SHOGUN
v2.0.0
|
The FixedDegree String kernel takes as input two strings of same size and counts the number of matches of length d.
Note that additional normalisation is applied, i.e.
Definition at line 31 of file FixedDegreeStringKernel.h.
Public Member Functions | |
CFixedDegreeStringKernel () | |
CFixedDegreeStringKernel (int32_t size, int32_t degree) | |
CFixedDegreeStringKernel (CStringFeatures< char > *l, CStringFeatures< char > *r, int32_t degree) | |
virtual | ~CFixedDegreeStringKernel () |
virtual bool | init (CFeatures *l, CFeatures *r) |
virtual void | cleanup () |
virtual EKernelType | get_kernel_type () |
virtual const char * | get_name () const |
virtual EFeatureClass | get_feature_class () |
virtual EFeatureType | get_feature_type () |
float64_t | kernel (int32_t idx_a, int32_t idx_b) |
SGMatrix< float64_t > | get_kernel_matrix () |
template<class T > | |
SGMatrix< T > | get_kernel_matrix () |
virtual SGVector< float64_t > | get_kernel_col (int32_t j) |
virtual SGVector< float64_t > | get_kernel_row (int32_t i) |
void | get_kernel_row (int32_t docnum, int32_t *active2dnum, float64_t *buffer, bool full_line=false) |
virtual bool | set_normalizer (CKernelNormalizer *normalizer) |
virtual CKernelNormalizer * | get_normalizer () |
virtual bool | init_normalizer () |
void | load (CFile *loader) |
void | save (CFile *writer) |
CFeatures * | get_lhs () |
CFeatures * | get_rhs () |
virtual int32_t | get_num_vec_lhs () |
virtual int32_t | get_num_vec_rhs () |
virtual bool | has_features () |
bool | get_lhs_equals_rhs () |
virtual void | remove_lhs_and_rhs () |
virtual void | remove_lhs () |
virtual void | remove_rhs () |
takes all necessary steps if the rhs is removed from kernel | |
void | set_cache_size (int32_t size) |
int32_t | get_cache_size () |
void | cache_reset () |
int32_t | get_max_elems_cache () |
int32_t | get_activenum_cache () |
void | cache_kernel_row (int32_t x) |
void | cache_multiple_kernel_rows (int32_t *key, int32_t varnum) |
void | kernel_cache_reset_lru () |
void | kernel_cache_shrink (int32_t totdoc, int32_t num_shrink, int32_t *after) |
void | resize_kernel_cache (KERNELCACHE_IDX size, bool regression_hack=false) |
void | set_time (int32_t t) |
int32_t | kernel_cache_touch (int32_t cacheidx) |
int32_t | kernel_cache_check (int32_t cacheidx) |
int32_t | kernel_cache_space_available () |
void | kernel_cache_init (int32_t size, bool regression_hack=false) |
void | kernel_cache_cleanup () |
void | list_kernel () |
bool | has_property (EKernelProperty p) |
virtual void | clear_normal () |
virtual void | add_to_normal (int32_t vector_idx, float64_t weight) |
EOptimizationType | get_optimization_type () |
virtual void | set_optimization_type (EOptimizationType t) |
bool | get_is_initialized () |
virtual bool | init_optimization (int32_t count, int32_t *IDX, float64_t *weights) |
virtual bool | delete_optimization () |
bool | init_optimization_svm (CSVM *svm) |
virtual float64_t | compute_optimized (int32_t vector_idx) |
virtual void | compute_batch (int32_t num_vec, int32_t *vec_idx, float64_t *target, int32_t num_suppvec, int32_t *IDX, float64_t *alphas, float64_t factor=1.0) |
float64_t | get_combined_kernel_weight () |
void | set_combined_kernel_weight (float64_t nw) |
virtual int32_t | get_num_subkernels () |
virtual void | compute_by_subkernel (int32_t vector_idx, float64_t *subkernel_contrib) |
virtual const float64_t * | get_subkernel_weights (int32_t &num_weights) |
virtual void | set_subkernel_weights (SGVector< float64_t > weights) |
virtual SGMatrix< float64_t > | get_parameter_gradient (TParameter *param, CSGObject *obj, index_t index=-1) |
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) |
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 | |
float64_t | compute (int32_t idx_a, int32_t idx_b) |
void | set_property (EKernelProperty p) |
void | unset_property (EKernelProperty p) |
void | set_is_initialized (bool p_init) |
int32_t | compute_row_start (int64_t offs, int32_t n, bool symmetric) |
virtual void | load_serializable_post () throw (ShogunException) |
virtual void | save_serializable_pre () throw (ShogunException) |
virtual void | save_serializable_post () throw (ShogunException) |
virtual void | register_params () |
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 bool | update_parameter_hash () |
Static Protected Member Functions | |
template<class T > | |
static void * | get_kernel_matrix_helper (void *p) |
Protected Attributes | |
int32_t | degree |
int32_t | cache_size |
cache_size in MB | |
KERNEL_CACHE | kernel_cache |
kernel cache | |
KERNELCACHE_ELEM * | kernel_matrix |
CFeatures * | lhs |
feature vectors to occur on left hand side | |
CFeatures * | rhs |
feature vectors to occur on right hand side | |
bool | lhs_equals_rhs |
lhs | |
int32_t | num_lhs |
number of feature vectors on left hand side | |
int32_t | num_rhs |
number of feature vectors on right hand side | |
float64_t | combined_kernel_weight |
bool | optimization_initialized |
EOptimizationType | opt_type |
uint64_t | properties |
CKernelNormalizer * | normalizer |
default constructor
Definition at line 27 of file FixedDegreeStringKernel.cpp.
