Template class StringFeatures implements a list of strings.
As this class is a template the underlying storage type is quite arbitrary and not limited to character strings, but could also be sequences of floating point numbers etc. Strings differ from matrices (cf. CDenseFeatures) in a way that the dimensionality of the feature vectors (i.e. the strings) is not fixed; it may vary between strings.
Most string kernels require StringFeatures but a number of them actually requires strings to have same length.
When preprocessors are attached to string features they may shorten the string, but are not allowed to return strings longer than max_string_length, as some algorithms depend on this.
Also note that string features cannot currently be computed on-the-fly.
(Partly) subset access is supported for this feature type. Simple use the (inherited) add_subset(), remove_subset() functions. If done, all calls that work with features are translated to the subset. See comments to find out whether it is supported for that method. See also CFeatures class documentation
Definition at line 72 of file StringFeatures.h.
Public Member Functions | |
CStringFeatures () | |
CStringFeatures (EAlphabet alpha) | |
CStringFeatures (SGStringList< ST > string_list, EAlphabet alpha) | |
CStringFeatures (SGStringList< ST > string_list, CAlphabet *alpha) | |
CStringFeatures (CAlphabet *alpha) | |
CStringFeatures (const CStringFeatures &orig) | |
CStringFeatures (CFile *loader, EAlphabet alpha=DNA) | |
virtual | ~CStringFeatures () |
virtual void | cleanup () |
virtual void | cleanup_feature_vector (int32_t num) |
virtual void | cleanup_feature_vectors (int32_t start, int32_t stop) |
virtual EFeatureClass | get_feature_class () const |
virtual EFeatureType | get_feature_type () const |
CAlphabet * | get_alphabet () |
virtual CFeatures * | duplicate () const |
SGVector< ST > | get_feature_vector (int32_t num) |
void | set_feature_vector (SGVector< ST > vector, int32_t num) |
void | enable_on_the_fly_preprocessing () |
void | disable_on_the_fly_preprocessing () |
ST * | get_feature_vector (int32_t num, int32_t &len, bool &dofree) |
CStringFeatures< ST > * | get_transposed () |
SGString< ST > * | get_transposed (int32_t &num_feat, int32_t &num_vec) |
void | free_feature_vector (ST *feat_vec, int32_t num, bool dofree) |
void | free_feature_vector (SGVector< ST > feat_vec, int32_t num) |
virtual ST | get_feature (int32_t vec_num, int32_t feat_num) |
virtual int32_t | get_vector_length (int32_t vec_num) |
virtual int32_t | get_max_vector_length () |
virtual int32_t | get_num_vectors () const |
floatmax_t | get_num_symbols () |
floatmax_t | get_max_num_symbols () |
floatmax_t | get_original_num_symbols () |
int32_t | get_order () |
ST | get_masked_symbols (ST symbol, uint8_t mask) |
ST | shift_offset (ST offset, int32_t amount) |
ST | shift_symbol (ST symbol, int32_t amount) |
virtual void | load (CFile *loader) |
void | load_ascii_file (char *fname, bool remap_to_bin=true, EAlphabet ascii_alphabet=DNA, EAlphabet binary_alphabet=RAWDNA) |
bool | load_fasta_file (const char *fname, bool ignore_invalid=false) |
bool | load_fastq_file (const char *fname, bool ignore_invalid=false, bool bitremap_in_single_string=false) |
bool | load_from_directory (char *dirname) |
void | set_features (SGStringList< ST > feats) |
bool | set_features (SGString< ST > *p_features, int32_t p_num_vectors, int32_t p_max_string_length) |
bool | append_features (CStringFeatures< ST > *sf) |
bool | append_features (SGString< ST > *p_features, int32_t p_num_vectors, int32_t p_max_string_length) |
SGStringList< ST > | get_features () |
virtual SGString< ST > * | get_features (int32_t &num_str, int32_t &max_str_len) |
virtual SGString< ST > * | copy_features (int32_t &num_str, int32_t &max_str_len) |
virtual void | get_features (SGString< ST > **dst, int32_t *num_str) |
virtual void | save (CFile *writer) |
virtual bool | load_compressed (char *src, bool decompress) |
virtual bool | save_compressed (char *dest, E_COMPRESSION_TYPE compression, int level) |
virtual int32_t | get_size () const |
virtual bool | apply_preprocessor (bool force_preprocessing=false) |
int32_t | obtain_by_sliding_window (int32_t window_size, int32_t step_size, int32_t skip=0) |
int32_t | obtain_by_position_list (int32_t window_size, CDynamicArray< int32_t > *positions, int32_t skip=0) |
bool | obtain_from_char (CStringFeatures< char > *sf, int32_t start, int32_t p_order, int32_t gap, bool rev) |
template<class CT > | |
bool | obtain_from_char_features (CStringFeatures< CT > *sf, int32_t start, int32_t p_order, int32_t gap, bool rev) |
bool | have_same_length (int32_t len=-1) |
void | embed_features (int32_t p_order) |
void | compute_symbol_mask_table (int64_t max_val) |
void | unembed_word (ST word, uint8_t *seq, int32_t len) |
