详细描述

template<class ST>
class shogun::CStringFileFeatures< ST >

File based string features.

StringFeatures that are file based. Underneath memory mapped files are used. Derived from CStringFeatures thus transparently enabling all of the StringFeature functionality.

Supported file format contains one string per line, lines of variable length are supported and must be separated by '
'.

在文件 StringFileFeatures.h 第 36 行定义.

类 CStringFileFeatures< ST > 继承关系图:

[图例]

Public 成员函数
	CStringFileFeatures ()

	CStringFileFeatures (const char *fname, EAlphabet alpha)

virtual	~CStringFileFeatures ()

virtual const char *	get_name () const

virtual void	cleanup_feature_vectors (int32_t start, int32_t stop)

virtual EFeatureClass	get_feature_class () const

virtual 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<>
EFeatureType	get_feature_type () const

CAlphabet *	get_alphabet ()

virtual CFeatures *	duplicate () const

SGVector< ST >	get_feature_vector (int32_t num)

ST *	get_feature_vector (int32_t num, int32_t &len, bool &dofree)

void	set_feature_vector (SGVector< ST > vector, int32_t num)

virtual void	set_feature_vector (int32_t num, ST *string, int32_t len)

void	enable_on_the_fly_preprocessing ()

void	disable_on_the_fly_preprocessing ()

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)

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)

ST	shift_offset (ST offset, int32_t amount)

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)

ST	shift_symbol (ST 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)

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 void	get_features (SGString< ST > *dst, int32_t num_str)

virtual SGString< ST > *	copy_features (int32_t &num_str, int32_t &max_str_len)

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 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)

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)

bool	have_same_length (int32_t len=-1)

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	embed_features (int32_t p_order)

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<>
void	compute_symbol_mask_table (int64_t max_val)

void	unembed_word (ST word, uint8_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)

ST	embed_word (ST *seq, int32_t len)

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)

void	determine_maximum_string_length ()

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 void	subset_changed_post ()

virtual void	add_preprocessor (CPreprocessor *p)

virtual void	del_preprocessor (int32_t num)

CPreprocessor *	get_preprocessor (int32_t num) const

void	set_preprocessed (int32_t num)

bool	is_preprocessed (int32_t num) const

int32_t	get_num_preprocessed () const

int32_t	get_num_preprocessors () const

void	clean_preprocessors ()

void	list_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 (CList *others)

virtual CFeatures *	create_merged_copy (CFeatures *other)

virtual void	add_subset (SGVector< index_t > subset)

virtual void	add_subset_in_place (SGVector< index_t > subset)

virtual void	remove_subset ()

virtual void	remove_all_subsets ()

virtual CSubsetStack *	get_subset_stack ()

virtual CFeatures *	copy_dimension_subset (SGVector< index_t > dims)

virtual bool	support_compatible_class () const

virtual bool	get_feature_class_compatibility (EFeatureClass rhs) const

virtual CSGObject *	shallow_copy () const

virtual CSGObject *	deep_copy () const

virtual bool	is_generic (EPrimitiveType *generic) const

template<class T >
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

void	unset_generic ()

virtual void	print_serializable (const char *prefix="")

virtual bool	save_serializable (CSerializableFile file, const char prefix="")

virtual bool	load_serializable (CSerializableFile file, const char prefix="")

void	set_global_io (SGIO *io)

SGIO *	get_global_io ()

void	set_global_parallel (Parallel *parallel)

Parallel *	get_global_parallel ()

void	set_global_version (Version *version)

Version *	get_global_version ()

SGStringList< char >	get_modelsel_names ()

void	print_modsel_params ()

char *	get_modsel_param_descr (const char *param_name)

index_t	get_modsel_param_index (const char *param_name)

void	build_gradient_parameter_dictionary (CMap< TParameter , CSGObject > *dict)

virtual void	update_parameter_hash ()

virtual bool	parameter_hash_changed ()

virtual bool	equals (CSGObject *other, float64_t accuracy=0.0, bool tolerant=false)

virtual CSGObject *	clone ()

静态 Public 成员函数
static ST *	get_zero_terminated_string_copy (SGString< ST > str)

Public 属性
SGIO *	io

Parallel *	parallel

Version *	version

Parameter *	m_parameters

Parameter *	m_model_selection_parameters

Parameter *	m_gradient_parameters

uint32_t	m_hash

Protected 成员函数
ST *	get_line (uint64_t &len, uint64_t &offs, int32_t &line_nr, uint64_t file_length)

virtual void	cleanup ()

virtual void	cleanup_feature_vector (int32_t num)

void	fetch_meta_info_from_file (int32_t granularity=1048576)

virtual ST *	compute_feature_vector (int32_t num, int32_t &len)

