class Isomap (part of the Efficient Dimension Reduction Toolkit) used to embed data using Isomap algorithm as described in
Silva, V. D., & Tenenbaum, J. B. (2003). Global versus local methods in nonlinear dimensionality reduction. Advances in Neural Information Processing Systems 15, 15(Figure 2), 721-728. MIT Press. Retrieved from http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.9.3407&rep=rep1&type=pdf
Shortest paths are being computed with Dijkstra's algorithm with heap in parallel. Due to sparsity of the kNN graph Fibonacci Heap with amortized O(1) Extract-Min operation time complexity is used.
It is possible to apply preprocessor to specified distance using apply_to_distance.
To use this converter with static interfaces please refer it by sg('create_converter','isomap',k);
Definition at line 49 of file Isomap.h.
Public Member Functions | |
CIsomap () | |
virtual | ~CIsomap () |
const char * | get_name () const |
void | set_k (int32_t k) |
int32_t | get_k () const |
virtual CDenseFeatures < float64_t > * | embed_distance (CDistance *distance) |
virtual CFeatures * | apply (CFeatures *features) |
SGVector< float64_t > | get_eigenvalues () const |
void | set_landmark_number (int32_t num) |
int32_t | get_landmark_number () const |
void | set_landmark (bool landmark) |
bool | get_landmark () const |
virtual CDenseFeatures < float64_t > * | embed (CFeatures *features) |
void | set_target_dim (int32_t dim) |
int32_t | get_target_dim () const |
void | set_distance (CDistance *distance) |
CDistance * | get_distance () const |
void | set_kernel (CKernel *kernel) |
CKernel * | get_kernel () const |
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 | |
virtual void | init () |
HELPERS. | |
virtual SGMatrix< float64_t > | process_distance_matrix (SGMatrix< float64_t > distance_matrix) |
SGMatrix< float64_t > | isomap_distance (SGMatrix< float64_t > D_matrix) |
SGMatrix< float64_t > | classic_embedding (SGMatrix< float64_t > distance_matrix) |
SGMatrix< float64_t > | landmark_embedding (SGMatrix< float64_t > distance_matrix) |
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 () |
Static Protected Member Functions | |
static void * | run_dijkstra_thread (void *p) |
THREADS. | |
static void * | run_triangulation_thread (void *p) |
STATIC. | |
static SGVector< int32_t > | shuffle (int32_t count, int32_t total_count) |
Protected Attributes | |
int32_t | m_k |
FIELDS. | |
SGVector< float64_t > | m_eigenvalues |
FIELDS. | |
bool | m_landmark |
int32_t | m_landmark_number |
int32_t | m_target_dim |
CDistance * | m_distance |
CKernel * | m_kernel |
CIsomap | ( | ) |
Definition at line 82 of file Isomap.cpp.
~CIsomap | ( | ) | [virtual] |
Definition at line 94 of file Isomap.cpp.
apply preprocessor to feature matrix, changes feature matrix to the one having target dimensionality
features | features which feature matrix should be processed |
Implements CEmbeddingConverter.
Definition at line 137 of file MultidimensionalScaling.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.
SGMatrix< float64_t > classic_embedding | ( | SGMatrix< float64_t > | distance_matrix | ) | [protected, inherited] |
classical embedding
distance_matrix | distance matrix to be used for embedding |
Definition at line 150 of file MultidimensionalScaling.cpp.
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.
CDenseFeatures< float64_t > * embed | ( | CFeatures * | features | ) | [virtual, inherited] |
embed given features, acts the same as apply, but returns DenseFeatures
features | features to embed |
Definition at line 35 of file EmbeddingConverter.cpp.
CDenseFeatures< float64_t > * embed_distance | ( | CDistance * | distance | ) | [virtual, inherited] |
apply preprocessor to CDistance
distance | (should be approximate euclidean for consistent result) |
Definition at line 117 of file MultidimensionalScaling.cpp.
CDistance * get_distance | ( | ) | const [inherited] |
get last embedding eigenvectors
Definition at line 84 of file MultidimensionalScaling.cpp.
