Detailed Description

This class can be used to provide on-the-fly vectorization of a document collection. Like in the standard Bag-of-Words representation, this class considers each document as a collection of tokens, which are then hashed into a new feature space of a specified dimension. This class is very flexible and allows the user to specify the tokenizer used to tokenize each document, specify whether the results should be normalized with regards to the sqrt of the document size, as well as to specify whether he wants to combine different tokens. The latter implements a k-skip n-grams approach, meaning that you can combine up to n tokens, while skipping up to k. Eg. for the tokens ["a", "b", "c", "d"], with n_grams = 2 and skips = 2, one would get the following combinations : ["a", "ab", "ac" (skipped 1), "ad" (skipped 2), "b", "bc", "bd" (skipped 1), "c", "cd", "d"].

Definition at line 38 of file HashedDocDotFeatures.h.

Inheritance diagram for CHashedDocDotFeatures:

[legend]

Public Member Functions
	CHashedDocDotFeatures (int32_t hash_bits=0, CStringFeatures< char > docs=NULL, CTokenizer tzer=NULL, bool normalize=true, int32_t n_grams=1, int32_t skips=0, int32_t size=0)

	CHashedDocDotFeatures (const CHashedDocDotFeatures &orig)

	CHashedDocDotFeatures (CFile *loader)

virtual	~CHashedDocDotFeatures ()

virtual int32_t	get_dim_feature_space () const

virtual float64_t	dot (int32_t vec_idx1, CDotFeatures *df, int32_t vec_idx2)

virtual float64_t	dense_dot_sgvec (int32_t vec_idx1, const SGVector< float64_t > vec2)

virtual float64_t	dense_dot (int32_t vec_idx1, const float64_t *vec2, int32_t vec2_len)

virtual void	add_to_dense_vec (float64_t alpha, int32_t vec_idx1, float64_t *vec2, int32_t vec2_len, bool abs_val=false)

virtual int32_t	get_nnz_features_for_vector (int32_t num)

virtual void *	get_feature_iterator (int32_t vector_index)

virtual bool	get_next_feature (int32_t &index, float64_t &value, void *iterator)

virtual void	free_feature_iterator (void *iterator)

void	set_doc_collection (CStringFeatures< char > *docs)

virtual const char *	get_name () const

virtual CFeatures *	duplicate () const

virtual EFeatureType	get_feature_type () const

virtual EFeatureClass	get_feature_class () const

virtual int32_t	get_num_vectors () const

virtual void	dense_dot_range (float64_t output, int32_t start, int32_t stop, float64_t alphas, float64_t *vec, int32_t dim, float64_t b)

virtual void	dense_dot_range_subset (int32_t sub_index, int32_t num, float64_t output, float64_t alphas, float64_t vec, int32_t dim, float64_t b)

float64_t	get_combined_feature_weight ()

void	set_combined_feature_weight (float64_t nw)

SGMatrix< float64_t >	get_computed_dot_feature_matrix ()

SGVector< float64_t >	get_computed_dot_feature_vector (int32_t num)

void	benchmark_add_to_dense_vector (int32_t repeats=5)

void	benchmark_dense_dot_range (int32_t repeats=5)

virtual SGVector< float64_t >	get_mean ()

virtual SGMatrix< float64_t >	get_cov ()

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

virtual void	load (CFile *loader)

virtual void	save (CFile *writer)

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 void	subset_changed_post ()

virtual CFeatures *	copy_subset (SGVector< index_t > indices)

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 CFeatures *	shallow_subset_copy ()

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)

bool	has (const std::string &name) const

template<typename T >
bool	has (const Tag< T > &tag) const

template<typename T , typename U = void>
bool	has (const std::string &name) const

template<typename T >
void	set (const Tag< T > &_tag, const T &value)

template<typename T , typename U = void>
void	set (const std::string &name, const T &value)

template<typename T >
T	get (const Tag< T > &_tag) const

template<typename T , typename U = void>
T	get (const std::string &name) const

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 ()