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)

Protected 属性
CMemoryMappedFile< ST > *	file

CAlphabet *	alphabet

int32_t	num_vectors

SGString< ST > *	features

ST *	single_string

int32_t	length_of_single_string
	length of prior single string 更多...

int32_t	max_string_length

floatmax_t	num_symbols
	number of used symbols 更多...

floatmax_t	original_num_symbols
	original number of used symbols (before higher order mapping) 更多...

int32_t	order
	order used in higher order mapping 更多...

ST *	symbol_mask_table
	order used in higher order mapping 更多...

int32_t	symbol_mask_table_len
	order used in higher order mapping 更多...

bool	preprocess_on_get
	preprocess on-the-fly? 更多...

CCache< ST > *	feature_cache

CSubsetStack *	m_subset_stack

构造及析构函数说明

CStringFileFeatures ( )

default constructor

在文件 StringFileFeatures.cpp 第 6 行定义.

CStringFileFeatures	(	const char *	fname,
		EAlphabet	alpha
	)

constructor

参数

fname	filename of the file containing line based features
alpha	alphabet (type) to use for string features

在文件 StringFileFeatures.cpp 第 10 行定义.

~CStringFileFeatures ( )

virtual

default destructor

在文件 StringFileFeatures.cpp 第 17 行定义.

成员函数说明

void add_preprocessor ( CPreprocessor * p )

virtualinherited

add preprocessor

参数

p	preprocessor to set

在文件 Features.cpp 第 85 行定义.

void add_subset ( SGVector< index_t > subset )

virtualinherited

Adds a subset of indices on top of the current subsets (possibly subset of subset). Every call causes a new active index vector to be stored. Added subsets can be removed one-by-one. If this is not needed, add_subset_in_place() should be used (does not store intermediate index vectors)

Calls subset_changed_post() afterwards

参数

subset subset of indices to add

被 CCombinedFeatures 重载.

在文件 Features.cpp 第 310 行定义.

void add_subset_in_place ( SGVector< index_t > subset )

virtualinherited

Sets/changes latest added subset. This allows to add multiple subsets with in-place memory requirements. They cannot be removed one-by-one afterwards, only the latest active can. If this is needed, use add_subset(). If no subset is active, this just adds.

Calls subset_changed_post() afterwards

参数

subset subset of indices to replace the latest one with.

在文件 Features.cpp 第 316 行定义.

bool append_features ( CStringFeatures< ST > * sf )

inherited

append features If the given string features have a subset, only this will be copied

not possible with subset

参数

sf	features to append

返回: if setting was successful

在文件 StringFeatures.cpp 第 899 行定义.

bool append_features	(	SGString< ST > *	p_features,
		int32_t	p_num_vectors,
		int32_t	p_max_string_length
	)

inherited

append features

not possible with subset

参数

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

返回: if setting was successful

在文件 StringFeatures.cpp 第 921 行定义.

bool apply_preprocessor ( bool force_preprocessing = false )

virtualinherited

apply preprocessor

参数

force_preprocessing if preprocssing shall be forced

返回: if applying was successful

在文件 StringFeatures.cpp 第 1177 行定义.

void build_gradient_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.

参数

dict	dictionary of parameters to be built.

在文件 SGObject.cpp 第 597 行定义.

bool check_feature_compatibility ( CFeatures * f ) const

inherited

check feature compatibility

参数

f	features to check for compatibility

返回: if features are compatible

在文件 Features.cpp 第 283 行定义.

void clean_preprocessors ( )

inherited

clears all preprocs

在文件 Features.cpp 第 116 行定义.

void cleanup ( )

protectedvirtual

cleanup string features

重载 CStringFeatures< ST > .

在文件 StringFileFeatures.cpp 第 53 行定义.

void cleanup_feature_vector ( int32_t num )

protectedvirtual

cleanup a single feature vector

重载 CStringFeatures< ST > .

在文件 StringFileFeatures.cpp 第 71 行定义.

void cleanup_feature_vectors	(	int32_t	start,
		int32_t	stop
	)

virtualinherited

cleanup multiple feature vectors

possible with subset

参数

start	index of first vector to be cleaned
stop	index of the last vector to be cleaned

在文件 StringFeatures.cpp 第 190 行定义.

