SHOGUN
4.1.0
|
This class can be used to convert a document collection contained in a CStringFeatures<char> object where each document is stored as a single vector into a hashed Bag-of-Words representation. 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 39 of file HashedDocConverter.h.
Public Member Functions | |
CHashedDocConverter () | |
CHashedDocConverter (int32_t hash_bits, bool normalize=false, int32_t n_grams=1, int32_t skips=0) | |
CHashedDocConverter (CTokenizer *tzer, int32_t hash_bits, bool normalize=false, int32_t n_grams=1, int32_t skips=0) | |
virtual | ~CHashedDocConverter () |
virtual CFeatures * | apply (CFeatures *features) |
SGSparseVector< float64_t > | apply (SGVector< char > document) |
virtual const char * | get_name () const |
void | set_normalization (bool normalize) |
void | set_k_skip_n_grams (int32_t k, int32_t n) |
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) |
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 index_t | generate_ngram_hashes (SGVector< uint32_t > &hashes, index_t hashes_start, index_t len, SGVector< index_t > &ngram_hashes, int32_t num_bits, int32_t ngrams, int32_t tokens_to_skip) |
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 | init (CTokenizer *tzer, int32_t d, bool normalize, int32_t n_grams, int32_t skips) |
int32_t | count_distinct_indices (CDynamicArray< uint32_t > &hashed_indices) |
SGSparseVector< float64_t > | create_hashed_representation (CDynamicArray< uint32_t > &hashed_indices) |
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 | |
int32_t | num_bits |
CTokenizer * | tokenizer |
bool | should_normalize |
int32_t | ngrams |
int32_t | tokens_to_skip |
Default constructor
Definition at line 23 of file HashedDocConverter.cpp.
CHashedDocConverter | ( | int32_t | hash_bits, |
bool | normalize = false , |
||
int32_t | n_grams = 1 , |
||
int32_t | skips = 0 |
||
) |
Constructor Creates tokens on whitespace
hash_bits | the number of bits of the hash. Means a dimension of size 2^(hash_bits). |
normalize | whether to normalize vectors or not |
n_grams | the max number of tokens to consider when combining tokens |
skips | the max number of tokens to skip when combining tokens |
Definition at line 28 of file HashedDocConverter.cpp.
CHashedDocConverter | ( | CTokenizer * | tzer, |
int32_t | hash_bits, | ||
bool | normalize = false , |
||
int32_t | n_grams = 1 , |
||
int32_t | skips = 0 |
||
) |
Constructor
tzer | the tokenizer to use |
hash_bits | the number of bits of the hash. Means a dimension of size 2^(hash_bits). |
normalize | whether to normalize vectors or not |
n_grams | the max number of tokens to consider when combining tokens |
skips | the max number of tokens to skip when combining tokens |
Definition at line 34 of file HashedDocConverter.cpp.
|
virtual |
Destructor
Definition at line 40 of file HashedDocConverter.cpp.
Hashes each string contained in features
features | the strings to be hashed. Must be an instance of CStringFeatures. |
Implements CConverter.
Definition at line 81 of file HashedDocConverter.cpp.
SGSparseVector< float64_t > apply | ( | SGVector< char > | document | ) |
Hashes the tokens contained in document
document | the char vector to tokenize and hash |
the array will contain all the hashes generated from the tokens
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+s-1 tokens
Reading token and storing index to hashed_indices
For remaining combinations
Normalizing vector
Definition at line 101 of file HashedDocConverter.cpp.
|
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.
dict | dictionary of parameters to be built. |
Definition at line 597 of file SGObject.cpp.
|
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.
Definition at line 714 of file SGObject.cpp.
|
protected |
This method takes a dynamic array as an argument, sorts it and returns the number of the distinct elements(indices here) in the array.
hashed_indices | the array to sort and count elements |
Counting nnz features
Definition at line 228 of file HashedDocConverter.cpp.
|
protected |
This method takes the dynamic array containing all the hashed indices of a document and returns a compact sparse representation with each index found and with the count of such index
hashed_indices | the array containing the hashed indices |
Definition at line 184 of file HashedDocConverter.cpp.
|
virtualinherited |
A deep copy. All the instance variables will also be copied.
Definition at line 198 of file SGObject.cpp.
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.
other | object to compare with |
accuracy | accuracy to use for comparison (optional) |
tolerant | allows linient check on float equality (within accuracy) |
Definition at line 618 of file SGObject.cpp.
|
static |
Generates all the k-skip n-grams combinations for the pre-hashed tokens in hashes, starting from hashes[hashes_start] and going up to hashes[1+len] in a circular manner. The generated tokens (maximun (n-1)(k+1)+1) are stored in ngram_hashes. The number of created tokens is returned in case fewer tokens are generated (due to a smaller len than the size of hashes). See class description for more information on k-skip n-grams.