ST | embed_word (ST *seq, int32_t len) |
void | determine_maximum_string_length () |
virtual void | set_feature_vector (int32_t num, ST *string, int32_t len) |
virtual void | get_histogram (float64_t **hist, int32_t *rows, int32_t *cols, bool normalize=true) |
virtual void | create_random (float64_t *hist, int32_t rows, int32_t cols, int32_t num_vec) |
virtual CFeatures * | copy_subset (SGVector< index_t > indices) |
virtual const char * | get_name () const |
virtual void | subset_changed_post () |
template<> | |
EFeatureType | get_feature_type () const |
template<> | |
EFeatureType | get_feature_type () const |
template<> | |
EFeatureType | get_feature_type () const |
template<> | |
EFeatureType | get_feature_type () const |
template<> | |
EFeatureType | get_feature_type () const |
template<> | |
EFeatureType | get_feature_type () const |
template<> | |
EFeatureType | get_feature_type () const |
template<> | |
EFeatureType | get_feature_type () const |
template<> | |
EFeatureType | get_feature_type () const |
template<> | |
EFeatureType | get_feature_type () const |
template<> | |
EFeatureType | get_feature_type () const |
template<> | |
EFeatureType | get_feature_type () const |
template<> | |
bool | get_masked_symbols (bool symbol, uint8_t mask) |
template<> | |
float32_t | get_masked_symbols (float32_t symbol, uint8_t mask) |
template<> | |
float64_t | get_masked_symbols (float64_t symbol, uint8_t mask) |
template<> | |
floatmax_t | get_masked_symbols (floatmax_t symbol, uint8_t mask) |
template<> | |
bool | shift_offset (bool symbol, int32_t amount) |
template<> | |
float32_t | shift_offset (float32_t symbol, int32_t amount) |
template<> | |
float64_t | shift_offset (float64_t symbol, int32_t amount) |
template<> | |
floatmax_t | shift_offset (floatmax_t symbol, int32_t amount) |
template<> | |
bool | shift_symbol (bool symbol, int32_t amount) |
template<> | |
float32_t | shift_symbol (float32_t symbol, int32_t amount) |
template<> | |
float64_t | shift_symbol (float64_t symbol, int32_t amount) |
template<> | |
floatmax_t | shift_symbol (floatmax_t symbol, int32_t amount) |
template<> | |
bool | obtain_from_char_features (CStringFeatures< CT > *sf, int32_t start, int32_t p_order, int32_t gap, bool rev) |
template<> | |
bool | obtain_from_char_features (CStringFeatures< CT > *sf, int32_t start, int32_t p_order, int32_t gap, bool rev) |
template<> | |
bool | obtain_from_char_features (CStringFeatures< CT > *sf, int32_t start, int32_t p_order, int32_t gap, bool rev) |
template<> | |
void | embed_features (int32_t p_order) |
template<> | |
void | embed_features (int32_t p_order) |
template<> | |
void | embed_features (int32_t p_order) |
template<> | |
void | compute_symbol_mask_table (int64_t max_val) |
template<> | |
void | compute_symbol_mask_table (int64_t max_val) |
template<> | |
void | compute_symbol_mask_table (int64_t max_val) |
template<> | |
float32_t | embed_word (float32_t *seq, int32_t len) |
template<> | |
float64_t | embed_word (float64_t *seq, int32_t len) |
template<> | |
floatmax_t | embed_word (floatmax_t *seq, int32_t len) |
template<> | |
void | unembed_word (float32_t word, uint8_t *seq, int32_t len) |
template<> | |
void | unembed_word (float64_t word, uint8_t *seq, int32_t len) |
template<> | |
void | unembed_word (floatmax_t word, uint8_t *seq, int32_t len) |
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 |
virtual bool | reshape (int32_t num_features, int32_t num_vectors) |
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 CFeatures * | create_merged_copy (CFeatures *other) |
virtual void | add_subset (SGVector< index_t > subset) |
virtual void | remove_subset () |
virtual void | remove_all_subsets () |
virtual CSubsetStack * | get_subset_stack () |
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 ST * | get_zero_terminated_string_copy (SGString< ST > str) |
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 ST * | compute_feature_vector (int32_t num, int32_t &len) |
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 | |
CAlphabet * | alphabet |
int32_t | num_vectors |
SGString< ST > * | features |
ST * | single_string |
int32_t | length_of_single_string |
length of prior single string | |
int32_t | max_string_length |
floatmax_t | num_symbols |
number of used symbols | |
floatmax_t | original_num_symbols |
original number of used symbols (before higher order mapping) | |
int32_t | order |
order used in higher order mapping | |
ST * | symbol_mask_table |
order used in higher order mapping | |
int32_t | symbol_mask_table_len |
order used in higher order mapping | |
bool | preprocess_on_get |
preprocess on-the-fly? | |
CCache< ST > * | feature_cache |
CSubsetStack * | m_subset_stack |
CStringFeatures | ( | ) |
default constructor
Definition at line 20 of file StringFeatures.cpp.