CSGObject * clone ( )

virtualinherited

Creates a clone of the current object. This is done via recursively traversing all parameters, which corresponds to a deep copy. Calling equals on the cloned object always returns true although none of the memory of both objects overlaps.

返回: an identical copy of the given object, which is disjoint in memory. NULL if the clone fails. Note that the returned object is SG_REF'ed

在文件 SGObject.cpp 第 714 行定义.

ST * compute_feature_vector	(	int32_t	num,
		int32_t &	len
	)

protectedvirtualinherited

compute feature vector for sample num if target is set the vector is written to target len is returned by reference

possible with subset

参数

num	which vector
len	length of vector

返回: feature vector

在文件 StringFeatures.cpp 第 1651 行定义.

void compute_symbol_mask_table ( int64_t max_val )

inherited

compute symbol mask table

required to access bit-based symbols

not implemented for subset

在文件 StringFeatures.cpp 第 1374 行定义.

void compute_symbol_mask_table ( int64_t max_val )

inherited

在文件 StringFeatures.cpp 第 1889 行定义.

void compute_symbol_mask_table ( int64_t max_val )

inherited

在文件 StringFeatures.cpp 第 1892 行定义.

void compute_symbol_mask_table ( int64_t max_val )

inherited

在文件 StringFeatures.cpp 第 1895 行定义.

CFeatures * copy_dimension_subset ( SGVector< index_t > dims )

virtualinherited

Creates a new CFeatures instance containing only the dimensions of the feature vector which are specified by the provided indices.

This method is needed for feature selection tasks NOT IMPLEMENTED!

参数

dims	indices of feature dimensions to copy

返回: new CFeatures instance with copies of specified features

被 CDenseFeatures< ST >, CDenseFeatures< uint32_t >, CDenseFeatures< float64_t >, CDenseFeatures< T > , 以及 CDenseFeatures< uint16_t > 重载.

在文件 Features.cpp 第 348 行定义.

SGString< ST > * copy_features	(	int32_t &	num_str,
		int32_t &	max_str_len
	)

virtualinherited

copy_features

possible with subset

参数

num_str	number of strings (returned)
max_str_len	maximal string length (returned)

返回: string features

在文件 StringFeatures.cpp 第 992 行定义.

CFeatures * copy_subset ( SGVector< index_t > indices )

virtualinherited

Creates a new CFeatures instance containing copies of the elements which are specified by the provided indices.

possible with subset

参数

indices indices of feature elements to copy

返回: new CFeatures instance with copies of feature data

重载 CFeatures .

在文件 StringFeatures.cpp 第 1610 行定义.

virtual CFeatures* create_merged_copy ( CList * others )

virtualinherited

Takes a list of feature instances and returns a new instance being a concatenation of a copy of this instace's data and the given instancess data. Note that the feature types have to be equal.

NOT IMPLEMENTED!

参数

others list of feature objects to append

返回: new feature object which contains copy of data of this instance and given ones

被 CDenseFeatures< ST >, CDenseFeatures< uint32_t >, CDenseFeatures< float64_t >, CDenseFeatures< T > , 以及 CDenseFeatures< uint16_t > 重载.

在文件 Features.h 第 235 行定义.

virtual CFeatures* create_merged_copy ( CFeatures * other )

virtualinherited

Convenience method for method with same name and list as parameter.

NOT IMPLEMENTED!

参数

other feature object to append

返回: new feature object which contains copy of data of this instance and of given one

被 CDenseFeatures< ST >, CDenseFeatures< uint32_t >, CDenseFeatures< float64_t >, CDenseFeatures< T >, CDenseFeatures< uint16_t > , 以及 CCombinedFeatures 重载.

在文件 Features.h 第 249 行定义.

void create_random	(	float64_t *	hist,
		int32_t	rows,
		int32_t	cols,
		int32_t	num_vec
	)

virtualinherited

create some random strings based on normalized histogram

not possible with subset

在文件 StringFeatures.cpp 第 1508 行定义.

CSGObject * deep_copy ( ) const

virtualinherited

A deep copy. All the instance variables will also be copied.

在文件 SGObject.cpp 第 198 行定义.

void del_preprocessor ( int32_t num )

virtualinherited

delete preprocessor from list

参数

num	index of preprocessor in list

在文件 Features.cpp 第 122 行定义.

void determine_maximum_string_length ( )

inherited

determine new maximum string length

possible with subset

在文件 StringFeatures.cpp 第 1431 行定义.

void disable_on_the_fly_preprocessing ( )

inherited

call this to disable on the fly feature preprocessing upon call to get_feature_vector. Useful when you manually apply preprocessors.

