SHOGUN  4.1.0
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Macros Modules Pages
List of all members | Public Member Functions | Static Public Member Functions | Public Attributes | Static Public Attributes | Protected Member Functions | Protected Attributes
CAlphabet Class Reference

Detailed Description

The class Alphabet implements an alphabet and alphabet utility functions.

These utility functions can be used to remap characters to more (bit-)efficient representations, check if a string is valid, compute histograms etc.

Currently supported alphabets are DNA, RAWDNA, RNA, PROTEIN, BINARY, ALPHANUM, CUBE, RAW, IUPAC_NUCLEIC_ACID and IUPAC_AMINO_ACID.

Definition at line 91 of file Alphabet.h.

Inheritance diagram for CAlphabet:
Inheritance graph
[legend]

Public Member Functions

 CAlphabet ()
 
 CAlphabet (char *alpha, int32_t len)
 
 CAlphabet (EAlphabet alpha)
 
 CAlphabet (CAlphabet *alpha)
 
virtual ~CAlphabet ()
 
bool set_alphabet (EAlphabet alpha)
 
EAlphabet get_alphabet () const
 
int32_t get_num_symbols () const
 
int32_t get_num_bits () const
 
uint8_t remap_to_bin (uint8_t c)
 
uint8_t remap_to_char (uint8_t c)
 
void clear_histogram ()
 clear histogram More...
 
template<class T >
void add_string_to_histogram (T *p, int64_t len)
 
void add_byte_to_histogram (uint8_t p)
 
void print_histogram ()
 print histogram More...
 
SGVector< int64_t > get_histogram ()
 
bool check_alphabet (bool print_error=true)
 
bool is_valid (uint8_t c)
 
bool check_alphabet_size (bool print_error=true)
 
int32_t get_num_symbols_in_histogram ()
 
int32_t get_max_value_in_histogram ()
 
int32_t get_num_bits_in_histogram ()
 
virtual const char * get_name () const
 
template<>
void translate_from_single_order (float32_t *obs, int32_t sequence_length, int32_t start, int32_t p_order, int32_t max_val, int32_t gap)
 
template<>
void translate_from_single_order (float64_t *obs, int32_t sequence_length, int32_t start, int32_t p_order, int32_t max_val, int32_t gap)
 
template<>
void translate_from_single_order (floatmax_t *obs, int32_t sequence_length, int32_t start, int32_t p_order, int32_t max_val, int32_t gap)
 
template<>
void translate_from_single_order_reversed (float32_t *obs, int32_t sequence_length, int32_t start, int32_t p_order, int32_t max_val, int32_t gap)
 
template<>
void translate_from_single_order_reversed (float64_t *obs, int32_t sequence_length, int32_t start, int32_t p_order, int32_t max_val, int32_t gap)
 
template<>
void translate_from_single_order_reversed (floatmax_t *obs, int32_t sequence_length, int32_t start, int32_t p_order, int32_t max_val, int32_t gap)
 
virtual CSGObjectshallow_copy () const
 
virtual CSGObjectdeep_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)
 
SGIOget_global_io ()
 
void set_global_parallel (Parallel *parallel)
 
Parallelget_global_parallel ()
 
void set_global_version (Version *version)
 
Versionget_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 CSGObjectclone ()
 

Static Public Member Functions

static const char * get_alphabet_name (EAlphabet alphabet)
 
template<class ST >
static void translate_from_single_order (ST *obs, int32_t sequence_length, int32_t start, int32_t p_order, int32_t max_val)
 
template<class ST >
static void translate_from_single_order_reversed (ST *obs, int32_t sequence_length, int32_t start, int32_t p_order, int32_t max_val)
 
template<class ST >
static 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)
 
template<class ST >
static 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)
 

Public Attributes

SGIOio
 
Parallelparallel
 
Versionversion
 
Parameterm_parameters
 
Parameterm_model_selection_parameters
 
Parameterm_gradient_parameters
 
uint32_t m_hash
 

Static Public Attributes

static const uint8_t B_A =0
 
static const uint8_t B_C =1
 
static const uint8_t B_G =2
 
static const uint8_t B_T =3
 
static const uint8_t B_0 =4
 
static const uint8_t MAPTABLE_UNDEF =0xff
 
static const char * alphabet_names [18]
 