CStringFeatures | ( | EAlphabet | alpha | ) |
constructor
alpha | alphabet (type) to use for string features |
Definition at line 26 of file StringFeatures.cpp.
CStringFeatures | ( | SGStringList< ST > | string_list, | |
EAlphabet | alpha | |||
) |
constructor
string_list | ||
alpha | alphabet (type) to use for string features |
Definition at line 36 of file StringFeatures.cpp.
CStringFeatures | ( | SGStringList< ST > | string_list, | |
CAlphabet * | alpha | |||
) |
constructor
string_list | ||
alpha | an actual alphabet |
Definition at line 48 of file StringFeatures.cpp.
CStringFeatures | ( | CAlphabet * | alpha | ) |
constructor
alpha | alphabet to use for string features |
Definition at line 60 of file StringFeatures.cpp.
CStringFeatures | ( | const CStringFeatures< ST > & | orig | ) |
copy constructor
Definition at line 72 of file StringFeatures.cpp.
CStringFeatures | ( | CFile * | loader, | |
EAlphabet | alpha = DNA | |||
) |
constructor
loader | File object via which to load data | |
alpha | alphabet (type) to use for string features |
Definition at line 112 of file StringFeatures.cpp.
~CStringFeatures | ( | ) | [virtual] |
Definition at line 127 of file StringFeatures.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.
bool append_features | ( | SGString< ST > * | p_features, | |
int32_t | p_num_vectors, | |||
int32_t | p_max_string_length | |||
) |
append features
not possible with subset
p_features | features to append | |
p_num_vectors | number of vectors | |
p_max_string_length | maximum string length |
note that p_features will be SG_FREE()'d on success
Definition at line 911 of file StringFeatures.cpp.
bool append_features | ( | CStringFeatures< ST > * | sf | ) |
append features If the given string features have a subset, only this will be copied
not possible with subset
sf | features to append |
Definition at line 889 of file StringFeatures.cpp.
bool apply_preprocessor | ( | bool | force_preprocessing = false |
) | [virtual] |
apply preprocessor
force_preprocessing | if preprocssing shall be forced |
Definition at line 1169 of file StringFeatures.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.
void cleanup | ( | ) | [virtual] |
cleanup string features.
removes any subset before
Reimplemented in CStringFileFeatures< ST >.
Definition at line 134 of file StringFeatures.cpp.
void cleanup_feature_vector | ( | int32_t | num | ) | [virtual] |
cleanup a single feature vector
possible with subset
num | number of the vector |
Reimplemented in CStringFileFeatures< ST >.
Definition at line 172 of file StringFeatures.cpp.
void cleanup_feature_vectors | ( | int32_t | start, | |
int32_t | stop | |||
) | [virtual] |
cleanup multiple feature vectors
possible with subset
start | index of first vector to be cleaned | |
stop | index of the last vector to be cleaned |
Definition at line 187 of file StringFeatures.cpp.