Static Public Member Functions
static uint32_t	calculate_token_hash (char *token, int32_t length, int32_t num_bits, uint32_t seed)

static void *	dense_dot_range_helper (void *p)

static SGVector< float64_t >	get_mean (CDotFeatures lhs, CDotFeatures rhs)

static SGMatrix< float64_t >	compute_cov (CDotFeatures lhs, CDotFeatures rhs)

Public Attributes
SGIO *	io

Parallel *	parallel

Version *	version

Parameter *	m_parameters

Parameter *	m_model_selection_parameters

Parameter *	m_gradient_parameters

uint32_t	m_hash

Protected Member Functions
void	display_progress (int32_t start, int32_t stop, int32_t v)

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)

template<typename T >
void	register_param (Tag< T > &_tag, const T &value)

template<typename T >
void	register_param (const std::string &name, const T &value)

Protected Attributes
CStringFeatures< char > *	doc_collection

int32_t	num_bits

CTokenizer *	tokenizer

bool	should_normalize

int32_t	ngrams

int32_t	tokens_to_skip

float64_t	combined_weight
	feature weighting in combined dot features More...

CSubsetStack *	m_subset_stack

Constructor & Destructor Documentation

CHashedDocDotFeatures	(	int32_t	hash_bits = `0`,
		CStringFeatures< char > *	docs = `NULL`,
		CTokenizer *	tzer = `NULL`,
		bool	normalize = `true`,
		int32_t	n_grams = `1`,
		int32_t	skips = `0`,
		int32_t	size = `0`
	)

constructor

Parameters

hash_bits	the number of bits of the hash. Means a dimension of size 2^(hash_bits).
docs	the document collection
tzer	the tokenizer to use on the documents
normalize	whether or not to normalize the result of the dot products
n_grams	max number of consecutive tokens to hash together (extra features)
skips	max number of tokens to skip when combining tokens
size	cache size

Definition at line 18 of file HashedDocDotFeatures.cpp.

CHashedDocDotFeatures ( const CHashedDocDotFeatures & orig )

copy constructor

Definition at line 30 of file HashedDocDotFeatures.cpp.

CHashedDocDotFeatures ( CFile * loader )

constructor

Parameters

loader File object via which to load data

Definition at line 37 of file HashedDocDotFeatures.cpp.

~CHashedDocDotFeatures ( )

virtual

destructor

Definition at line 74 of file HashedDocDotFeatures.cpp.

Member Function Documentation

void add_preprocessor ( CPreprocessor * p )

virtualinherited

add preprocessor

Parameters

p	preprocessor to set

Definition at line 85 of file Features.cpp.

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

Parameters

subset subset of indices to add

Reimplemented in CCombinedFeatures.

Definition at line 310 of file Features.cpp.

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

Parameters

subset subset of indices to replace the latest one with.

Definition at line 316 of file Features.cpp.

void add_to_dense_vec	(	float64_t	alpha,
		int32_t	vec_idx1,
		float64_t *	vec2,
		int32_t	vec2_len,
		bool	abs_val = `false`
	)

virtual

add vector 1 multiplied with alpha to dense vector2

Parameters

alpha	scalar alpha
vec_idx1	index of first vector
vec2	pointer to real valued vector
vec2_len	length of real valued vector
abs_val	if true add the absolute value

this vector will maintain the current n+k active tokens in a circular manner

the combinations generated from the current active tokens will be stored here to avoid creating new objects

Reading n+k-1 tokens

Implements CDotFeatures.

Definition at line 186 of file HashedDocDotFeatures.cpp.

void benchmark_add_to_dense_vector ( int32_t repeats = 5 )

inherited

run benchmark for add_to_dense_vec

Definition at line 318 of file DotFeatures.cpp.

void benchmark_dense_dot_range ( int32_t repeats = 5 )

inherited

run benchmark for dense_dot_range

Definition at line 341 of file DotFeatures.cpp.

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

dict	dictionary of parameters to be built.

Definition at line 630 of file SGObject.cpp.

uint32_t calculate_token_hash	(	char *	token,
		int32_t	length,
		int32_t	num_bits,
		uint32_t	seed
	)

static

Helper method to calculate the murmur hash of a token and restrict it to a specified dimension range.

