SHOGUN
4.1.0
|
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
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) |
index_t | get_num_components () const |
CDistribution * | get_component (index_t index) const |
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_t > | get_nth_mean (int32_t num) |
virtual void | set_nth_mean (SGVector< float64_t > mean, int32_t num) |
virtual SGMatrix< float64_t > | get_nth_cov (int32_t num) |
virtual void | set_nth_cov (SGMatrix< float64_t > cov, int32_t num) |
virtual SGVector< float64_t > | get_coef () |
virtual void | set_coef (const SGVector< float64_t > coefficients) |
virtual vector< CGaussian * > | get_comp () |
virtual void | set_comp (vector< CGaussian * > components) |
SGVector< float64_t > | sample () |
SGVector< float64_t > | cluster (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_t > | get_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 SGVector< float64_t > | get_likelihood_for_all_examples () |
virtual void | set_features (CFeatures *f) |
virtual CFeatures * | get_features () |
virtual void | set_pseudo_count (float64_t pseudo) |
virtual float64_t | get_pseudo_count () |
virtual float64_t | update_params_em (float64_t *alpha_k, int32_t len) |
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 () |
Static Public Member Functions | |
static CDistribution * | obtain_from_generic (CSGObject *object) |
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 | 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 | |
vector< CGaussian * > | m_components |
SGVector< float64_t > | m_coefficients |
CFeatures * | features |
float64_t | pseudo_count |
|
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 597 of file SGObject.cpp.
|
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 714 of file SGObject.cpp.
|
virtualinherited |
A deep copy. All the instance variables will also be copied.
Definition at line 198 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 618 of file SGObject.cpp.
|
virtual |
CDistribution * get_component | ( | index_t | index | ) | const |
|
virtualinherited |
get partial derivative of likelihood function
num_param | partial derivative against which param |
num_example | which example |
Definition at line 134 of file Distribution.h.
|
virtualinherited |
|
inherited |
|
inherited |
|
inherited |
|
virtual |
compute likelihood for example
abstract base method
num_example | which example |
Reimplemented from CDistribution.
compute likelihood for all vectors in sample
Definition at line 65 of file Distribution.cpp.
|
virtual |
get partial derivative of likelihood function (logarithmic)
num_param | derivative against which param |
num_example | which example |
Implements CDistribution.
compute log likelihood for each example
Definition at line 39 of file Distribution.cpp.
|
virtual |
compute log likelihood for example
abstract base method
num_example | which example |
Implements CDistribution.
|
virtualinherited |
compute log likelihood for whole sample
Definition at line 28 of file Distribution.cpp.
|
virtual |
get model parameter (logarithmic)
Implements CDistribution.
|
virtualinherited |
get model parameter
num_param | which param |
Definition at line 123 of file Distribution.h.
|
inherited |
Definition at line 498 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 522 of file SGObject.cpp.
|
inherited |
Returns index of model selection parameter with provided index
param_name | name of model selection parameter |
Definition at line 535 of file SGObject.cpp.
|
virtual |
index_t get_num_components | ( | ) | const |
|
virtual |
|
virtualinherited |
get number of parameters in model that are relevant, i.e. > ALMOST_NEG_INFTY
Definition at line 52 of file Distribution.cpp.
|
virtualinherited |
|
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 296 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 369 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 426 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 421 of file SGObject.cpp.
|
staticinherited |
obtain from generic
object | generic object |
Definition at line 85 of file Distribution.cpp.
|
virtualinherited |
Definition at line 262 of file SGObject.cpp.
|
inherited |
prints all parameter registered for model selection and their type
Definition at line 474 of file SGObject.cpp.
|
virtualinherited |
prints registered parameters out
prefix | prefix for members |
Definition at line 308 of file SGObject.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 314 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 436 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 431 of file SGObject.cpp.
|
virtual |
|
virtualinherited |
|
inherited |
Definition at line 41 of file SGObject.cpp.
|
inherited |
Definition at line 46 of file SGObject.cpp.
|
inherited |
Definition at line 51 of file SGObject.cpp.
|
inherited |
Definition at line 56 of file SGObject.cpp.
|
inherited |
Definition at line 61 of file SGObject.cpp.
|
inherited |
Definition at line 66 of file SGObject.cpp.
|
inherited |
Definition at line 71 of file SGObject.cpp.
|
inherited |
Definition at line 76 of file SGObject.cpp.
|
inherited |
Definition at line 81 of file SGObject.cpp.
|
inherited |
Definition at line 86 of file SGObject.cpp.
|
inherited |
Definition at line 91 of file SGObject.cpp.
|
inherited |
Definition at line 96 of file SGObject.cpp.
|
inherited |
Definition at line 101 of file SGObject.cpp.
|
inherited |
Definition at line 106 of file SGObject.cpp.
|
inherited |
Definition at line 111 of file SGObject.cpp.
|
inherited |
set generic type to T
|
inherited |
|
inherited |
set the parallel object
parallel | parallel object to use |
Definition at line 241 of file SGObject.cpp.
|
inherited |
set the version object
version | version object to use |
Definition at line 283 of file SGObject.cpp.
|
virtualinherited |
|
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 |
set training data for use with EM or SMEM
data | training data |
init features with data if necessary and assure type is correct
Implements CDistribution.
|
inherited |
unset generic type
this has to be called in classes specializing a template class
Definition at line 303 of file SGObject.cpp.
|
virtualinherited |
Updates the hash of current parameter combination
Definition at line 248 of file SGObject.cpp.
update parameters in the em maximization step for mixture model of which this distribution is a part
abstract base method
alpha_k | "belongingness" values of various data points |
len | length of alpha_k array |
Reimplemented in CGaussian.
Definition at line 78 of file Distribution.cpp.
|
protectedinherited |
feature vectors
Definition at line 209 of file Distribution.h.
|
inherited |
io
Definition at line 369 of file SGObject.h.
|
inherited |
parameters wrt which we can compute gradients
Definition at line 384 of file SGObject.h.
|
inherited |
Hash of parameter values
Definition at line 387 of file SGObject.h.
|
inherited |
model selection parameters
Definition at line 381 of file SGObject.h.
|
inherited |
parameters
Definition at line 378 of file SGObject.h.
|
inherited |
parallel
Definition at line 372 of file SGObject.h.
|
protectedinherited |
pseudo count
Definition at line 211 of file Distribution.h.
|
inherited |
version
Definition at line 375 of file SGObject.h.