.
|
virtualinherited |
If the SGSerializable is a class template then TRUE will be returned and GENERIC is set to the type of the generic.
generic | set to the type of the generic if returning TRUE |
Definition at line 329 of file SGObject.cpp.
|
virtualinherited |
Load this object from file. If it will fail (returning FALSE) then this object will contain inconsistent data and should not be used!
file | where to load from |
prefix | prefix for members |
Definition at line 402 of file SGObject.cpp.
|
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.
ShogunException | will be thrown if an error occurs. |
Reimplemented in CKernel, CWeightedDegreePositionStringKernel, CList, CAlphabet, CLinearHMM, CGaussianKernel, CInverseMultiQuadricKernel, CCircularKernel, and CExponentialKernel.
Definition at line 459 of file SGObject.cpp.
|
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.
ShogunException | will be thrown if an error occurs. |
Reimplemented in CDynamicArray< T >, CDynamicArray< float64_t >, CDynamicArray< float32_t >, CDynamicArray< int32_t >, CDynamicArray< char >, CDynamicArray< bool >, and CDynamicObjectArray.
Definition at line 454 of file SGObject.cpp.
|
virtualinherited |
Definition at line 295 of file SGObject.cpp.
|
protectedvirtualinherited |
Precomputes the kernel on labels and replaces the m_kernel_labels with an instance of CCustomKernel. Labels features are set via CDependenceMaximization::set_labels call.
Reimplemented from CFeatureSelection< float64_t >.
Definition at line 60 of file KernelDependenceMaximization.cpp.
|
inherited |
prints all parameter registered for model selection and their type
Definition at line 507 of file SGObject.cpp.
|
virtualinherited |
prints registered parameters out
prefix | prefix for members |
Definition at line 341 of file SGObject.cpp.
|
protectedinherited |
Registers a class parameter which is identified by a tag. This enables the parameter to be modified by set() and retrieved by get(). Parameters can be registered in the constructor of the class.
_tag | name and type information of parameter |
value | value of the parameter |
Definition at line 439 of file SGObject.h.
|
protectedinherited |
Registers a class parameter which is identified by a name. This enables the parameter to be modified by set() and retrieved by get(). Parameters can be registered in the constructor of the class.
name | name of the parameter |
value | value of the parameter along with type information |
Definition at line 452 of file SGObject.h.
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
features | the features object from which specific features has to be removed |
ranks | the ranks of the features based on their measures, 0 being the lowest rank which corresponds to smallest measure. |
Implements CFeatureSelection< float64_t >.
Definition at line 130 of file DependenceMaximization.cpp.
|
virtualinherited |
Save this object to file.
file | where to save the object; will be closed during returning if PREFIX is an empty string. |
prefix | prefix for members |
Definition at line 347 of file SGObject.cpp.
|
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.
ShogunException | will be thrown if an error occurs. |
Reimplemented in CKernel.
Definition at line 469 of file SGObject.cpp.
|
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.
ShogunException | will be thrown if an error occurs. |
Reimplemented in CKernel, CDynamicArray< T >, CDynamicArray< float64_t >, CDynamicArray< float32_t >, CDynamicArray< int32_t >, CDynamicArray< char >, CDynamicArray< bool >, and CDynamicObjectArray.
Definition at line 464 of file SGObject.cpp.
|
inherited |
Setter for a class parameter, identified by a Tag. Throws an exception if the class does not have such a parameter.
_tag | name and type information of parameter |
value | value of the parameter |
Definition at line 328 of file SGObject.h.
|
inherited |
Setter for a class parameter, identified by a name. Throws an exception if the class does not have such a parameter.
name | name of the parameter |
value | value of the parameter along with type information |
Definition at line 354 of file SGObject.h.
|
virtual |
Since only shogun::BACKWARD_ELIMINATION algorithm is applicable for BAHSIC, and this is set internally, this method is overridden to prevent this to be set from public API.
algorithm | the feature selection algorithm to use |
Implements CKernelDependenceMaximization.