Parameters

token	pointer to the token
length	the length of the token
num_bits	the number of bits to maintain in the hash
seed	a seed for the hash

Definition at line 262 of file HashedDocDotFeatures.cpp.

bool check_feature_compatibility ( CFeatures * f ) const

inherited

check feature compatibility

Parameters

f	features to check for compatibility

Returns: if features are compatible

Definition at line 283 of file Features.cpp.

void clean_preprocessors ( )

inherited

clears all preprocs

Definition at line 116 of file Features.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 747 of file SGObject.cpp.

SGMatrix< float64_t > compute_cov	(	CDotFeatures *	lhs,
		CDotFeatures *	rhs
	)

staticinherited

compute the covariance of two CDotFeatures together

Returns: covariance

Definition at line 469 of file DotFeatures.cpp.

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!

Parameters

dims	indices of feature dimensions to copy

Returns: new CFeatures instance with copies of specified features

Reimplemented in CDenseFeatures< ST >, CDenseFeatures< uint32_t >, CDenseFeatures< float64_t >, CDenseFeatures< T >, and CDenseFeatures< uint16_t >.

Definition at line 348 of file Features.cpp.

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.

This method is needed for a KernelMachine to store its model data. NOT IMPLEMENTED!

Parameters

indices indices of feature elements to copy

Returns: new CFeatures instance with copies of feature data

Reimplemented in CStringFeatures< ST >, CStringFeatures< T >, CStringFeatures< uint8_t >, CStringFeatures< char >, CStringFeatures< uint16_t >, CSparseFeatures< ST >, CSparseFeatures< float64_t >, CSparseFeatures< T >, CDenseFeatures< ST >, CDenseFeatures< uint32_t >, CDenseFeatures< float64_t >, CDenseFeatures< T >, CDenseFeatures< uint16_t >, and CCombinedFeatures.

Definition at line 340 of file Features.cpp.

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!

Parameters

others list of feature objects to append

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

Reimplemented in CDenseFeatures< ST >, CDenseFeatures< uint32_t >, CDenseFeatures< float64_t >, CDenseFeatures< T >, and CDenseFeatures< uint16_t >.

Definition at line 235 of file Features.h.

virtual CFeatures* create_merged_copy ( CFeatures * other )

virtualinherited

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

NOT IMPLEMENTED!

Parameters

other feature object to append

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

Reimplemented in CDenseFeatures< ST >, CDenseFeatures< uint32_t >, CDenseFeatures< float64_t >, CDenseFeatures< T >, CDenseFeatures< uint16_t >, and CCombinedFeatures.

Definition at line 249 of file Features.h.

CSGObject * deep_copy ( ) const

virtualinherited

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

Definition at line 231 of file SGObject.cpp.

void del_preprocessor ( int32_t num )

virtualinherited

delete preprocessor from list

Parameters

num	index of preprocessor in list

Definition at line 122 of file Features.cpp.

float64_t dense_dot	(	int32_t	vec_idx1,
		const float64_t *	vec2,
		int32_t	vec2_len
	)

virtual

compute dot product between vector1 and a dense vector

Parameters

vec_idx1	index of first vector
vec2	pointer to real valued vector
vec2_len	length of real valued vector

this vector will maintain the current n+k active tokens in a circular manner

the combinations generated from the current active tokens will be stored here to avoid creating new objects

Reading n+k-1 tokens

Reading token and storing indices to hashed_indices

Implements CDotFeatures.

Definition at line 113 of file HashedDocDotFeatures.cpp.

void dense_dot_range	(	float64_t *	output,
		int32_t	start,
		int32_t	stop,
		float64_t *	alphas,
		float64_t *	vec,
		int32_t	dim,
		float64_t	b
	)

virtualinherited

Compute the dot product for a range of vectors. This function makes use of dense_dot alphas[i] * sparse[i]^T * w + b

Parameters

output	result for the given vector range
start	start vector range from this idx
stop	stop vector range at this idx
alphas	scalars to multiply with, may be NULL
vec	dense vector to compute dot product with
dim	length of the dense vector
b	bias

note that the result will be written to output[0...(stop-start-1)]

Reimplemented in CCombinedDotFeatures, and CHashedWDFeaturesTransposed.

