Public Member Functions | Public Attributes | Protected Member Functions | Protected Attributes

CGMM Class Reference


Detailed Description

Gaussian Mixture Model interface.

Takes input of number of Gaussians to fit and a covariance type to use. Parameter estimation is done using either the Expectation-Maximization or Split-Merge Expectation-Maximization algorithms. To estimate the GMM parameters, the train(...) method has to be run to set the training data and then either train_em(...) or train_smem(...) to do the actual estimation. The EM algorithm is described here: http://en.wikipedia.org/wiki/Expectation-maximization_algorithm The SMEM algorithm is described here: http://mlg.eng.cam.ac.uk/zoubin/papers/uedanc.pdf

Definition at line 40 of file GMM.h.

Inheritance diagram for CGMM:
Inheritance graph
[legend]

List of all members.

Public Member Functions

 CGMM ()
 CGMM (int32_t n, ECovType cov_type=FULL)
 CGMM (vector< CGaussian * > components, SGVector< float64_t > coefficients, bool copy=false)
virtual ~CGMM ()
void cleanup ()
virtual bool train (CFeatures *data=NULL)
float64_t train_em (float64_t min_cov=1e-9, int32_t max_iter=1000, float64_t min_change=1e-9)
float64_t train_smem (int32_t max_iter=100, int32_t max_cand=5, float64_t min_cov=1e-9, int32_t max_em_iter=1000, float64_t min_change=1e-9)
void max_likelihood (SGMatrix< float64_t > alpha, float64_t min_cov)
virtual int32_t get_num_model_parameters ()
virtual float64_t get_log_model_parameter (int32_t num_param)
virtual float64_t get_log_derivative (int32_t num_param, int32_t num_example)
virtual float64_t get_log_likelihood_example (int32_t num_example)
virtual float64_t get_likelihood_example (int32_t num_example)
virtual SGVector< float64_tget_nth_mean (int32_t num)
virtual void set_nth_mean (SGVector< float64_t > mean, int32_t num)
virtual SGMatrix< float64_tget_nth_cov (int32_t num)
virtual void set_nth_cov (SGMatrix< float64_t > cov, int32_t num)
virtual SGVector< float64_tget_coef ()
virtual void set_coef (const SGVector< float64_t > coefficients)
virtual vector< CGaussian * > get_comp ()
virtual void set_comp (vector< CGaussian * > components)
SGVector< float64_tsample ()
SGVector< float64_tcluster (SGVector< float64_t > point)
virtual const char * get_name () const
virtual int32_t get_num_relevant_model_parameters ()
virtual float64_t get_log_likelihood_sample ()
virtual SGVector< float64_tget_log_likelihood ()
virtual float64_t get_model_parameter (int32_t num_param)
virtual float64_t get_derivative (int32_t num_param, int32_t num_example)
virtual void set_features (CFeatures *f)
virtual CFeaturesget_features ()
virtual void set_pseudo_count (float64_t pseudo)
virtual float64_t get_pseudo_count ()
virtual CSGObjectshallow_copy () const
virtual CSGObjectdeep_copy () const
virtual bool is_generic (EPrimitiveType *generic) const
template<class T >
void set_generic ()
void unset_generic ()
virtual void print_serializable (const char *prefix="")
virtual bool save_serializable (CSerializableFile *file, const char *prefix="", int32_t param_version=VERSION_PARAMETER)
virtual bool load_serializable (CSerializableFile *file, const char *prefix="", int32_t param_version=VERSION_PARAMETER)
DynArray< TParameter * > * load_file_parameters (const SGParamInfo *param_info, int32_t file_version, CSerializableFile *file, const char *prefix="")
DynArray< TParameter * > * load_all_file_parameters (int32_t file_version, int32_t current_version, CSerializableFile *file, const char *prefix="")
void map_parameters (DynArray< TParameter * > *param_base, int32_t &base_version, DynArray< const SGParamInfo * > *target_param_infos)
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_parameter_dictionary (CMap< TParameter *, CSGObject * > &dict)

Public Attributes

SGIOio
Parallelparallel
Versionversion
Parameterm_parameters
Parameterm_model_selection_parameters
ParameterMapm_parameter_map
uint32_t m_hash

Protected Member Functions

virtual TParametermigrate (DynArray< TParameter * > *param_base, const SGParamInfo *target)
virtual void one_to_one_migration_prepare (DynArray< TParameter * > *param_base, const SGParamInfo *target, TParameter *&replacement, TParameter *&to_migrate, char *old_name=NULL)
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)
virtual bool update_parameter_hash ()

Protected Attributes

vector< CGaussian * > m_components
SGVector< float64_tm_coefficients
CFeaturesfeatures
float64_t pseudo_count

Constructor & Destructor Documentation

CGMM (  ) 

default constructor

Definition at line 28 of file GMM.cpp.