ST * compute_feature_vector | ( | int32_t | num, | |
int32_t & | len | |||
) | [protected, virtual] |
compute feature vector for sample num if target is set the vector is written to target len is returned by reference
possible with subset
num | which vector | |
len | length of vector |
Definition at line 1642 of file StringFeatures.cpp.
void compute_symbol_mask_table | ( | int64_t | max_val | ) |
Definition at line 1882 of file StringFeatures.cpp.
void compute_symbol_mask_table | ( | int64_t | max_val | ) |
Definition at line 1885 of file StringFeatures.cpp.
void compute_symbol_mask_table | ( | int64_t | max_val | ) |
compute symbol mask table
required to access bit-based symbols
not implemented for subset
Definition at line 1366 of file StringFeatures.cpp.
void compute_symbol_mask_table | ( | int64_t | max_val | ) |
Definition at line 1888 of file StringFeatures.cpp.
SGString< ST > * copy_features | ( | int32_t & | num_str, | |
int32_t & | max_str_len | |||
) | [virtual] |
copy_features
possible with subset
num_str | number of strings (returned) | |
max_str_len | maximal string length (returned) |
Definition at line 982 of file StringFeatures.cpp.
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.
Definition at line 1601 of file StringFeatures.cpp.
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.
NOT IMPLEMENTED!
other | feature object to append |
Reimplemented in CCombinedFeatures, CDenseFeatures< ST >, CDenseFeatures< uint32_t >, CDenseFeatures< float64_t >, CDenseFeatures< T >, and CDenseFeatures< uint16_t >.
Definition at line 234 of file Features.h.
void create_random | ( | float64_t * | hist, | |
int32_t | rows, | |||
int32_t | cols, | |||
int32_t | num_vec | |||
) | [virtual] |
create some random strings based on normalized histogram
not possible with subset
Definition at line 1499 of file StringFeatures.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.
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.
void determine_maximum_string_length | ( | ) |
determine new maximum string length
possible with subset
Definition at line 1422 of file StringFeatures.cpp.
void disable_on_the_fly_preprocessing | ( | ) |
call this to disable on the fly feature preprocessing on get_feature_vector. Useful when you manually apply preprocessors.
Definition at line 267 of file StringFeatures.cpp.
CFeatures * duplicate | ( | ) | const [virtual] |
duplicate feature object
Implements CFeatures.
Definition at line 215 of file StringFeatures.cpp.
void embed_features | ( | int32_t | p_order | ) |
Definition at line 1872 of file StringFeatures.cpp.
void embed_features | ( | int32_t | p_order | ) |
Definition at line 1878 of file StringFeatures.cpp.
void embed_features | ( | int32_t | p_order | ) |
Definition at line 1875 of file StringFeatures.cpp.
void embed_features | ( | int32_t | p_order | ) |
embed string features in bit representation in-place
not implemented for subset
Definition at line 1312 of file StringFeatures.cpp.
Definition at line 1892 of file StringFeatures.cpp.
Definition at line 1896 of file StringFeatures.cpp.
floatmax_t embed_word | ( | floatmax_t * | seq, | |
int32_t | len | |||
) |
Definition at line 1900 of file StringFeatures.cpp.
ST embed_word | ( | ST * | seq, | |
int32_t | len | |||
) |
embed a single word
seq | sequence of size len in a bitfield | |
len |
Definition at line 1409 of file StringFeatures.cpp.
void enable_on_the_fly_preprocessing | ( | ) |
call this to preprocess string features upon get_feature_vector
Definition at line 262 of file StringFeatures.cpp.
void free_feature_vector | ( | SGVector< ST > | feat_vec, | |
int32_t | num | |||
) |
free feature vector
possible with subset
feat_vec | feature vector to free | |
num | index in feature cache, possibly from subset |
Definition at line 372 of file StringFeatures.cpp.
void free_feature_vector | ( | ST * | feat_vec, | |
int32_t | num, | |||
bool | dofree | |||
) |
free feature vector
possible with subset
feat_vec | feature vector to free | |
num | index in feature cache, possibly from subset | |
dofree | if vector should be really deleted |
Definition at line 354 of file StringFeatures.cpp.
CAlphabet * get_alphabet | ( | ) |
get alphabet used in string features
Definition at line 209 of file StringFeatures.cpp.
int32_t get_cache_size | ( | ) | const [inherited] |
ST get_feature | ( | int32_t | vec_num, | |
int32_t | feat_num | |||
) | [virtual] |
get feature
possible with subset
vec_num | which vector | |
feat_num | which feature, possibly from subset |
Definition at line 387 of file StringFeatures.cpp.
EFeatureClass get_feature_class | ( | ) | const [virtual] |
get feature class
Implements CFeatures.