CFixedDegreeStringKernel | ( | int32_t | size, |
int32_t | degree | ||
) |
constructor
size | cache size |
degree | the degree |
Definition at line 33 of file FixedDegreeStringKernel.cpp.
CFixedDegreeStringKernel | ( | CStringFeatures< char > * | l, |
CStringFeatures< char > * | r, | ||
int32_t | degree | ||
) |
constructor
l | features of left-hand side |
r | features of right-hand side |
degree | the degree |
Definition at line 39 of file FixedDegreeStringKernel.cpp.
|
virtual |
Definition at line 47 of file FixedDegreeStringKernel.cpp.
|
virtualinherited |
add vector*factor to 'virtual' normal vector
vector_idx | index |
weight | weight |
Reimplemented in CCombinedKernel, CWeightedDegreeStringKernel, CWeightedDegreePositionStringKernel, CCommUlongStringKernel, CCommWordStringKernel, CLinearKernel, CLinearStringKernel, and CWeightedCommWordStringKernel.
Definition at line 829 of file Kernel.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 1204 of file SGObject.cpp.
|
inherited |
|
inherited |
|
virtual |
clean up kernel
Reimplemented from CKernel.
Definition at line 58 of file FixedDegreeStringKernel.cpp.
|
virtualinherited |
for optimizable kernels, i.e. kernels where the weight vector can be computed explicitly (if it fits into memory)
Reimplemented in CCombinedKernel, CWeightedDegreeStringKernel, CWeightedDegreePositionStringKernel, CCommUlongStringKernel, CCommWordStringKernel, CLinearKernel, and CLinearStringKernel.
Definition at line 834 of file Kernel.cpp.
|
protectedvirtual |
compute kernel function for features a and b idx_{a,b} denote the index of the feature vectors in the corresponding feature object
idx_a | index a |
idx_b | index b |
Implements CKernel.
Definition at line 63 of file FixedDegreeStringKernel.cpp.
|
virtualinherited |
computes output for a batch of examples in an optimized fashion (favorable if kernel supports it, i.e. has KP_BATCHEVALUATION. to the outputvector target (of length num_vec elements) the output for the examples enumerated in vec_idx are added. therefore make sure that it is initialized with ZERO. the following num_suppvec, IDX, alphas arguments are the number of support vectors, their indices and weights
Reimplemented in CCombinedKernel, CWeightedDegreeStringKernel, and CWeightedDegreePositionStringKernel.
Definition at line 822 of file Kernel.cpp.
|
virtualinherited |
compute by subkernel
vector_idx | index |
subkernel_contrib | subkernel contribution |
Reimplemented in CCombinedKernel, CWeightedDegreeStringKernel, and CWeightedDegreePositionStringKernel.
Definition at line 844 of file Kernel.cpp.
|
virtualinherited |
compute optimized
vector_idx | index to compute |
Reimplemented in CCombinedKernel, CWeightedDegreeStringKernel, CWeightedDegreePositionStringKernel, CCommWordStringKernel, CCommUlongStringKernel, CLinearKernel, CLinearStringKernel, and CWeightedCommWordStringKernel.
