SHOGUN
v2.0.0
|
Template class Trie implements a suffix trie, i.e. a tree in which all suffixes up to a certain length are stored.
It is excessively used in the CWeightedDegreeStringKernel and CWeightedDegreePositionStringKernel to construct the whole features space and enormously helps here to speed up SVM training and evaluation.
Note that depending on the underlying structure used, a single symbol in the tree requires 20 bytes (DNATrie). It is also used to do the efficient recursion in computing positional oligomer importance matrices (POIMs) where the structure requires * 20+3*8 (POIMTrie) bytes.
Finally note that this tree may use compact internal nodes (for strings that appear without modifications, thus not requiring further branches), which may save a lot of memory on higher degree tries.
Public Member Functions | |
CTrie () | |
CTrie (int32_t d, bool p_use_compact_terminal_nodes=true) | |
CTrie (const CTrie &to_copy) | |
virtual | ~CTrie () |
const CTrie & | operator= (const CTrie &to_copy) |
bool | compare_traverse (int32_t node, const CTrie &other, int32_t other_node) |
bool | compare (const CTrie &other) |
bool | find_node (int32_t node, int32_t *trace, int32_t &trace_len) const |
int32_t | find_deepest_node (int32_t start_node, int32_t &deepest_node) const |
void | display_node (int32_t node) const |
void | destroy () |
void | set_degree (int32_t d) |
void | create (int32_t len, bool p_use_compact_terminal_nodes=true) |
void | delete_trees (bool p_use_compact_terminal_nodes=true) |
void | add_to_trie (int32_t i, int32_t seq_offset, int32_t *vec, float32_t alpha, float64_t *weights, bool degree_times_position_weights) |
float64_t | compute_abs_weights_tree (int32_t tree, int32_t depth) |
float64_t * | compute_abs_weights (int32_t &len) |
float64_t | compute_by_tree_helper (int32_t *vec, int32_t len, int32_t seq_pos, int32_t tree_pos, int32_t weight_pos, float64_t *weights, bool degree_times_position_weights) |
void | compute_by_tree_helper (int32_t *vec, int32_t len, int32_t seq_pos, int32_t tree_pos, int32_t weight_pos, float64_t *LevelContrib, float64_t factor, int32_t mkl_stepsize, float64_t *weights, bool degree_times_position_weights) |
void | compute_scoring_helper (int32_t tree, int32_t i, int32_t j, float64_t weight, int32_t d, int32_t max_degree, int32_t num_feat, int32_t num_sym, int32_t sym_offset, int32_t offs, float64_t *result) |
void | add_example_to_tree_mismatch_recursion (int32_t tree, int32_t i, float64_t alpha, int32_t *vec, int32_t len_rem, int32_t degree_rec, int32_t mismatch_rec, int32_t max_mismatch, float64_t *weights) |
void | traverse (int32_t tree, const int32_t p, struct TreeParseInfo info, const int32_t depth, int32_t *const x, const int32_t k) |
void | count (const float64_t w, const int32_t depth, const struct TreeParseInfo info, const int32_t p, int32_t *x, const int32_t k) |
int32_t | compact_nodes (int32_t start_node, int32_t depth, float64_t *weights) |
float64_t | get_cumulative_score (int32_t pos, uint64_t seq, int32_t deg, float64_t *weights) |
void | fill_backtracking_table_recursion (Trie *tree, int32_t depth, uint64_t seq, float64_t value, DynArray< ConsensusEntry > *table, float64_t *weights) |
void | fill_backtracking_table (int32_t pos, DynArray< ConsensusEntry > *prev, DynArray< ConsensusEntry > *cur, bool cumulative, float64_t *weights) |
void | POIMs_extract_W (float64_t *const *const W, const int32_t K) |
void | POIMs_precalc_SLR (const float64_t *const distrib) |
void | POIMs_get_SLR (const int32_t parentIdx, const int32_t sym, const int32_t depth, float64_t *S, float64_t *L, float64_t *R) |