在文件 StringFeatures.cpp 第 270 行定义.

CFeatures * duplicate ( ) const

virtualinherited

duplicate feature object

返回: feature object

实现了 CFeatures.

在文件 StringFeatures.cpp 第 218 行定义.

void embed_features ( int32_t p_order )

inherited

embed string features in bit representation in-place

not implemented for subset

在文件 StringFeatures.cpp 第 1320 行定义.

void embed_features ( int32_t p_order )

inherited

在文件 StringFeatures.cpp 第 1879 行定义.

void embed_features ( int32_t p_order )

inherited

在文件 StringFeatures.cpp 第 1882 行定义.

void embed_features ( int32_t p_order )

inherited

在文件 StringFeatures.cpp 第 1885 行定义.

ST embed_word	(	ST *	seq,
		int32_t	len
	)

inherited

embed a single word

参数

seq	sequence of size len in a bitfield
len

在文件 StringFeatures.cpp 第 1418 行定义.

float32_t embed_word	(	float32_t *	seq,
		int32_t	len
	)

inherited

在文件 StringFeatures.cpp 第 1899 行定义.

float64_t embed_word	(	float64_t *	seq,
		int32_t	len
	)

inherited

在文件 StringFeatures.cpp 第 1903 行定义.

floatmax_t embed_word	(	floatmax_t *	seq,
		int32_t	len
	)

inherited

在文件 StringFeatures.cpp 第 1907 行定义.

void enable_on_the_fly_preprocessing ( )

inherited

call this to preprocess string features upon call to get_feature_vector

在文件 StringFeatures.cpp 第 265 行定义.

bool equals	(	CSGObject *	other,
		float64_t	accuracy = `0.0`,
		bool	tolerant = `false`
	)

virtualinherited

Recursively compares the current SGObject to another one. Compares all registered numerical parameters, recursion upon complex (SGObject) parameters. Does not compare pointers!

May be overwritten but please do with care! Should not be necessary in most cases.

参数

other	object to compare with
accuracy	accuracy to use for comparison (optional)
tolerant	allows linient check on float equality (within accuracy)

返回: true if all parameters were equal, false if not

在文件 SGObject.cpp 第 618 行定义.

void fetch_meta_info_from_file ( int32_t granularity = 1048576 )

protected

obtain meta information from file

i.e., determine number of strings and their lengths

在文件 StringFileFeatures.cpp 第 77 行定义.

void free_feature_vector	(	ST *	feat_vec,
		int32_t	num,
		bool	dofree
	)

inherited

free feature vector

possible with subset

参数

feat_vec	feature vector to free
num	index in feature cache, possibly from subset
dofree	if vector should be really deleted

在文件 StringFeatures.cpp 第 357 行定义.

void free_feature_vector	(	SGVector< ST >	feat_vec,
		int32_t	num
	)

inherited

free feature vector

possible with subset

参数

feat_vec	feature vector to free
num	index in feature cache, possibly from subset

在文件 StringFeatures.cpp 第 375 行定义.

CAlphabet * get_alphabet ( )

inherited

get alphabet used in string features

返回: alphabet

在文件 StringFeatures.cpp 第 212 行定义.

int32_t get_cache_size ( ) const

inherited

get cache size

返回: cache size

在文件 Features.cpp 第 160 行定义.

ST get_feature	(	int32_t	vec_num,
		int32_t	feat_num
	)

virtualinherited

get feature

possible with subset

参数

vec_num	which vector
feat_num	which feature, possibly from subset

返回: feature

在文件 StringFeatures.cpp 第 390 行定义.

EFeatureClass get_feature_class ( ) const

virtualinherited

get feature class

返回: feature class STRING

实现了 CFeatures.

在文件 StringFeatures.cpp 第 208 行定义.

bool get_feature_class_compatibility ( EFeatureClass rhs ) const

virtualinherited

Given a class in right hand side, does this class support compatible computation?

for example, is this->dot(rhs_prt) valid, where rhs_prt is the class in right hand side

参数

rhs	the class in right hand side

返回: whether this class supports compatible computation

被 CDenseSubSamplesFeatures< ST > 重载.

在文件 Features.cpp 第 355 行定义.