SHOGUN
4.1.0
|
Template class SparseFeatures implements sparse matrices.
Features are an array of SGSparseVector. Within each vector feat_index are sorted (increasing).
Sparse feature vectors can be accessed via get_sparse_feature_vector() and should be freed (this operation is a NOP in most cases) via free_sparse_feature_vector().
As this is a template class it can directly be used for different data types like sparse matrices of real valued, integer, byte etc type.
(Partly) subset access is supported for this feature type. Simple use the (inherited) add_subset(), remove_subset() functions. If done, all calls that work with features are translated to the subset. See comments to find out whether it is supported for that method. See also CFeatures class documentation
Definition at line 26 of file HashedDocConverter.h.
Public Member Functions | |
CSparseFeatures (int32_t size=0) | |
CSparseFeatures (SGSparseMatrix< ST > sparse) | |
CSparseFeatures (SGMatrix< ST > dense) | |
CSparseFeatures (const CSparseFeatures &orig) | |
CSparseFeatures (CFile *loader) | |
virtual | ~CSparseFeatures () |
void | free_sparse_feature_matrix () |
void | free_sparse_features () |
virtual CFeatures * | duplicate () const |
ST | get_feature (int32_t num, int32_t index) |
SGVector< ST > | get_full_feature_vector (int32_t num) |
virtual int32_t | get_nnz_features_for_vector (int32_t num) |
SGSparseVector< ST > | get_sparse_feature_vector (int32_t num) |
ST | dense_dot (ST alpha, int32_t num, ST *vec, int32_t dim, ST b) |
void | add_to_dense_vec (float64_t alpha, int32_t num, float64_t *vec, int32_t dim, bool abs_val=false) |
void | free_sparse_feature_vector (int32_t num) |
SGSparseVector< ST > * | get_sparse_feature_matrix (int32_t &num_feat, int32_t &num_vec) |
SGSparseMatrix< ST > | get_sparse_feature_matrix () |
CSparseFeatures< ST > * | get_transposed () |
SGSparseVector< ST > * | get_transposed (int32_t &num_feat, int32_t &num_vec) |
void | set_sparse_feature_matrix (SGSparseMatrix< ST > sm) |
SGMatrix< ST > | get_full_feature_matrix () |
virtual void | set_full_feature_matrix (SGMatrix< ST > full) |
virtual bool | apply_preprocessor (bool force_preprocessing=false) |
void | obtain_from_simple (CDenseFeatures< ST > *sf) |
virtual int32_t | get_num_vectors () const |
int32_t | get_num_features () const |
int32_t | set_num_features (int32_t num) |
virtual EFeatureClass | get_feature_class () const |
virtual EFeatureType | get_feature_type () const |
void | free_feature_vector (int32_t num) |
int64_t | get_num_nonzero_entries () |
float64_t * | compute_squared (float64_t *sq) |
float64_t | compute_squared_norm (CSparseFeatures< float64_t > *lhs, float64_t *sq_lhs, int32_t idx_a, CSparseFeatures< float64_t > *rhs, float64_t *sq_rhs, int32_t idx_b) |
void | load (CFile *loader) |
SGVector< float64_t > | load_with_labels (CLibSVMFile *loader) |
void | save (CFile *writer) |
void | save_with_labels (CLibSVMFile *writer, SGVector< float64_t > labels) |
void | sort_features () |
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 * | 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 CFeatures * | copy_subset (SGVector< index_t > indices) |
virtual const char * | get_name () const |
template<> | |
void | add_to_dense_vec (float64_t alpha, int32_t num, float64_t *vec, int32_t dim, bool abs_val) |
template<> | |
void | obtain_from_simple (CDenseFeatures< complex128_t > *sf) |
template<> | |
float64_t * | compute_squared (float64_t *sq) |
template<> | |
float64_t | dot (int32_t vec_idx1, CDotFeatures *df, int32_t vec_idx2) |
template<> | |
float64_t | dense_dot (int32_t vec_idx1, const float64_t *vec2, int32_t vec2_len) |
template<> | |
bool | get_next_feature (int32_t &index, float64_t &value, void *iterator) |
