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 56 of file SparseFeatures.h.
Public Member Functions | |
| CSparseFeatures (int32_t size=0) | |
| CSparseFeatures (SGSparseVector< ST > *src, int32_t num_feat, int32_t num_vec, bool copy=false) | |
| 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) |
| ST * | get_full_feature_vector (int32_t num, int32_t &len) |
| 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 bool | set_full_feature_matrix (SGMatrix< ST > full) |
| virtual bool | apply_preprocessor (bool force_preprocessing=false) |
| virtual int32_t | get_size () const |
| bool | obtain_from_simple (CDenseFeatures< ST > *sf) |
| virtual int32_t | get_num_vectors () const |
| int32_t | get_num_features () |
| 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) |
| void | save (CFile *writer) |
| CRegressionLabels * | load_svmlight_file (char *fname, bool do_sort_features=true) |
| void | sort_features () |
| bool | write_svmlight_file (char *fname, CRegressionLabels *label) |
| 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 |
| 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 int32_t | add_preprocessor (CPreprocessor *p) |
| set preprocessor | |
| virtual CPreprocessor * | del_preprocessor (int32_t num) |
| del current preprocessor | |
| CPreprocessor * | get_preprocessor (int32_t num) const |
| get current preprocessor | |
| void | set_preprocessed (int32_t num) |
| bool | is_preprocessed (int32_t num) const |
| int32_t | get_num_preprocessed () const |
| get whether specified preprocessor (or all if num=1) was/were already applied | |
| int32_t | get_num_preprocessors () const |
| void | clean_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 (CFeatures *other) |
| virtual void | add_subset (SGVector< index_t > subset) |
| virtual void | remove_subset () |
| virtual void | remove_all_subsets () |
| virtual CSubsetStack * | get_subset_stack () |
| virtual void | subset_changed_post () |
| virtual CSGObject * | shallow_copy () const |
| virtual CSGObject * | deep_copy () const |
| virtual bool | is_generic (EPrimitiveType *generic) const |
| template<class T > | |
| void | set_generic () |
| void | unset_generic () |
| virtual void | print_serializable (const char *prefix="") |
| virtual bool | save_serializable (CSerializableFile *file, const char *prefix="", int32_t param_version=VERSION_PARAMETER) |
| virtual bool | load_serializable (CSerializableFile *file, const char *prefix="", int32_t param_version=VERSION_PARAMETER) |
| DynArray< TParameter * > * | load_file_parameters (const SGParamInfo *param_info, int32_t file_version, CSerializableFile *file, const char *prefix="") |
| DynArray< TParameter * > * | load_all_file_parameters (int32_t file_version, int32_t current_version, CSerializableFile *file, const char *prefix="") |
| void | map_parameters (DynArray< TParameter * > *param_base, int32_t &base_version, DynArray< const SGParamInfo * > *target_param_infos) |
| 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_parameter_dictionary (CMap< TParameter *, CSGObject * > &dict) |
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 |
| ParameterMap * | m_parameter_map |
| 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 TParameter * | migrate (DynArray< TParameter * > *param_base, const SGParamInfo *target) |
| virtual void | one_to_one_migration_prepare (DynArray< TParameter * > *param_base, const SGParamInfo *target, TParameter *&replacement, TParameter *&to_migrate, char *old_name=NULL) |
| 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) |
| virtual bool | update_parameter_hash () |
Protected Attributes | |
| int32_t | num_vectors |
| total number of vectors | |
| int32_t | num_features |
| total number of features | |
| SGSparseVector< ST > * | sparse_feature_matrix |
| array of sparse vectors of size num_vectors | |
| CCache< SGSparseVectorEntry < ST > > * | feature_cache |
| float64_t | combined_weight |
| feature weighting in combined dot features | |
| CSubsetStack * | m_subset_stack |
| CSparseFeatures | ( | int32_t | size = 0 |
) |
| CSparseFeatures | ( | SGSparseVector< ST > * | src, | |
| int32_t | num_feat, | |||
| int32_t | num_vec, | |||
| bool | copy = false | |||
| ) |
convenience constructor that creates sparse features from the ones passed as argument
| src | dense feature matrix | |
| num_feat | number of features | |
| num_vec | number of vectors | |
| copy | true to copy feature matrix |
Definition at line 21 of file SparseFeatures.cpp.
