class CStateModel base, abstract class for the internal state representation used in the CHMSVMModel.
Definition at line 28 of file StateModel.h.
Public Member Functions | |
CStateModel () | |
virtual | ~CStateModel () |
int32_t | get_num_states () const |
int32_t | get_num_transmission_params () const |
virtual SGMatrix< float64_t > | loss_matrix (CSequence *label_seq)=0 |
virtual float64_t | loss (CSequence *label_seq_lhs, CSequence *label_seq_rhs)=0 |
virtual void | reshape_emission_params (SGVector< float64_t > &emission_weights, SGVector< float64_t > w, int32_t num_feats, int32_t num_obs)=0 |
virtual void | reshape_transmission_params (SGMatrix< float64_t > &transmission_weights, SGVector< float64_t > w)=0 |
virtual SGVector< int32_t > | labels_to_states (CSequence *label_seq) const =0 |
virtual CSequence * | states_to_labels (SGVector< int32_t > state_seq) const =0 |
virtual void | weights_to_vector (SGVector< float64_t > &psi, SGMatrix< float64_t > transmission_weights, SGVector< float64_t > emission_weights, int32_t num_feats, int32_t num_obs) const =0 |
virtual SGVector< int32_t > | get_monotonicity (int32_t num_free_states, int32_t num_feats) const |
SGVector< float64_t > | get_start_states () const |
SGVector< float64_t > | get_stop_states () const |
virtual const char * | get_name () const |
virtual CSGObject * | shallow_copy () const |
virtual CSGObject * | deep_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) |
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_parameter_dictionary (CMap< TParameter *, CSGObject * > &dict) |
Public Attributes | |
SGIO * | io |
Parallel * | parallel |
Version * | version |
Parameter * | m_parameters |
Parameter * | m_model_selection_parameters |
ParameterMap * | m_parameter_map |
uint32_t | m_hash |
Protected Member Functions | |
virtual TParameter * | migrate (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 | |
int32_t | m_num_states |
int32_t | m_num_transmission_params |
SGMatrix< float64_t > | m_state_loss_mat |
SGVector< float64_t > | m_p |
SGVector< float64_t > | m_q |
CStateModel | ( | ) |
default constructor
Definition at line 15 of file StateModel.cpp.
~CStateModel | ( | ) | [virtual] |
destructor
Definition at line 20 of file StateModel.cpp.
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.
dict | dictionary of parameters to be built. |
Definition at line 1201 of file SGObject.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.
SGIO * get_global_io | ( | ) | [inherited] |
Parallel * get_global_parallel | ( | ) | [inherited] |
Version * get_global_version | ( | ) | [inherited] |
SGStringList< char > get_modelsel_names | ( | ) | [inherited] |
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
param_name | name 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
param_name | name of model selection parameter |
Definition at line 1145 of file SGObject.cpp.
SGVector< int32_t > get_monotonicity | ( | int32_t | num_free_states, | |
int32_t | num_feats | |||
) | const [virtual] |
specify monotonicity constraints for feature scoring functions. The elements of the vector returned can take one of three values:
By default, this method returns a vector of zeros (no monotonicity constraints). Re-implement this method in a child class to specify constraints.
num_free_states | number of states whose parameters are learnt | |
num_feats | number of features |
Reimplemented in CTwoStateModel.
Definition at line 48 of file StateModel.cpp.
virtual const char* get_name | ( | ) | const [virtual] |
Implements CSGObject.
Reimplemented in CTwoStateModel.
Definition at line 182 of file StateModel.h.
int32_t get_num_states | ( | ) | const |
Definition at line 24 of file StateModel.cpp.
int32_t get_num_transmission_params | ( | ) | const |
Definition at line 29 of file StateModel.cpp.
return the distribution of start states, i.e. the specification of which states may appear in the start of a state sequence and which may not. The elements of the vector returned can take one out of two values:
The distrubtion of start states m_p must be initialized in the constructor of CStateModel's child classes.
Definition at line 56 of file StateModel.cpp.
return the distribution of stop states, i.e. the specification of which states may appear in the end of a state sequence and which may not. The elements of the vector returned can take one out of two values:
The distrubtion of stop states m_q must be initialized in the constructor of CStateModel's child classes.
Definition at line 61 of file StateModel.cpp.
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.
generic | set to the type of the generic if returning TRUE |
Definition at line 278 of file SGObject.cpp.
translates label sequence to state sequence
label_seq | label sequence |
Implemented in CTwoStateModel.
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)
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 |
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
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 |
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!
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) |
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.