Definition at line 67 of file DotFeatures.cpp.

void * dense_dot_range_helper ( void * p )

staticinherited

Compute the dot product for a range of vectors. This function is called by the threads created in dense_dot_range

Definition at line 231 of file DotFeatures.cpp.

void dense_dot_range_subset	(	int32_t *	sub_index,
		int32_t	num,
		float64_t *	output,
		float64_t *	alphas,
		float64_t *	vec,
		int32_t	dim,
		float64_t	b
	)

virtualinherited

Compute the dot product for a subset of vectors. This function makes use of dense_dot alphas[i] * sparse[i]^T * w + b

Parameters

sub_index	index for which to compute outputs
num	length of index
output	result for the given vector range
alphas	scalars to multiply with, may be NULL
vec	dense vector to compute dot product with
dim	length of the dense vector
b	bias

Reimplemented in CCombinedDotFeatures, and CHashedWDFeaturesTransposed.

Definition at line 153 of file DotFeatures.cpp.

float64_t dense_dot_sgvec	(	int32_t	vec_idx1,
		const SGVector< float64_t >	vec2
	)

virtual

compute dot product between vector1 and a dense vector

Parameters

vec_idx1	index of first vector
vec2	dense vector

Reimplemented from CDotFeatures.

Definition at line 108 of file HashedDocDotFeatures.cpp.

void display_progress	(	int32_t	start,
		int32_t	stop,
		int32_t	v
	)

protectedinherited

display progress output

Parameters

start	minimum value
stop	maximum value
v	current value

Definition at line 528 of file DotFeatures.cpp.

float64_t dot	(	int32_t	vec_idx1,
		CDotFeatures *	df,
		int32_t	vec_idx2
	)

virtual

compute dot product between vector1 and vector2, appointed by their indices

Parameters

vec_idx1	index of first vector
df	DotFeatures (of same kind) to compute dot product with
vec_idx2	index of second vector

Implements CDotFeatures.

Definition at line 85 of file HashedDocDotFeatures.cpp.

CFeatures * duplicate ( ) const

virtual

duplicate feature object

Returns: feature object

Implements CFeatures.

Definition at line 305 of file HashedDocDotFeatures.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

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

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

Definition at line 651 of file SGObject.cpp.

void free_feature_iterator ( void * iterator )

virtual

clean up iterator call this function with the iterator returned by get_feature_iterator NOT IMPLEMENTED

Parameters

iterator as returned by get_feature_iterator

Implements CDotFeatures.

Definition at line 295 of file HashedDocDotFeatures.cpp.

T get ( const Tag< T > & _tag ) const

inherited

Getter for a class parameter, identified by a Tag. Throws an exception if the class does not have such a parameter.

Parameters

_tag	name and type information of parameter

Returns: value of the parameter identified by the input tag

Definition at line 367 of file SGObject.h.

T get ( const std::string & name ) const

inherited

Getter for a class parameter, identified by a name. Throws an exception if the class does not have such a parameter.

Parameters

name	name of the parameter

Returns: value of the parameter corresponding to the input name and type

Definition at line 388 of file SGObject.h.

int32_t get_cache_size ( ) const

inherited

get cache size

Returns: cache size

Definition at line 160 of file Features.cpp.

float64_t get_combined_feature_weight ( )

inherited

get combined feature weight

Returns: combined feature weight

Definition at line 154 of file DotFeatures.h.

SGMatrix< float64_t > get_computed_dot_feature_matrix ( )

inherited

compute the feature matrix in feature space

Returns: computed feature matrix

Definition at line 284 of file DotFeatures.cpp.

SGVector< float64_t > get_computed_dot_feature_vector ( int32_t num )

inherited

compute the feature vector in feature space

Returns: computed feature vector

Definition at line 305 of file DotFeatures.cpp.