| CSparseFeatures | ( | SGSparseMatrix< ST > | sparse | ) |
convenience constructor that creates sparse features from sparse features
| sparse | sparse matrix |
Definition at line 37 of file SparseFeatures.cpp.
| CSparseFeatures | ( | SGMatrix< ST > | dense | ) |
convenience constructor that creates sparse features from dense features
| dense | dense feature matrix |
Definition at line 46 of file SparseFeatures.cpp.
| CSparseFeatures | ( | const CSparseFeatures< ST > & | orig | ) |
copy constructor
Definition at line 55 of file SparseFeatures.cpp.
| CSparseFeatures | ( | CFile * | loader | ) |
constructor loading features from file
| loader | File object to load data from |
Definition at line 77 of file SparseFeatures.cpp.
| ~CSparseFeatures | ( | ) | [virtual] |
default destructor
Definition at line 86 of file SparseFeatures.cpp.
| int32_t add_preprocessor | ( | CPreprocessor * | p | ) | [virtual, inherited] |
set preprocessor
add preprocessor
| p | preprocessor to set |
Definition at line 81 of file Features.cpp.
adds a subset of indices on top of the current subsets (possibly subset o subset. Calls subset_changed_post() afterwards
| subset | subset of indices to add |
Reimplemented in CCombinedFeatures.
Definition at line 351 of file Features.cpp.
| void add_to_dense_vec | ( | float64_t | alpha, | |
| int32_t | num, | |||
| float64_t * | vec, | |||
| int32_t | dim, | |||
| bool | abs_val = false | |||
| ) | [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 270 of file SparseFeatures.cpp.
| bool apply_preprocessor | ( | bool | force_preprocessing = false |
) | [virtual] |
apply preprocessor
possible with subset
| force_preprocessing | if preprocssing shall be forced |
Definition at line 503 of file SparseFeatures.cpp.
| void benchmark_add_to_dense_vector | ( | int32_t | repeats = 5 |
) | [inherited] |
run benchmark for add_to_dense_vec
Definition at line 318 of file DotFeatures.cpp.
| void benchmark_dense_dot_range | ( | int32_t | repeats = 5 |
) | [inherited] |
run benchmark for dense_dot_range
Definition at line 341 of file DotFeatures.cpp.
| void build_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.
| dict | dictionary of parameters to be built. |
Definition at line 1201 of file SGObject.cpp.
| bool check_feature_compatibility | ( | CFeatures * | f | ) | const [inherited] |
check feature compatibility
| f | features to check for compatibility |
Definition at line 326 of file Features.cpp.
| void clean_preprocessors | ( | ) | [inherited] |
clears all preprocs
Definition at line 137 of file Features.cpp.
| SGMatrix< float64_t > compute_cov | ( | CDotFeatures * | lhs, | |
| CDotFeatures * | rhs | |||
| ) | [static, inherited] |
compute the covariance of two CDotFeatures together
Definition at line 469 of file DotFeatures.cpp.
| SGSparseVectorEntry< ST > * compute_sparse_feature_vector | ( | int32_t | num, | |
| int32_t & | len, | |||
| SGSparseVectorEntry< ST > * | target = NULL | |||
| ) | [protected, virtual] |
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 1021 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 583 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 602 of file SparseFeatures.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 998 of file SparseFeatures.cpp.
Takes another feature instance and returns a new instance which is a concatenation of a copy if this instace's data and the given instance's data. Note that the feature types have to be equal.