void | POIMs_add_SLR (float64_t *const *const poims, const int32_t K, const int32_t debug) |
bool | get_use_compact_terminal_nodes () |
void | set_use_compact_terminal_nodes (bool p_use_compact_terminal_nodes) |
int32_t | get_num_used_nodes () |
void | set_position_weights (float64_t *p_position_weights) |
int32_t | get_node (bool last_node=false) |
void | check_treemem () |
void | set_weights_in_tree (bool weights_in_tree_) |
bool | get_weights_in_tree () |
void | POIMs_extract_W_helper (const int32_t nodeIdx, const int32_t depth, const int32_t offset, const int32_t y0, float64_t *const *const W, const int32_t K) |
void | POIMs_calc_SLR_helper1 (const float64_t *const distrib, const int32_t i, const int32_t nodeIdx, int32_t left_tries_idx[4], const int32_t depth, int32_t const lastSym, float64_t *S, float64_t *L, float64_t *R) |
void | POIMs_calc_SLR_helper2 (const float64_t *const distrib, const int32_t i, const int32_t nodeIdx, int32_t left_tries_idx[4], const int32_t depth, float64_t *S, float64_t *L, float64_t *R) |
void | POIMs_add_SLR_helper1 (const int32_t nodeIdx, const int32_t depth, const int32_t i, const int32_t y0, float64_t *const *const poims, const int32_t K, const int32_t debug) |
void | POIMs_add_SLR_helper2 (float64_t *const *const poims, const int32_t K, const int32_t k, const int32_t i, const int32_t y, const float64_t valW, const float64_t valS, const float64_t valL, const float64_t valR, const int32_t debug) |
virtual const char * | get_name () const |
template<> | |
void | POIMs_extract_W_helper (const int32_t nodeIdx, const int32_t depth, const int32_t offset, const int32_t y0, float64_t *const *const W, const int32_t K) |
template<> | |
void | POIMs_extract_W (float64_t *const *const W, const int32_t K) |
template<> | |
void | POIMs_calc_SLR_helper1 (const float64_t *const distrib, const int32_t i, const int32_t nodeIdx, int32_t left_tries_idx[4], const int32_t depth, int32_t const lastSym, float64_t *S, float64_t *L, float64_t *R) |
template<> | |
void | POIMs_calc_SLR_helper2 (const float64_t *const distrib, const int32_t i, const int32_t nodeIdx, int32_t left_tries_idx[4], const int32_t depth, float64_t *S, float64_t *L, float64_t *R) |
template<> | |
void | POIMs_precalc_SLR (const float64_t *const distrib) |
template<> | |
void | POIMs_get_SLR (const int32_t parentIdx, const int32_t sym, const int32_t depth, float64_t *S, float64_t *L, float64_t *R) |
template<> | |
void | POIMs_add_SLR_helper2 (float64_t *const *const poims, const int32_t K, const int32_t k, const int32_t i, const int32_t y, const float64_t valW, const float64_t valS, const float64_t valL, const float64_t valR, const int32_t debug) |
template<> | |
void | POIMs_add_SLR_helper1 (const int32_t nodeIdx, const int32_t depth, const int32_t i, const int32_t y0, float64_t *const *const poims, const int32_t K, const int32_t debug) |
template<> | |
void | POIMs_add_SLR (float64_t *const *const poims, const int32_t K, const int32_t debug) |
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 | |
int32_t | NUM_SYMS |
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 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 | length |
int32_t * | trees |
int32_t | degree |
float64_t * | position_weights |
Trie * | TreeMem |
int32_t | TreeMemPtr |
int32_t | TreeMemPtrMax |
bool | use_compact_terminal_nodes |
bool | weights_in_tree |
int32_t * | nofsKmers |
CTrie | ( | int32_t | d, |
bool | p_use_compact_terminal_nodes = true |
||
) |
|
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.