virtual float64_t | dense_dot_sgvec (int32_t vec_idx1, const SGVector< float64_t > vec2) |
virtual void | dense_dot_range (float64_t *output, int32_t start, int32_t stop, float64_t *alphas, float64_t *vec, int32_t dim, float64_t b) |
virtual void | dense_dot_range_subset (int32_t *sub_index, int32_t num, float64_t *output, float64_t *alphas, float64_t *vec, int32_t dim, float64_t b) |
float64_t | get_combined_feature_weight () |
void | set_combined_feature_weight (float64_t nw) |
SGMatrix< float64_t > | get_computed_dot_feature_matrix () |
SGVector< float64_t > | get_computed_dot_feature_vector (int32_t num) |
void | benchmark_add_to_dense_vector (int32_t repeats=5) |
void | benchmark_dense_dot_range (int32_t repeats=5) |
virtual SGVector< float64_t > | get_mean () |
virtual SGMatrix< float64_t > | get_cov () |
virtual void | add_preprocessor (CPreprocessor *p) |
virtual void | del_preprocessor (int32_t num) |
CPreprocessor * | get_preprocessor (int32_t num) const |
void | set_preprocessed (int32_t num) |
bool | is_preprocessed (int32_t num) const |
int32_t | get_num_preprocessed () const |
int32_t | get_num_preprocessors () const |
void | clean_preprocessors () |
void | list_preprocessors () |
int32_t | get_cache_size () const |
virtual bool | reshape (int32_t num_features, int32_t num_vectors) |
void | list_feature_obj () const |
bool | check_feature_compatibility (CFeatures *f) const |
bool | has_property (EFeatureProperty p) const |
void | set_property (EFeatureProperty p) |
void | unset_property (EFeatureProperty p) |
virtual CFeatures * | create_merged_copy (CList *others) |
virtual CFeatures * | create_merged_copy (CFeatures *other) |
virtual void | add_subset (SGVector< index_t > subset) |
virtual void | add_subset_in_place (SGVector< index_t > subset) |
virtual void | remove_subset () |
virtual void | remove_all_subsets () |
virtual CSubsetStack * | get_subset_stack () |
virtual void | subset_changed_post () |
virtual CFeatures * | copy_dimension_subset (SGVector< index_t > dims) |
virtual bool | support_compatible_class () const |
virtual bool | get_feature_class_compatibility (EFeatureClass rhs) const |
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 void * | dense_dot_range_helper (void *p) |
static SGVector< float64_t > | get_mean (CDotFeatures *lhs, CDotFeatures *rhs) |
static SGMatrix< float64_t > | compute_cov (CDotFeatures *lhs, CDotFeatures *rhs) |
Public Attributes | |
SGIO * | io |
Parallel * | parallel |
Version * | version |
Parameter * | m_parameters |
Parameter * | m_model_selection_parameters |
Parameter * | m_gradient_parameters |
uint32_t | m_hash |
Protected Member Functions | |
virtual SGSparseVectorEntry< ST > * | compute_sparse_feature_vector (int32_t num, int32_t &len, SGSparseVectorEntry< ST > *target=NULL) |
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 | |
SGSparseMatrix< ST > | sparse_feature_matrix |
array of sparse vectors of size num_vectors More... | |
CCache< SGSparseVectorEntry < ST > > * | feature_cache |
float64_t | combined_weight |
feature weighting in combined dot features More... | |
CSubsetStack * | m_subset_stack |
CSparseFeatures | ( | int32_t | size = 0 | ) |
CSparseFeatures | ( | SGSparseMatrix< ST > | sparse | ) |
convenience constructor that creates sparse features from sparse features
sparse | sparse matrix |
Definition at line 22 of file SparseFeatures.cpp.
CSparseFeatures | ( | SGMatrix< ST > | dense | ) |
convenience constructor that creates sparse features from dense features
dense | dense feature matrix |
Definition at line 30 of file SparseFeatures.cpp.
CSparseFeatures | ( | const CSparseFeatures< ST > & | orig | ) |
copy constructor
Definition at line 38 of file SparseFeatures.cpp.