NOT IMPLEMENTED!
| other | feature object to append |
Reimplemented in CCombinedFeatures, CDenseFeatures< ST >, CDenseFeatures< uint32_t >, CDenseFeatures< float64_t >, CDenseFeatures< T >, and CDenseFeatures< uint16_t >.
Definition at line 234 of file Features.h.
| virtual CSGObject* deep_copy | ( | ) | const [virtual, inherited] |
A deep copy. All the instance variables will also be copied.
Definition at line 131 of file SGObject.h.
| CPreprocessor * del_preprocessor | ( | int32_t | num | ) | [virtual, inherited] |
del current preprocessor
delete preprocessor from list caller has to clean up returned preproc
| num | index of preprocessor in list |
Definition at line 143 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 249 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 932 of file SparseFeatures.cpp.
| void dense_dot_range | ( | float64_t * | output, | |
| int32_t | start, | |||
| int32_t | stop, | |||
| float64_t * | alphas, | |||
| float64_t * | vec, | |||
| int32_t | dim, | |||
| float64_t | b | |||
| ) | [virtual, inherited] |
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.
| void * dense_dot_range_helper | ( | void * | p | ) | [static, inherited] |
Compute the dot product for a range of vectors. This function is called by the threads created in dense_dot_range
Reimplemented in CHashedWDFeaturesTransposed.
Definition at line 231 of file DotFeatures.cpp.
| void dense_dot_range_subset | ( | int32_t * | sub_index, | |
| int32_t | num, | |||
| float64_t * | output, | |||
| float64_t * | alphas, | |||
| float64_t * | vec, | |||
| int32_t | dim, | |||
| float64_t | b | |||
| ) | [virtual, inherited] |
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.
| float64_t dense_dot_sgvec | ( | int32_t | vec_idx1, | |
| const SGVector< float64_t > | vec2 | |||
| ) | [virtual, inherited] |
compute dot product between vector1 and a dense vector
| vec_idx1 | index of first vector | |
| vec2 | dense vector |
Definition at line 62 of file DotFeatures.cpp.
| void display_progress | ( | int32_t | start, | |
| int32_t | stop, | |||
| int32_t | v | |||
| ) | [protected, inherited] |
display progress output
| start | minimum value | |
| stop | maximum value | |
| v | current value |
Definition at line 528 of file DotFeatures.cpp.
| float64_t dot | ( | int32_t | vec_idx1, | |
| CDotFeatures * | df, | |||
| int32_t | vec_idx2 | |||
| ) | [virtual] |
compute dot product between vector1 and vector2, appointed by their indices
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 915 of file SparseFeatures.cpp.
| CFeatures * duplicate | ( | ) | const [virtual] |
duplicate feature object
Implements CFeatures.
Definition at line 106 of file SparseFeatures.cpp.
| void free_feature_iterator | ( | void * | iterator | ) | [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 988 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 565 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 304 of file SparseFeatures.cpp.
| void free_sparse_features | ( | ) |
free sparse feature matrix and cache
any subset is removed
Definition at line 100 of file SparseFeatures.cpp.
| int32_t get_cache_size | ( | ) | const [inherited] |
| float64_t get_combined_feature_weight | ( | ) | [inherited] |
get combined feature weight
Definition at line 151 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.
| 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())
Implements CDotFeatures.
Definition at line 910 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 111 of file SparseFeatures.cpp.
| EFeatureClass get_feature_class | ( | ) | const [virtual] |
get feature class
Implements CFeatures.
Definition at line 560 of file SparseFeatures.cpp.
| void * get_feature_iterator | ( | int32_t | vector_index | ) | [virtual] |
iterate over the non-zero features
call get_feature_iterator first, followed by get_next_feature and free_feature_iterator to cleanup
possible with subset
| vector_index | the index of the vector over whose components to iterate over |
Implements CDotFeatures.
