The class TOPFeatures implements TOP kernel features obtained from two Hidden Markov models.
It was used in
K. Tsuda, M. Kawanabe, G. Raetsch, S. Sonnenburg, and K.R. Mueller. A new discriminative kernel from probabilistic models. Neural Computation, 14:2397-2414, 2002.
which also has the details.
Note that TOP-features are computed on the fly, so to be effective feature caching should be enabled.
It inherits its functionality from CDenseFeatures, which should be consulted for further reference.
Definition at line 68 of file TOPFeatures.h.
Public Member Functions | |
CTOPFeatures () | |
CTOPFeatures (int32_t size, CHMM *p, CHMM *n, bool neglin, bool poslin) | |
CTOPFeatures (const CTOPFeatures &orig) | |
virtual | ~CTOPFeatures () |
void | set_models (CHMM *p, CHMM *n) |
virtual float64_t * | set_feature_matrix () |
int32_t | compute_num_features () |
bool | compute_relevant_indizes (CHMM *hmm, T_HMM_INDIZES *hmm_idx) |
virtual const char * | get_name () const |
virtual CFeatures * | duplicate () const |
void | free_feature_matrix () |
void | free_features () |
float64_t * | get_feature_vector (int32_t num, int32_t &len, bool &dofree) |
SGVector< float64_t > | get_feature_vector (int32_t num) |
void | set_feature_vector (SGVector< float64_t > vector, int32_t num) |
void | free_feature_vector (float64_t *feat_vec, int32_t num, bool dofree) |
void | free_feature_vector (SGVector< float64_t > vec, int32_t num) |
void | vector_subset (int32_t *idx, int32_t idx_len) |
void | feature_subset (int32_t *idx, int32_t idx_len) |
SGMatrix< float64_t > | get_feature_matrix () |
float64_t * | get_feature_matrix (int32_t &num_feat, int32_t &num_vec) |
SGMatrix< float64_t > | steal_feature_matrix () |
void | set_feature_matrix (SGMatrix< float64_t > matrix) |
CDenseFeatures< float64_t > * | get_transposed () |
float64_t * | get_transposed (int32_t &num_feat, int32_t &num_vec) |
virtual void | copy_feature_matrix (SGMatrix< float64_t > src) |
void | obtain_from_dot (CDotFeatures *df) |
virtual bool | apply_preprocessor (bool force_preprocessing=false) |
virtual int32_t | get_size () const |
virtual int32_t | get_num_vectors () const |
int32_t | get_num_features () |
void | set_num_features (int32_t num) |
void | set_num_vectors (int32_t num) |
void | initialize_cache () |
virtual EFeatureClass | get_feature_class () const |
virtual EFeatureType | get_feature_type () const |
virtual bool | reshape (int32_t p_num_features, int32_t p_num_vectors) |
virtual int32_t | get_dim_feature_space () const |
virtual float64_t | dot (int32_t vec_idx1, CDotFeatures *df, int32_t vec_idx2) |
virtual float64_t | dense_dot (int32_t vec_idx1, const float64_t *vec2, int32_t vec2_len) |
virtual void | add_to_dense_vec (float64_t alpha, int32_t vec_idx1, float64_t *vec2, int32_t vec2_len, bool abs_val=false) |
virtual int32_t | get_nnz_features_for_vector (int32_t num) |
virtual void | load (CFile *loader) |
virtual void | save (CFile *saver) |
virtual void * | get_feature_iterator (int32_t vector_index) |
virtual bool | get_next_feature (int32_t &index, float64_t &value, void *iterator) |
virtual void | free_feature_iterator (void *iterator) |
virtual CFeatures * | copy_subset (SGVector< index_t > indices) |
virtual bool | is_equal (CDenseFeatures *rhs) |
CFeatures * | create_merged_copy (CFeatures *other) |
virtual float64_t | dense_dot_sgvec (int32_t vec_idx1, const SGVector< float64_t > vec2) |
virtual void | dense_dot_range (float64_t *output, int32_t start, int32_t stop, float64_t *alphas, float64_t *vec, int32_t dim, float64_t b) |
virtual void | dense_dot_range_subset (int32_t *sub_index, int32_t num, float64_t *output, float64_t *alphas, float64_t *vec, int32_t dim, float64_t b) |
float64_t | get_combined_feature_weight () |
void | set_combined_feature_weight (float64_t nw) |
SGMatrix< float64_t > | get_computed_dot_feature_matrix () |