CSparseFeatures | ( | CFile * | loader | ) |
constructor loading features from file
loader | File object to load data from |
Definition at line 47 of file SparseFeatures.cpp.
|
virtual |
default destructor
Definition at line 55 of file SparseFeatures.cpp.
|
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
subset | subset of indices to add |
Reimplemented in CCombinedFeatures.
Definition at line 310 of file Features.cpp.
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
subset | subset of indices to replace the latest one with. |
Definition at line 316 of file Features.cpp.
|
virtual |
add a sparse feature vector onto a dense one dense+=alpha*sparse
possible with subset
alpha | scalar to multiply with |
num | index of feature vector |
vec | dense vector |
dim | length of the dense vector |
abs_val | if true, do dense+=alpha*abs(sparse) |
Implements CDotFeatures.
Definition at line 164 of file SparseFeatures.cpp.
|
virtual |
add vector 1 multiplied with alpha to dense vector2
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 198 of file SparseFeatures.cpp.
|
virtual |
apply preprocessor
possible with subset
force_preprocessing | if preprocssing shall be forced |
Definition at line 287 of file SparseFeatures.cpp.
|
inherited |
run benchmark for add_to_dense_vec
Definition at line 318 of file DotFeatures.cpp.
|
inherited |
run benchmark for dense_dot_range
Definition at line 341 of file DotFeatures.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.
|
inherited |
check feature compatibility
f | features to check for compatibility |
Definition at line 283 of file Features.cpp.
|
inherited |
clears all preprocs
Definition at line 116 of file Features.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.
|
staticinherited |
compute the covariance of two CDotFeatures together
Definition at line 469 of file DotFeatures.cpp.
|
protectedvirtual |
compute feature vector for sample num if target is set the vector is written to target len is returned by reference
NOT IMPLEMENTED!
num | num |
len | len |
target | target |
Definition at line 594 of file SparseFeatures.cpp.
compute a^2 on all feature vectors
possible with subset
sq | the square for each vector is stored in here |
Definition at line 372 of file SparseFeatures.cpp.
Definition at line 391 of file SparseFeatures.cpp.
float64_t compute_squared_norm | ( | CSparseFeatures< float64_t > * | lhs, |
float64_t * | sq_lhs, | ||
int32_t | idx_a, | ||
CSparseFeatures< float64_t > * | rhs, | ||
float64_t * | sq_rhs, | ||
int32_t | idx_b | ||
) |
compute (a-b)^2 (== a^2+b^2-2ab) usually called by kernels'/distances' compute functions works on two feature vectors, although it is a member of a single feature: can either be called by lhs or rhs.
possible wiht subsets on lhs or rhs
lhs | left-hand side features |
sq_lhs | squared values of left-hand side |
idx_a | index of left-hand side's vector to compute |
rhs | right-hand side features |
sq_rhs | squared values of right-hand side |
idx_b | index of right-hand side's vector to compute |
Definition at line 397 of file SparseFeatures.cpp.
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!
dims | indices of feature dimensions to copy |
Reimplemented in CDenseFeatures< ST >, CDenseFeatures< uint32_t >, CDenseFeatures< float64_t >, CDenseFeatures< T >, and CDenseFeatures< uint16_t >.
Definition at line 348 of file Features.cpp.
Creates a new CFeatures instance containing copies of the elements which are specified by the provided indices.
indices | indices of feature elements to copy |
Reimplemented from CFeatures.
Definition at line 572 of file SparseFeatures.cpp.
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!
others | list of feature objects to append |
Reimplemented in CDenseFeatures< ST >, CDenseFeatures< uint32_t >, CDenseFeatures< float64_t >, CDenseFeatures< T >, and CDenseFeatures< uint16_t >.
Definition at line 235 of file Features.h.
Convenience method for method with same name and list as parameter.
NOT IMPLEMENTED!
other | feature object to append |
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.
|
virtualinherited |
A deep copy. All the instance variables will also be copied.
Definition at line 198 of file SGObject.cpp.
|
virtualinherited |
delete preprocessor from list
num | index of preprocessor in list |
Definition at line 122 of file Features.cpp.