SGMatrix< float64_t > get_cov ( )

virtualinherited

get covariance

Returns: covariance

Definition at line 427 of file DotFeatures.cpp.

int32_t get_dim_feature_space ( ) const

virtual

obtain the dimensionality of the feature space

(not mix this up with the dimensionality of the input space, usually obtained via get_num_features())

Returns: dimensionality

Implements CDotFeatures.

Definition at line 80 of file HashedDocDotFeatures.cpp.

EFeatureClass get_feature_class ( ) const

virtual

get feature class

Returns: feature class DENSE

Implements CFeatures.

Definition at line 315 of file HashedDocDotFeatures.cpp.

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

Parameters

rhs	the class in right hand side

Returns: whether this class supports compatible computation

Reimplemented in CDenseSubSamplesFeatures< ST >.

Definition at line 355 of file Features.cpp.

void * get_feature_iterator ( int32_t vector_index )

virtual

iterate over the non-zero features

call get_feature_iterator first, followed by get_next_feature and free_feature_iterator to cleanup NOT IMPLEMENTED

Parameters

vector_index the index of the vector over whose components to iterate over

Returns: feature iterator (to be passed to get_next_feature)

Implements CDotFeatures.

Definition at line 283 of file HashedDocDotFeatures.cpp.

EFeatureType get_feature_type ( ) const

virtual

get feature type

Returns: templated feature type

Implements CFeatures.

Definition at line 310 of file HashedDocDotFeatures.cpp.

SGIO * get_global_io ( )

inherited

get the io object

Returns: io object

Definition at line 268 of file SGObject.cpp.

Parallel * get_global_parallel ( )

inherited

get the parallel object

Returns: parallel object

Definition at line 310 of file SGObject.cpp.

Version * get_global_version ( )

inherited

get the version object

Returns: version object

Definition at line 323 of file SGObject.cpp.

SGVector< float64_t > get_mean ( )

virtualinherited

get mean

Returns: mean returned

Definition at line 384 of file DotFeatures.cpp.

SGVector< float64_t > get_mean	(	CDotFeatures *	lhs,
		CDotFeatures *	rhs
	)

staticinherited

get mean of two CDotFeature objects

Returns: mean returned

Definition at line 402 of file DotFeatures.cpp.

SGStringList< char > get_modelsel_names ( )

inherited

Returns: vector of names of all parameters which are registered for model selection

Definition at line 531 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_name name of the parameter

Returns: description of the parameter

Definition at line 555 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_name name of model selection parameter

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

Definition at line 568 of file SGObject.cpp.

const char * get_name ( ) const

virtual

Returns the name of the SGSerializable instance. It MUST BE the CLASS NAME without the prefixed `C'.

Returns: name of the SGSerializable

Implements CSGObject.

Definition at line 300 of file HashedDocDotFeatures.cpp.

bool get_next_feature	(	int32_t &	index,
		float64_t &	value,
		void *	iterator
	)

virtual

iterate over the non-zero features NOT IMPLEMENTED

call this function with the iterator returned by get_feature_iterator and call free_feature_iterator to cleanup

Parameters

index	is returned by reference (-1 when not available)
value	is returned by reference
iterator	as returned by get_feature_iterator

Returns: true if a new non-zero feature got returned

Implements CDotFeatures.

Definition at line 289 of file HashedDocDotFeatures.cpp.

int32_t get_nnz_features_for_vector ( int32_t num )

virtual

get number of non-zero features in vector

(in case accurate estimates are too expensive overestimating is OK)

Parameters

num	which vector

Returns: number of sparse features in vector

Implements CDotFeatures.

Definition at line 275 of file HashedDocDotFeatures.cpp.

int32_t get_num_preprocessed ( ) const

inherited

get the number of applied preprocs

Returns: number of applied preprocessors

Definition at line 103 of file Features.cpp.

int32_t get_num_preprocessors ( ) const

inherited

get number of preprocessors

Returns: number of preprocessors

Definition at line 155 of file Features.cpp.

int32_t get_num_vectors ( ) const

virtual

get number of feature vectors

Returns: number of feature vectors

Implements CFeatures.

Definition at line 320 of file HashedDocDotFeatures.cpp.