SGVector< float64_t > | get_computed_dot_feature_vector (int32_t num) |
void | benchmark_add_to_dense_vector (int32_t repeats=5) |
void | benchmark_dense_dot_range (int32_t repeats=5) |
virtual SGVector< float64_t > | get_mean () |
virtual SGMatrix< float64_t > | get_cov () |
virtual int32_t | add_preprocessor (CPreprocessor *p) |
set preprocessor | |
virtual CPreprocessor * | del_preprocessor (int32_t num) |
del current preprocessor | |
CPreprocessor * | get_preprocessor (int32_t num) const |
get current preprocessor | |
void | set_preprocessed (int32_t num) |
bool | is_preprocessed (int32_t num) const |
int32_t | get_num_preprocessed () const |
get whether specified preprocessor (or all if num=1) was/were already applied | |
int32_t | get_num_preprocessors () const |
void | clean_preprocessors () |
int32_t | get_cache_size () const |
void | list_feature_obj () const |
bool | check_feature_compatibility (CFeatures *f) const |
bool | has_property (EFeatureProperty p) const |
void | set_property (EFeatureProperty p) |
void | unset_property (EFeatureProperty p) |
virtual void | add_subset (SGVector< index_t > subset) |
virtual void | remove_subset () |
virtual void | remove_all_subsets () |
virtual CSubsetStack * | get_subset_stack () |
virtual void | subset_changed_post () |
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) |
Static Public Member Functions | |
static void * | dense_dot_range_helper (void *p) |
static SGVector< float64_t > | get_mean (CDotFeatures *lhs, CDotFeatures *rhs) |
static SGMatrix< float64_t > | compute_cov (CDotFeatures *lhs, CDotFeatures *rhs) |
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 float64_t * | compute_feature_vector (int32_t num, int32_t &len, float64_t *target=NULL) |
void | compute_feature_vector (float64_t *addr, int32_t num, int32_t &len) |
void | display_progress (int32_t start, int32_t stop, int32_t v) |
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 | |
CHMM * | pos |
CHMM * | neg |
bool | neglinear |
bool | poslinear |
T_HMM_INDIZES | pos_relevant_indizes |
T_HMM_INDIZES | neg_relevant_indizes |
int32_t | num_vectors |
number of vectors in cache | |
int32_t | num_features |
number of features in cache | |
SGMatrix< float64_t > | feature_matrix |
CCache< float64_t > * | feature_cache |
float64_t | combined_weight |
feature weighting in combined dot features | |
CSubsetStack * | m_subset_stack |
CTOPFeatures | ( | ) |
default constructor
Definition at line 18 of file TOPFeatures.cpp.
CTOPFeatures | ( | int32_t | size, | |
CHMM * | p, | |||
CHMM * | n, | |||
bool | neglin, | |||
bool | poslin | |||
) |
constructor
size | cache size | |
p | positive HMM | |
n | negative HMM | |
neglin | if negative HMM is of linear shape | |
poslin | if positive HMM is of linear shape |
Definition at line 23 of file TOPFeatures.cpp.
CTOPFeatures | ( | const CTOPFeatures & | orig | ) |
copy constructor
Definition at line 34 of file TOPFeatures.cpp.
~CTOPFeatures | ( | ) | [virtual] |
Definition at line 44 of file TOPFeatures.cpp.
int32_t add_preprocessor | ( | CPreprocessor * | p | ) | [virtual, inherited] |
set preprocessor
add preprocessor
p | preprocessor to set |
Definition at line 81 of file Features.cpp.
adds a subset of indices on top of the current subsets (possibly subset o subset. Calls subset_changed_post() afterwards
subset | subset of indices to add |
Reimplemented in CCombinedFeatures.
Definition at line 351 of file Features.cpp.
virtual void add_to_dense_vec | ( | float64_t | alpha, | |
int32_t | vec_idx1, | |||
float64_t * | vec2, | |||
int32_t | vec2_len, | |||
bool | abs_val = false | |||
) | [virtual, inherited] |
add vector 1 multiplied with alpha to dense vector2
possible with subset
alpha | scalar alpha | |
vec_idx1 | index of first vector | |
vec2 | pointer to real valued vector | |
vec2_len | length of real valued vector | |
abs_val | if true add the absolute value |
Implements CDotFeatures.