Definition at line 205 of file StringFeatures.cpp.
EFeatureType get_feature_type | ( | ) | const [virtual] |
get feature type the char feature can deal with
Implements CFeatures.
Definition at line 1702 of file StringFeatures.cpp.
EFeatureType get_feature_type | ( | ) | const [virtual] |
get feature type the char feature can deal with
Implements CFeatures.
Definition at line 1711 of file StringFeatures.cpp.
EFeatureType get_feature_type | ( | ) | const [virtual] |
get feature type the BYTE feature can deal with
Implements CFeatures.
Definition at line 1720 of file StringFeatures.cpp.
EFeatureType get_feature_type | ( | ) | const [virtual] |
get feature type the SHORT feature can deal with
Implements CFeatures.
Definition at line 1729 of file StringFeatures.cpp.
EFeatureType get_feature_type | ( | ) | const [virtual] |
get feature type the WORD feature can deal with
Implements CFeatures.
Definition at line 1738 of file StringFeatures.cpp.
EFeatureType get_feature_type | ( | ) | const [virtual] |
get feature type the INT feature can deal with
Implements CFeatures.
Definition at line 1747 of file StringFeatures.cpp.
EFeatureType get_feature_type | ( | ) | const [virtual] |
get feature type the INT feature can deal with
Implements CFeatures.
Definition at line 1756 of file StringFeatures.cpp.
EFeatureType get_feature_type | ( | ) | const [virtual] |
get feature type the LONG feature can deal with
Implements CFeatures.
Definition at line 1765 of file StringFeatures.cpp.
EFeatureType get_feature_type | ( | ) | const [virtual] |
get feature type the ULONG feature can deal with
Implements CFeatures.
Definition at line 1774 of file StringFeatures.cpp.
EFeatureType get_feature_type | ( | ) | const [virtual] |
get feature type the SHORTREAL feature can deal with
Implements CFeatures.
Definition at line 1783 of file StringFeatures.cpp.
EFeatureType get_feature_type | ( | ) | const [virtual] |
get feature type the DREAL feature can deal with
Implements CFeatures.
Definition at line 1792 of file StringFeatures.cpp.
EFeatureType get_feature_type | ( | ) | const [virtual] |
get feature type the LONGREAL feature can deal with
Implements CFeatures.
Definition at line 1801 of file StringFeatures.cpp.
EFeatureType get_feature_type | ( | ) | const [virtual] |
get feature type
Implements CFeatures.
Definition at line 207 of file StringFeatures.cpp.
SGVector< ST > get_feature_vector | ( | int32_t | num | ) |
get string for selected example num
possible with subset
num | index of the string |
Definition at line 220 of file StringFeatures.cpp.
ST * get_feature_vector | ( | int32_t | num, | |
int32_t & | len, | |||
bool & | dofree | |||
) |
get feature vector for sample num
possible with subset
num | index of feature vector | |
len | length is returned by reference | |
dofree | whether returned vector must be freed by caller via free_feature_vector |
Definition at line 272 of file StringFeatures.cpp.
SGStringList< ST > get_features | ( | ) |
SGString< ST > * get_features | ( | int32_t & | num_str, | |
int32_t & | max_str_len | |||
) | [virtual] |
get_features
not possible with subset
num_str | number of strings (returned) | |
max_str_len | maximal string length (returned) |
Definition at line 972 of file StringFeatures.cpp.
void get_features | ( | SGString< ST > ** | dst, | |
int32_t * | num_str | |||
) | [virtual] |
get_features (swig compatible)
possible with subset
dst | string features (returned) | |
num_str | number of strings (returned) |
Definition at line 1004 of file StringFeatures.cpp.
SGIO * get_global_io | ( | ) | [inherited] |
Parallel * get_global_parallel | ( | ) | [inherited] |
Version * get_global_version | ( | ) | [inherited] |
void get_histogram | ( | float64_t ** | hist, | |
int32_t * | rows, | |||
int32_t * | cols, | |||
bool | normalize = true | |||
) | [virtual] |
compute histogram over strings
possible with subset
Definition at line 1457 of file StringFeatures.cpp.
bool get_masked_symbols | ( | bool | symbol, | |
uint8_t | mask | |||
) |
Definition at line 1806 of file StringFeatures.cpp.
Definition at line 1810 of file StringFeatures.cpp.
Definition at line 1814 of file StringFeatures.cpp.
floatmax_t get_masked_symbols | ( | floatmax_t | symbol, | |
uint8_t | mask | |||
) |
Definition at line 1818 of file StringFeatures.cpp.
