CStringFeatures< ST > Class Template Reference

Inheritance diagram for CStringFeatures< ST >:

[legend]

List of all members.

Public Member Functions
	CStringFeatures (EAlphabet alpha)
	CStringFeatures (CAlphabet *alpha)
	CStringFeatures (const CStringFeatures &orig)
	CStringFeatures (char *fname, EAlphabet alpha=DNA)
virtual	~CStringFeatures ()
void	cleanup ()
virtual EFeatureClass	get_feature_class ()
virtual EFeatureType	get_feature_type ()
CAlphabet *	get_alphabet ()
virtual CFeatures *	duplicate () const
void	select_feature_vector (int32_t num)
void	get_string (ST **dst, int32_t *len)
virtual ST *	get_feature_vector (int32_t num, int32_t &len)
virtual void	set_feature_vector (int32_t num, ST *string, int32_t len)
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 ()
float128_t	get_num_symbols ()
float128_t	get_max_num_symbols ()
float128_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 bool	load (char *fname)
bool	load_dna_file (char *fname, bool remap_to_bin=true)
bool	load_from_directory (char *dirname)
bool	set_features (T_STRING< ST > *p_features, int32_t p_num_vectors, int32_t p_max_string_length)
virtual T_STRING< ST > *	get_features (int32_t &num_str, int32_t &max_str_len)
virtual bool	save (char *dest)
virtual int32_t	get_size ()
virtual bool	apply_preproc (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)
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 ()
Protected Member Functions
void	translate_from_single_order (ST *obs, int32_t sequence_length, int32_t start, int32_t p_order, int32_t max_val)
void	translate_from_single_order_reversed (ST *obs, int32_t sequence_length, int32_t start, int32_t p_order, int32_t max_val)
void	translate_from_single_order (ST *obs, int32_t sequence_length, int32_t start, int32_t p_order, int32_t max_val, int32_t gap)
void	translate_from_single_order_reversed (ST *obs, int32_t sequence_length, int32_t start, int32_t p_order, int32_t max_val, int32_t gap)
Protected Attributes
CAlphabet *	alphabet
	alphabet
int32_t	num_vectors
	number of string vectors
T_STRING< ST > *	features
	this contains the array of features.
ST *	single_string
	true when single string / created by sliding window
int32_t	length_of_single_string
	length of prior single string
int32_t	max_string_length
	length of longest string
float128_t	num_symbols
	number of used symbols
float128_t	original_num_symbols
	original number of used symbols (before higher order mapping)
int32_t	order
	order used in higher order mapping
int32_t	selected_vector
	vector to be obtained via get_string
ST *	symbol_mask_table
	order used in higher order mapping

---

Detailed Description

template<class ST>
class CStringFeatures< ST >

Template class StringFeatures implements a list of strings. As this class is 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.

Note: StringFeatures do not support PreProcs

Definition at line 68 of file StringFeatures.h.

---

Constructor & Destructor Documentation

template<class ST>

CStringFeatures< ST >::CStringFeatures

(

EAlphabet

alpha

)

constructor

Parameters:

alpha

alphabet (type) to use for string features

Definition at line 75 of file StringFeatures.h.

template<class ST>

CStringFeatures< ST >::CStringFeatures

(

CAlphabet *

alpha

)

constructor

Parameters:

alpha

alphabet to use for string features

Definition at line 91 of file StringFeatures.h.

template<class ST>

CStringFeatures< ST >::CStringFeatures

(

const CStringFeatures< ST > &

orig

)

copy constructor

Definition at line 104 of file StringFeatures.h.

template<class ST>

CStringFeatures< ST >::CStringFeatures	(	char *	fname,
		EAlphabet	alpha = DNA
	)

constructor

Parameters:

	fname	filename to load features from
	alpha	alphabet (type) to use for string features

Definition at line 144 of file StringFeatures.h.

template<class ST>

virtual CStringFeatures< ST >::~CStringFeatures

(

)

[virtual]

Definition at line 157 of file StringFeatures.h.

---

Member Function Documentation

template<class ST>

virtual bool CStringFeatures< ST >::apply_preproc

(

bool

force_preprocessing = false

)

[virtual]

apply preprocessor

Parameters:

force_preprocessing

if preprocssing shall be forced

Returns:

if applying was successful

Definition at line 729 of file StringFeatures.h.

template<class ST>

void CStringFeatures< ST >::cleanup

(

)

cleanup string features

Definition at line 169 of file StringFeatures.h.

template<class ST>

virtual CFeatures* CStringFeatures< ST >::duplicate

(

)

const [virtual]

duplicate feature object

Returns:

feature object

Implements CFeatures.