virtual bool apply_preprocessor | ( | bool | force_preprocessing = false |
) | [virtual, inherited] |
apply preprocessor
applies preprocessors to ALL features (subset removed before and restored afterwards)
not possible with subset
force_preprocessing | if preprocssing shall be forced |
void benchmark_add_to_dense_vector | ( | int32_t | repeats = 5 |
) | [inherited] |
run benchmark for add_to_dense_vec
Definition at line 318 of file DotFeatures.cpp.
void benchmark_dense_dot_range | ( | int32_t | repeats = 5 |
) | [inherited] |
run benchmark for dense_dot_range
Definition at line 341 of file DotFeatures.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.
bool check_feature_compatibility | ( | CFeatures * | f | ) | const [inherited] |
check feature compatibility
f | features to check for compatibility |
Definition at line 326 of file Features.cpp.
void clean_preprocessors | ( | ) | [inherited] |
clears all preprocs
Definition at line 137 of file Features.cpp.
SGMatrix< float64_t > compute_cov | ( | CDotFeatures * | lhs, | |
CDotFeatures * | rhs | |||
) | [static, inherited] |
compute the covariance of two CDotFeatures together
Definition at line 469 of file DotFeatures.cpp.
void compute_feature_vector | ( | float64_t * | addr, | |
int32_t | num, | |||
int32_t & | len | |||
) | [protected] |
computes the feature vector to the address addr
addr | address | |
num | num | |
len | len |
Definition at line 102 of file TOPFeatures.cpp.
float64_t * compute_feature_vector | ( | int32_t | num, | |
int32_t & | len, | |||
float64_t * | target = NULL | |||
) | [protected, virtual] |
compute feature vector
num | num | |
len | len | |
target |
Reimplemented from CDenseFeatures< float64_t >.
Definition at line 86 of file TOPFeatures.cpp.
int32_t compute_num_features | ( | ) |
compute number of features
Definition at line 332 of file TOPFeatures.cpp.
bool compute_relevant_indizes | ( | CHMM * | hmm, | |
T_HMM_INDIZES * | hmm_idx | |||
) |
compute relevant indices
hmm | HMM to compute for | |
hmm_idx | HMM index |
Definition at line 229 of file TOPFeatures.cpp.
copy feature matrix store copy of feature_matrix, where num_features is the column offset, and columns are linear in memory see below for definition of feature_matrix
not possible with subset
src | feature matrix to copy |
Creates a new CFeatures instance containing copies of the elements which are specified by the provided indices.
possible with subset
indices | indices of feature elements to copy |
Reimplemented from CFeatures.
Takes another feature instance and returns a new instance which is a concatenation of a copy if this instace's data and the given instance's data. Note that the feature types have to be equal.
other | feature object to append |
Reimplemented from CFeatures.
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.
CPreprocessor * del_preprocessor | ( | int32_t | num | ) | [virtual, inherited] |
del current preprocessor
delete preprocessor from list caller has to clean up returned preproc
num | index of preprocessor in list |
Definition at line 143 of file Features.cpp.
virtual float64_t dense_dot | ( | int32_t | vec_idx1, | |
const float64_t * | vec2, | |||
int32_t | vec2_len | |||
) | [virtual, inherited] |
compute dot product between vector1 and a dense vector
possible with subset
vec_idx1 | index of first vector | |
vec2 | pointer to real valued vector | |
vec2_len | length of real valued vector |
Implements CDotFeatures.
void dense_dot_range | ( | float64_t * | output, | |
int32_t | start, | |||
int32_t | stop, | |||
float64_t * | alphas, | |||
float64_t * | vec, | |||
int32_t | dim, | |||
float64_t | b | |||
) | [virtual, inherited] |
Compute the dot product for a range of vectors. This function makes use of dense_dot alphas[i] * sparse[i]^T * w + b
output | result for the given vector range | |
start | start vector range from this idx | |
stop | stop vector range at this idx | |
alphas | scalars to multiply with, may be NULL | |
vec | dense vector to compute dot product with | |
dim | length of the dense vector | |
b | bias |
note that the result will be written to output[0...(stop-start-1)]
Reimplemented in CCombinedDotFeatures, and CHashedWDFeaturesTransposed.
Definition at line 67 of file DotFeatures.cpp.
void * dense_dot_range_helper | ( | void * | p | ) | [static, inherited] |
Compute the dot product for a range of vectors. This function is called by the threads created in dense_dot_range
Reimplemented in CHashedWDFeaturesTransposed.