ST get_masked_symbols | ( | ST | symbol, | |
uint8_t | mask | |||
) |
a higher order mapped symbol will be shaped such that the symbols specified by bits in the mask will be returned.
symbol | symbol to mask | |
mask | mask to apply |
Definition at line 430 of file StringFeatures.cpp.
floatmax_t get_max_num_symbols | ( | ) |
get maximum number of symbols
Note: floatmax_t sounds weird, but int64_t is not long enough (and there is no int128_t type)
Definition at line 424 of file StringFeatures.cpp.
int32_t get_max_vector_length | ( | ) | [virtual] |
get maximum vector length
this one is updated when a subset is set
Definition at line 412 of file StringFeatures.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] |
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.
floatmax_t get_num_symbols | ( | ) |
get number of symbols
Note: floatmax_t sounds weird, but LONG is not long enough
Definition at line 422 of file StringFeatures.cpp.
int32_t get_num_vectors | ( | ) | const [virtual] |
Implements CFeatures.
Definition at line 417 of file StringFeatures.cpp.
int32_t get_order | ( | ) |
order used for higher order mapping
Definition at line 428 of file StringFeatures.cpp.
floatmax_t get_original_num_symbols | ( | ) |
number of symbols before higher order mapping
Definition at line 426 of file StringFeatures.cpp.
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.
int32_t get_size | ( | ) | const [virtual] |
get memory footprint of one feature
Implements CFeatures.
Definition at line 1167 of file StringFeatures.cpp.
CSubsetStack * get_subset_stack | ( | ) | [virtual, inherited] |
CStringFeatures< ST > * get_transposed | ( | ) |
get a transposed copy of the features
possible with subset
Definition at line 310 of file StringFeatures.cpp.
SGString< ST > * get_transposed | ( | int32_t & | num_feat, | |
int32_t & | num_vec | |||
) |
compute and return the transpose of string features matrix which will be prepocessed. num_feat, num_vectors are returned by reference caller has to clean up
note that strings all have to have same length
possible with subset
num_feat | number of features in matrix | |
num_vec | number of vectors in matrix |
Definition at line 323 of file StringFeatures.cpp.
int32_t get_vector_length | ( | int32_t | vec_num | ) | [virtual] |
get vector length
possible with subset
vec_num | which vector, possibly from subset |
Definition at line 401 of file StringFeatures.cpp.
ST * get_zero_terminated_string_copy | ( | SGString< ST > | str | ) | [static] |
get a zero terminated copy of the string
str | the string to copy |
note that this function is only sensible for character strings
Definition at line 1434 of file StringFeatures.cpp.
bool has_property | ( | EFeatureProperty | p | ) | const [inherited] |
check if features have given property
p | feature property |
Definition at line 336 of file Features.cpp.
bool have_same_length | ( | int32_t | len = -1 |
) |
check if length of each vector in this feature object equals the given length. if existant, only subset is checked
possible for subset
len | vector length to check against |
Definition at line 1293 of file StringFeatures.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.
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] |
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.
void load_ascii_file | ( | char * | fname, | |
bool | remap_to_bin = true , |
|||
EAlphabet | ascii_alphabet = DNA , |
|||
EAlphabet | binary_alphabet = RAWDNA | |||
) |
load ascii line-based string features from file.
any subset is removed before
fname | filename to load from | |
remap_to_bin | if translation to other binary alphabet should be performed | |
ascii_alphabet | src alphabet | |
binary_alphabet | alphabet to translate to |
Definition at line 448 of file StringFeatures.cpp.
bool load_compressed | ( | char * | src, | |
bool | decompress | |||
) | [virtual] |
load compressed features from file
any subset is removed before
src | filename to load from | |
decompress | whether to decompress on loading |
Definition at line 1012 of file StringFeatures.cpp.
bool load_fasta_file | ( | const char * | fname, | |
bool | ignore_invalid = false | |||
) |
load fasta file as string features
any subset is removed before
fname | filename to load from | |
ignore_invalid | if set to true, characters other than A,C,G,T are converted to A |
Definition at line 581 of file StringFeatures.cpp.