CPreprocessor * get_preprocessor ( int32_t num ) const

inherited

get specified preprocessor

Parameters

num	index of preprocessor in list

Definition at line 93 of file Features.cpp.

CSubsetStack * get_subset_stack ( )

virtualinherited

returns subset stack

Returns: subset stack

Definition at line 334 of file Features.cpp.

bool has ( const std::string & name ) const

inherited

Checks if object has a class parameter identified by a name.

Parameters

name	name of the parameter

Returns: true if the parameter exists with the input name

Definition at line 289 of file SGObject.h.

bool has ( const Tag< T > & tag ) const

inherited

Checks if object has a class parameter identified by a Tag.

Parameters

tag	tag of the parameter containing name and type information

Returns: true if the parameter exists with the input tag

Definition at line 301 of file SGObject.h.

bool has ( const std::string & name ) const

inherited

Checks if a type exists for a class parameter identified by a name.

Parameters

name	name of the parameter

Returns: true if the parameter exists with the input name and type

Definition at line 312 of file SGObject.h.

bool has_property ( EFeatureProperty p ) const

inherited

check if features have given property

Parameters

p	feature property

Returns: if features have given property

Definition at line 295 of file Features.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

generic set to the type of the generic if returning TRUE

Returns: TRUE if a class template.

Definition at line 329 of file SGObject.cpp.

bool is_preprocessed ( int32_t num ) const

inherited

get whether specified preprocessor was already applied

Parameters

num	index of preprocessor in list

Definition at line 149 of file Features.cpp.

void list_feature_obj ( ) const

inherited

list feature object

Definition at line 171 of file Features.cpp.

void list_preprocessors ( )

inherited

print preprocessors

Definition at line 131 of file Features.cpp.

void load ( CFile * loader )

virtualinherited

load features from file

Parameters

loader File object via which data shall be loaded

Reimplemented in CDenseFeatures< ST >, CDenseFeatures< uint32_t >, CDenseFeatures< float64_t >, CDenseFeatures< T >, CDenseFeatures< uint16_t >, CSparseFeatures< ST >, CSparseFeatures< float64_t >, CSparseFeatures< T >, CStringFeatures< ST >, CStringFeatures< T >, CStringFeatures< uint8_t >, CStringFeatures< char >, and CStringFeatures< uint16_t >.

Definition at line 269 of file Features.cpp.

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

file	where to load from
prefix	prefix for members

Returns: TRUE if done, otherwise FALSE

Definition at line 402 of file SGObject.cpp.

void load_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::LOAD_SERIALIZABLE_POST is called.

Exceptions

ShogunException will be thrown if an error occurs.

Reimplemented in CKernel, CWeightedDegreePositionStringKernel, CList, CAlphabet, CLinearHMM, CGaussianKernel, CInverseMultiQuadricKernel, CCircularKernel, and CExponentialKernel.

Definition at line 459 of file SGObject.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

ShogunException will 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 454 of file SGObject.cpp.

bool parameter_hash_changed ( )

virtualinherited

Returns: whether parameter combination has changed since last update

Definition at line 295 of file SGObject.cpp.

void print_modsel_params ( )

inherited

prints all parameter registered for model selection and their type

Definition at line 507 of file SGObject.cpp.

void print_serializable ( const char * prefix = "" )

virtualinherited

prints registered parameters out

Parameters

prefix prefix for members

Definition at line 341 of file SGObject.cpp.

void register_param	(	Tag< T > &	_tag,
		const T &	value
	)

protectedinherited

Registers a class parameter which is identified by a tag. This enables the parameter to be modified by set() and retrieved by get(). Parameters can be registered in the constructor of the class.

Parameters

_tag	name and type information of parameter
value	value of the parameter

Definition at line 439 of file SGObject.h.

void register_param	(	const std::string &	name,
		const T &	value
	)

protectedinherited

Registers a class parameter which is identified by a name. This enables the parameter to be modified by set() and retrieved by get(). Parameters can be registered in the constructor of the class.