int32_t compact_nodes | ( | int32_t | start_node, |
int32_t | depth, | ||
float64_t * | weights | ||
) |
bool compare | ( | const CTrie< Trie > & | other | ) |
bool compare_traverse | ( | int32_t | node, |
const CTrie< Trie > & | other, | ||
int32_t | other_node | ||
) |
float64_t * compute_abs_weights | ( | int32_t & | len | ) |
float64_t compute_abs_weights_tree | ( | int32_t | tree, |
int32_t | depth | ||
) |
void compute_by_tree_helper | ( | int32_t * | vec, |
int32_t | len, | ||
int32_t | seq_pos, | ||
int32_t | tree_pos, | ||
int32_t | weight_pos, | ||
float64_t * | LevelContrib, | ||
float64_t | factor, | ||
int32_t | mkl_stepsize, | ||
float64_t * | weights, | ||
bool | degree_times_position_weights | ||
) |
compute by tree helper
vec | vector |
len | length |
seq_pos | sequence position |
tree_pos | tree position |
weight_pos | weight position |
LevelContrib | level contribution |
factor | factor |
mkl_stepsize | MKL stepsize |
weights | |
degree_times_position_weights | if degree times position weights shall be applied |
void count | ( | const float64_t | w, |
const int32_t | depth, | ||
const struct TreeParseInfo | info, | ||
const int32_t | p, | ||
int32_t * | x, | ||
const int32_t | k | ||
) |
void create | ( | int32_t | len, |
bool | p_use_compact_terminal_nodes = true |
||
) |
|
virtualinherited |
A deep copy. All the instance variables will also be copied.
Definition at line 131 of file SGObject.h.
void delete_trees | ( | bool | p_use_compact_terminal_nodes = true | ) |
void display_node | ( | int32_t | node | ) | const |
int32_t find_deepest_node | ( | int32_t | start_node, |
int32_t & | deepest_node | ||
) | const |
bool find_node | ( | int32_t | node, |
int32_t * | trace, | ||
int32_t & | trace_len | ||
) | const |
|
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 |
int32_t get_node | ( | bool | last_node = false | ) |
int32_t get_num_used_nodes | ( | ) |
bool get_use_compact_terminal_nodes | ( | ) |
bool get_weights_in_tree | ( | ) |
|
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 |
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 in CKernel, CWeightedDegreePositionStringKernel, CList, CAlphabet, CLinearHMM, CGaussianKernel, CANOVAKernel, CInverseMultiQuadricKernel, CCircularKernel, and CExponentialKernel.
Definition at line 1033 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 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.
void POIMs_add_SLR | ( | float64_t *const *const | poims, |
const int32_t | K, | ||
const int32_t | debug | ||
) |
void POIMs_add_SLR | ( | float64_t *const *const | poims, |
const int32_t | K, | ||
const int32_t | debug | ||
) |
POIMs add SLR
poims | POIMs |
K | K |
debug | debug level |
void POIMs_add_SLR_helper1 | ( | const int32_t | nodeIdx, |
const int32_t | depth, | ||
const int32_t | i, | ||
const int32_t | y0, | ||
float64_t *const *const | poims, | ||
const int32_t | K, | ||
const int32_t | debug | ||
) |
void POIMs_add_SLR_helper1 | ( | const int32_t | nodeIdx, |
const int32_t | depth, | ||
const int32_t | i, | ||
const int32_t | y0, | ||
float64_t *const *const | poims, | ||
const int32_t | K, | ||
const int32_t | debug | ||
) |
POIMs add SLR helper 1
nodeIdx | node index |
depth | depth |
i | i |
y0 | y0 |
poims | POIMs |
K | K |
debug | debug level |
void POIMs_add_SLR_helper2 | ( | float64_t *const *const | poims, |
const int32_t | K, | ||
const int32_t | k, | ||
const int32_t | i, | ||
const int32_t | y, | ||
const float64_t | valW, | ||
const float64_t | valS, | ||
const float64_t | valL, | ||
const float64_t | valR, | ||