Definition at line 955 of file SparseFeatures.cpp.
| virtual EFeatureType get_feature_type | ( | ) | const [virtual] |
| SGMatrix< ST > get_full_feature_matrix | ( | ) |
gets a copy of a full feature matrix
possible with subset
Definition at line 403 of file SparseFeatures.cpp.
| ST * get_full_feature_vector | ( | int32_t | num, | |
| int32_t & | len | |||
| ) |
converts a sparse feature vector into a dense one preprocessed compute_feature_vector caller cleans up
| num | index of feature vector | |
| len | length is returned by reference |
Definition at line 132 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 156 of file SparseFeatures.cpp.
| SGIO * get_global_io | ( | ) | [inherited] |
| Parallel * get_global_parallel | ( | ) | [inherited] |
| Version * get_global_version | ( | ) | [inherited] |
| SGVector< float64_t > get_mean | ( | CDotFeatures * | lhs, | |
| CDotFeatures * | rhs | |||
| ) | [static, inherited] |
get mean of two CDotFeature objects
Definition at line 402 of file DotFeatures.cpp.
| SGStringList< char > get_modelsel_names | ( | ) | [inherited] |
Definition at line 1108 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
| param_name | name of the parameter |
Definition at line 1132 of file SGObject.cpp.
| index_t get_modsel_param_index | ( | const char * | param_name | ) | [inherited] |
Returns index of model selection parameter with provided index
| param_name | name of model selection parameter |
Definition at line 1145 of file SGObject.cpp.
| virtual const char* get_name | ( | ) | const [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
| 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 974 of file SparseFeatures.cpp.
| int32_t get_nnz_features_for_vector | ( | int32_t | num | ) | [virtual] |
get number of non-zero features in vector
| num | which vector |
Implements CDotFeatures.
Definition at line 182 of file SparseFeatures.cpp.
| int32_t get_num_features | ( | ) |
get number of features
Definition at line 547 of file SparseFeatures.cpp.
| int64_t get_num_nonzero_entries | ( | ) |
get number of non-zero entries in sparse feature matrix
Definition at line 573 of file SparseFeatures.cpp.
| int32_t get_num_preprocessed | ( | ) | const [inherited] |
get whether specified preprocessor (or all if num=1) was/were already applied
get the number of applied preprocs
Definition at line 123 of file Features.cpp.
| int32_t get_num_preprocessors | ( | ) | const [inherited] |
get number of preprocessors
Definition at line 198 of file Features.cpp.
| int32_t get_num_vectors | ( | ) | const [virtual] |
get number of feature vectors, possibly of subset
Implements CFeatures.
Definition at line 542 of file SparseFeatures.cpp.
| CPreprocessor * get_preprocessor | ( | int32_t | num | ) | const [inherited] |
get current preprocessor
get specified preprocessor
| num | index of preprocessor in list |
Definition at line 111 of file Features.cpp.
| int32_t get_size | ( | ) | const [virtual] |
get memory footprint of one feature
Implements CFeatures.
Definition at line 529 of file SparseFeatures.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 |
Definition at line 312 of file SparseFeatures.cpp.
| SGSparseMatrix< ST > get_sparse_feature_matrix | ( | ) |
get the sparse feature matrix
not possible with subset
Definition at line 323 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 190 of file SparseFeatures.cpp.
| CSubsetStack * get_subset_stack | ( | ) | [virtual, inherited] |
| CSparseFeatures< ST > * get_transposed | ( | ) |
get a transposed copy of the features
possible with subset
Definition at line 333 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 |
Definition at line 342 of file SparseFeatures.cpp.
| bool has_property | ( | EFeatureProperty | p | ) | const [inherited] |
check if features have given property
| p | feature property |
Definition at line 336 of file Features.cpp.
| bool is_generic | ( | EPrimitiveType * | generic | ) | const [virtual, inherited] |
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 278 of file SGObject.cpp.