SGIO * get_global_io | ( | ) | [inherited] |
Parallel * get_global_parallel | ( | ) | [inherited] |
Version * get_global_version | ( | ) | [inherited] |
int32_t get_k | ( | ) | const |
CKernel * get_kernel | ( | ) | const [inherited] |
bool get_landmark | ( | ) | const [inherited] |
getter for landmark parameter
Definition at line 107 of file MultidimensionalScaling.cpp.
int32_t get_landmark_number | ( | ) | const [inherited] |
get number of landmarks
Definition at line 97 of file MultidimensionalScaling.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.
const char * get_name | ( | ) | const [virtual] |
int32_t get_target_dim | ( | ) | const [inherited] |
getter for target dimension
Definition at line 46 of file EmbeddingConverter.cpp.
void init | ( | ) | [protected, virtual] |
HELPERS.
default init
Reimplemented from CMultidimensionalScaling.
Definition at line 89 of file Isomap.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.
approximate geodesic distance with shortest path in kNN graph
D_matrix | distance matrix (deleted on exit) |
Definition at line 119 of file Isomap.cpp.
SGMatrix< float64_t > landmark_embedding | ( | SGMatrix< float64_t > | distance_matrix | ) | [protected, inherited] |
landmark embedding (approximate, accuracy varies with m_landmark_num parameter)
distance_matrix | distance matrix to be used for embedding |
Definition at line 258 of file MultidimensionalScaling.cpp.
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.
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.
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.
SGMatrix< float64_t > process_distance_matrix | ( | SGMatrix< float64_t > | distance_matrix | ) | [protected, virtual] |
process distance matrix (redefined in isomap, for mds does nothing)
distance_matrix | distance matrix |
Reimplemented from CMultidimensionalScaling.
Definition at line 114 of file Isomap.cpp.
void * run_dijkstra_thread | ( | void * | p | ) | [static, protected] |
void * run_triangulation_thread | ( | void * | p | ) | [static, protected, inherited] |
STATIC.
run triangulation thread for landmark embedding
p | thread parameters |
Definition at line 390 of file MultidimensionalScaling.cpp.
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_distance | ( | CDistance * | distance | ) | [inherited] |
setter for distance
distance | distance to set |
Definition at line 51 of file EmbeddingConverter.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.
void set_k | ( | int32_t | k | ) |
void set_kernel | ( | CKernel * | kernel | ) | [inherited] |
setter for kernel
kernel | kernel to set |
Definition at line 64 of file EmbeddingConverter.cpp.
void set_landmark | ( | bool | landmark | ) | [inherited] |
setter for landmark parameter
landmark | true if landmark embedding should be used |
Definition at line 102 of file MultidimensionalScaling.cpp.
void set_landmark_number | ( | int32_t | num | ) | [inherited] |
set number of landmarks should be lesser than number of examples and greater than 3 for consistent embedding as triangulation is used
num | number of landmark to be set |
Definition at line 89 of file MultidimensionalScaling.cpp.
void set_target_dim | ( | int32_t | dim | ) | [inherited] |
setter for target dimension
dim | target dimension |
Definition at line 40 of file EmbeddingConverter.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.
static SGVector<int32_t> shuffle | ( | int32_t | count, | |
int32_t | total_count | |||
) | [static, protected, inherited] |
subroutine used to shuffle count indexes among of total_count ones with Fisher-Yates (known as Knuth too) shuffle algorithm
count | number of indexes to be shuffled and returned | |
total_count | total number of indexes |
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.
bool update_parameter_hash | ( | ) | [protected, virtual, inherited] |
Updates the hash of current parameter combination.
Definition at line 237 of file SGObject.cpp.
io
Definition at line 462 of file SGObject.h.
CDistance* m_distance [protected, inherited] |
distance to be used
Definition at line 97 of file EmbeddingConverter.h.
SGVector<float64_t> m_eigenvalues [protected, inherited] |
uint32_t m_hash [inherited] |
Hash of parameter values
Definition at line 480 of file SGObject.h.
int32_t m_k [protected] |
kernel to be used
Definition at line 100 of file EmbeddingConverter.h.
bool m_landmark [protected, inherited] |
use landmark approximation?
Definition at line 148 of file MultidimensionalScaling.h.
int32_t m_landmark_number [protected, inherited] |
number of landmarks
Definition at line 151 of file MultidimensionalScaling.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.
int32_t m_target_dim [protected, inherited] |
target dim of dimensionality reduction preprocessor
Definition at line 94 of file EmbeddingConverter.h.
parallel
Definition at line 465 of file SGObject.h.
version
Definition at line 468 of file SGObject.h.