SHOGUN  4.2.0
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Macros Modules Pages
List of all members | Public Member Functions | Public Attributes | Protected Member Functions | Protected Attributes
CStreamingHashedDocDotFeatures Class Reference

Detailed Description

This class implements streaming features for 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"].

The current example is stored as a combination of current_vector and current_label. Call get_next_example() followed by get_current_vector() to iterate through the stream.

Definition at line 42 of file StreamingHashedDocDotFeatures.h.

Inheritance diagram for CStreamingHashedDocDotFeatures:
[legend]

Public Member Functions

 CStreamingHashedDocDotFeatures ()
 
 CStreamingHashedDocDotFeatures (CStreamingFile *file, bool is_labelled, int32_t size, CTokenizer *tzer, int32_t bits=20)
 
 CStreamingHashedDocDotFeatures (CStringFeatures< char > *dot_features, CTokenizer *tzer, int32_t bits=20, float64_t *lab=NULL)
 
virtual ~CStreamingHashedDocDotFeatures ()
 
virtual float32_t dot (CStreamingDotFeatures *df)
 
virtual float32_t dense_dot (const float32_t *vec2, int32_t vec2_len)
 
virtual void add_to_dense_vec (float32_t alpha, float32_t *vec2, int32_t vec2_len, bool abs_val=false)
 
virtual int32_t get_dim_feature_space () const
 
virtual const char * get_name () const
 
virtual int32_t get_num_vectors () const
 
virtual CFeaturesduplicate () const
 
virtual void set_vector_reader ()
 
virtual void set_vector_and_label_reader ()
 
virtual EFeatureType get_feature_type () const
 
virtual EFeatureClass get_feature_class () const
 
virtual void start_parser ()
 
virtual void end_parser ()
 
virtual float64_t get_label ()
 
virtual bool get_next_example ()
 
virtual void release_example ()
 
virtual int32_t get_num_features ()
 
SGSparseVector< float64_tget_vector ()
 
void set_normalization (bool normalize)
 
void set_k_skip_n_grams (int32_t k, int32_t n)
 
virtual void dense_dot_range (float32_t *output, float32_t *alphas, float32_t *vec, int32_t dim, float32_t b, int32_t num_vec=0)
 
virtual void expand_if_required (float32_t *&vec, int32_t &len)
 
virtual void expand_if_required (float64_t *&vec, int32_t &len)
 
virtual void * get_feature_iterator ()
 
virtual int32_t get_nnz_features_for_vector ()
 
virtual bool get_next_feature (int32_t &index, float32_t &value, void *iterator)
 
virtual void free_feature_iterator (void *iterator)
 
void set_read_functions ()
 
virtual bool get_has_labels ()
 
virtual bool is_seekable ()
 
virtual void reset_stream ()
 
virtual CFeaturesget_streamed_features (index_t num_elements)
 
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 CFeaturesshallow_subset_copy ()
 
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)
 
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 >
get (const Tag< T > &_tag) const
 
template<typename T , typename U = void>
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 CSGObjectclone ()
 

Public Attributes

SGIOio
 
Parallelparallel
 
Versionversion
 
Parameterm_parameters
 
Parameterm_model_selection_parameters
 
Parameterm_gradient_parameters
 
uint32_t m_hash
 

Protected Member Functions

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

int32_t num_bits
 
SGSparseVector< float64_tcurrent_vector
 
CTokenizertokenizer
 
CHashedDocConverterconverter
 
CInputParser< char > parser
 
float64_t current_label
 
bool has_labels
 Whether examples are labelled or not. More...
 
CStreamingFileworking_file
 The StreamingFile object to read from. More...
 
bool seekable
 Whether the stream is seekable. More...
 
CSubsetStackm_subset_stack
 

Constructor & Destructor Documentation

Constructor

Definition at line 24 of file StreamingHashedDocDotFeatures.cpp.

CStreamingHashedDocDotFeatures ( CStreamingFile file,
bool  is_labelled,
int32_t  size,
CTokenizer tzer,
int32_t  bits = 20 
)

Constructor with input information passed. Will use normalization and no quadratic features by default, user should use the set_normalization() and set_k_skip_n_gram() methods to change that.

