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 | Protected Member Functions | Protected Attributes
CHashedDocDotFeatures Class Reference

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:
Inheritance graph
[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 CFeaturesduplicate () 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_tget_computed_dot_feature_matrix ()
 
SGVector< float64_tget_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_tget_mean ()
 
virtual SGMatrix< float64_tget_cov ()
 
virtual void add_preprocessor (CPreprocessor *p)
 
virtual void del_preprocessor (int32_t num)
 
CPreprocessorget_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 CFeaturescreate_merged_copy (CList *others)
 
virtual CFeaturescreate_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 CSubsetStackget_subset_stack ()
 
virtual void subset_changed_post ()
 
virtual CFeaturescopy_subset (SGVector< index_t > indices)
 
virtual CFeaturescopy_dimension_subset (SGVector< index_t > dims)
 
virtual bool support_compatible_class () const
 
virtual bool get_feature_class_compatibility (EFeatureClass rhs) const
 
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 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_tget_mean (CDotFeatures *lhs, CDotFeatures *rhs)
 
static SGMatrix< float64_tcompute_cov (CDotFeatures *lhs, CDotFeatures *rhs)
 

Public Attributes

SGIOio
 
Parallelparallel
 
Versionversion
 
Parameterm_parameters
 
Parameterm_model_selection_parameters
 
Parameterm_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)
 

Protected Attributes

CStringFeatures< char > * doc_collection
 
int32_t num_bits
 
CTokenizertokenizer
 
bool should_normalize
 
int32_t ngrams
 
int32_t tokens_to_skip
 
float64_t combined_weight
 feature weighting in combined dot features More...
 
CSubsetStackm_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_bitsthe number of bits of the hash. Means a dimension of size 2^(hash_bits).
docsthe document collection
tzerthe tokenizer to use on the documents
normalizewhether or not to normalize the result of the dot products
n_gramsmax number of consecutive tokens to hash together (extra features)
skipsmax number of tokens to skip when combining tokens
sizecache size

Definition at line 18 of file HashedDocDotFeatures.cpp.

copy constructor

Definition at line 30 of file HashedDocDotFeatures.cpp.

constructor

Parameters
loaderFile 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
ppreprocessor 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
subsetsubset 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
subsetsubset 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
alphascalar alpha
vec_idx1index of first vector
vec2pointer to real valued vector
vec2_lenlength of real valued vector
abs_valif 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
dictdictionary of parameters to be built.

Definition at line 597 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
tokenpointer to the token
lengththe length of the token
num_bitsthe number of bits to maintain in the hash
seeda seed for the hash

Definition at line 262 of file HashedDocDotFeatures.cpp.

bool check_feature_compatibility ( CFeatures f) const
inherited

check feature compatibility

Parameters
ffeatures 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 714 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
dimsindices 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
indicesindices 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
otherslist 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
otherfeature 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 198 of file SGObject.cpp.

void del_preprocessor ( int32_t  num)
virtualinherited

delete preprocessor from list

Parameters
numindex 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_idx1index of first vector
vec2pointer to real valued vector
vec2_lenlength 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
outputresult for the given vector range
startstart vector range from this idx
stopstop vector range at this idx
alphasscalars to multiply with, may be NULL
vecdense vector to compute dot product with
dimlength of the dense vector
bbias

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_indexindex for which to compute outputs
numlength of index
outputresult for the given vector range
alphasscalars to multiply with, may be NULL
vecdense vector to compute dot product with
dimlength of the dense vector
bbias

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_idx1index of first vector
vec2dense 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
startminimum value
stopmaximum value
vcurrent 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_idx1index of first vector
dfDotFeatures (of same kind) to compute dot product with
vec_idx2index 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
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.

void free_feature_iterator ( void *  iterator)
virtual

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

Parameters
iteratoras returned by get_feature_iterator

Implements CDotFeatures.

Definition at line 295 of file HashedDocDotFeatures.cpp.

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
rhsthe 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_indexthe 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 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< 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 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.

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
indexis returned by reference (-1 when not available)
valueis returned by reference
iteratoras 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
numwhich 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
numindex 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_property ( EFeatureProperty  p) const
inherited

check if features have given property

Parameters
pfeature 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
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_preprocessed ( int32_t  num) const
inherited

get whether specified preprocessor was already applied

Parameters
numindex 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
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
)
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
ShogunExceptionwill be thrown if an error occurs.

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

Definition at line 426 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
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_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.

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_featuresnew number of features
num_vectorsnew 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
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.

void set_combined_feature_weight ( float64_t  nw)
inherited

set combined kernel weight

Parameters
nwnew 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
docsthe document collection

Definition at line 269 of file HashedDocDotFeatures.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.

void set_preprocessed ( int32_t  num)
inherited

set applied flag for preprocessor

Parameters
numindex of preprocessor in list

Definition at line 143 of file Features.cpp.

void set_property ( EFeatureProperty  p)
inherited

set property

Parameters
pkernel 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 192 of file SGObject.cpp.

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 303 of file SGObject.cpp.

void unset_property ( EFeatureProperty  p)
inherited

unset property

Parameters
pkernel 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 248 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 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.

CSubsetStack* m_subset_stack
protectedinherited

subset used for index transformations

Definition at line 352 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 372 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 375 of file SGObject.h.


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

SHOGUN Machine Learning Toolbox - Documentation