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. CSimpleFeatures) 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) set_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
Definition at line 71 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 () |
virtual EFeatureType | get_feature_type () |
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 () |
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 () |
template<> | |
EFeatureType | get_feature_type () |
template<> | |
EFeatureType | get_feature_type () |
template<> | |
EFeatureType | get_feature_type () |
template<> | |
EFeatureType | get_feature_type () |
template<> | |
EFeatureType | get_feature_type () |
template<> | |
EFeatureType | get_feature_type () |
template<> | |
EFeatureType | get_feature_type () |
template<> | |
EFeatureType | get_feature_type () |
template<> | |
EFeatureType | get_feature_type () |
template<> | |
EFeatureType | get_feature_type () |
template<> | |
EFeatureType | get_feature_type () |
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) |
Static Public Member Functions | |
static ST * | get_zero_terminated_string_copy (SGString< ST > str) |
Protected Member Functions | |
virtual ST * | compute_feature_vector (int32_t num, int32_t &len) |
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 | |
bool | preprocess_on_get |
preprocess on-the-fly? | |
CCache< ST > * | feature_cache |
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 111 of file StringFeatures.cpp.
~CStringFeatures | ( | ) | [virtual] |
Definition at line 126 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 879 of file StringFeatures.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 901 of file StringFeatures.cpp.
bool apply_preprocessor | ( | bool | force_preprocessing = false |
) | [virtual] |
apply preprocessor
force_preprocessing | if preprocssing shall be forced |
Definition at line 1159 of file StringFeatures.cpp.
void cleanup | ( | ) | [virtual] |
cleanup string features.
removes any subset before
Reimplemented in CStringFileFeatures< ST >.
Definition at line 133 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 161 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 176 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 1625 of file StringFeatures.cpp.
void compute_symbol_mask_table | ( | int64_t | max_val | ) |
Definition at line 1863 of file StringFeatures.cpp.
void compute_symbol_mask_table | ( | int64_t | max_val | ) |
Definition at line 1866 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 1356 of file StringFeatures.cpp.
void compute_symbol_mask_table | ( | int64_t | max_val | ) |
Definition at line 1869 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 972 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 1591 of file StringFeatures.cpp.
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 1489 of file StringFeatures.cpp.
void determine_maximum_string_length | ( | ) |
determine new maximum string length
possible with subset
Definition at line 1412 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 256 of file StringFeatures.cpp.
CFeatures * duplicate | ( | ) | const [virtual] |
duplicate feature object
Implements CFeatures.
Definition at line 204 of file StringFeatures.cpp.
void embed_features | ( | int32_t | p_order | ) |
Definition at line 1853 of file StringFeatures.cpp.
void embed_features | ( | int32_t | p_order | ) |
Definition at line 1859 of file StringFeatures.cpp.
void embed_features | ( | int32_t | p_order | ) |
Definition at line 1856 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 1302 of file StringFeatures.cpp.
floatmax_t embed_word | ( | floatmax_t * | seq, | |
int32_t | len | |||
) |
Definition at line 1881 of file StringFeatures.cpp.
Definition at line 1873 of file StringFeatures.cpp.
Definition at line 1877 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 1399 of file StringFeatures.cpp.
void enable_on_the_fly_preprocessing | ( | ) |
call this to preprocess string features upon get_feature_vector
Definition at line 251 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 361 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 343 of file StringFeatures.cpp.
CAlphabet * get_alphabet | ( | ) |
get alphabet used in string features
Definition at line 198 of file StringFeatures.cpp.
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 379 of file StringFeatures.cpp.
EFeatureClass get_feature_class | ( | ) | [virtual] |
get feature class
Implements CFeatures.
Definition at line 194 of file StringFeatures.cpp.
EFeatureType get_feature_type | ( | ) | [virtual] |
get feature type the char feature can deal with
Implements CFeatures.
Definition at line 1683 of file StringFeatures.cpp.
EFeatureType get_feature_type | ( | ) | [virtual] |
get feature type the LONG feature can deal with
Implements CFeatures.
Definition at line 1746 of file StringFeatures.cpp.
EFeatureType get_feature_type | ( | ) | [virtual] |
get feature type the char feature can deal with
Implements CFeatures.
Definition at line 1692 of file StringFeatures.cpp.
EFeatureType get_feature_type | ( | ) | [virtual] |
get feature type the BYTE feature can deal with
Implements CFeatures.
Definition at line 1701 of file StringFeatures.cpp.
EFeatureType get_feature_type | ( | ) | [virtual] |
get feature type the SHORT feature can deal with
Implements CFeatures.
Definition at line 1710 of file StringFeatures.cpp.
EFeatureType get_feature_type | ( | ) | [virtual] |
get feature type the WORD feature can deal with
Implements CFeatures.
Definition at line 1719 of file StringFeatures.cpp.
EFeatureType get_feature_type | ( | ) | [virtual] |
get feature type the INT feature can deal with
Implements CFeatures.
Definition at line 1728 of file StringFeatures.cpp.
EFeatureType get_feature_type | ( | ) | [virtual] |
get feature type the INT feature can deal with
Implements CFeatures.
Definition at line 1737 of file StringFeatures.cpp.
EFeatureType get_feature_type | ( | ) | [virtual] |
get feature type the ULONG feature can deal with
Implements CFeatures.
Definition at line 1755 of file StringFeatures.cpp.
EFeatureType get_feature_type | ( | ) | [virtual] |
get feature type the SHORTREAL feature can deal with
Implements CFeatures.
Definition at line 1764 of file StringFeatures.cpp.
EFeatureType get_feature_type | ( | ) | [virtual] |
get feature type the DREAL feature can deal with
Implements CFeatures.