CGMM ( int32_t  n,
ECovType  cov_type = FULL 
)

constructor

Parameters:
n number of Gaussians
cov_type covariance type

Definition at line 33 of file GMM.cpp.

CGMM ( vector< CGaussian * >  components,
SGVector< float64_t coefficients,
bool  copy = false 
)

constructor

Parameters:
components GMM components
coefficients mixing coefficients
copy true if should be copied

Definition at line 49 of file GMM.cpp.

~CGMM (  )  [virtual]

Definition at line 98 of file GMM.cpp.


Member Function Documentation

void build_parameter_dictionary ( CMap< TParameter *, CSGObject * > &  dict  )  [inherited]

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

Parameters:
dict dictionary of parameters to be built.

Definition at line 1201 of file SGObject.cpp.

void cleanup (  ) 

cleanup

Definition at line 104 of file GMM.cpp.

SGVector< float64_t > cluster ( SGVector< float64_t point  ) 

cluster point

Returns:
log likelihood of belonging to clusters and the log likelihood of being generated by this GMM The length of the returned vector is number of components + 1

Definition at line 756 of file GMM.cpp.

virtual CSGObject* deep_copy (  )  const [virtual, inherited]

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

Definition at line 131 of file SGObject.h.

SGVector< float64_t > get_coef (  )  [virtual]

get coefficients

Returns:
coeffiecients

Definition at line 687 of file GMM.cpp.

vector< CGaussian * > get_comp (  )  [virtual]

get components

Returns:
components

Definition at line 697 of file GMM.cpp.

virtual float64_t get_derivative ( int32_t  num_param,
int32_t  num_example 
) [virtual, inherited]

get partial derivative of likelihood function

Parameters:
num_param partial derivative against which param
num_example which example
Returns:
derivative of likelihood function

Definition at line 129 of file Distribution.h.

virtual CFeatures* get_features (  )  [virtual, inherited]

get feature vectors

Returns:
feature vectors

Definition at line 160 of file Distribution.h.

SGIO * get_global_io (  )  [inherited]

get the io object

Returns:
io object

Definition at line 224 of file SGObject.cpp.

Parallel * get_global_parallel (  )  [inherited]

get the parallel object

Returns:
parallel object

Definition at line 259 of file SGObject.cpp.

Version * get_global_version (  )  [inherited]

get the version object

Returns:
version object

Definition at line 272 of file SGObject.cpp.

float64_t get_likelihood_example ( int32_t  num_example  )  [virtual]

compute likelihood for example

abstract base method

Parameters:
num_example which example
Returns:
likelihood for example

Reimplemented from CDistribution.

Definition at line 658 of file GMM.cpp.

float64_t get_log_derivative ( int32_t  num_param,
int32_t  num_example 
) [virtual]

get partial derivative of likelihood function (logarithmic)

Parameters:
num_param derivative against which param
num_example which example
Returns:
derivative of likelihood (logarithmic)

Implements CDistribution.

Definition at line 646 of file GMM.cpp.

SGVector< float64_t > get_log_likelihood (  )  [virtual, inherited]

compute log likelihood for each example

Returns:
log likelihood vector

Definition at line 37 of file Distribution.cpp.

float64_t get_log_likelihood_example ( int32_t  num_example  )  [virtual]

compute log likelihood for example

abstract base method

Parameters:
num_example which example
Returns:
log likelihood for example

Implements CDistribution.

Definition at line 652 of file GMM.cpp.

float64_t get_log_likelihood_sample (  )  [virtual, inherited]

compute log likelihood for whole sample

Returns:
log likelihood for whole sample

Definition at line 26 of file Distribution.cpp.

float64_t get_log_model_parameter ( int32_t  num_param  )  [virtual]

get model parameter (logarithmic)

Returns:
model parameter (logarithmic) if num_param < m_dim returns an element from the mean, else return an element from the covariance

Implements CDistribution.