Parameters

name	name of the parameter
value	value of the parameter along with type information

Definition at line 452 of file SGObject.h.

void remove_all_subsets ( )

virtualinherited

removes all subsets Calls subset_changed_post() afterwards

Reimplemented in CCombinedFeatures.

Definition at line 328 of file Features.cpp.

void remove_subset ( )

virtualinherited

removes that last added subset from subset stack, if existing Calls subset_changed_post() afterwards

Reimplemented in CCombinedFeatures.

Definition at line 322 of file Features.cpp.

bool reshape	(	int32_t	num_features,
		int32_t	num_vectors
	)

virtualinherited

in case there is a feature matrix allow for reshaping

NOT IMPLEMENTED!

Parameters

num_features	new number of features
num_vectors	new number of vectors

Returns: if reshaping was successful

Reimplemented in CDenseFeatures< ST >, CDenseFeatures< uint32_t >, CDenseFeatures< float64_t >, CDenseFeatures< T >, and CDenseFeatures< uint16_t >.

Definition at line 165 of file Features.cpp.

void save ( CFile * writer )

virtualinherited

save features to file

Parameters

writer File object via which data shall be saved

Reimplemented in CStringFeatures< ST >, CStringFeatures< T >, CStringFeatures< uint8_t >, CStringFeatures< char >, CStringFeatures< uint16_t >, CDenseFeatures< ST >, CDenseFeatures< uint32_t >, CDenseFeatures< float64_t >, CDenseFeatures< T >, CDenseFeatures< uint16_t >, CSparseFeatures< ST >, CSparseFeatures< float64_t >, and CSparseFeatures< T >.

Definition at line 276 of file Features.cpp.

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

virtualinherited

Save this object to file.

Parameters

file	where to save the object; will be closed during returning if PREFIX is an empty string.
prefix	prefix for members

Returns: TRUE if done, otherwise FALSE

Definition at line 347 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

ShogunException will be thrown if an error occurs.

Reimplemented in CKernel.

Definition at line 469 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

ShogunException will 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 464 of file SGObject.cpp.

void set	(	const Tag< T > &	_tag,
		const T &	value
	)

inherited

Setter for a class parameter, identified by a Tag. Throws an exception if the class does not have such a parameter.

Parameters

_tag	name and type information of parameter
value	value of the parameter

Definition at line 328 of file SGObject.h.

void set	(	const std::string &	name,
		const T &	value
	)

inherited

Setter for a class parameter, identified by a name. Throws an exception if the class does not have such a parameter.

Parameters

name	name of the parameter
value	value of the parameter along with type information

Definition at line 354 of file SGObject.h.

void set_combined_feature_weight ( float64_t nw )

inherited

set combined kernel weight

Parameters

nw	new combined feature weight

Definition at line 160 of file DotFeatures.h.

void set_doc_collection ( CStringFeatures< char > * docs )

set the document collection to work on

Parameters

docs	the document collection

Definition at line 269 of file HashedDocDotFeatures.cpp.

void set_generic ( )

inherited

Definition at line 74 of file SGObject.cpp.

void set_generic ( )

inherited

Definition at line 79 of file SGObject.cpp.

void set_generic ( )

inherited

Definition at line 84 of file SGObject.cpp.

void set_generic ( )

inherited

Definition at line 89 of file SGObject.cpp.

void set_generic ( )

inherited

Definition at line 94 of file SGObject.cpp.

void set_generic ( )

inherited

Definition at line 99 of file SGObject.cpp.

void set_generic ( )

inherited

Definition at line 104 of file SGObject.cpp.

void set_generic ( )

inherited

Definition at line 109 of file SGObject.cpp.

void set_generic ( )

inherited

Definition at line 114 of file SGObject.cpp.

void set_generic ( )

inherited

Definition at line 119 of file SGObject.cpp.

void set_generic ( )

inherited

Definition at line 124 of file SGObject.cpp.

void set_generic ( )

inherited

Definition at line 129 of file SGObject.cpp.

void set_generic ( )

inherited

Definition at line 134 of file SGObject.cpp.

void set_generic ( )

inherited

Definition at line 139 of file SGObject.cpp.

