SHOGUN
v3.0.0
|
The class LinearHMM is for learning Higher Order Markov chains.
While learning the parameters \({\bf \theta}\) in
\begin{eqnarray*} P({\bf x}|{\bf \theta}^\pm)&=&P(x_1, \ldots, x_N|{\bf \theta}^\pm)\\ &=&P(x_1,\ldots,x_{d}|{\bf \theta}^\pm)\prod_{i=d+1}^N P(x_i|x_{i-1},\ldots,x_{i-d},{\bf \theta}^\pm) \end{eqnarray*}
are determined.
A more detailed description can be found in
Durbin et.al, Biological Sequence Analysis -Probabilistic Models of Proteins and Nucleic Acids, 1998
Definition at line 39 of file LinearHMM.h.
Public Member Functions | |
CLinearHMM () | |
CLinearHMM (CStringFeatures< uint16_t > *f) | |
CLinearHMM (int32_t p_num_features, int32_t p_num_symbols) | |
virtual | ~CLinearHMM () |
virtual bool | train (CFeatures *data=NULL) |
bool | train (const int32_t *indizes, int32_t num_indizes, float64_t pseudo_count) |
float64_t | get_log_likelihood_example (uint16_t *vector, int32_t len) |
float64_t | get_likelihood_example (uint16_t *vector, int32_t len) |
virtual float64_t | get_log_likelihood_example (int32_t num_example) |
virtual float64_t | get_log_derivative (int32_t num_param, int32_t num_example) |
virtual float64_t | get_log_derivative_obsolete (uint16_t obs, int32_t pos) |
virtual float64_t | get_derivative_obsolete (uint16_t *vector, int32_t len, int32_t pos) |
virtual int32_t | get_sequence_length () |
virtual int32_t | get_num_symbols () |
virtual int32_t | get_num_model_parameters () |
virtual float64_t | get_positional_log_parameter (uint16_t obs, int32_t position) |
virtual float64_t | get_log_model_parameter (int32_t num_param) |
virtual SGVector< float64_t > | get_log_transition_probs () |
virtual bool | set_log_transition_probs (const SGVector< float64_t > probs) |
virtual SGVector< float64_t > | get_transition_probs () |
virtual bool | set_transition_probs (const SGVector< float64_t > probs) |
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 float64_t | get_likelihood_example (int32_t num_example) |
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 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::get_version_parameter()) |
virtual bool | load_serializable (CSerializableFile *file, const char *prefix="", int32_t param_version=Version::get_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_gradient_parameter_dictionary (CMap< TParameter *, CSGObject * > *dict) |
virtual bool | update_parameter_hash () |
virtual bool | equals (CSGObject *other, float64_t accuracy=0.0) |
virtual CSGObject * | clone () |
Public Attributes | |
SGIO * | io |
Parallel * | parallel |
Version * | version |
Parameter * | m_parameters |
Parameter * | m_model_selection_parameters |
Parameter * | m_gradient_parameters |
ParameterMap * | m_parameter_map |
uint32_t | m_hash |
Protected Member Functions | |
virtual void | load_serializable_post () throw (ShogunException) |
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 | save_serializable_pre () throw (ShogunException) |
virtual void | save_serializable_post () throw (ShogunException) |
Protected Attributes | |
int32_t | sequence_length |
int32_t | num_symbols |
int32_t | num_params |
float64_t * | transition_probs |
float64_t * | log_transition_probs |
CFeatures * | features |
float64_t | pseudo_count |
CLinearHMM | ( | ) |
default constructor
Definition at line 22 of file LinearHMM.cpp.
CLinearHMM | ( | CStringFeatures< uint16_t > * | f | ) |
CLinearHMM | ( | int32_t | p_num_features, |
int32_t | p_num_symbols | ||
) |
constructor
p_num_features | number of features |
p_num_symbols | number of symbols in features |
Definition at line 38 of file LinearHMM.cpp.
|
virtual |
Definition at line 48 of file LinearHMM.cpp.
|
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 1196 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 1313 of file SGObject.cpp.
|
virtualinherited |
A deep copy. All the instance variables will also be copied.