Definition at line 639 of file GMM.cpp.

virtual float64_t get_model_parameter ( int32_t  num_param  )  [virtual, inherited]

get model parameter

Parameters:
num_param which param
Returns:
model parameter

Definition at line 118 of file Distribution.h.

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

Definition at line 1108 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_name name of the parameter
Returns:
description of the parameter

Definition at line 1132 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_name name of model selection parameter
Returns:
index of model selection parameter with provided name, -1 if there is no such

Definition at line 1145 of file SGObject.cpp.

virtual const char* get_name (  )  const [virtual]
Returns:
object name

Implements CSGObject.

Definition at line 212 of file GMM.h.

SGMatrix< float64_t > get_nth_cov ( int32_t  num  )  [virtual]

get nth covariance

Parameters:
num index of covariance to retrieve
Returns:
covariance

Definition at line 675 of file GMM.cpp.

SGVector< float64_t > get_nth_mean ( int32_t  num  )  [virtual]

get nth mean

Parameters:
num index of mean to retrieve
Returns:
mean

Definition at line 663 of file GMM.cpp.

int32_t get_num_model_parameters (  )  [virtual]

get number of parameters in model

Returns:
number of parameters in model

Implements CDistribution.

Definition at line 634 of file GMM.cpp.

int32_t get_num_relevant_model_parameters (  )  [virtual, inherited]

get number of parameters in model that are relevant, i.e. > ALMOST_NEG_INFTY

Returns:
number of relevant model parameters

Definition at line 50 of file Distribution.cpp.

virtual float64_t get_pseudo_count (  )  [virtual, inherited]

get pseudo count

Returns:
pseudo count

Definition at line 176 of file Distribution.h.

bool is_generic ( EPrimitiveType *  generic  )  const [virtual, inherited]

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

Parameters:
generic set to the type of the generic if returning TRUE
Returns:
TRUE if a class template.

Definition at line 278 of file SGObject.cpp.

DynArray< TParameter * > * load_all_file_parameters ( int32_t  file_version,
int32_t  current_version,
CSerializableFile file,
const char *  prefix = "" 
) [inherited]

maps all parameters of this instance to the provided file version and loads all parameter data from the file into an array, which is sorted (basically calls load_file_parameter(...) for all parameters and puts all results into a sorted array)

Parameters:
file_version parameter version of the file
current_version version from which mapping begins (you want to use VERSION_PARAMETER for this in most cases)
file file to load from
prefix prefix for members
Returns:
(sorted) array of created TParameter instances with file data

Definition at line 679 of file SGObject.cpp.

DynArray< TParameter * > * load_file_parameters ( const SGParamInfo param_info,
int32_t  file_version,
CSerializableFile file,
const char *  prefix = "" 
) [inherited]

loads some specified parameters from a file with a specified version The provided parameter info has a version which is recursively mapped until the file parameter version is reached. Note that there may be possibly multiple parameters in the mapping, therefore, a set of TParameter instances is returned

Parameters:
param_info information of parameter
file_version parameter version of the file, must be <= provided parameter version
file file to load from
prefix prefix for members
Returns:
new array with TParameter instances with the attached data

Definition at line 523 of file SGObject.cpp.

bool load_serializable ( CSerializableFile file,
const char *  prefix = "",
int32_t  param_version = VERSION_PARAMETER 
) [virtual, inherited]

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

Parameters:
file where to load from
prefix prefix for members
param_version (optional) a parameter version different to (this is mainly for testing, better do not use)
Returns:
TRUE if done, otherwise FALSE

Reimplemented in CModelSelectionParameters.

Definition at line 354 of file SGObject.cpp.

void load_serializable_post (  )  throw (ShogunException) [protected, virtual, inherited]

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

Exceptions:
ShogunException Will be thrown if an error occurres.

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

Definition at line 1033 of file SGObject.cpp.

void load_serializable_pre (  )  throw (ShogunException) [protected, virtual, inherited]

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

Exceptions:
ShogunException Will be thrown if an error occurres.