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.
ShogunException | Will be thrown if an error occurres. |
Definition at line 1028 of file SGObject.cpp.
computes the loss between two sequences of labels using the Hamming loss and the state loss matrix
label_seq_lhs | one label sequence | |
label_seq_rhs | other label sequence |
Implemented in CTwoStateModel.
computes a loss matrix with m_num_states rows and number of columns equal to the length of label_seq. This matrix can be added directly to the emission matrix used in Viterbi decoding during training to form the loss-augmented emission matrix
label_seq | label sequence (normally the true label sequence) |
Implemented in CTwoStateModel.
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
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.
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
param_base | set of TParameter instances to use for migration | |
target | parameter info for the resulting TParameter |
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)
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
prefix | prefix for members |
Definition at line 290 of file SGObject.cpp.
virtual void reshape_emission_params | ( | SGVector< float64_t > & | emission_weights, | |
SGVector< float64_t > | w, | |||
int32_t | num_feats, | |||
int32_t | num_obs | |||
) | [pure virtual] |
arranges the emission parameterss of the weight vector into a vector adding zero elements for the states whose parameters are not learnt. This vector is suitable to iterate through when constructing the emission matrix used in Viterbi decoding
emission_weights | emission parameters outputted | |
w | the weight vector | |
num_feats | number of features | |
num_obs | number of emission scores per feature and state |
Implemented in CTwoStateModel.
virtual void reshape_transmission_params | ( | SGMatrix< float64_t > & | transmission_weights, | |
SGVector< float64_t > | w | |||
) | [pure virtual] |
arranges the tranmission parameterss of the weight vector into a matrix adding zero elements for the states whose parameters are not learnt. This matrix is suitable to iterate during Viterbi decoding
transmission_weights | transmission parameters outputted | |
w | the weight vector |
Implemented in CTwoStateModel.
bool save_serializable | ( | CSerializableFile * | file, | |
const char * | prefix = "" , |
|||
int32_t | param_version = VERSION_PARAMETER | |||
) | [virtual, inherited] |
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 | |
param_version | (optional) a parameter version different to (this is mainly for testing, better do not use) |
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.
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.
ShogunException | Will be thrown if an error occurres. |
Reimplemented in CKernel.
Definition at line 1038 of file SGObject.cpp.
void set_generic< floatmax_t > | ( | ) | [inherited] |
set generic type to T
void set_global_io | ( | SGIO * | io | ) | [inherited] |
void set_global_parallel | ( | Parallel * | parallel | ) | [inherited] |
set the parallel object
parallel | parallel object to use |
Definition at line 230 of file SGObject.cpp.
void set_global_version | ( | Version * | version | ) | [inherited] |
set the version object
version | version object to use |
Definition at line 265 of file SGObject.cpp.
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.
translates state sequence to label sequence
state_seq | state sequence |
Implemented in CTwoStateModel.
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.
Definition at line 237 of file SGObject.cpp.
virtual void weights_to_vector | ( | SGVector< float64_t > & | psi, | |
SGMatrix< float64_t > | transmission_weights, | |||
SGVector< float64_t > | emission_weights, | |||
int32_t | num_feats, | |||
int32_t | num_obs | |||
) | const [pure virtual] |
reshapes the transition and emission weights into a vector (the joint feature vector so it will be possible to take the dot product with the weight vector)
psi | output vector | |
transmission_weights | counts of the state transitions for a state sequence | |
emission_weights | counts of the emission scores for a state sequence and a feature vector | |
num_feats | number of features | |
num_obs | number of emission scores per feature and state |
Implemented in CTwoStateModel.
io
Definition at line 462 of file SGObject.h.
uint32_t m_hash [inherited] |
Hash of parameter values
Definition at line 480 of file SGObject.h.
Parameter* m_model_selection_parameters [inherited] |
model selection parameters
Definition at line 474 of file SGObject.h.
int32_t m_num_states [protected] |
the number of states
Definition at line 190 of file StateModel.h.
int32_t m_num_transmission_params [protected] |
the number of transmission parameters
Definition at line 193 of file StateModel.h.
the distribution of start states
Definition at line 199 of file StateModel.h.
ParameterMap* m_parameter_map [inherited] |
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.
the distribution of stop states
Definition at line 202 of file StateModel.h.
SGMatrix< float64_t > m_state_loss_mat [protected] |
state loss matrix, loss for every pair of states
Definition at line 196 of file StateModel.h.
parallel
Definition at line 465 of file SGObject.h.
version
Definition at line 468 of file SGObject.h.