Parameters
fileCStreamingFile to take input from.
is_labelledWhether examples are labelled or not.
sizeNumber of examples to be held in the parser's "ring".
tzerthe tokenizer to use on the document collection
bitsthe number of bits of the new dimension (means a dimension of size 2^bits)

Definition at line 17 of file StreamingHashedDocDotFeatures.cpp.

CStreamingHashedDocDotFeatures ( CStringFeatures< char > *  dot_features,
CTokenizer tzer,
int32_t  bits = 20,
float64_t lab = NULL 
)

Constructor taking a CDotFeatures object and optionally, labels, as args. Will use normalization and no quadratic features by default, user should use the set_normalization() and set_k_skip_n_gram() methods to change that.

The derived class should implement it so that the Streaming*Features class uses the DotFeatures object as the input, getting examples one by one from the DotFeatures object (and labels, if applicable).

Parameters
dot_featuresCDotFeatures object
tzerthe tokenizer to use on the document collection
bitsthe number of bits of the new dimension (means a dimension of size 2^bits)
lablabels (optional)

Definition at line 29 of file StreamingHashedDocDotFeatures.cpp.

Destructor

Definition at line 76 of file StreamingHashedDocDotFeatures.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 ( float32_t  alpha,
float32_t vec2,
int32_t  vec2_len,
bool  abs_val = false 
)
virtual

add current vector multiplied with alpha to dense vector, 'vec'

Parameters
alphascalar alpha
vec2real valued vector to add to
vec2_lenlength of vector
abs_valif true add the absolute value

Implements CStreamingDotFeatures.

Definition at line 108 of file StreamingHashedDocDotFeatures.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 630 of file SGObject.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 747 of file SGObject.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 231 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.

float32_t dense_dot ( const float32_t vec2,
int32_t  vec2_len 
)
virtual

compute dot product between current vector and a dense vector

Parameters
vec2real valued vector
vec2_lenlength of vector

Implements CStreamingDotFeatures.

Definition at line 95 of file StreamingHashedDocDotFeatures.cpp.

void dense_dot_range ( float32_t output,
float32_t alphas,
float32_t vec,
int32_t  dim,
float32_t  b,
int32_t  num_vec = 0 
)
virtualinherited

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

Parameters
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
num_vecnumber of vectors to operate on (indices 0 to num_vec-1)

If num_vec == 0 or left to its default value, the function attempts to return dot product for all vectors. However, the given output vector must be preallocated!

note that the result will be written to output[0...(num_vec-1)] except when num_vec = 0

Definition at line 30 of file StreamingDotFeatures.cpp.

float32_t dot ( CStreamingDotFeatures df)
virtual

compute dot product between vectors of two StreamingDotFeatures objects.

Parameters
dfStreamingDotFeatures (of same kind) to compute dot product with

Implements CStreamingDotFeatures.

Definition at line 85 of file StreamingHashedDocDotFeatures.cpp.

CFeatures * duplicate ( ) const
virtual

Duplicate the object.

Returns
a duplicate object as CFeatures*

Implements CFeatures.

Definition at line 127 of file StreamingHashedDocDotFeatures.cpp.

void end_parser ( )
virtual

End the parser. Wait for the parsing thread to complete.

Implements CStreamingFeatures.

Definition at line 148 of file StreamingHashedDocDotFeatures.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 651 of file SGObject.cpp.

void expand_if_required ( float32_t *&  vec,
int32_t &  len 
)
virtualinherited

Expand the vector passed so that it its length is equal to the dimensionality of the features. The previous values are kept intact through realloc, and the new ones are set to zero.

Parameters
vecfloat32_t* vector
lenlength of the vector

Reimplemented in CStreamingVwFeatures.

Definition at line 53 of file StreamingDotFeatures.cpp.

void expand_if_required ( float64_t *&  vec,
int32_t &  len 
)
virtualinherited

Expand the vector passed so that it its length is equal to the dimensionality of the features. The previous values are kept intact through realloc, and the new ones are set to zero.

Parameters
vecfloat64_t* vector
lenlength of the vector

Reimplemented in CStreamingVwFeatures.

Definition at line 64 of file StreamingDotFeatures.cpp.

void free_feature_iterator ( void *  iterator)
virtualinherited

clean up iterator call this function with the iterator returned by get_first_feature

Parameters
iteratoras returned by get_first_feature

Definition at line 93 of file StreamingDotFeatures.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
_tagname 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
namename 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.