Definition at line 231 of file DotFeatures.cpp.
void dense_dot_range_subset | ( | int32_t * | sub_index, | |
int32_t | num, | |||
float64_t * | output, | |||
float64_t * | alphas, | |||
float64_t * | vec, | |||
int32_t | dim, | |||
float64_t | b | |||
) | [virtual, inherited] |
Compute the dot product for a subset of vectors. This function makes use of dense_dot alphas[i] * sparse[i]^T * w + b
sub_index | index for which to compute outputs | |
num | length of index | |
output | result for the given vector range | |
alphas | scalars to multiply with, may be NULL | |
vec | dense vector to compute dot product with | |
dim | length of the dense vector | |
b | bias |
Reimplemented in CCombinedDotFeatures, and CHashedWDFeaturesTransposed.
Definition at line 153 of file DotFeatures.cpp.
float64_t dense_dot_sgvec | ( | int32_t | vec_idx1, | |
const SGVector< float64_t > | vec2 | |||
) | [virtual, inherited] |
compute dot product between vector1 and a dense vector
vec_idx1 | index of first vector | |
vec2 | dense vector |
Definition at line 62 of file DotFeatures.cpp.
void display_progress | ( | int32_t | start, | |
int32_t | stop, | |||
int32_t | v | |||
) | [protected, inherited] |
display progress output
start | minimum value | |
stop | maximum value | |
v | current value |
Definition at line 528 of file DotFeatures.cpp.
virtual float64_t dot | ( | int32_t | vec_idx1, | |
CDotFeatures * | df, | |||
int32_t | vec_idx2 | |||
) | [virtual, inherited] |
compute dot product between vector1 and vector2, appointed by their indices
possible with subset
vec_idx1 | index of first vector | |
df | DotFeatures (of same kind) to compute dot product with | |
vec_idx2 | index of second vector |
Implements CDotFeatures.
virtual CFeatures* duplicate | ( | ) | const [virtual, inherited] |
void feature_subset | ( | int32_t * | idx, | |
int32_t | idx_len | |||
) | [inherited] |
Extracts the features mentioned in idx and replaces them in feature matrix in place.
It does not resize the allocated memory block.
Not possible with subset.
idx | index with features that shall remain in the feature matrix | |
idx_len | length of the index |
Note: assumes idx is sorted
virtual void free_feature_iterator | ( | void * | iterator | ) | [virtual, inherited] |
clean up iterator call this function with the iterator returned by get_first_feature
iterator | as returned by get_first_feature |
Implements CDotFeatures.
void free_feature_matrix | ( | ) | [inherited] |
free feature matrix
Any subset is removed
void free_feature_vector | ( | float64_t * | feat_vec, | |
int32_t | num, | |||
bool | dofree | |||
) | [inherited] |
free feature vector
possible with subset
feat_vec | feature vector to free | |
num | index in feature cache | |
dofree | if vector should be really deleted |
free feature vector
possible with subset
vec | feature vector to free | |
num | index in feature cache |
void free_features | ( | ) | [inherited] |
free feature matrix and cache
Any subset is removed
int32_t get_cache_size | ( | ) | const [inherited] |
float64_t get_combined_feature_weight | ( | ) | [inherited] |
get combined feature weight
Definition at line 151 of file DotFeatures.h.
compute the feature matrix in feature space
Definition at line 284 of file DotFeatures.cpp.
compute the feature vector in feature space
Definition at line 305 of file DotFeatures.cpp.
virtual int32_t get_dim_feature_space | ( | ) | const [virtual, inherited] |
obtain the dimensionality of the feature space
(not mix this up with the dimensionality of the input space, usually obtained via get_num_features())
Implements CDotFeatures.
virtual EFeatureClass get_feature_class | ( | ) | const [virtual, inherited] |
virtual void* get_feature_iterator | ( | int32_t | vector_index | ) | [virtual, inherited] |
iterate over the non-zero features
call get_feature_iterator first, followed by get_next_feature and free_feature_iterator to cleanup
possible with subset
vector_index | the index of the vector over whose components to iterate over |
Implements CDotFeatures.