Protected Member Functions

void init_map_table ()
 
void copy_histogram (CAlphabet *src)
 
virtual void load_serializable_post () throw (ShogunException)
 
virtual void load_serializable_pre () throw (ShogunException)
 
virtual void save_serializable_pre () throw (ShogunException)
 
virtual void save_serializable_post () throw (ShogunException)
 

Protected Attributes

EAlphabet alphabet
 
int32_t num_symbols
 
int32_t num_bits
 
bool valid_chars [1<< (sizeof(uint8_t)*8)]
 
uint8_t maptable_to_bin [1<< (sizeof(uint8_t)*8)]
 
uint8_t maptable_to_char [1<< (sizeof(uint8_t)*8)]
 
int64_t histogram [1<< (sizeof(uint8_t)*8)]
 

Constructor & Destructor Documentation

CAlphabet ( )

default constructor

Definition at line 35 of file Alphabet.cpp.

CAlphabet ( char *  alpha,
int32_t  len 
)

constructor

Parameters
alphaalphabet to use
lenlen

Definition at line 41 of file Alphabet.cpp.

CAlphabet ( EAlphabet  alpha)

constructor

Parameters
alphaalphabet (type) to use

Definition at line 88 of file Alphabet.cpp.

CAlphabet ( CAlphabet alpha)

constructor

Parameters
alphaalphabet to use

Definition at line 95 of file Alphabet.cpp.

~CAlphabet ( )
virtual

Definition at line 104 of file Alphabet.cpp.

Member Function Documentation

void add_byte_to_histogram ( uint8_t  p)

add element to histogram

Parameters
pelement

Definition at line 193 of file Alphabet.h.

void add_string_to_histogram ( T *  p,
int64_t  len 
)

make histogram for whole string

Parameters
pstring
lenlength of string

Definition at line 183 of file Alphabet.h.

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.

Parameters
dictdictionary of parameters to be built.

Definition at line 597 of file SGObject.cpp.

bool check_alphabet ( bool  print_error = true)

check whether symbols in histogram are valid in alphabet e.g. for DNA if only letters ACGT appear

Parameters
print_errorif errors shall be printed
Returns
if symbols in histogram are valid in alphabet

Definition at line 617 of file Alphabet.cpp.

bool check_alphabet_size ( bool  print_error = true)

check whether symbols in histogram ALL fit in alphabet

Parameters
print_errorif errors shall be printed
Returns
if symbols in histogram ALL fit in alphabet

Definition at line 639 of file Alphabet.cpp.

void clear_histogram ( )

clear histogram

Definition at line 544 of file Alphabet.cpp.

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.

Returns
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

Definition at line 714 of file SGObject.cpp.

void copy_histogram ( CAlphabet src)
protected

copy histogram

Parameters
srcalphabet to copy histogram from

Definition at line 656 of file Alphabet.cpp.

CSGObject * deep_copy ( ) const
virtualinherited

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

Definition at line 198 of file SGObject.cpp.

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.

Parameters
otherobject to compare with
accuracyaccuracy to use for comparison (optional)
tolerantallows linient check on float equality (within accuracy)
Returns
true if all parameters were equal, false if not

Definition at line 618 of file SGObject.cpp.

EAlphabet get_alphabet ( ) const

get alphabet

Returns
alphabet

Definition at line 130 of file Alphabet.h.

const char * get_alphabet_name ( EAlphabet  alphabet)
static

return alphabet name

Parameters
alphabetalphabet type to get name from

Definition at line 669 of file Alphabet.cpp.

SGIO * get_global_io ( )
inherited

get the io object

Returns
io object

Definition at line 235 of file SGObject.cpp.

Parallel * get_global_parallel ( )
inherited

get the parallel object

Returns
parallel object

Definition at line 277 of file SGObject.cpp.

Version * get_global_version ( )
inherited

get the version object

Returns
version object

Definition at line 290 of file SGObject.cpp.

SGVector< int64_t > get_histogram ( )

get histogram

Returns
histogram

Definition at line 612 of file Alphabet.cpp.

int32_t get_max_value_in_histogram ( )

return maximum value in histogram

Returns
maximum value in histogram

Definition at line 550 of file Alphabet.cpp.