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 CStreamingDotFeatures.

Definition at line 117 of file StreamingHashedDocDotFeatures.cpp.

EFeatureClass get_feature_class ( ) const
virtual

Return the feature class

Returns
C_STREAMING_DENSE

Implements CFeatures.

Definition at line 137 of file StreamingHashedDocDotFeatures.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 ( )
virtualinherited

iterate over the non-zero features

call get_feature_iterator first, followed by get_next_feature and free_feature_iterator to cleanup

Returns
feature iterator (to be passed to get_next_feature)

Definition at line 75 of file StreamingDotFeatures.cpp.

EFeatureType get_feature_type ( ) const
virtual

Return the feature type, depending on T.

Returns
Feature type as EFeatureType

Implements CFeatures.

Definition at line 132 of file StreamingHashedDocDotFeatures.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.

bool get_has_labels ( )
virtualinherited

Return whether the examples are labelled or not.

Returns
true if labelled, else false

Definition at line 35 of file StreamingFeatures.cpp.

float64_t get_label ( )
virtual

Return the label of the current example.

Raise an error if the input has been specified as unlabelled.

Returns
Label (if labelled example)

Implements CStreamingFeatures.

Definition at line 177 of file StreamingHashedDocDotFeatures.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_namename 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_namename 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

Return the name.

Returns
the name of the class

Implements CSGObject.

Definition at line 122 of file StreamingHashedDocDotFeatures.cpp.

bool get_next_example ( )
virtual

Indicate to the parser that it must fetch the next example.

Returns
true on success, false on failure (i.e., no more examples).

Implements CStreamingFeatures.

Definition at line 153 of file StreamingHashedDocDotFeatures.cpp.

bool get_next_feature ( int32_t &  index,
float32_t value,
void *  iterator 
)
virtualinherited

iterate over the non-zero features

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

Parameters
indexis returned by reference (-1 when not available)
valueis returned by reference
iteratoras returned by get_first_feature
Returns
true if a new non-zero feature got returned

Definition at line 87 of file StreamingDotFeatures.cpp.

int32_t get_nnz_features_for_vector ( )
virtualinherited

get number of non-zero features in vector

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

Returns
number of sparse features in vector

Reimplemented in CStreamingVwFeatures, CStreamingSparseFeatures< T >, CStreamingDenseFeatures< T >, CStreamingDenseFeatures< float64_t >, and CStreamingDenseFeatures< float32_t >.

Definition at line 81 of file StreamingDotFeatures.cpp.

int32_t get_num_features ( )
virtual

Get the number of features in the current example.

Returns
number of features in current example

Implements CStreamingFeatures.

Definition at line 172 of file StreamingHashedDocDotFeatures.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

Return the number of vectors stored in this object.

Returns
1 if current_vector exists, else 0.

Implements CFeatures.

Definition at line 182 of file StreamingHashedDocDotFeatures.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.

virtual CFeatures* get_streamed_features ( index_t  num_elements)
virtualinherited

Returns a new CFeatures instance which contains num_elements elements from the underlying stream. Not SG_REF'ed

Parameters
num_elementsnum elements to save from stream
Returns
CFeatures object of underlying type, might be smaller than requested if the stream stopped. A warning is issued in this case.

NOT IMPLEMENTED!

Reimplemented in CStreamingDenseFeatures< T >, CStreamingDenseFeatures< float64_t >, and CStreamingDenseFeatures< float32_t >.

Definition at line 191 of file StreamingFeatures.h.

CSubsetStack * get_subset_stack ( )
virtualinherited

returns subset stack

Returns
subset stack

Definition at line 334 of file Features.cpp.

SGSparseVector< float64_t > get_vector ( )

Get the current example

Returns
a SGSparseVector representing the hashed version of the string last read

Definition at line 197 of file StreamingHashedDocDotFeatures.cpp.

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

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

Parameters
namename 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
tagtag 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
namename 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
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 329 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.

bool is_seekable ( )
virtualinherited

Whether the stream is seekable (to check if multiple epochs are possible), i.e., whether we can process examples in a batch fashion.