Definition at line 53 of file BAHSIC.cpp.
|
inherited |
Definition at line 74 of file SGObject.cpp.
|
inherited |
Definition at line 79 of file SGObject.cpp.
|
inherited |
Definition at line 84 of file SGObject.cpp.
|
inherited |
Definition at line 89 of file SGObject.cpp.
|
inherited |
Definition at line 94 of file SGObject.cpp.
|
inherited |
Definition at line 99 of file SGObject.cpp.
|
inherited |
Definition at line 104 of file SGObject.cpp.
|
inherited |
Definition at line 109 of file SGObject.cpp.
|
inherited |
Definition at line 114 of file SGObject.cpp.
|
inherited |
Definition at line 119 of file SGObject.cpp.
|
inherited |
Definition at line 124 of file SGObject.cpp.
|
inherited |
Definition at line 129 of file SGObject.cpp.
|
inherited |
Definition at line 134 of file SGObject.cpp.
|
inherited |
Definition at line 139 of file SGObject.cpp.
|
inherited |
Definition at line 144 of file SGObject.cpp.
|
inherited |
set generic type to T
|
inherited |
|
inherited |
set the parallel object
parallel | parallel object to use |
Definition at line 274 of file SGObject.cpp.
|
inherited |
set the version object
version | version object to use |
Definition at line 316 of file SGObject.cpp.
|
inherited |
kernel | the kernel for features (data) |
Definition at line 99 of file KernelDependenceMaximization.cpp.
|
inherited |
kernel | the kernel for labels |
Definition at line 115 of file KernelDependenceMaximization.cpp.
|
virtualinherited |
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
labels | the labels |
Reimplemented from CFeatureSelection< float64_t >.
Definition at line 187 of file DependenceMaximization.cpp.
|
inherited |
Use this method to set the number or percentile of features to be removed in each iteration.
num_remove | number or percentage of features to be removed in each iteration |
|
virtualinherited |
policy | feature removal policy |
Implements CFeatureSelection< float64_t >.
Definition at line 179 of file DependenceMaximization.cpp.
|
inherited |
target_dim | the target dimension to achieve |
|
virtualinherited |
A shallow copy. All the SGObject instance variables will be simply assigned and SG_REF-ed.
Reimplemented in CGaussianKernel.
Definition at line 225 of file SGObject.cpp.
|
inherited |
unset generic type
this has to be called in classes specializing a template class
Definition at line 336 of file SGObject.cpp.
|
virtualinherited |
Updates the hash of current parameter combination
Definition at line 281 of file SGObject.cpp.
|
inherited |
io
Definition at line 537 of file SGObject.h.
|
protectedinherited |
Wrapper algorithm for feature selection
Definition at line 302 of file FeatureSelection.h.
|
protectedinherited |
The estimator for performing statistical tests for independence which is used for computing measures
Definition at line 157 of file DependenceMaximization.h.
|
inherited |
parameters wrt which we can compute gradients
Definition at line 552 of file SGObject.h.
|
inherited |
Hash of parameter values
Definition at line 555 of file SGObject.h.
|
protectedinherited |
The kernel for data (features) to be used in CKernelIndependenceTest
Definition at line 93 of file KernelDependenceMaximization.h.
|
protectedinherited |
The kernel for labels to be used in CKernelIndependenceTest
Definition at line 96 of file KernelDependenceMaximization.h.
|
protectedinherited |
The labels for the feature vectors
Definition at line 316 of file FeatureSelection.h.
|
protectedinherited |
The feature for the labels
Definition at line 160 of file DependenceMaximization.h.
|
inherited |
model selection parameters
Definition at line 549 of file SGObject.h.
|
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.
|
inherited |
parameters
Definition at line 546 of file SGObject.h.
|
protectedinherited |
Feature removal policy
Definition at line 305 of file FeatureSelection.h.
|
protectedinherited |
The indices of features that are selected
Definition at line 319 of file FeatureSelection.h.
|
protectedinherited |
Target dimension
Definition at line 299 of file FeatureSelection.h.
|
inherited |
parallel
Definition at line 540 of file SGObject.h.
|
inherited |
version
Definition at line 543 of file SGObject.h.