SGStringList< char > get_modelsel_names ( )
inherited
Returns
vector of names of all parameters which are registered for model selection

Definition at line 498 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

Parameters
param_namename of the parameter
Returns
description of the parameter

Definition at line 522 of file SGObject.cpp.

index_t get_modsel_param_index ( const char *  param_name)
inherited

Returns index of model selection parameter with provided index

Parameters
param_namename of model selection parameter
Returns
index of model selection parameter with provided name, -1 if there is no such

Definition at line 535 of file SGObject.cpp.

virtual const char* get_name ( ) const
virtual
Returns
object name

Implements CSGObject.

Definition at line 261 of file Alphabet.h.

int32_t get_num_bits ( ) const

get number of bits necessary to store all symbols in alphabet

Returns
number of necessary storage bits

Definition at line 149 of file Alphabet.h.

int32_t get_num_bits_in_histogram ( )

return number of bits required to store all symbols in histogram

Returns
number of bits required to store all symbols in histogram

Definition at line 577 of file Alphabet.cpp.

int32_t get_num_symbols ( ) const

get number of symbols in alphabet

Returns
number of symbols

Definition at line 139 of file Alphabet.h.

int32_t get_num_symbols_in_histogram ( )

return number of symbols in histogram

Returns
number of symbols in histogram

Definition at line 565 of file Alphabet.cpp.

void init_map_table ( )
protected

init map table

Definition at line 179 of file Alphabet.cpp.

bool is_generic ( EPrimitiveType *  generic) const
virtualinherited

If the SGSerializable is a class template then TRUE will be returned and GENERIC is set to the type of the generic.

Parameters
genericset to the type of the generic if returning TRUE
Returns
TRUE if a class template.

Definition at line 296 of file SGObject.cpp.

bool is_valid ( uint8_t  c)

check whether symbols are valid in alphabet e.g. for DNA if symbol is one of the A,C,G or T

Parameters
csymbol
Returns
if symbol is a valid character in alphabet

Definition at line 221 of file Alphabet.h.

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

Load this object from file. If it will fail (returning FALSE) then this object will contain inconsistent data and should not be used!

Parameters
filewhere to load from
prefixprefix for members
Returns
TRUE if done, otherwise FALSE

Definition at line 369 of file SGObject.cpp.

void load_serializable_post ( )
throw (ShogunException
)
protectedvirtual

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.

Exceptions
ShogunExceptionWill be thrown if an error occurres.

Reimplemented from CSGObject.

Definition at line 749 of file Alphabet.cpp.

void load_serializable_pre ( )
throw (ShogunException
)
protectedvirtualinherited

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.

Exceptions
ShogunExceptionwill be thrown if an error occurs.

Reimplemented in CDynamicArray< T >, CDynamicArray< float64_t >, CDynamicArray< float32_t >, CDynamicArray< int32_t >, CDynamicArray< char >, CDynamicArray< bool >, and CDynamicObjectArray.

Definition at line 421 of file SGObject.cpp.

bool parameter_hash_changed ( )
virtualinherited
Returns
whether parameter combination has changed since last update

Definition at line 262 of file SGObject.cpp.

void print_histogram ( )

print histogram

Definition at line 587 of file Alphabet.cpp.

void print_modsel_params ( )
inherited

prints all parameter registered for model selection and their type

Definition at line 474 of file SGObject.cpp.

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

prints registered parameters out

Parameters
prefixprefix for members

Definition at line 308 of file SGObject.cpp.

uint8_t remap_to_bin ( uint8_t  c)

remap element e.g translate ACGT to 0123

Parameters
celement to remap
Returns
remapped element

Definition at line 159 of file Alphabet.h.

uint8_t remap_to_char ( uint8_t  c)

remap element e.g translate 0123 to ACGT

Parameters
celement to remap
Returns
remapped element

Definition at line 169 of file Alphabet.h.

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

Save this object to file.

Parameters
filewhere to save the object; will be closed during returning if PREFIX is an empty string.
prefixprefix for members
Returns
TRUE if done, otherwise FALSE

Definition at line 314 of file SGObject.cpp.

void save_serializable_post ( )
throw (ShogunException
)
protectedvirtualinherited

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.