Definition at line 1028 of file SGObject.cpp.

void map_parameters ( DynArray< TParameter * > *  param_base,
int32_t &  base_version,
DynArray< const SGParamInfo * > *  target_param_infos 
) [inherited]

Takes a set of TParameter instances (base) with a certain version and a set of target parameter infos and recursively maps the base level wise to the current version using CSGObject::migrate(...). The base is replaced. After this call, the base version containing parameters should be of same version/type as the initial target parameter infos. Note for this to work, the migrate methods and all the internal parameter mappings have to match

Parameters:
param_base set of TParameter instances that are mapped to the provided target parameter infos
base_version version of the parameter base
target_param_infos set of SGParamInfo instances that specify the target parameter base

Definition at line 717 of file SGObject.cpp.

void max_likelihood ( SGMatrix< float64_t alpha,
float64_t  min_cov 
)

maximum likelihood estimation

Parameters:
alpha point assignment
min_cov minimum covariance

Definition at line 518 of file GMM.cpp.

TParameter * migrate ( DynArray< TParameter * > *  param_base,
const SGParamInfo target 
) [protected, virtual, inherited]

creates a new TParameter instance, which contains migrated data from the version that is provided. The provided parameter data base is used for migration, this base is a collection of all parameter data of the previous version. Migration is done FROM the data in param_base TO the provided param info Migration is always one version step. Method has to be implemented in subclasses, if no match is found, base method has to be called.

If there is an element in the param_base which equals the target, a copy of the element is returned. This represents the case when nothing has changed and therefore, the migrate method is not overloaded in a subclass

Parameters:
param_base set of TParameter instances to use for migration
target parameter info for the resulting TParameter
Returns:
a new TParameter instance with migrated data from the base of the type which is specified by the target parameter

Definition at line 923 of file SGObject.cpp.

void one_to_one_migration_prepare ( DynArray< TParameter * > *  param_base,
const SGParamInfo target,
TParameter *&  replacement,
TParameter *&  to_migrate,
char *  old_name = NULL 
) [protected, virtual, inherited]

This method prepares everything for a one-to-one parameter migration. One to one here means that only ONE element of the parameter base is needed for the migration (the one with the same name as the target). Data is allocated for the target (in the type as provided in the target SGParamInfo), and a corresponding new TParameter instance is written to replacement. The to_migrate pointer points to the single needed TParameter instance needed for migration. If a name change happened, the old name may be specified by old_name. In addition, the m_delete_data flag of to_migrate is set to true. So if you want to migrate data, the only thing to do after this call is converting the data in the m_parameter fields. If unsure how to use - have a look into an example for this. (base_migration_type_conversion.cpp for example)

Parameters:
param_base set of TParameter instances to use for migration
target parameter info for the resulting TParameter
replacement (used as output) here the TParameter instance which is returned by migration is created into
to_migrate the only source that is used for migration
old_name with this parameter, a name change may be specified

Definition at line 864 of file SGObject.cpp.

void print_modsel_params (  )  [inherited]

prints all parameter registered for model selection and their type

Definition at line 1084 of file SGObject.cpp.

void print_serializable ( const char *  prefix = ""  )  [virtual, inherited]

prints registered parameters out

Parameters:
prefix prefix for members

Definition at line 290 of file SGObject.cpp.

SGVector< float64_t > sample (  ) 

sample from model

Returns:
sample

Definition at line 742 of file GMM.cpp.

bool save_serializable ( CSerializableFile file,
const char *  prefix = "",
int32_t  param_version = VERSION_PARAMETER 
) [virtual, inherited]

Save this object to file.

Parameters:
file where to save the object; will be closed during returning if PREFIX is an empty string.
prefix prefix for members
param_version (optional) a parameter version different to (this is mainly for testing, better do not use)
Returns:
TRUE if done, otherwise FALSE

Reimplemented in CModelSelectionParameters.

Definition at line 296 of file SGObject.cpp.

void save_serializable_post (  )  throw (ShogunException) [protected, virtual, inherited]

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

Exceptions:
ShogunException Will be thrown if an error occurres.

Reimplemented in CKernel.

Definition at line 1043 of file SGObject.cpp.

void save_serializable_pre (  )  throw (ShogunException) [protected, virtual, inherited]

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

Exceptions:
ShogunException Will be thrown if an error occurres.

Reimplemented in CKernel.