Definition at line 160 of file SGObject.h.
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) |
Definition at line 1217 of file SGObject.cpp.
|
virtualinherited |
get partial derivative of likelihood function
num_param | partial derivative against which param |
num_example | which example |
Definition at line 129 of file Distribution.h.
|
virtual |
obsolete get one example's derivative
vector | vector |
len | length |
pos | position |
Definition at line 131 of file LinearHMM.h.
|
virtualinherited |
|
inherited |
|
inherited |
|
inherited |
float64_t get_likelihood_example | ( | uint16_t * | vector, |
int32_t | len | ||
) |
get one example's likelihood
vector | the example |
len | length of vector |
Definition at line 213 of file LinearHMM.cpp.
|
virtualinherited |
compute likelihood for example
num_example | which example |
Reimplemented in CGMM.
Definition at line 140 of file Distribution.h.
|
virtual |
get logarithm of one example's derivative's likelihood
num_param | which example's param |
num_example | which example |
Implements CDistribution.
Definition at line 223 of file LinearHMM.cpp.
|
virtual |
obsolete get logarithm of one example's derivative's likelihood
obs | observation |
pos | position |
Definition at line 119 of file LinearHMM.h.
compute log likelihood for each example
Definition at line 37 of file Distribution.cpp.
float64_t get_log_likelihood_example | ( | uint16_t * | vector, |
int32_t | len | ||
) |
get logarithm of one example's likelihood
vector | the example |
len | length of vector |
Definition at line 186 of file LinearHMM.cpp.
|
virtual |
get logarithm of one example's likelihood
num_example | which example |
Implements CDistribution.
Definition at line 196 of file LinearHMM.cpp.
|
virtualinherited |
compute log likelihood for whole sample
Definition at line 26 of file Distribution.cpp.
|
virtual |
get logarithm of given model parameter
num_param | which param |
Implements CDistribution.
Definition at line 173 of file LinearHMM.h.
get logarithm of all transition probs
Definition at line 266 of file LinearHMM.cpp.
|
virtualinherited |
get model parameter
num_param | which param |
Definition at line 118 of file Distribution.h.
|
inherited |
Definition at line 1100 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 1124 of file SGObject.cpp.
|
inherited |
Returns index of model selection parameter with provided index
param_name | name of model selection parameter |
Definition at line 1137 of file SGObject.cpp.
|
virtual |
|
virtual |
get number of model parameters
Implements CDistribution.
Definition at line 154 of file LinearHMM.h.
|
virtualinherited |
get number of parameters in model that are relevant, i.e. > ALMOST_NEG_INFTY
Definition at line 50 of file Distribution.cpp.
|
virtual |
get number of symbols in examples
Definition at line 148 of file LinearHMM.h.
|
virtual |
get positional log parameter
obs | observation |
position | position |
Definition at line 162 of file LinearHMM.h.
|
virtualinherited |
|
virtual |
get sequence length of each example
Definition at line 142 of file LinearHMM.h.
get all transition probs
Definition at line 242 of file LinearHMM.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 268 of file SGObject.cpp.
|
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::get_version_parameter() for this in most cases) |
file | file to load from |
prefix | prefix for members |
Definition at line 673 of file SGObject.cpp.
|
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 514 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 |
param_version | (optional) a parameter version different to (this is mainly for testing, better do not use) |
Definition at line 345 of file SGObject.cpp.
|
protectedvirtual |
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 from CSGObject.
Definition at line 290 of file LinearHMM.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 occurres. |
Reimplemented in CDynamicArray< T >, CDynamicArray< float64_t >, CDynamicArray< float32_t >, CDynamicArray< int32_t >, CDynamicArray< char >, CDynamicArray< bool >, CDynamicArray< uint64_t >, and CDynamicObjectArray.