Definition at line 1773 of file StringFeatures.cpp.
EFeatureType get_feature_type | ( | ) | [virtual] |
get feature type
Implements CFeatures.
Definition at line 196 of file StringFeatures.cpp.
EFeatureType get_feature_type | ( | ) | [virtual] |
get feature type the LONGREAL feature can deal with
Implements CFeatures.
Definition at line 1782 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 209 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 261 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 962 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 994 of file StringFeatures.cpp.
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 1447 of file StringFeatures.cpp.
Definition at line 1791 of file StringFeatures.cpp.
bool get_masked_symbols | ( | bool | symbol, | |
uint8_t | mask | |||
) |
Definition at line 1787 of file StringFeatures.cpp.
Definition at line 1795 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 422 of file StringFeatures.cpp.
floatmax_t get_masked_symbols | ( | floatmax_t | symbol, | |
uint8_t | mask | |||
) |
Definition at line 1799 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 416 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 404 of file StringFeatures.cpp.
virtual const char* get_name | ( | ) | const [virtual] |
floatmax_t get_num_symbols | ( | ) |
get number of symbols
Note: floatmax_t sounds weird, but LONG is not long enough
Definition at line 414 of file StringFeatures.cpp.
int32_t get_num_vectors | ( | ) | const [virtual] |
Implements CFeatures.
Definition at line 409 of file StringFeatures.cpp.
int32_t get_order | ( | ) |
order used for higher order mapping
Definition at line 420 of file StringFeatures.cpp.
floatmax_t get_original_num_symbols | ( | ) |
number of symbols before higher order mapping
Definition at line 418 of file StringFeatures.cpp.
int32_t get_size | ( | ) | [virtual] |
get memory footprint of one feature
Implements CFeatures.
Definition at line 1157 of file StringFeatures.cpp.
CStringFeatures< ST > * get_transposed | ( | ) |
get a transposed copy of the features
possible with subset
Definition at line 299 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 312 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 393 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 1424 of file StringFeatures.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 1283 of file StringFeatures.cpp.
virtual void load | ( | CFile * | loader | ) | [virtual] |
load features from file
loader | File object via which to load data |
Reimplemented from CFeatures.
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 440 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 1002 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 573 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 666 of file StringFeatures.cpp.
bool load_from_directory | ( | char * | dirname | ) |
load features from directory
removes subset before
dirname | directory name to load from |
Definition at line 767 of file StringFeatures.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 1220 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 1183 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 1278 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 1951 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 1843 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 1847 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 1839 of file StringFeatures.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 1097 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 1433 of file StringFeatures.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 227 of file StringFeatures.cpp.
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 842 of file StringFeatures.cpp.
void set_features | ( | SGStringList< ST > | feats | ) |
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 428 of file StringFeatures.cpp.
floatmax_t shift_offset | ( | floatmax_t | symbol, | |
int32_t | amount | |||
) |
Definition at line 1816 of file StringFeatures.cpp.
bool shift_offset | ( | bool | symbol, | |
int32_t | amount | |||
) |
Definition at line 1804 of file StringFeatures.cpp.
Definition at line 1808 of file StringFeatures.cpp.
Definition at line 1812 of file StringFeatures.cpp.
Definition at line 1825 of file StringFeatures.cpp.
floatmax_t shift_symbol | ( | floatmax_t | symbol, | |
int32_t | amount | |||
) |
Definition at line 1833 of file StringFeatures.cpp.
Definition at line 1829 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 434 of file StringFeatures.cpp.
bool shift_symbol | ( | bool | symbol, | |
int32_t | amount | |||
) |
Definition at line 1821 of file StringFeatures.cpp.
void subset_changed_post | ( | ) | [virtual] |
post method when subset is changed
Reimplemented from CFeatures.
Definition at line 1619 of file StringFeatures.cpp.
void unembed_word | ( | float64_t | word, | |
uint8_t * | seq, | |||
int32_t | len | |||
) |
Definition at line 1889 of file StringFeatures.cpp.
void unembed_word | ( | floatmax_t | word, | |
uint8_t * | seq, | |||
int32_t | len | |||
) |
Definition at line 1892 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 1383 of file StringFeatures.cpp.
void unembed_word | ( | float32_t | word, | |
uint8_t * | seq, | |||
int32_t | len | |||
) |
Definition at line 1886 of file StringFeatures.cpp.
alphabet
Definition at line 672 of file StringFeatures.h.
CCache<ST>* feature_cache [protected] |
feature cache
Definition at line 705 of file StringFeatures.h.
this contains the array of features
Definition at line 678 of file StringFeatures.h.
int32_t length_of_single_string [protected] |
length of prior single string
Definition at line 684 of file StringFeatures.h.
int32_t max_string_length [protected] |
length of longest string (for subset, is updated)
Definition at line 687 of file StringFeatures.h.
floatmax_t num_symbols [protected] |
number of used symbols
Definition at line 690 of file StringFeatures.h.
int32_t num_vectors [protected] |
number of string vectors (for subset, is updated)
Definition at line 675 of file StringFeatures.h.
int32_t order [protected] |
order used in higher order mapping
Definition at line 696 of file StringFeatures.h.
floatmax_t original_num_symbols [protected] |
original number of used symbols (before higher order mapping)
Definition at line 693 of file StringFeatures.h.
bool preprocess_on_get [protected] |
preprocess on-the-fly?
Definition at line 702 of file StringFeatures.h.
ST* single_string [protected] |
true when single string / created by sliding window
Definition at line 681 of file StringFeatures.h.
ST* symbol_mask_table [protected] |
order used in higher order mapping
Definition at line 699 of file StringFeatures.h.