Definition at line 217 of file StringFeatures.h.

template<class ST>

CAlphabet* CStringFeatures< ST >::get_alphabet

(

)

get alphabet used in string features

Returns:

alphabet

Definition at line 207 of file StringFeatures.h.

template<class ST>

virtual ST CStringFeatures< ST >::get_feature	(	int32_t	vec_num,
		int32_t	feat_num
	)			[virtual]

get feature

Parameters:

	vec_num	which vector
	feat_num	which feature

Returns:

feature

Definition at line 285 of file StringFeatures.h.

template<class ST>

virtual EFeatureClass CStringFeatures< ST >::get_feature_class

(

)

[virtual]

get feature class

Returns:

feature class STRING

Implements CFeatures.

Definition at line 195 of file StringFeatures.h.

template<>

EFeatureType CStringFeatures< float64_t >::get_feature_type

(

)

[virtual]

get feature type the DREAL feature can deal with

Returns:

feature type DREAL

Implements CFeatures.

Definition at line 1313 of file StringFeatures.h.

template<>

EFeatureType CStringFeatures< uint64_t >::get_feature_type

(

)

[virtual]

get feature type the ULONG feature can deal with

Returns:

feature type ULONG

Implements CFeatures.

Definition at line 1304 of file StringFeatures.h.

template<>

EFeatureType CStringFeatures< int64_t >::get_feature_type

(

)

[virtual]

get feature type the LONG feature can deal with

Returns:

feature type LONG

Implements CFeatures.

Definition at line 1295 of file StringFeatures.h.

template<>

EFeatureType CStringFeatures< uint32_t >::get_feature_type

(

)

[virtual]

get feature type the INT feature can deal with

Returns:

feature type INT

Implements CFeatures.

Definition at line 1286 of file StringFeatures.h.

template<>

EFeatureType CStringFeatures< int32_t >::get_feature_type

(

)

[virtual]

get feature type the INT feature can deal with

Returns:

feature type INT

Implements CFeatures.

Definition at line 1277 of file StringFeatures.h.

template<>

EFeatureType CStringFeatures< int16_t >::get_feature_type

(

)

[virtual]

get feature type the SHORT feature can deal with

Returns:

feature type SHORT

Implements CFeatures.

Definition at line 1259 of file StringFeatures.h.

template<>

EFeatureType CStringFeatures< char >::get_feature_type

(

)

[virtual]

get feature type the char feature can deal with

Returns:

feature type char

Implements CFeatures.

Definition at line 1241 of file StringFeatures.h.

template<class ST>

virtual EFeatureType CStringFeatures< ST >::get_feature_type

(

)

[virtual]

get feature type

Returns:

templated feature type

Implements CFeatures.

template<class ST>

virtual ST* CStringFeatures< ST >::get_feature_vector	(	int32_t	num,
		int32_t &	len
	)			[virtual]

get feature vector for sample num

Parameters:

	num	index of feature vector
	len	length is returned by reference

Returns:

feature vector for sample num

Definition at line 255 of file StringFeatures.h.

template<class ST>

virtual T_STRING<ST>* CStringFeatures< ST >::get_features	(	int32_t &	num_str,
		int32_t &	max_str_len
	)			[virtual]

get_features

Parameters:

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

Returns:

string features

Definition at line 701 of file StringFeatures.h.

template<class ST>

ST CStringFeatures< 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.

Parameters:

	symbol	symbol to mask
	mask	mask to apply

Returns:

masked symbol

Definition at line 356 of file StringFeatures.h.

template<class ST>

float128_t CStringFeatures< ST >::get_max_num_symbols

(

)

get maximum number of symbols

Note: float128_t sounds weird, but LONG is not long enough

Returns:

maximum number of symbols

Definition at line 333 of file StringFeatures.h.

template<class ST>

virtual int32_t CStringFeatures< ST >::get_max_vector_length

(

)

[virtual]

get maximum vector length

Returns:

maximum vector/string length

Definition at line 308 of file StringFeatures.h.

template<class ST>

float128_t CStringFeatures< ST >::get_num_symbols

(

)

get number of symbols

Note: float128_t sounds weird, but LONG is not long enough

Returns:

number of symbols

Definition at line 325 of file StringFeatures.h.

template<class ST>

virtual int32_t CStringFeatures< ST >::get_num_vectors

(

)

[virtual]

get number of vectors

Returns:

number of vectors

Implements CFeatures.