Exceptions
ShogunExceptionwill be thrown if an error occurs.

Reimplemented in CKernel.

Definition at line 436 of file SGObject.cpp.

void save_serializable_pre ( )
throw (ShogunException
)
protectedvirtualinherited

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.

Exceptions
ShogunExceptionwill be thrown if an error occurs.

Reimplemented in CKernel, CDynamicArray< T >, CDynamicArray< float64_t >, CDynamicArray< float32_t >, CDynamicArray< int32_t >, CDynamicArray< char >, CDynamicArray< bool >, and CDynamicObjectArray.

Definition at line 431 of file SGObject.cpp.

bool set_alphabet ( EAlphabet  alpha)

set alphabet and initialize mapping table (for remap)

Parameters
alphanew alphabet

Definition at line 108 of file Alphabet.cpp.

void set_generic ( )
inherited

Definition at line 41 of file SGObject.cpp.

void set_generic ( )
inherited

Definition at line 46 of file SGObject.cpp.

void set_generic ( )
inherited

Definition at line 51 of file SGObject.cpp.

void set_generic ( )
inherited

Definition at line 56 of file SGObject.cpp.

void set_generic ( )
inherited

Definition at line 61 of file SGObject.cpp.

void set_generic ( )
inherited

Definition at line 66 of file SGObject.cpp.

void set_generic ( )
inherited

Definition at line 71 of file SGObject.cpp.

void set_generic ( )
inherited

Definition at line 76 of file SGObject.cpp.

void set_generic ( )
inherited

Definition at line 81 of file SGObject.cpp.

void set_generic ( )
inherited

Definition at line 86 of file SGObject.cpp.

void set_generic ( )
inherited

Definition at line 91 of file SGObject.cpp.

void set_generic ( )
inherited

Definition at line 96 of file SGObject.cpp.

void set_generic ( )
inherited

Definition at line 101 of file SGObject.cpp.

void set_generic ( )
inherited

Definition at line 106 of file SGObject.cpp.

void set_generic ( )
inherited

Definition at line 111 of file SGObject.cpp.

void set_generic ( )
inherited

set generic type to T

void set_global_io ( SGIO io)
inherited

set the io object

Parameters
ioio object to use

Definition at line 228 of file SGObject.cpp.

void set_global_parallel ( Parallel parallel)
inherited

set the parallel object

Parameters
parallelparallel object to use

Definition at line 241 of file SGObject.cpp.

void set_global_version ( Version version)
inherited

set the version object

Parameters
versionversion object to use

Definition at line 283 of file SGObject.cpp.

CSGObject * shallow_copy ( ) const
virtualinherited

A shallow copy. All the SGObject instance variables will be simply assigned and SG_REF-ed.

Reimplemented in CGaussianKernel.

Definition at line 192 of file SGObject.cpp.

void translate_from_single_order ( ST *  obs,
int32_t  sequence_length,
int32_t  start,
int32_t  p_order,
int32_t  max_val 
)
static

translate from single order

Parameters
obsobservation
sequence_lengthlength of sequence
startstart
p_orderorder
max_valmaximum value

Definition at line 760 of file Alphabet.cpp.

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 
)
static

translate from single order

Parameters
obsobservation
sequence_lengthlength of sequence
startstart
p_orderorder
max_valmaximum value
gapgap

Definition at line 836 of file Alphabet.cpp.

void translate_from_single_order ( float32_t obs,
int32_t  sequence_length,
int32_t  start,
int32_t  p_order,
int32_t  max_val,
int32_t  gap 
)

Definition at line 955 of file Alphabet.cpp.

void translate_from_single_order ( float64_t obs,
int32_t  sequence_length,
int32_t  start,
int32_t  p_order,
int32_t  max_val,
int32_t  gap 
)

Definition at line 959 of file Alphabet.cpp.

void translate_from_single_order ( floatmax_t obs,
int32_t  sequence_length,
int32_t  start,
int32_t  p_order,
int32_t  max_val,
int32_t  gap 
)

Definition at line 963 of file Alphabet.cpp.

void translate_from_single_order_reversed ( ST *  obs,
int32_t  sequence_length,
int32_t  start,
int32_t  p_order,
int32_t  max_val 
)
static

translate from single order reversed

Parameters
obsobservation
sequence_lengthlength of sequence
startstart
p_orderorder
max_valmaximum value

Definition at line 798 of file Alphabet.cpp.