void set_generic ( )

inherited

Definition at line 144 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

io	io object to use

Definition at line 261 of file SGObject.cpp.

void set_global_parallel ( Parallel * parallel )

inherited

set the parallel object

Parameters

parallel parallel object to use

Definition at line 274 of file SGObject.cpp.

void set_global_version ( Version * version )

inherited

set the version object

Parameters

version version object to use

Definition at line 316 of file SGObject.cpp.

void set_preprocessed ( int32_t num )

inherited

set applied flag for preprocessor

Parameters

num	index of preprocessor in list

Definition at line 143 of file Features.cpp.

void set_property ( EFeatureProperty p )

inherited

set property

Parameters

p	kernel property to set

Definition at line 300 of file Features.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 225 of file SGObject.cpp.

virtual CFeatures* shallow_subset_copy ( )

virtualinherited

Reimplemented in CDenseFeatures< ST >, CDenseFeatures< uint32_t >, CDenseFeatures< float64_t >, CDenseFeatures< T >, and CDenseFeatures< uint16_t >.

Definition at line 336 of file Features.h.

virtual void subset_changed_post ( )

virtualinherited

method may be overwritten to update things that depend on subset

Reimplemented in CStringFeatures< ST >, CStringFeatures< T >, CStringFeatures< uint8_t >, CStringFeatures< char >, and CStringFeatures< uint16_t >.

Definition at line 293 of file Features.h.

virtual bool support_compatible_class ( ) const

virtualinherited

does this class support compatible computation bewteen difference classes? for example, this->dot(rhs_prt), can rhs_prt be an instance of a difference class?

Returns: whether this class supports compatible computation

Reimplemented in CDenseSubSamplesFeatures< ST >.

Definition at line 323 of file Features.h.

void unset_generic ( )

inherited

unset generic type

this has to be called in classes specializing a template class

Definition at line 336 of file SGObject.cpp.

void unset_property ( EFeatureProperty p )

inherited

unset property

Parameters

p	kernel property to unset

Definition at line 305 of file Features.cpp.

void update_parameter_hash ( )

virtualinherited

Updates the hash of current parameter combination

Definition at line 281 of file SGObject.cpp.

Member Data Documentation

float64_t combined_weight

protectedinherited

feature weighting in combined dot features

Definition at line 249 of file DotFeatures.h.

CStringFeatures<char>* doc_collection

protected

the document collection

Definition at line 201 of file HashedDocDotFeatures.h.

SGIO* io

inherited

io

Definition at line 537 of file SGObject.h.

Parameter* m_gradient_parameters

inherited

parameters wrt which we can compute gradients

Definition at line 552 of file SGObject.h.

uint32_t m_hash

inherited

Hash of parameter values

Definition at line 555 of file SGObject.h.

Parameter* m_model_selection_parameters

inherited

model selection parameters

Definition at line 549 of file SGObject.h.

Parameter* m_parameters

inherited

parameters

Definition at line 546 of file SGObject.h.

CSubsetStack* m_subset_stack

protectedinherited

subset used for index transformations

Definition at line 361 of file Features.h.

int32_t ngrams

protected

n for ngrams for quadratic features

Definition at line 213 of file HashedDocDotFeatures.h.

int32_t num_bits

protected

number of bits of hash

Definition at line 204 of file HashedDocDotFeatures.h.

Parallel* parallel

inherited

parallel

Definition at line 540 of file SGObject.h.

bool should_normalize

protected

if should normalize the dot product results

Definition at line 210 of file HashedDocDotFeatures.h.

CTokenizer* tokenizer

protected

tokenizer

Definition at line 207 of file HashedDocDotFeatures.h.

int32_t tokens_to_skip

protected

tokens to skip when combining tokens

Definition at line 216 of file HashedDocDotFeatures.h.

Version* version

inherited

version

Definition at line 543 of file SGObject.h.

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

Detailed Description

Public Member Functions

Static Public Member Functions

Public Attributes

Protected Member Functions

Protected Attributes

Constructor & Destructor Documentation

Member Function Documentation

Member Data Documentation