| bool is_preprocessed | ( | int32_t | num | ) | const [inherited] |
get whether specified preprocessor was already applied
| num | index of preprocessor in list |
Definition at line 193 of file Features.cpp.
| void list_feature_obj | ( | ) | const [inherited] |
list feature object
Definition at line 214 of file Features.cpp.
| void load | ( | CFile * | loader | ) | [virtual] |
load features from file
any subset is removed before
| loader | File object to load data from |
Reimplemented from CFeatures.
| DynArray< TParameter * > * load_all_file_parameters | ( | int32_t | file_version, | |
| int32_t | current_version, | |||
| CSerializableFile * | file, | |||
| const char * | prefix = "" | |||
| ) | [inherited] |
maps all parameters of this instance to the provided file version and loads all parameter data from the file into an array, which is sorted (basically calls load_file_parameter(...) for all parameters and puts all results into a sorted array)
| file_version | parameter version of the file | |
| current_version | version from which mapping begins (you want to use VERSION_PARAMETER for this in most cases) | |
| file | file to load from | |
| prefix | prefix for members |
Definition at line 679 of file SGObject.cpp.
| DynArray< TParameter * > * load_file_parameters | ( | const SGParamInfo * | param_info, | |
| int32_t | file_version, | |||
| CSerializableFile * | file, | |||
| const char * | prefix = "" | |||
| ) | [inherited] |
loads some specified parameters from a file with a specified version The provided parameter info has a version which is recursively mapped until the file parameter version is reached. Note that there may be possibly multiple parameters in the mapping, therefore, a set of TParameter instances is returned
| param_info | information of parameter | |
| file_version | parameter version of the file, must be <= provided parameter version | |
| file | file to load from | |
| prefix | prefix for members |
Definition at line 523 of file SGObject.cpp.
| bool load_serializable | ( | CSerializableFile * | file, | |
| const char * | prefix = "", |
|||
| int32_t | param_version = VERSION_PARAMETER | |||
| ) | [virtual, inherited] |
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 | |
| param_version | (optional) a parameter version different to (this is mainly for testing, better do not use) |
Reimplemented in CModelSelectionParameters.
Definition at line 354 of file SGObject.cpp.
| void load_serializable_post | ( | ) | throw (ShogunException) [protected, virtual, inherited] |
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 occurres. |
Reimplemented in CLinearHMM, CAlphabet, CANOVAKernel, CCircularKernel, CExponentialKernel, CGaussianKernel, CInverseMultiQuadricKernel, CKernel, CWeightedDegreePositionStringKernel, and CList.
Definition at line 1033 of file SGObject.cpp.
| void load_serializable_pre | ( | ) | throw (ShogunException) [protected, virtual, inherited] |
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 occurres. |
Definition at line 1028 of file SGObject.cpp.
| CRegressionLabels * load_svmlight_file | ( | char * | fname, | |
| bool | do_sort_features = true | |||
| ) |
load features from file
any subset is removed before
| fname | filename to load from | |
| do_sort_features | if true features will be sorted to ensure they are in ascending order |
Definition at line 662 of file SparseFeatures.cpp.
| void map_parameters | ( | DynArray< TParameter * > * | param_base, | |
| int32_t & | base_version, | |||
| DynArray< const SGParamInfo * > * | target_param_infos | |||
| ) | [inherited] |
Takes a set of TParameter instances (base) with a certain version and a set of target parameter infos and recursively maps the base level wise to the current version using CSGObject::migrate(...). The base is replaced. After this call, the base version containing parameters should be of same version/type as the initial target parameter infos. Note for this to work, the migrate methods and all the internal parameter mappings have to match
| param_base | set of TParameter instances that are mapped to the provided target parameter infos | |
| base_version | version of the parameter base | |
| target_param_infos | set of SGParamInfo instances that specify the target parameter base |
Definition at line 717 of file SGObject.cpp.
| TParameter * migrate | ( | DynArray< TParameter * > * | param_base, | |
| const SGParamInfo * | target | |||
| ) | [protected, virtual, inherited] |
creates a new TParameter instance, which contains migrated data from the version that is provided. The provided parameter data base is used for migration, this base is a collection of all parameter data of the previous version. Migration is done FROM the data in param_base TO the provided param info Migration is always one version step. Method has to be implemented in subclasses, if no match is found, base method has to be called.