const int32_t | debug | ||
) |
POIMs add SLR helper 2
poims | POIMs |
K | K |
k | k |
i | i |
y | y |
valW | value W |
valS | value S |
valL | value L |
valR | value R |
debug | debug level |
void POIMs_calc_SLR_helper1 | ( | const float64_t *const | distrib, |
const int32_t | i, | ||
const int32_t | nodeIdx, | ||
int32_t | left_tries_idx[4], | ||
const int32_t | depth, | ||
int32_t const | lastSym, | ||
float64_t * | S, | ||
float64_t * | L, | ||
float64_t * | R | ||
) |
POIMs calc SLR helper
distrib | distribution |
i | i |
nodeIdx | node index |
left_tries_idx | left tries index |
depth | depth |
lastSym | last symbol |
S | S |
L | L |
R | R |
void POIMs_calc_SLR_helper2 | ( | const float64_t *const | distrib, |
const int32_t | i, | ||
const int32_t | nodeIdx, | ||
int32_t | left_tries_idx[4], | ||
const int32_t | depth, | ||
float64_t * | S, | ||
float64_t * | L, | ||
float64_t * | R | ||
) |
POIMs calc SLR helper 2
distrib | distribution |
i | i |
nodeIdx | node index |
left_tries_idx | left tries index |
depth | depth |
S | S |
L | L |
R | R |
void POIMs_extract_W | ( | float64_t *const *const | W, |
const int32_t | K | ||
) |
void POIMs_extract_W | ( | float64_t *const *const | W, |
const int32_t | K | ||
) |
POIMs extract W
W | W |
K | K |
void POIMs_extract_W_helper | ( | const int32_t | nodeIdx, |
const int32_t | depth, | ||
const int32_t | offset, | ||
const int32_t | y0, | ||
float64_t *const *const | W, | ||
const int32_t | K | ||
) |
void POIMs_extract_W_helper | ( | const int32_t | nodeIdx, |
const int32_t | depth, | ||
const int32_t | offset, | ||
const int32_t | y0, | ||
float64_t *const *const | W, | ||
const int32_t | K | ||
) |
POIMs extract W helper
nodeIdx | node index |
depth | depth |
offset | offset |
y0 | y0 |
W | W |
K | K |
void POIMs_get_SLR | ( | const int32_t | parentIdx, |
const int32_t | sym, | ||
const int32_t | depth, | ||
float64_t * | S, | ||
float64_t * | L, | ||
float64_t * | R | ||
) |
POIMs get SLR
parentIdx | parent index |
sym | symbol |
depth | depth |
S | will point to S |
L | will point to L |
R | will point to R |
void POIMs_precalc_SLR | ( | const float64_t *const | distrib | ) |
POIMs precalc SLR
distrib | distribution |
|
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.
|
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 in CKernel.
Definition at line 1043 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 occurres. |
Reimplemented in CKernel.
Definition at line 1038 of file SGObject.cpp.
void set_degree | ( | int32_t | d | ) |
|
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.
void set_position_weights | ( | float64_t * | p_position_weights | ) |
void set_use_compact_terminal_nodes | ( | bool | p_use_compact_terminal_nodes | ) |
void set_weights_in_tree | ( | bool | weights_in_tree_ | ) |
|
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.
void traverse | ( | int32_t | tree, |
const int32_t | p, | ||
struct TreeParseInfo | info, | ||
const int32_t | depth, | ||
int32_t *const | x, | ||
const int32_t | k | ||
) |
|
inherited |
unset generic type
this has to be called in classes specializing a template class
Definition at line 285 of file SGObject.cpp.
|
protectedvirtualinherited |
Updates the hash of current parameter combination.
Definition at line 237 of file SGObject.cpp.
|
inherited |
io
Definition at line 462 of file SGObject.h.
|
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.
|
inherited |
parallel
Definition at line 465 of file SGObject.h.
|
protected |
|
inherited |
version
Definition at line 468 of file SGObject.h.