bool load_fastq_file | ( | const char * | fname, | |
bool | ignore_invalid = false , |
|||
bool | bitremap_in_single_string = false | |||
) |
load fastq file as string features
removes subset beforehand
fname | filename to load from | |
ignore_invalid | if set to true, characters other than A,C,G,T are converted to A | |
bitremap_in_single_string | if set to true, do binary embedding of symbols |
Definition at line 674 of file StringFeatures.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_from_directory | ( | char * | dirname | ) |
load features from directory
removes subset before
dirname | directory name to load from |
Definition at line 775 of file StringFeatures.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.
int32_t obtain_by_position_list | ( | int32_t | window_size, | |
CDynamicArray< int32_t > * | positions, | |||
int32_t | skip = 0 | |||
) |
extracts windows of size window_size from first string using the positions in list
not implemented for subset
window_size | window size | |
positions | positions | |
skip | skip |
Definition at line 1230 of file StringFeatures.cpp.
int32_t obtain_by_sliding_window | ( | int32_t | window_size, | |
int32_t | step_size, | |||
int32_t | skip = 0 | |||
) |
slides a window of size window_size over the current single string step_size is the amount by which the window is shifted. creates (string_len-window_size)/step_size many feature obj if skip is nonzero, skip the first 'skip' characters of each string
not implemented for subset
window_size | window size | |
step_size | step size | |
skip | skip |
Definition at line 1193 of file StringFeatures.cpp.
bool obtain_from_char | ( | CStringFeatures< char > * | sf, | |
int32_t | start, | |||
int32_t | p_order, | |||
int32_t | gap, | |||
bool | rev | |||
) |
obtain string features from char features
wrapper for template method
any subset is removed before, subset of parameter sf is possible
sf | string features | |
start | start | |
p_order | order | |
gap | gap | |
rev | reverse |
Definition at line 1288 of file StringFeatures.cpp.
bool obtain_from_char_features | ( | CStringFeatures< CT > * | sf, | |
int32_t | start, | |||
int32_t | p_order, | |||
int32_t | gap, | |||
bool | rev | |||
) |
Definition at line 1862 of file StringFeatures.cpp.
bool obtain_from_char_features | ( | CStringFeatures< CT > * | sf, | |
int32_t | start, | |||
int32_t | p_order, | |||
int32_t | gap, | |||
bool | rev | |||
) |
Definition at line 1858 of file StringFeatures.cpp.
bool obtain_from_char_features | ( | CStringFeatures< CT > * | sf, | |
int32_t | start, | |||
int32_t | p_order, | |||
int32_t | gap, | |||
bool | rev | |||
) |
Definition at line 1866 of file StringFeatures.cpp.
bool obtain_from_char_features | ( | CStringFeatures< CT > * | sf, | |
int32_t | start, | |||
int32_t | p_order, | |||
int32_t | gap, | |||
bool | rev | |||
) |
template obtain from char features
any subset is removed before, subset of parameter sf is possible
sf | string features | |
start | start | |
p_order | order | |
gap | gap | |
rev | reverse |
Definition at line 1970 of file StringFeatures.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.
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.
bool reshape | ( | int32_t | num_features, | |
int32_t | num_vectors | |||
) | [virtual, inherited] |
in case there is a feature matrix allow for reshaping
NOT IMPLEMENTED!
num_features | new number of features | |
num_vectors | new number of vectors |
Reimplemented in CDenseFeatures< ST >, CDenseFeatures< uint32_t >, CDenseFeatures< float64_t >, CDenseFeatures< T >, and CDenseFeatures< uint16_t >.
Definition at line 208 of file Features.cpp.
virtual void save | ( | CFile * | writer | ) | [virtual] |
save features to file
not possible with subset
writer | File object via which to save data |
Reimplemented from CFeatures.
bool save_compressed | ( | char * | dest, | |
E_COMPRESSION_TYPE | compression, | |||
int | level | |||
) | [virtual] |
save compressed features to file
not possible with subset
dest | filename to save to | |
compression | compressor to use | |
level | compression level to use (1-9) |
Definition at line 1107 of file StringFeatures.cpp.
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_feature_vector | ( | SGVector< ST > | vector, | |
int32_t | num | |||
) |
set string for selected example num
not possible with subset
vector | ||
num | index of the string |
Definition at line 238 of file StringFeatures.cpp.
void set_feature_vector | ( | int32_t | num, | |
ST * | string, | |||
int32_t | len | |||
) | [virtual] |
set feature vector for sample num
possible with subset
num | index of feature vector | |
string | string with the feature vector's content | |
len | length of the string |
Definition at line 1443 of file StringFeatures.cpp.
void set_features | ( | SGStringList< ST > | feats | ) |
bool set_features | ( | SGString< ST > * | p_features, | |
int32_t | p_num_vectors, | |||
int32_t | p_max_string_length | |||
) |
set features
not possible with subset
p_features | new features | |
p_num_vectors | number of vectors | |
p_max_string_length | maximum string length |
Definition at line 850 of file StringFeatures.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.