If there is an element in the param_base which equals the target, a copy of the element is returned. This represents the case when nothing has changed and therefore, the migrate method is not overloaded in a subclass
| param_base | set of TParameter instances to use for migration | |
| target | parameter info for the resulting TParameter |
Definition at line 923 of file SGObject.cpp.
| bool 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 534 of file SparseFeatures.cpp.
| void one_to_one_migration_prepare | ( | DynArray< TParameter * > * | param_base, | |
| const SGParamInfo * | target, | |||
| TParameter *& | replacement, | |||
| TParameter *& | to_migrate, | |||
| char * | old_name = NULL | |||
| ) | [protected, virtual, inherited] |
This method prepares everything for a one-to-one parameter migration. One to one here means that only ONE element of the parameter base is needed for the migration (the one with the same name as the target). Data is allocated for the target (in the type as provided in the target SGParamInfo), and a corresponding new TParameter instance is written to replacement. The to_migrate pointer points to the single needed TParameter instance needed for migration. If a name change happened, the old name may be specified by old_name. In addition, the m_delete_data flag of to_migrate is set to true. So if you want to migrate data, the only thing to do after this call is converting the data in the m_parameter fields. If unsure how to use - have a look into an example for this. (base_migration_type_conversion.cpp for example)
| param_base | set of TParameter instances to use for migration | |
| target | parameter info for the resulting TParameter | |
| replacement | (used as output) here the TParameter instance which is returned by migration is created into | |
| to_migrate | the only source that is used for migration | |
| old_name | with this parameter, a name change may be specified |
Definition at line 864 of file SGObject.cpp.
| void print_modsel_params | ( | ) | [inherited] |
prints all parameter registered for model selection and their type
Definition at line 1084 of file SGObject.cpp.
| void print_serializable | ( | const char * | prefix = "" |
) | [virtual, inherited] |
prints registered parameters out
| prefix | prefix for members |
Definition at line 290 of file SGObject.cpp.
| void remove_all_subsets | ( | ) | [virtual, inherited] |
removes all subsets Calls subset_changed_post() afterwards
Reimplemented in CCombinedFeatures.
Definition at line 363 of file Features.cpp.
| void remove_subset | ( | ) | [virtual, inherited] |
removes that last added subset from subset stack, if existing Calls subset_changed_post() afterwards
Reimplemented in CCombinedFeatures.
Definition at line 357 of file Features.cpp.
| bool reshape | ( | int32_t | num_features, | |
| int32_t | num_vectors | |||
| ) | [virtual, inherited] |
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 208 of file Features.cpp.
| void save | ( | CFile * | writer | ) | [virtual] |
save features to file
not possible with subset
| writer | File object to write data to |
Reimplemented from CFeatures.
| bool save_serializable | ( | CSerializableFile * | file, | |
| const char * | prefix = "", |
|||
| int32_t | param_version = VERSION_PARAMETER | |||
| ) | [virtual, inherited] |
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 | |
| param_version | (optional) a parameter version different to (this is mainly for testing, better do not use) |
Reimplemented in CModelSelectionParameters.
Definition at line 296 of file SGObject.cpp.
| void save_serializable_post | ( | ) | throw (ShogunException) [protected, virtual, inherited] |
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 occurres. |
Reimplemented in CKernel.
Definition at line 1043 of file SGObject.cpp.
| void save_serializable_pre | ( | ) | throw (ShogunException) [protected, virtual, inherited] |
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 occurres. |
Reimplemented in CKernel.