Definition at line 1038 of file SGObject.cpp.

void set_coef ( const SGVector< float64_t coefficients  )  [virtual]

set coefficients

Parameters:
coefficients mixing coefficients

Definition at line 692 of file GMM.cpp.

void set_comp ( vector< CGaussian * >  components  )  [virtual]

set components

Parameters:
components Gaussian components

Definition at line 702 of file GMM.cpp.

virtual void set_features ( CFeatures f  )  [virtual, inherited]

set feature vectors

Parameters:
f new feature vectors

Definition at line 149 of file Distribution.h.

void set_generic< floatmax_t > (  )  [inherited]

set generic type to T

void set_global_io ( SGIO io  )  [inherited]

set the io object

Parameters:
io io object to use

Definition at line 217 of file SGObject.cpp.

void set_global_parallel ( Parallel parallel  )  [inherited]

set the parallel object

Parameters:
parallel parallel object to use

Definition at line 230 of file SGObject.cpp.

void set_global_version ( Version version  )  [inherited]

set the version object

Parameters:
version version object to use

Definition at line 265 of file SGObject.cpp.

void set_nth_cov ( SGMatrix< float64_t cov,
int32_t  num 
) [virtual]

set nth covariance

Parameters:
cov new covariance
num index of covariance to set

Definition at line 681 of file GMM.cpp.

void set_nth_mean ( SGVector< float64_t mean,
int32_t  num 
) [virtual]

set nth mean

Parameters:
mean new mean
num index mean to set

Definition at line 669 of file GMM.cpp.

virtual void set_pseudo_count ( float64_t  pseudo  )  [virtual, inherited]

set pseudo count

Parameters:
pseudo new pseudo count

Definition at line 170 of file Distribution.h.

virtual CSGObject* shallow_copy (  )  const [virtual, inherited]

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

Reimplemented in CGaussianKernel.

Definition at line 122 of file SGObject.h.

bool train ( CFeatures data = NULL  )  [virtual]

set training data for use with EM or SMEM

Parameters:
data training data
Returns:
true

init features with data if necessary and assure type is correct

Implements CDistribution.

Definition at line 113 of file GMM.cpp.

float64_t train_em ( float64_t  min_cov = 1e-9,
int32_t  max_iter = 1000,
float64_t  min_change = 1e-9 
)

learn model using EM

Parameters:
min_cov minimum covariance
max_iter maximum iterations
min_change minimum change in log likelihood
Returns:
log likelihood of training data

Definition at line 128 of file GMM.cpp.

float64_t train_smem ( int32_t  max_iter = 100,
int32_t  max_cand = 5,
float64_t  min_cov = 1e-9,
int32_t  max_em_iter = 1000,
float64_t  min_change = 1e-9 
)

learn model using SMEM

Parameters:
max_iter maximum SMEM iterations
max_cand maximum split-merge candidates
min_cov minimum covariance
max_em_iter maximum iterations for EM
min_change minimum change in log likelihood
Returns:
log likelihood of training data

Definition at line 199 of file GMM.cpp.

void unset_generic (  )  [inherited]

unset generic type

this has to be called in classes specializing a template class

Definition at line 285 of file SGObject.cpp.

bool update_parameter_hash (  )  [protected, virtual, inherited]

Updates the hash of current parameter combination.

Returns:
bool if parameter combination has changed since last update.

Definition at line 237 of file SGObject.cpp.


Member Data Documentation

CFeatures* features [protected, inherited]

feature vectors

Definition at line 180 of file Distribution.h.

SGIO* io [inherited]

io

Definition at line 462 of file SGObject.h.

Mixture coefficients

Definition at line 242 of file GMM.h.

vector<CGaussian*> m_components [protected]

Mixture components

Definition at line 240 of file GMM.h.

uint32_t m_hash [inherited]

Hash of parameter values

Definition at line 480 of file SGObject.h.

model selection parameters

Definition at line 474 of file SGObject.h.

map for different parameter versions

Definition at line 477 of file SGObject.h.

Parameter* m_parameters [inherited]

parameters

Definition at line 471 of file SGObject.h.

Parallel* parallel [inherited]

parallel

Definition at line 465 of file SGObject.h.

float64_t pseudo_count [protected, inherited]

pseudo count

Definition at line 182 of file Distribution.h.

Version* version [inherited]

version

Definition at line 468 of file SGObject.h.


The documentation for this class was generated from the following files:
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Defines

SHOGUN Machine Learning Toolbox - Documentation