Public Member Functions | Protected Member Functions | Protected Attributes

CHashedWDFeatures Class Reference


Detailed Description

Features that compute the Weighted Degreee Kernel feature space explicitly.

See also:
CWeightedDegreeStringKernel

Definition at line 28 of file HashedWDFeatures.h.

Inheritance diagram for CHashedWDFeatures:
Inheritance graph
[legend]

List of all members.

Public Member Functions

 CHashedWDFeatures (void)
 CHashedWDFeatures (CStringFeatures< uint8_t > *str, int32_t start_order, int32_t order, int32_t from_order, int32_t hash_bits=12)
 CHashedWDFeatures (const CHashedWDFeatures &orig)
virtual ~CHashedWDFeatures ()
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 (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)
virtual CFeaturesduplicate () const
virtual EFeatureType get_feature_type ()
virtual EFeatureClass get_feature_class ()
virtual int32_t get_num_vectors () const
virtual int32_t get_size ()
void set_normalization_const (float64_t n=0)
float64_t get_normalization_const ()
virtual const char * get_name () const

Protected Member Functions

void set_wd_weights ()

Protected Attributes

CStringFeatures< uint8_t > * strings
int32_t degree
int32_t start_degree
int32_t from_degree
int32_t string_length
int32_t num_strings
int32_t alphabet_size
int32_t w_dim
int32_t partial_w_dim
float64_twd_weights
uint32_t mask
int32_t m_hash_bits
float64_t normalization_const

Constructor & Destructor Documentation

CHashedWDFeatures ( void   ) 

default constructor

Definition at line 16 of file HashedWDFeatures.cpp.

CHashedWDFeatures ( CStringFeatures< uint8_t > *  str,
int32_t  start_order,
int32_t  order,
int32_t  from_order,
int32_t  hash_bits = 12 
)

constructor

Parameters:
str stringfeatures (of bytes)
start_order do degrees starting with start_order up to order
order of wd kernel
from_order use first order weights from higher order weighting
hash_bits number of bits in hash

Definition at line 37 of file HashedWDFeatures.cpp.

CHashedWDFeatures ( const CHashedWDFeatures orig  ) 

copy constructor

Definition at line 64 of file HashedWDFeatures.cpp.

~CHashedWDFeatures (  )  [virtual]

destructor

Definition at line 80 of file HashedWDFeatures.cpp.


Member Function Documentation

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

Implements CDotFeatures.

Definition at line 164 of file HashedWDFeatures.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

Implements CDotFeatures.

Definition at line 118 of file HashedWDFeatures.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 86 of file HashedWDFeatures.cpp.

CFeatures * duplicate (  )  const [virtual]

duplicate feature object

Returns:
feature object

Implements CFeatures.

Definition at line 249 of file HashedWDFeatures.cpp.

virtual void free_feature_iterator ( void *  iterator  )  [virtual]

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

Parameters:
iterator as returned by get_first_feature

Implements CDotFeatures.

Definition at line 162 of file HashedWDFeatures.h.

virtual 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 58 of file HashedWDFeatures.h.

virtual EFeatureClass get_feature_class (  )  [virtual]

get feature class

Returns:
feature class

Implements CFeatures.

Definition at line 186 of file HashedWDFeatures.h.

virtual 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

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 134 of file HashedWDFeatures.h.

virtual EFeatureType get_feature_type (  )  [virtual]

get feature type

Returns:
templated feature type

Implements CFeatures.

Definition at line 177 of file HashedWDFeatures.h.

virtual const char* get_name ( void   )  const [virtual]
Returns:
object name

Implements CSGObject.

Definition at line 212 of file HashedWDFeatures.h.

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

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:
index is returned by reference (-1 when not available)
value is returned by reference
iterator as returned by get_first_feature
Returns:
true if a new non-zero feature got returned

Implements CDotFeatures.

Definition at line 150 of file HashedWDFeatures.h.

virtual int32_t get_nnz_features_for_vector ( int32_t  num  )  [virtual]

get number of non-zero features in vector

Parameters:
num which vector
Returns:
number of non-zero features in vector

Implements CDotFeatures.

Definition at line 97 of file HashedWDFeatures.h.

float64_t get_normalization_const (  ) 

get normalization constant

Definition at line 206 of file HashedWDFeatures.h.

virtual int32_t get_num_vectors (  )  const [virtual]

get number of examples/vectors, possibly corresponding to the current subset

abstract base method

Returns:
number of examples/vectors (possibly of subset, if implemented)

Implements CFeatures.

Definition at line 191 of file HashedWDFeatures.h.

virtual int32_t get_size (  )  [virtual]

get memory footprint of one feature

abstract base method

Returns:
memory footprint of one feature

Implements CFeatures.

Definition at line 196 of file HashedWDFeatures.h.

void set_normalization_const ( float64_t  n = 0  ) 

set normalization constant

Parameters:
n n=0 means automagic

Definition at line 233 of file HashedWDFeatures.cpp.

void set_wd_weights (  )  [protected]

create wd kernel weighting heuristic

Definition at line 213 of file HashedWDFeatures.cpp.


Member Data Documentation

int32_t alphabet_size [protected]

size of alphabet

Definition at line 237 of file HashedWDFeatures.h.

int32_t degree [protected]

degree

Definition at line 227 of file HashedWDFeatures.h.

int32_t from_degree [protected]

from degree

Definition at line 231 of file HashedWDFeatures.h.

int32_t m_hash_bits [protected]

number of bits in hash

Definition at line 247 of file HashedWDFeatures.h.

uint32_t mask [protected]

mask

Definition at line 245 of file HashedWDFeatures.h.

normalization const

Definition at line 250 of file HashedWDFeatures.h.

int32_t num_strings [protected]

number of strings

Definition at line 235 of file HashedWDFeatures.h.

int32_t partial_w_dim [protected]

partial w dim == hashsize

Definition at line 241 of file HashedWDFeatures.h.

int32_t start_degree [protected]

start_degree

Definition at line 229 of file HashedWDFeatures.h.

int32_t string_length [protected]

length of string in vector

Definition at line 233 of file HashedWDFeatures.h.

CStringFeatures<uint8_t>* strings [protected]

stringfeatures the wdfeatures are based on

Definition at line 224 of file HashedWDFeatures.h.

int32_t w_dim [protected]

w dim

Definition at line 239 of file HashedWDFeatures.h.

float64_t* wd_weights [protected]

wd weights

Definition at line 243 of file HashedWDFeatures.h.


The documentation for this class was generated from the following files:
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Defines

SHOGUN Machine Learning Toolbox - Documentation