Definition at line 1038 of file SGObject.cpp.
| void set_combined_feature_weight | ( | float64_t | nw | ) | [inherited] |
set combined kernel weight
| nw | new combined feature weight |
Definition at line 157 of file DotFeatures.h.
| bool set_full_feature_matrix | ( | SGMatrix< ST > | full | ) | [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 427 of file SparseFeatures.cpp.
| void set_generic< floatmax_t > | ( | ) | [inherited] |
set generic type to T
| void set_global_io | ( | SGIO * | io | ) | [inherited] |
| void set_global_parallel | ( | Parallel * | parallel | ) | [inherited] |
set the parallel object
| parallel | parallel object to use |
Definition at line 230 of file SGObject.cpp.
| void set_global_version | ( | Version * | version | ) | [inherited] |
set the version object
| version | version object to use |
Definition at line 265 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 552 of file SparseFeatures.cpp.
| void set_preprocessed | ( | int32_t | num | ) | [inherited] |
set applied flag for preprocessor
| num | index of preprocessor in list |
Definition at line 188 of file Features.cpp.
| void set_property | ( | EFeatureProperty | p | ) | [inherited] |
| void set_sparse_feature_matrix | ( | SGSparseMatrix< ST > | sm | ) |
set sparse feature matrix
not possible with subset
| sm | sparse feature matrix |
Definition at line 386 of file SparseFeatures.cpp.
| virtual CSGObject* shallow_copy | ( | ) | const [virtual, inherited] |
A shallow copy. All the SGObject instance variables will be simply assigned and SG_REF-ed.
Reimplemented in CGaussianKernel.
Definition at line 122 of file SGObject.h.
| void sort_features | ( | ) |
ensure that features occur in ascending order, only call when no preprocessors are attached
not possiblwe with subset
Definition at line 828 of file SparseFeatures.cpp.
| virtual void subset_changed_post | ( | ) | [virtual, inherited] |
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 262 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 285 of file SGObject.cpp.
| void unset_property | ( | EFeatureProperty | p | ) | [inherited] |
| bool update_parameter_hash | ( | ) | [protected, virtual, inherited] |
Updates the hash of current parameter combination.
Definition at line 237 of file SGObject.cpp.
| bool write_svmlight_file | ( | char * | fname, | |
| CRegressionLabels * | label | |||
| ) |
write features to file using svm light format
not possible with subset
| fname | filename to write to | |
| label | Label object (number of labels must correspond to number of features) |
Definition at line 873 of file SparseFeatures.cpp.
float64_t combined_weight [protected, inherited] |
feature weighting in combined dot features
Definition at line 246 of file DotFeatures.h.
CCache< SGSparseVectorEntry<ST> >* feature_cache [protected] |
feature cache
Definition at line 542 of file SparseFeatures.h.
io
Definition at line 462 of file SGObject.h.
uint32_t m_hash [inherited] |
Hash of parameter values
Definition at line 480 of file SGObject.h.
Parameter* m_model_selection_parameters [inherited] |
model selection parameters
Definition at line 474 of file SGObject.h.
ParameterMap* m_parameter_map [inherited] |
map for different parameter versions
Definition at line 477 of file SGObject.h.
Parameter* m_parameters [inherited] |
parameters
Definition at line 471 of file SGObject.h.
CSubsetStack* m_subset_stack [protected, inherited] |
subset used for index transformations
Definition at line 296 of file Features.h.
int32_t num_features [protected] |
total number of features
Definition at line 536 of file SparseFeatures.h.
int32_t num_vectors [protected] |
total number of vectors
Definition at line 533 of file SparseFeatures.h.
parallel
Definition at line 465 of file SGObject.h.
SGSparseVector<ST>* sparse_feature_matrix [protected] |
array of sparse vectors of size num_vectors
Definition at line 539 of file SparseFeatures.h.
version
Definition at line 468 of file SGObject.h.