A stream can usually seekable when it comes from a file or when it comes from another conventional CFeatures object.

Returns
true if seekable, else false.

Definition at line 40 of file StreamingFeatures.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 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
ShogunExceptionwill 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
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 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
prefixprefix 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
_tagname and type information of parameter
valuevalue 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
namename of the parameter
valuevalue of the parameter along with type information

Definition at line 452 of file SGObject.h.

void release_example ( )
virtual

Indicate that processing of the current example is done. The parser then considers it safe to dispose of that example and replace it with another one.

Implements CStreamingFeatures.

Definition at line 167 of file StreamingHashedDocDotFeatures.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.

void reset_stream ( )
virtualinherited
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 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
ShogunExceptionwill 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
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 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
_tagname and type information of parameter
valuevalue 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
namename of the parameter
valuevalue of the parameter along with type information

Definition at line 354 of file SGObject.h.

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
ioio object to use

Definition at line 261 of file SGObject.cpp.

void set_global_parallel ( Parallel parallel)
inherited

set the parallel object

Parameters
parallelparallel object to use

Definition at line 274 of file SGObject.cpp.

void set_global_version ( Version version)
inherited

set the version object

Parameters
versionversion object to use

Definition at line 316 of file SGObject.cpp.

void set_k_skip_n_grams ( int32_t  k,
int32_t  n 
)

Method used to specify the parameters for the quadratic approach of k-skip n-grams. See class description for more details and an example.

Parameters
kthe max number of allowed skips
nthe max number of tokens to combine

Definition at line 207 of file StreamingHashedDocDotFeatures.cpp.

void set_normalization ( bool  normalize)

specify whether hashed vector should be normalized or not

Parameters
normalizewhether to normalize

Definition at line 202 of file StreamingHashedDocDotFeatures.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.

void set_read_functions ( )
inherited

Set the vector reading functions.

The functions are implemented specific to the type in the derived class.

Definition at line 29 of file StreamingFeatures.cpp.

void set_vector_and_label_reader ( )
virtual

Sets the read function (in case the examples are labelled) to get_*_vector_and_label from CStreamingFile.

The exact function depends on type T.

The parser uses the function set by this while reading labelled examples.

Implements CStreamingFeatures.

Definition at line 192 of file StreamingHashedDocDotFeatures.cpp.

void set_vector_reader ( )
virtual

Sets the read function (in case the examples are unlabelled) to get_*_vector() from CStreamingFile.

The exact function depends on type T.

The parser uses the function set by this while reading unlabelled examples.

Implements CStreamingFeatures.

Definition at line 187 of file StreamingHashedDocDotFeatures.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
void start_parser ( )
virtual

Start the parser. It stores parsed examples from the input in a separate thread.

Implements CStreamingFeatures.

Definition at line 142 of file StreamingHashedDocDotFeatures.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 336 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 281 of file SGObject.cpp.

Member Data Documentation

CHashedDocConverter* converter
protected

Converter

Definition at line 253 of file StreamingHashedDocDotFeatures.h.

float64_t current_label
protected

The current example's label

Definition at line 259 of file StreamingHashedDocDotFeatures.h.

SGSparseVector<float64_t> current_vector
protected

Current example

Definition at line 247 of file StreamingHashedDocDotFeatures.h.

bool has_labels
protectedinherited

Whether examples are labelled or not.

Definition at line 201 of file StreamingFeatures.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 num_bits
protected

number of bits for the target dimension

Definition at line 244 of file StreamingHashedDocDotFeatures.h.

Parallel* parallel
inherited

parallel

Definition at line 540 of file SGObject.h.

CInputParser<char> parser
protected

The parser

Definition at line 256 of file StreamingHashedDocDotFeatures.h.

bool seekable
protectedinherited

Whether the stream is seekable.

Definition at line 207 of file StreamingFeatures.h.

CTokenizer* tokenizer
protected

CTokenizer

Definition at line 250 of file StreamingHashedDocDotFeatures.h.

Version* version
inherited

version

Definition at line 543 of file SGObject.h.

CStreamingFile* working_file
protectedinherited

The StreamingFile object to read from.

Definition at line 204 of file StreamingFeatures.h.


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

SHOGUN Machine Learning Toolbox - Documentation