ST dense_dot | ( | ST | alpha, |
int32_t | num, | ||
ST * | vec, | ||
int32_t | dim, | ||
ST | b | ||
) |
compute the dot product between dense weights and a sparse feature vector alpha * sparse^T * w + b
possible with subset
alpha | scalar to multiply with |
num | index of feature vector |
vec | dense vector to compute dot product with |
dim | length of the dense vector |
b | bias |
Definition at line 156 of file SparseFeatures.cpp.
compute dot product between vector1 and a dense vector
possible with subset
vec_idx1 | index of first vector |
vec2 | pointer to real valued vector |
vec2_len | length of real valued vector |
Implements CDotFeatures.
Definition at line 487 of file SparseFeatures.cpp.
compute dot product between vector1 and a dense vector
vec_idx1 | index of first vector |
vec2 | pointer to real valued vector |
vec2_len | length of real valued vector |
Implements CDotFeatures.
Definition at line 517 of file SparseFeatures.cpp.
|
virtualinherited |
Compute the dot product for a range of vectors. This function makes use of dense_dot alphas[i] * sparse[i]^T * w + b
output | result for the given vector range |
start | start vector range from this idx |
stop | stop vector range at this idx |
alphas | scalars to multiply with, may be NULL |
vec | dense vector to compute dot product with |
dim | length of the dense vector |
b | bias |
note that the result will be written to output[0...(stop-start-1)]
Reimplemented in CCombinedDotFeatures, and CHashedWDFeaturesTransposed.
Definition at line 67 of file DotFeatures.cpp.
|
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.
|
virtualinherited |
Compute the dot product for a subset of vectors. This function makes use of dense_dot alphas[i] * sparse[i]^T * w + b
sub_index | index for which to compute outputs |
num | length of index |
output | result for the given vector range |
alphas | scalars to multiply with, may be NULL |
vec | dense vector to compute dot product with |
dim | length of the dense vector |
b | bias |
Reimplemented in CCombinedDotFeatures, and CHashedWDFeaturesTransposed.
Definition at line 153 of file DotFeatures.cpp.
compute dot product between vector1 and a dense vector
vec_idx1 | index of first vector |
vec2 | dense vector |
Reimplemented in CHashedDocDotFeatures.
Definition at line 62 of file DotFeatures.cpp.
|
protectedinherited |
display progress output
start | minimum value |
stop | maximum value |
v | current value |
Definition at line 528 of file DotFeatures.cpp.
|
virtual |
compute dot product between vector1 and vector2, appointed by their indices
possible with subset of this instance and of DotFeatures
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 462 of file SparseFeatures.cpp.
|
virtual |
compute dot product between vector1 and vector2, appointed by their indices
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 480 of file SparseFeatures.cpp.
|
virtual |
duplicate feature object
Implements CFeatures.
Definition at line 60 of file SparseFeatures.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.
|
virtual |
clean up iterator call this function with the iterator returned by get_first_feature
iterator | as returned by get_first_feature |
Implements CDotFeatures.
Definition at line 564 of file SparseFeatures.cpp.
void free_feature_vector | ( | int32_t | num | ) |
free feature vector
possible with subset
num | index of vector in cache |
Definition at line 354 of file SparseFeatures.cpp.
void free_sparse_feature_matrix | ( | ) |
void free_sparse_feature_vector | ( | int32_t | num | ) |
free sparse feature vector
possible with subset
num | index of this vector in the cache |
Definition at line 204 of file SparseFeatures.cpp.
void free_sparse_features | ( | ) |
free sparse feature matrix and cache
any subset is removed
Definition at line 269 of file SparseFeatures.cpp.
|
inherited |
|
inherited |
get combined feature weight
Definition at line 154 of file DotFeatures.h.
compute the feature matrix in feature space
Definition at line 284 of file DotFeatures.cpp.
compute the feature vector in feature space
Definition at line 305 of file DotFeatures.cpp.
|
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())
Implements CDotFeatures.
Definition at line 457 of file SparseFeatures.cpp.
ST get_feature | ( | int32_t | num, |
int32_t | index | ||
) |
get a single feature
possible with subset
num | number of feature vector to retrieve |
index | index of feature in this vector |
Definition at line 65 of file SparseFeatures.cpp.
|
virtual |
get feature class
Implements CFeatures.