Definition at line 317 of file StringFeatures.h.

template<class ST>

int32_t CStringFeatures< ST >::get_order

(

)

order used for higher order mapping

Returns:

order

Definition at line 347 of file StringFeatures.h.

template<class ST>

float128_t CStringFeatures< ST >::get_original_num_symbols

(

)

number of symbols before higher order mapping

Returns:

original number of symbols

Definition at line 341 of file StringFeatures.h.

template<class ST>

virtual int32_t CStringFeatures< ST >::get_size

(

)

[virtual]

get memory footprint of one feature

Returns:

memory footprint of one feature

Implements CFeatures.

Definition at line 722 of file StringFeatures.h.

template<class ST>

void CStringFeatures< ST >::get_string	(	ST **	dst,
		int32_t *	len
	)

get feature vector for selected example

Parameters:

	dst	destination where vector will be stored
	len	number of features in vector

Definition at line 239 of file StringFeatures.h.

template<class ST>

virtual int32_t CStringFeatures< ST >::get_vector_length

(

int32_t

vec_num

)

[virtual]

get vector length

Parameters:

vec_num

which vector

Returns:

length of vector

Definition at line 298 of file StringFeatures.h.

template<class ST>

bool CStringFeatures< ST >::have_same_length

(

int32_t

len

)

check if length of each vector in this feature object equals the given length.

Parameters:

len

vector length to check against

Returns:

if length of each vector in this feature object equals the given length.

Definition at line 974 of file StringFeatures.h.

template<class ST>

virtual bool CStringFeatures< ST >::load

(

char *

fname

)

[virtual]

load features from file

Parameters:

fname

filename to load from

Returns:

if loading was successful

Reimplemented from CFeatures.

Definition at line 391 of file StringFeatures.h.

template<class ST>

bool CStringFeatures< ST >::load_dna_file	(	char *	fname,
		bool	remap_to_bin = true
	)

load DNA features from file

Parameters:

	fname	filename to load from
	remap_to_bin	if remap_to_bin

Returns:

if loading was successful

Definition at line 451 of file StringFeatures.h.

template<class ST>

bool CStringFeatures< ST >::load_from_directory

(

char *

dirname

)

load features from directory

Parameters:

dirname

directory name to load from

Returns:

if loading was successful

Definition at line 584 of file StringFeatures.h.

template<class ST>

int32_t CStringFeatures< ST >::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

Parameters:

	window_size	window size
	positions	positions
	skip	skip

Returns:

something inty

Definition at line 800 of file StringFeatures.h.

template<class ST>

int32_t CStringFeatures< ST >::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

Parameters:

	window_size	window size
	step_size	step size
	skip	skip

Returns:

something inty

Definition at line 757 of file StringFeatures.h.

template<class ST>

bool CStringFeatures< ST >::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

Parameters:

	sf	string features
	start	start
	p_order	order
	gap	gap
	rev	reverse

Returns:

if obtaining was successful

Definition at line 866 of file StringFeatures.h.

template<class ST>

template<class CT >

bool CStringFeatures< ST >::obtain_from_char_features	(	CStringFeatures< CT > *	sf,
		int32_t	start,
		int32_t	p_order,
		int32_t	gap,
		bool	rev
	)

template obtain from char features

Parameters:

	sf	string features
	start	start
	p_order	order
	gap	gap
	rev	reverse

Returns:

if obtaining was successful

Definition at line 881 of file StringFeatures.h.

template<class ST>

virtual bool CStringFeatures< ST >::save

(

char *

dest

)

[virtual]

save features to file

Parameters:

dest

filename to save to

Returns:

if saving was successful

Reimplemented from CFeatures.

Definition at line 713 of file StringFeatures.h.

template<class ST>

void CStringFeatures< ST >::select_feature_vector

(

int32_t

num

)

select feature vector

Parameters:

num

which feature vector to select

Definition at line 226 of file StringFeatures.h.

template<class ST>

virtual void CStringFeatures< ST >::set_feature_vector	(	int32_t	num,
		ST *	string,
		int32_t	len
	)			[virtual]

set feature vector for sample num

Parameters:

	num	index of feature vector
	string	string with the feature vector's content
	len	length of the string

Definition at line 270 of file StringFeatures.h.

template<class ST>

bool CStringFeatures< ST >::set_features	(	T_STRING< ST > *	p_features,
		int32_t	p_num_vectors,
		int32_t	p_max_string_length
	)

set features

Parameters:

	p_features	new features
	p_num_vectors	number of vectors
	p_max_string_length	maximum string length