Definition at line 1024 of file SGObject.cpp.
|
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 711 of file SGObject.cpp.
|
protectedvirtualinherited |
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 918 of file SGObject.cpp.
|
protectedvirtualinherited |
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 858 of file SGObject.cpp.
|
inherited |
prints all parameter registered for model selection and their type
Definition at line 1076 of file SGObject.cpp.
|
virtualinherited |
prints registered parameters out
prefix | prefix for members |
Definition at line 280 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 |
param_version | (optional) a parameter version different to (this is mainly for testing, better do not use) |
Definition at line 286 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 occurres. |
Reimplemented in CKernel.
Definition at line 1039 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 occurres. |
Reimplemented in CKernel, CDynamicArray< T >, CDynamicArray< float64_t >, CDynamicArray< float32_t >, CDynamicArray< int32_t >, CDynamicArray< char >, CDynamicArray< bool >, CDynamicArray< uint64_t >, and CDynamicObjectArray.
Definition at line 1034 of file SGObject.cpp.
|
virtualinherited |
|
inherited |
set generic type to T
Definition at line 41 of file SGObject.cpp.
|
inherited |
|
inherited |
set the parallel object
parallel | parallel object to use |
Definition at line 220 of file SGObject.cpp.
|
inherited |
set the version object
version | version object to use |
Definition at line 255 of file SGObject.cpp.
set logarithm of all transition probs
probs | new logarithm transition probs |
Definition at line 271 of file LinearHMM.cpp.
|
virtualinherited |
set all transition probs
probs | new transition probs |
Definition at line 247 of file LinearHMM.cpp.
|
virtualinherited |
A shallow copy. All the SGObject instance variables will be simply assigned and SG_REF-ed.
Reimplemented in CGaussianKernel.
Definition at line 151 of file SGObject.h.
|
virtual |
estimate LinearHMM distribution
data | training data (parameter can be avoided if distance or kernel-based classifiers are used and distance/kernels are initialized with train data) |
Implements CDistribution.
Definition at line 54 of file LinearHMM.cpp.
bool train | ( | const int32_t * | indizes, |
int32_t | num_indizes, | ||
float64_t | pseudo_count | ||
) |
alternative train distribution
indizes | indices |
num_indizes | number of indices |
pseudo_count | pseudo count |
Definition at line 123 of file LinearHMM.cpp.
|
inherited |
unset generic type
this has to be called in classes specializing a template class
Definition at line 275 of file SGObject.cpp.
|
virtualinherited |
Updates the hash of current parameter combination.
Definition at line 227 of file SGObject.cpp.
|
protectedinherited |
feature vectors
Definition at line 180 of file Distribution.h.
|
inherited |
io
Definition at line 514 of file SGObject.h.
|
protected |
logarithm of transition probs
Definition at line 226 of file LinearHMM.h.
|
inherited |
parameters wrt which we can compute gradients
Definition at line 529 of file SGObject.h.
|
inherited |
Hash of parameter values
Definition at line 535 of file SGObject.h.
|
inherited |
model selection parameters
Definition at line 526 of file SGObject.h.
|
inherited |
map for different parameter versions
Definition at line 532 of file SGObject.h.
|
inherited |
parameters
Definition at line 523 of file SGObject.h.
|
protected |
number of parameters
Definition at line 222 of file LinearHMM.h.
|
protected |
number of symbols in examples
Definition at line 220 of file LinearHMM.h.
|
inherited |
parallel
Definition at line 517 of file SGObject.h.
|
protectedinherited |
pseudo count
Definition at line 182 of file Distribution.h.
|
protected |
examples' sequence length
Definition at line 218 of file LinearHMM.h.
|
protected |
transition probs
Definition at line 224 of file LinearHMM.h.
|
inherited |
version
Definition at line 520 of file SGObject.h.