Definition at line 349 of file SparseFeatures.cpp.
|
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
rhs | the class in right hand side |
Reimplemented in CDenseSubSamplesFeatures< ST >.
Definition at line 355 of file Features.cpp.
|
virtual |
iterate over the non-zero features
call get_feature_iterator first, followed by get_next_feature and free_feature_iterator to cleanup
possible with subset
vector_index | the index of the vector over whose components to iterate over |
Implements CDotFeatures.
Definition at line 524 of file SparseFeatures.cpp.
|
virtual |
SGMatrix< ST > get_full_feature_matrix | ( | ) |
gets a copy of a full feature matrix
possible with subset
Definition at line 244 of file SparseFeatures.cpp.
SGVector< ST > get_full_feature_vector | ( | int32_t | num | ) |
get the fully expanded dense feature vector num
num | index of feature vector |
Definition at line 78 of file SparseFeatures.cpp.
|
inherited |
|
inherited |
|
inherited |
|
staticinherited |
get mean of two CDotFeature objects
Definition at line 402 of file DotFeatures.cpp.
|
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 |
|
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
index | is returned by reference (-1 when not available) |
value | is returned by reference |
iterator | as returned by get_first_feature |
Implements CDotFeatures.
Definition at line 543 of file SparseFeatures.cpp.
|
virtual |
iterate over the non-zero features
call this function with the iterator returned by get_feature_iterator and call free_feature_iterator to cleanup
index | is returned by reference (-1 when not available) |
value | is returned by reference |
iterator | as returned by get_feature_iterator |
Implements CDotFeatures.
Definition at line 557 of file SparseFeatures.cpp.
|
virtual |
get number of non-zero features in vector
num | which vector |
Implements CDotFeatures.
Definition at line 86 of file SparseFeatures.cpp.
int32_t get_num_features | ( | ) | const |
int64_t get_num_nonzero_entries | ( | ) |
get number of non-zero entries in sparse feature matrix
Definition at line 362 of file SparseFeatures.cpp.
|
inherited |
get the number of applied preprocs
Definition at line 103 of file Features.cpp.
|
inherited |
get number of preprocessors
Definition at line 155 of file Features.cpp.
|
virtual |
get number of feature vectors, possibly of subset
Implements CFeatures.
Definition at line 331 of file SparseFeatures.cpp.
|
inherited |
get specified preprocessor
num | index of preprocessor in list |
Definition at line 93 of file Features.cpp.
SGSparseVector<ST>* get_sparse_feature_matrix | ( | int32_t & | num_feat, |
int32_t & | num_vec | ||
) |
get the pointer to the sparse feature matrix num_feat,num_vectors are returned by reference
not possible with subset
num_feat | number of features in matrix |
num_vec | number of vectors in matrix |
SGSparseMatrix< ST > get_sparse_feature_matrix | ( | ) |
get the sparse feature matrix
not possible with subset
Definition at line 212 of file SparseFeatures.cpp.
SGSparseVector< ST > get_sparse_feature_vector | ( | int32_t | num | ) |
get sparse feature vector for sample num from the matrix as it is if matrix is initialized, else return preprocessed compute_feature_vector
possible with subset
num | index of feature vector |
Definition at line 94 of file SparseFeatures.cpp.
|
virtualinherited |
CSparseFeatures< ST > * get_transposed | ( | ) |
get a transposed copy of the features
not possible with subset
Definition at line 220 of file SparseFeatures.cpp.
SGSparseVector<ST>* get_transposed | ( | int32_t & | num_feat, |
int32_t & | num_vec | ||
) |
compute and return the transpose of the sparse feature matrix which will be prepocessed. num_feat, num_vectors are returned by reference caller has to clean up
possible with subset
num_feat | number of features in matrix |
num_vec | number of vectors in matrix |
|
inherited |
check if features have given property
p | feature property |
Definition at line 295 of file Features.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.
|
inherited |
get whether specified preprocessor was already applied
num | index of preprocessor in list |
Definition at line 149 of file Features.cpp.
|
inherited |
list feature object
Definition at line 171 of file Features.cpp.
|
inherited |
print preprocessors
Definition at line 131 of file Features.cpp.
|
virtual |
load features from file
any subset is removed before
loader | File object to load data from |
Reimplemented from CFeatures.