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 
)
static

translate from single order reversed

Parameters
obsobservation
sequence_lengthlength of sequence
startstart
p_orderorder
max_valmaximum value
gapgap

Definition at line 898 of file Alphabet.cpp.

void translate_from_single_order_reversed ( float32_t obs,
int32_t  sequence_length,
int32_t  start,
int32_t  p_order,
int32_t  max_val,
int32_t  gap 
)

Definition at line 967 of file Alphabet.cpp.

void translate_from_single_order_reversed ( float64_t obs,
int32_t  sequence_length,
int32_t  start,
int32_t  p_order,
int32_t  max_val,
int32_t  gap 
)

Definition at line 971 of file Alphabet.cpp.

void translate_from_single_order_reversed ( floatmax_t obs,
int32_t  sequence_length,
int32_t  start,
int32_t  p_order,
int32_t  max_val,
int32_t  gap 
)

Definition at line 975 of file Alphabet.cpp.

void unset_generic ( )
inherited

unset generic type

this has to be called in classes specializing a template class

Definition at line 303 of file SGObject.cpp.

void update_parameter_hash ( )
virtualinherited

Updates the hash of current parameter combination

Definition at line 248 of file SGObject.cpp.

Member Data Documentation

EAlphabet alphabet
protected

alphabet

Definition at line 353 of file Alphabet.h.

const char * alphabet_names
static
Initial value:
={
"DNA","RAWDNA", "RNA", "PROTEIN", "BINARY", "ALPHANUM",
"CUBE", "RAW", "IUPAC_NUCLEIC_ACID", "IUPAC_AMINO_ACID",
"NONE", "DIGIT", "DIGIT2", "RAWDIGIT", "RAWDIGIT2", "UNKNOWN",
"SNP", "RAWSNP"}

alphabet names

Definition at line 338 of file Alphabet.h.

const uint8_t B_0 =4
static

B_0

Definition at line 334 of file Alphabet.h.

const uint8_t B_A =0
static

B_A

Definition at line 326 of file Alphabet.h.

const uint8_t B_C =1
static

B_C

Definition at line 328 of file Alphabet.h.

const uint8_t B_G =2
static

B_G

Definition at line 330 of file Alphabet.h.

const uint8_t B_T =3
static

B_T

Definition at line 332 of file Alphabet.h.

int64_t histogram[1<< (sizeof(uint8_t)*8)]
protected

histogram

Definition at line 365 of file Alphabet.h.

SGIO* io
inherited

io

Definition at line 369 of file SGObject.h.

Parameter* m_gradient_parameters
inherited

parameters wrt which we can compute gradients

Definition at line 384 of file SGObject.h.

uint32_t m_hash
inherited

Hash of parameter values

Definition at line 387 of file SGObject.h.

Parameter* m_model_selection_parameters
inherited

model selection parameters

Definition at line 381 of file SGObject.h.

Parameter* m_parameters
inherited

parameters

Definition at line 378 of file SGObject.h.

uint8_t maptable_to_bin[1<< (sizeof(uint8_t)*8)]
protected

maptable to bin

Definition at line 361 of file Alphabet.h.

uint8_t maptable_to_char[1<< (sizeof(uint8_t)*8)]
protected

maptable to char

Definition at line 363 of file Alphabet.h.

const uint8_t MAPTABLE_UNDEF =0xff
static

MAPTABLE UNDEF

Definition at line 336 of file Alphabet.h.

int32_t num_bits
protected

number of bits

Definition at line 357 of file Alphabet.h.

int32_t num_symbols
protected

number of symbols

Definition at line 355 of file Alphabet.h.

Parallel* parallel
inherited

parallel

Definition at line 372 of file SGObject.h.

bool valid_chars[1<< (sizeof(uint8_t)*8)]
protected

valid chars

Definition at line 359 of file Alphabet.h.

Version* version
inherited

version

Definition at line 375 of file SGObject.h.


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

SHOGUN Machine Learning Toolbox - Documentation