Definition at line 816 of file Kernel.cpp.
|
protectedinherited |
|
virtualinherited |
A deep copy. All the instance variables will also be copied.
Definition at line 131 of file SGObject.h.
|
virtualinherited |
delete optimization
Reimplemented in CCombinedKernel, CWeightedDegreeStringKernel, CWeightedDegreePositionStringKernel, CCommWordStringKernel, CCommUlongStringKernel, CLinearKernel, and CLinearStringKernel.
Definition at line 810 of file Kernel.cpp.
|
inherited |
|
inherited |
|
inherited |
|
virtualinherited |
return feature class the kernel can deal with
Implements CKernel.
Definition at line 69 of file StringKernel.h.
|
virtualinherited |
|
inherited |
|
inherited |
|
inherited |
|
inherited |
|
inherited |
|
staticprotectedinherited |
|
inherited |
get kernel row
docnum | docnum |
active2dnum | active2dnum |
buffer | buffer |
full_line | full line |
Definition at line 226 of file Kernel.cpp.
|
virtual |
return what type of kernel we are
Implements CStringKernel< char >.
Definition at line 73 of file FixedDegreeStringKernel.h.
|
inherited |
|
inherited |
|
inherited |
|
inherited |
Definition at line 1108 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 1132 of file SGObject.cpp.
|
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 |
return the kernel's name
Reimplemented from CStringKernel< char >.
Definition at line 82 of file FixedDegreeStringKernel.h.
|
virtualinherited |
obtain the current kernel normalizer
Definition at line 150 of file Kernel.cpp.
|
virtualinherited |
get number of subkernels
Reimplemented in CCombinedKernel, CWeightedDegreeStringKernel, CWeightedDegreePositionStringKernel, and CProductKernel.
Definition at line 839 of file Kernel.cpp.
|
virtualinherited |
get number of vectors of lhs features
Reimplemented in CCustomKernel.
|
virtualinherited |
get number of vectors of rhs features
Reimplemented in CCustomKernel.
|
inherited |
|
virtualinherited |
return derivative with respect to specified parameter
param | the parameter |
obj | the object that owns the parameter |
index | the index of the element if parameter is a vector |
Reimplemented in CCombinedKernel, CProductKernel, CGaussianKernel, CLinearARDKernel, and CGaussianARDKernel.
Definition at line 952 of file Kernel.cpp.
|
inherited |
|
virtualinherited |
get subkernel weights
num_weights | number of weights will be stored here |
Reimplemented in CCombinedKernel, CWeightedDegreeStringKernel, and CWeightedDegreePositionStringKernel.
Definition at line 850 of file Kernel.cpp.
|
virtualinherited |
test whether features have been assigned to lhs and rhs
Reimplemented in CCustomKernel, CCombinedKernel, and CProductKernel.
|
inherited |
initialize kernel
l | features of left-hand side |
r | features of right-hand side |
Reimplemented from CStringKernel< char >.
Definition at line 52 of file FixedDegreeStringKernel.cpp.
|
virtualinherited |
initialize the current kernel normalizer
Definition at line 156 of file Kernel.cpp.
|
virtualinherited |
initialize optimization
count | count |
IDX | index |
weights | weights |
Reimplemented in CCombinedKernel, CWeightedDegreeStringKernel, CWeightedDegreePositionStringKernel, CCommWordStringKernel, CCommUlongStringKernel, CLinearKernel, and CLinearStringKernel.
Definition at line 803 of file Kernel.cpp.
|
inherited |
initialize optimization
svm | svm model |
Definition at line 865 of file Kernel.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 278 of file SGObject.cpp.
|
inherited |
|
inherited |
|
inherited |
cleanup kernel cache
Definition at line 552 of file Kernel.cpp.
|
inherited |
initialize kernel cache
size | size to initialize to |
regression_hack | if hack for regression shall be applied |
Definition at line 169 of file Kernel.cpp.
|
inherited |
kernel cache reset lru
Definition at line 539 of file Kernel.cpp.
|
inherited |
kernel cache shrink
totdoc | totdoc |
num_shrink | number of shrink |
after | after |
Definition at line 483 of file Kernel.cpp.
|
inherited |
|
inherited |
|
inherited |
list kernel
Definition at line 691 of file Kernel.cpp.
|
inherited |
load the kernel matrix
loader | File object via which to load data |
Definition at line 631 of file Kernel.cpp.
|
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.
|
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.
|
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 |
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.
|
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 occurres. |
Reimplemented from CSGObject.