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.
floatmax_t shift_offset | ( | floatmax_t | symbol, | |
int32_t | amount | |||
) |
Definition at line 1835 of file StringFeatures.cpp.
bool shift_offset | ( | bool | symbol, | |
int32_t | amount | |||
) |
Definition at line 1823 of file StringFeatures.cpp.
Definition at line 1827 of file StringFeatures.cpp.
ST shift_offset | ( | ST | offset, | |
int32_t | amount | |||
) |
shift offset to the left by amount
offset | offset to shift | |
amount | amount to shift the offset |
Definition at line 436 of file StringFeatures.cpp.
Definition at line 1831 of file StringFeatures.cpp.
ST shift_symbol | ( | ST | symbol, | |
int32_t | amount | |||
) |
shift symbol to the right by amount (taking care of custom symbol sizes)
symbol | symbol to shift | |
amount | amount to shift the symbol |
Definition at line 442 of file StringFeatures.cpp.
floatmax_t shift_symbol | ( | floatmax_t | symbol, | |
int32_t | amount | |||
) |
Definition at line 1852 of file StringFeatures.cpp.
bool shift_symbol | ( | bool | symbol, | |
int32_t | amount | |||
) |
Definition at line 1840 of file StringFeatures.cpp.
Definition at line 1848 of file StringFeatures.cpp.
Definition at line 1844 of file StringFeatures.cpp.
void subset_changed_post | ( | ) | [virtual] |
post method when subset is changed
Reimplemented from CFeatures.
Definition at line 1636 of file StringFeatures.cpp.
void unembed_word | ( | float64_t | word, | |
uint8_t * | seq, | |||
int32_t | len | |||
) |
Definition at line 1908 of file StringFeatures.cpp.
void unembed_word | ( | ST | word, | |
uint8_t * | seq, | |||
int32_t | len | |||
) |
remap bit-based word to character sequence
word | word to remap | |
seq | sequence of size len that remapped characters are written to | |
len | length of sequence and word |
Definition at line 1393 of file StringFeatures.cpp.
void unembed_word | ( | float32_t | word, | |
uint8_t * | seq, | |||
int32_t | len | |||
) |
Definition at line 1905 of file StringFeatures.cpp.
void unembed_word | ( | floatmax_t | word, | |
uint8_t * | seq, | |||
int32_t | len | |||
) |
Definition at line 1911 of file StringFeatures.cpp.
void unset_generic | ( | ) | [inherited] |
unset generic type
this has to be called in classes specializing a template class
Definition at line 285 of file SGObject.cpp.
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.
alphabet
Definition at line 673 of file StringFeatures.h.
CCache<ST>* feature_cache [protected] |
feature cache
Definition at line 709 of file StringFeatures.h.
this contains the array of features
Definition at line 679 of file StringFeatures.h.
io
Definition at line 462 of file SGObject.h.
int32_t length_of_single_string [protected] |
length of prior single string
Definition at line 685 of file StringFeatures.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.
int32_t max_string_length [protected] |
length of longest string (for subset, is updated)
Definition at line 688 of file StringFeatures.h.
floatmax_t num_symbols [protected] |
number of used symbols
Definition at line 691 of file StringFeatures.h.
int32_t num_vectors [protected] |
number of string vectors (for subset, is updated)
Definition at line 676 of file StringFeatures.h.
int32_t order [protected] |
order used in higher order mapping
Definition at line 697 of file StringFeatures.h.
floatmax_t original_num_symbols [protected] |
original number of used symbols (before higher order mapping)
Definition at line 694 of file StringFeatures.h.
parallel
Definition at line 465 of file SGObject.h.
bool preprocess_on_get [protected] |
preprocess on-the-fly?
Definition at line 706 of file StringFeatures.h.
ST* single_string [protected] |
true when single string / created by sliding window
Definition at line 682 of file StringFeatures.h.
ST* symbol_mask_table [protected] |
order used in higher order mapping
Definition at line 700 of file StringFeatures.h.
int32_t symbol_mask_table_len [protected] |
order used in higher order mapping
Definition at line 703 of file StringFeatures.h.
version
Definition at line 468 of file SGObject.h.