hashes | the hashes of the tokens to combine as k-skip n-grams |
hashes_start | the index in hashes to consider as the starting point |
len | the maximum allowed number of tokens to reach in a circular manner, starting from hashes_start |
ngram_hashes | the vector where to store the generated hashes. Must have been created to be able to store at most (n-1)(k+1)+1 tokens. |
num_bits | the dimension in which to limit the hashed indices (means a dimension of size 2^num_bits) |
ngrams | the n in k-skip n-grams or the max number of tokens to combine |
tokens_to_skip | the k in k-skip n-grams or the max number of tokens to skip when combining |
Definition at line 205 of file HashedDocConverter.cpp.
|
inherited |
|
inherited |
|
inherited |
|
inherited |
Definition at line 498 of file SGObject.cpp.
|
inherited |
Returns description of a given parameter string, if it exists. SG_ERROR otherwise
param_name | name of the parameter |
Definition at line 522 of file SGObject.cpp.
|
inherited |
Returns index of model selection parameter with provided index
param_name | name of model selection parameter |
Definition at line 535 of file SGObject.cpp.
|
virtual |
Reimplemented from CConverter.
Definition at line 76 of file HashedDocConverter.cpp.
|
protected |
init
Definition at line 45 of file HashedDocConverter.cpp.
|
virtualinherited |
If the SGSerializable is a class template then TRUE will be returned and GENERIC is set to the type of the generic.
generic | set to the type of the generic if returning TRUE |
Definition at line 296 of file SGObject.cpp.
|
virtualinherited |
Load this object from file. If it will fail (returning FALSE) then this object will contain inconsistent data and should not be used!
file | where to load from |
prefix | prefix for members |
Definition at line 369 of file SGObject.cpp.
|
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.
ShogunException | will 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.
|
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.
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 421 of file SGObject.cpp.
|
virtualinherited |
Definition at line 262 of file SGObject.cpp.
|
inherited |
prints all parameter registered for model selection and their type
Definition at line 474 of file SGObject.cpp.
|
virtualinherited |
prints registered parameters out
prefix | prefix for members |
Definition at line 308 of file SGObject.cpp.
|
virtualinherited |
Save this object to file.
file | where to save the object; will be closed during returning if PREFIX is an empty string. |
prefix | prefix for members |
Definition at line 314 of file SGObject.cpp.
|
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.
ShogunException | will be thrown if an error occurs. |
Reimplemented in CKernel.
Definition at line 436 of file SGObject.cpp.
|
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.
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 431 of file SGObject.cpp.
|
inherited |
Definition at line 41 of file SGObject.cpp.
|
inherited |
Definition at line 46 of file SGObject.cpp.
|
inherited |
Definition at line 51 of file SGObject.cpp.
|
inherited |
Definition at line 56 of file SGObject.cpp.
|
inherited |
Definition at line 61 of file SGObject.cpp.
|
inherited |
Definition at line 66 of file SGObject.cpp.
|
inherited |
Definition at line 71 of file SGObject.cpp.
|
inherited |
Definition at line 76 of file SGObject.cpp.
|
inherited |
Definition at line 81 of file SGObject.cpp.
|
inherited |
Definition at line 86 of file SGObject.cpp.
|
inherited |
Definition at line 91 of file SGObject.cpp.
|
inherited |
Definition at line 96 of file SGObject.cpp.
|
inherited |
Definition at line 101 of file SGObject.cpp.
|
inherited |
Definition at line 106 of file SGObject.cpp.
|
inherited |
Definition at line 111 of file SGObject.cpp.
|
inherited |
set generic type to T
|
inherited |
|
inherited |
set the parallel object
parallel | parallel object to use |
Definition at line 241 of file SGObject.cpp.
|
inherited |
set the version object
version | version object to use |
Definition at line 283 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.
k | the max number of allowed skips |
n | the max number of tokens to combine |
Definition at line 251 of file HashedDocConverter.cpp.
void set_normalization | ( | bool | normalize | ) |
specify whether hashed vector should be normalized or not
normalize | whether to normalize |
Definition at line 246 of file HashedDocConverter.cpp.
|
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.
|
inherited |
unset generic type
this has to be called in classes specializing a template class
Definition at line 303 of file SGObject.cpp.
|
virtualinherited |
Updates the hash of current parameter combination
Definition at line 248 of file SGObject.cpp.
|
inherited |
io
Definition at line 369 of file SGObject.h.
|
inherited |
parameters wrt which we can compute gradients
Definition at line 384 of file SGObject.h.
|
inherited |
Hash of parameter values
Definition at line 387 of file SGObject.h.
|
inherited |
model selection parameters
Definition at line 381 of file SGObject.h.
|
inherited |
parameters
Definition at line 378 of file SGObject.h.
|
protected |
the number of consecutives tokens for quadratic
Definition at line 154 of file HashedDocConverter.h.
|
protected |
the number of bits of the hash
Definition at line 145 of file HashedDocConverter.h.
|
inherited |
parallel
Definition at line 372 of file SGObject.h.
|
protected |
whether to normalize or not
Definition at line 151 of file HashedDocConverter.h.
|
protected |
the tokenizer
Definition at line 148 of file HashedDocConverter.h.
|
protected |
the number of tokens to skip
Definition at line 157 of file HashedDocConverter.h.
|
inherited |
version
Definition at line 375 of file SGObject.h.