Reimplemented in CWeightedDegreePositionStringKernel, CGaussianKernel, CANOVAKernel, CInverseMultiQuadricKernel, CCircularKernel, and CExponentialKernel.
Definition at line 883 of file Kernel.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 occurres. |
Definition at line 1028 of file SGObject.cpp.
|
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.
|
protectedvirtualinherited |
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.
|
protectedvirtualinherited |
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.
|
inherited |
prints all parameter registered for model selection and their type
Definition at line 1084 of file SGObject.cpp.
|
virtualinherited |
prints registered parameters out
prefix | prefix for members |
Definition at line 290 of file SGObject.cpp.
|
protectedvirtualinherited |
Separate the function of parameter registration This can be the first stage of a general framework for cross-validation or other parameter-based operations
Reimplemented in CSpectrumMismatchRBFKernel, CSNPStringKernel, CANOVAKernel, CRegulatoryModulesStringKernel, CGaussianMatchStringKernel, CGaussianShortRealKernel, CTensorProductPairKernel, CDistanceKernel, and CHistogramIntersectionKernel.
Definition at line 906 of file Kernel.cpp.
|
virtualinherited |
remove lhs from kernel
Reimplemented in CWeightedDegreeStringKernel, CWeightedDegreePositionStringKernel, CCombinedKernel, CProductKernel, CSpectrumMismatchRBFKernel, CCommUlongStringKernel, and CSpectrumRBFKernel.
Definition at line 662 of file Kernel.cpp.
|
virtualinherited |
remove lhs and rhs from kernel
Reimplemented in CCombinedKernel, and CProductKernel.
Definition at line 645 of file Kernel.cpp.
|
virtualinherited |
takes all necessary steps if the rhs is removed from kernel
remove rhs from kernel
Reimplemented in CCombinedKernel, CProductKernel, and CCommUlongStringKernel.
Definition at line 676 of file Kernel.cpp.
|
inherited |
resize kernel cache
size | new size |
regression_hack | hack for regression |
Definition at line 85 of file Kernel.cpp.
|
inherited |
save kernel matrix
writer | File object via which to save data |
Definition at line 637 of file Kernel.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 |
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.
|
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 occurres. |
Reimplemented from CSGObject.
Definition at line 898 of file Kernel.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 occurres. |
Reimplemented from CSGObject.
Definition at line 890 of file Kernel.cpp.
|
inherited |
|
inherited |
|
inherited |
set generic type to T
Definition at line 41 of file SGObject.cpp.
|
inherited |
|
inherited |
set the parallel object
parallel | parallel object to use |
Definition at line 230 of file SGObject.cpp.
|
inherited |
set the version object
version | version object to use |
Definition at line 265 of file SGObject.cpp.
|
protectedinherited |
|
virtualinherited |
set the current kernel normalizer
Reimplemented in CWeightedDegreeStringKernel.
Definition at line 138 of file Kernel.cpp.
|
virtualinherited |
|
protectedinherited |
set subkernel weights
weights | new subkernel weights |
Reimplemented in CCombinedKernel, CWeightedDegreeStringKernel, and CWeightedDegreePositionStringKernel.
Definition at line 856 of file Kernel.cpp.
|
inherited |
|
virtualinherited |
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.
|
inherited |
unset generic type
this has to be called in classes specializing a template class
Definition at line 285 of file SGObject.cpp.
|
protectedinherited |
|
protectedvirtualinherited |
Updates the hash of current parameter combination.
Definition at line 237 of file SGObject.cpp.
|
protectedinherited |
|
protected |
the degree
Definition at line 95 of file FixedDegreeStringKernel.h.
|
inherited |
io
Definition at line 462 of file SGObject.h.
|
protectedinherited |
|
protectedinherited |
|
inherited |
Hash of parameter values
Definition at line 480 of file SGObject.h.
|
inherited |
model selection parameters
Definition at line 474 of file SGObject.h.
|
inherited |
map for different parameter versions
Definition at line 477 of file SGObject.h.
|
inherited |
parameters
Definition at line 471 of file SGObject.h.
|
protectedinherited |
|
protectedinherited |
|
protectedinherited |
|
protectedinherited |
|
protectedinherited |
|
inherited |
parallel
Definition at line 465 of file SGObject.h.
|
protectedinherited |
|
inherited |
version
Definition at line 468 of file SGObject.h.