Definition at line 640 of file SparseFeatures.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.
SGVector< float64_t > load_with_labels | ( | CLibSVMFile * | loader | ) |
load features from file
any subset is removed before
loader | File object to load data from |
Definition at line 648 of file SparseFeatures.cpp.
void obtain_from_simple | ( | CDenseFeatures< ST > * | sf | ) |
obtain sparse features from simple features
subset on input is ignored, subset of this instance is removed
sf | simple features |
Definition at line 319 of file SparseFeatures.cpp.
void obtain_from_simple | ( | CDenseFeatures< complex128_t > * | sf | ) |
Definition at line 326 of file SparseFeatures.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 |
removes all subsets Calls subset_changed_post() afterwards
Reimplemented in CCombinedFeatures.
Definition at line 328 of file Features.cpp.
|
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.
|
virtualinherited |
in case there is a feature matrix allow for reshaping
NOT IMPLEMENTED!
num_features | new number of features |
num_vectors | new number of vectors |
Reimplemented in CDenseFeatures< ST >, CDenseFeatures< uint32_t >, CDenseFeatures< float64_t >, CDenseFeatures< T >, and CDenseFeatures< uint16_t >.
Definition at line 165 of file Features.cpp.
|
virtual |
save features to file
not possible with subset
writer | File object to write data to |
Reimplemented from CFeatures.
Definition at line 656 of file SparseFeatures.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.
void save_with_labels | ( | CLibSVMFile * | writer, |
SGVector< float64_t > | labels | ||
) |
save features to file
not possible with subset
writer | File object to write data to |
labels | vector with labels to write out |
Definition at line 664 of file SparseFeatures.cpp.
|
inherited |
set combined kernel weight
nw | new combined feature weight |
Definition at line 160 of file DotFeatures.h.
|
virtual |
creates a sparse feature matrix from a full dense feature matrix necessary to set feature_matrix, num_features and num_vectors where num_features is the column offset, and columns are linear in memory see above for definition of sparse_feature_matrix
any subset is removed before
full | full feature matrix |
Definition at line 280 of file SparseFeatures.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.
int32_t set_num_features | ( | int32_t | num | ) |
set number of features
Sometimes when loading sparse features not all possible dimensions are used. This may pose a problem to classifiers when being applied to higher dimensional test-data. This function allows to artificially explode the feature space
num | the number of features, must be larger than the current number of features |
Definition at line 341 of file SparseFeatures.cpp.
|
inherited |
set applied flag for preprocessor
num | index of preprocessor in list |
Definition at line 143 of file Features.cpp.
|
inherited |
void set_sparse_feature_matrix | ( | SGSparseMatrix< ST > | sm | ) |
set sparse feature matrix
not possible with subset
sm | sparse feature matrix |
Definition at line 228 of file SparseFeatures.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.
void sort_features | ( | ) |
ensure that features occur in ascending order, only call when no preprocessors are attached
not possiblwe with subset
Definition at line 603 of file SparseFeatures.cpp.
|
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.
|
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?
Reimplemented in CDenseSubSamplesFeatures< ST >.
Definition at line 323 of file Features.h.
|
inherited |
unset generic type
this has to be called in classes specializing a template class
Definition at line 303 of file SGObject.cpp.
|
inherited |
|
virtualinherited |
Updates the hash of current parameter combination
Definition at line 248 of file SGObject.cpp.
|
protectedinherited |
feature weighting in combined dot features
Definition at line 249 of file DotFeatures.h.
|
protected |
feature cache
Definition at line 503 of file SparseFeatures.h.
|
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.
|
protectedinherited |
subset used for index transformations
Definition at line 352 of file Features.h.
|
inherited |
parallel
Definition at line 372 of file SGObject.h.
|
protected |
array of sparse vectors of size num_vectors
Definition at line 500 of file SparseFeatures.h.
|
inherited |
version
Definition at line 375 of file SGObject.h.