Getter the feature matrix
in-place without subset a copy with subset
float64_t * get_feature_matrix | ( | int32_t & | num_feat, | |
int32_t & | num_vec | |||
) | [inherited] |
get the pointer to the feature matrix num_feat,num_vectors are returned by reference
subset is ignored
num_feat | number of features in matrix | |
num_vec | number of vectors in matrix |
virtual EFeatureType get_feature_type | ( | ) | const [virtual, inherited] |
float64_t * get_feature_vector | ( | int32_t | num, | |
int32_t & | len, | |||
bool & | dofree | |||
) | [inherited] |
get feature vector for sample num from the matrix as it is if matrix is initialized, else return preprocessed compute_feature_vector (not implemented)
num | index of feature vector | |
len | length is returned by reference | |
dofree | whether returned vector must be freed by caller via free_feature_vector |
get feature vector num
possible with subset
num | index of vector |
SGIO * get_global_io | ( | ) | [inherited] |
Parallel * get_global_parallel | ( | ) | [inherited] |
Version * get_global_version | ( | ) | [inherited] |
SGVector< float64_t > get_mean | ( | CDotFeatures * | lhs, | |
CDotFeatures * | rhs | |||
) | [static, inherited] |
get mean of two CDotFeature objects
Definition at line 402 of file DotFeatures.cpp.
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.
virtual const char* get_name | ( | ) | const [virtual] |
Reimplemented from CDenseFeatures< float64_t >.
Definition at line 117 of file TOPFeatures.h.
virtual bool get_next_feature | ( | int32_t & | index, | |
float64_t & | value, | |||
void * | iterator | |||
) | [virtual, inherited] |
iterate over the non-zero features
call this function with the iterator returned by get_first_feature and call free_feature_iterator to cleanup
possible with subset
index | is returned by reference (-1 when not available) | |
value | is returned by reference | |
iterator | as returned by get_first_feature |
Implements CDotFeatures.
virtual int32_t get_nnz_features_for_vector | ( | int32_t | num | ) | [virtual, inherited] |
get number of non-zero features in vector
num | which vector |
Implements CDotFeatures.
int32_t get_num_features | ( | ) | [inherited] |
get number of features (of possible subset)
int32_t get_num_preprocessed | ( | ) | const [inherited] |
get whether specified preprocessor (or all if num=1) was/were already applied
get the number of applied preprocs
Definition at line 123 of file Features.cpp.
int32_t get_num_preprocessors | ( | ) | const [inherited] |
get number of preprocessors
Definition at line 198 of file Features.cpp.
virtual int32_t get_num_vectors | ( | ) | const [virtual, inherited] |
CPreprocessor * get_preprocessor | ( | int32_t | num | ) | const [inherited] |
get current preprocessor
get specified preprocessor
num | index of preprocessor in list |
Definition at line 111 of file Features.cpp.
virtual int32_t get_size | ( | ) | const [virtual, inherited] |
CSubsetStack * get_subset_stack | ( | ) | [virtual, inherited] |
CDenseFeatures<float64_t >* get_transposed | ( | ) | [inherited] |
get a transposed copy of the features
possible with subset
float64_t * get_transposed | ( | int32_t & | num_feat, | |
int32_t & | num_vec | |||
) | [inherited] |
compute and return the transpose of the feature matrix which will be prepocessed. num_feat, num_vectors are returned by reference caller has to clean up
possible with subset
num_feat | number of features in matrix | |
num_vec | number of vectors in matrix |
bool has_property | ( | EFeatureProperty | p | ) | const [inherited] |
check if features have given property
p | feature property |
Definition at line 336 of file Features.cpp.
void initialize_cache | ( | ) | [inherited] |
Initialize cache
not possible with subset
virtual bool is_equal | ( | CDenseFeatures< float64_t > * | rhs | ) | [virtual, inherited] |
checks if the contents of this CDenseFeatures object are the same to the contents of rhs
rhs | other CDenseFeatures object to compare to this one |
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.
bool is_preprocessed | ( | int32_t | num | ) | const [inherited] |
get whether specified preprocessor was already applied
num | index of preprocessor in list |
Definition at line 193 of file Features.cpp.
void list_feature_obj | ( | ) | const [inherited] |
list feature object
Definition at line 214 of file Features.cpp.
virtual void load | ( | CFile * | loader | ) | [virtual, inherited] |
load features from file
loader | File object via which to load data |
Reimplemented from CFeatures.
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.
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 obtain_from_dot | ( | CDotFeatures * | df | ) | [inherited] |
obtain dense features from other dotfeatures
removes any subset before
df | dotfeatures to obtain features from |
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.
void remove_all_subsets | ( | ) | [virtual, inherited] |
removes all subsets Calls subset_changed_post() afterwards
Reimplemented in CCombinedFeatures.