Returns:

if setting was successful

Definition at line 657 of file StringFeatures.h.

template<class ST>

ST CStringFeatures< ST >::shift_offset	(	ST	offset,
		int32_t	amount
	)

shift offset to the left by amount

Parameters:

	offset	offset to shift
	amount	amount to shift the offset

Returns:

shifted offset

Definition at line 368 of file StringFeatures.h.

template<class ST>

ST CStringFeatures< ST >::shift_symbol	(	ST	symbol,
		int32_t	amount
	)

shift symbol to the right by amount (taking care of custom symbol sizes)

Parameters:

	symbol	symbol to shift
	amount	amount to shift the symbol

Returns:

shifted symbol

Definition at line 380 of file StringFeatures.h.

template<class ST>

void CStringFeatures< ST >::translate_from_single_order	(	ST *	obs,
		int32_t	sequence_length,
		int32_t	start,
		int32_t	p_order,
		int32_t	max_val,
		int32_t	gap
	)			[protected]

translate from single order

Parameters:

	obs	observation
	sequence_length	length of sequence
	start	start
	p_order	order
	max_val	maximum value
	gap	gap

Definition at line 1080 of file StringFeatures.h.

template<class ST>

void CStringFeatures< ST >::translate_from_single_order	(	ST *	obs,
		int32_t	sequence_length,
		int32_t	start,
		int32_t	p_order,
		int32_t	max_val
	)			[protected]

translate from single order

Parameters:

	obs	observation
	sequence_length	length of sequence
	start	start
	p_order	order
	max_val	maximum value

Definition at line 997 of file StringFeatures.h.

template<class ST>

void CStringFeatures< ST >::translate_from_single_order_reversed	(	ST *	obs,
		int32_t	sequence_length,
		int32_t	start,
		int32_t	p_order,
		int32_t	max_val,
		int32_t	gap
	)			[protected]

translate from single order reversed

Parameters:

	obs	observation
	sequence_length	length of sequence
	start	start
	p_order	order
	max_val	maximum value
	gap	gap

Definition at line 1147 of file StringFeatures.h.

template<class ST>

void CStringFeatures< ST >::translate_from_single_order_reversed	(	ST *	obs,
		int32_t	sequence_length,
		int32_t	start,
		int32_t	p_order,
		int32_t	max_val
	)			[protected]

translate from single order reversed

Parameters:

	obs	observation
	sequence_length	length of sequence
	start	start
	p_order	order
	max_val	maximum value

Definition at line 1038 of file StringFeatures.h.

---

Member Data Documentation

template<class ST>

CAlphabet* CStringFeatures< ST >::alphabet [protected]

alphabet

Definition at line 1204 of file StringFeatures.h.

template<class ST>

T_STRING<ST>* CStringFeatures< ST >::features [protected]

this contains the array of features.

Definition at line 1210 of file StringFeatures.h.

template<class ST>

int32_t CStringFeatures< ST >::length_of_single_string [protected]

length of prior single string

Definition at line 1216 of file StringFeatures.h.

template<class ST>

int32_t CStringFeatures< ST >::max_string_length [protected]

length of longest string

Definition at line 1219 of file StringFeatures.h.

template<class ST>

float128_t CStringFeatures< ST >::num_symbols [protected]

number of used symbols

Definition at line 1222 of file StringFeatures.h.

template<class ST>

int32_t CStringFeatures< ST >::num_vectors [protected]

number of string vectors

Definition at line 1207 of file StringFeatures.h.

template<class ST>

int32_t CStringFeatures< ST >::order [protected]

order used in higher order mapping

Definition at line 1228 of file StringFeatures.h.

template<class ST>

float128_t CStringFeatures< ST >::original_num_symbols [protected]

original number of used symbols (before higher order mapping)

Definition at line 1225 of file StringFeatures.h.

template<class ST>

int32_t CStringFeatures< ST >::selected_vector [protected]

vector to be obtained via get_string

Definition at line 1231 of file StringFeatures.h.

template<class ST>

ST* CStringFeatures< ST >::single_string [protected]

true when single string / created by sliding window

Definition at line 1213 of file StringFeatures.h.

template<class ST>

ST* CStringFeatures< ST >::symbol_mask_table [protected]

order used in higher order mapping

Definition at line 1234 of file StringFeatures.h.

---

The documentation for this class was generated from the following file:

• StringFeatures.h