Definition at line 363 of file Features.cpp.
void remove_subset | ( | ) | [virtual, inherited] |
removes that last added subset from subset stack, if existing Calls subset_changed_post() afterwards
Reimplemented in CCombinedFeatures.
Definition at line 357 of file Features.cpp.
virtual bool reshape | ( | int32_t | p_num_features, | |
int32_t | p_num_vectors | |||
) | [virtual, inherited] |
reshape
not possible with subset
p_num_features | new number of features | |
p_num_vectors | new number of vectors |
Reimplemented from CFeatures.
virtual void save | ( | CFile * | saver | ) | [virtual, inherited] |
save features to file
saver | File object via which to save data |
Reimplemented from CFeatures.
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_combined_feature_weight | ( | float64_t | nw | ) | [inherited] |
set combined kernel weight
nw | new combined feature weight |
Definition at line 157 of file DotFeatures.h.
float64_t * set_feature_matrix | ( | ) | [virtual] |
Setter for feature matrix
any subset is removed
num_cols is number of feature vectors num_rows is number of dims of vectors see below for definition of feature_matrix
matrix | feature matrix to set |
set feature vector num
possible with subset
vector | vector | |
num | index if vector to set |
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.
void set_num_features | ( | int32_t | num | ) | [inherited] |
set number of features
num | number to set |
void set_num_vectors | ( | int32_t | num | ) | [inherited] |
set number of vectors
not possible with subset
num | number to set |
void set_preprocessed | ( | int32_t | num | ) | [inherited] |
set applied flag for preprocessor
num | index of preprocessor in list |
Definition at line 188 of file Features.cpp.
void set_property | ( | EFeatureProperty | p | ) | [inherited] |
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.
steals feature matrix, i.e. returns matrix and forget about it subset is ignored
virtual void subset_changed_post | ( | ) | [virtual, inherited] |
method may be overwritten to update things that depend on subset
Reimplemented in CStringFeatures< ST >, CStringFeatures< T >, CStringFeatures< uint8_t >, CStringFeatures< char >, and CStringFeatures< uint16_t >.
Definition at line 262 of file Features.h.
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.
void unset_property | ( | EFeatureProperty | p | ) | [inherited] |
bool update_parameter_hash | ( | ) | [protected, virtual, inherited] |
Updates the hash of current parameter combination.
Definition at line 237 of file SGObject.cpp.
void vector_subset | ( | int32_t * | idx, | |
int32_t | idx_len | |||
) | [inherited] |
Extracts the feature vectors mentioned in idx and replaces them in feature matrix in place.
It does not resize the allocated memory block.
not possible with subset
idx | index with examples that shall remain in the feature matrix | |
idx_len | length of the index |
Note: assumes idx is sorted
float64_t combined_weight [protected, inherited] |
feature weighting in combined dot features
Definition at line 246 of file DotFeatures.h.
CCache<float64_t >* feature_cache [protected, inherited] |
feature cache
Definition at line 530 of file DenseFeatures.h.
SGMatrix<float64_t > feature_matrix [protected, inherited] |
Feature matrix and its associated number of vectors and features. Note that num_vectors / num_features above match matrix sizes if feature_matrix.matrix != NULL
Definition at line 527 of file DenseFeatures.h.
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.
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.
CSubsetStack* m_subset_stack [protected, inherited] |
subset used for index transformations
Definition at line 296 of file Features.h.
negative HMM
Definition at line 145 of file TOPFeatures.h.
T_HMM_INDIZES neg_relevant_indizes [protected] |
negative relevant indices
Definition at line 154 of file TOPFeatures.h.
bool neglinear [protected] |
if negative HMM is a LinearHMM
Definition at line 147 of file TOPFeatures.h.
int32_t num_features [protected, inherited] |
number of features in cache
Definition at line 521 of file DenseFeatures.h.
int32_t num_vectors [protected, inherited] |
number of vectors in cache
Definition at line 518 of file DenseFeatures.h.
parallel
Definition at line 465 of file SGObject.h.
positive HMM
Definition at line 143 of file TOPFeatures.h.
T_HMM_INDIZES pos_relevant_indizes [protected] |
positive relevant indices
Definition at line 152 of file TOPFeatures.h.
bool poslinear [protected] |
if positive HMM is a LinearHMM
Definition at line 149 of file TOPFeatures.h.
version
Definition at line 468 of file SGObject.h.