SHOGUN
4.1.0
|
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 \(\Phi(x)\) 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 () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
void | unset_generic () |
virtual void | print_serializable (const char *prefix="") |
virtual bool | save_serializable (CSerializableFile *file, const char *prefix="") |
virtual bool | load_serializable (CSerializableFile *file, const char *prefix="") |
void | set_global_io (SGIO *io) |
SGIO * | get_global_io () |
void | set_global_parallel (Parallel *parallel) |
Parallel * | get_global_parallel () |
void | set_global_version (Version *version) |
Version * | get_global_version () |
SGStringList< char > | get_modelsel_names () |
void | print_modsel_params () |
char * | get_modsel_param_descr (const char *param_name) |
index_t | get_modsel_param_index (const char *param_name) |
void | build_gradient_parameter_dictionary (CMap< TParameter *, CSGObject * > *dict) |
virtual void | update_parameter_hash () |
virtual bool | parameter_hash_changed () |
virtual bool | equals (CSGObject *other, float64_t accuracy=0.0, bool tolerant=false) |
virtual CSGObject * | clone () |
Public Attributes | |
int32_t | NUM_SYMS |
SGIO * | io |
Parallel * | parallel |
Version * | version |
Parameter * | m_parameters |
Parameter * | m_model_selection_parameters |
Parameter * | m_gradient_parameters |
uint32_t | m_hash |
Protected Member Functions | |
virtual void | load_serializable_pre () throw (ShogunException) |
virtual void | load_serializable_post () throw (ShogunException) |
virtual void | save_serializable_pre () throw (ShogunException) |
virtual void | save_serializable_post () throw (ShogunException) |
Protected Attributes | |
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 597 of file SGObject.cpp.
|
virtualinherited |
Creates a clone of the current object. This is done via recursively traversing all parameters, which corresponds to a deep copy. Calling equals on the cloned object always returns true although none of the memory of both objects overlaps.
Definition at line 714 of file SGObject.cpp.
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 198 of file SGObject.cpp.
void delete_trees | ( | bool | p_use_compact_terminal_nodes = true | ) |
void display_node | ( | int32_t | node | ) | const |
Recursively compares the current SGObject to another one. Compares all registered numerical parameters, recursion upon complex (SGObject) parameters. Does not compare pointers!
May be overwritten but please do with care! Should not be necessary in most cases.
other | object to compare with |
accuracy | accuracy to use for comparison (optional) |
tolerant | allows linient check on float equality (within accuracy) |
Definition at line 618 of file SGObject.cpp.
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 498 of file SGObject.cpp.
|
inherited |
Returns description of a given parameter string, if it exists. SG_ERROR otherwise
param_name | name of the parameter |
Definition at line 522 of file SGObject.cpp.
|
inherited |
Returns index of model selection parameter with provided index
param_name | name of model selection parameter |
Definition at line 535 of file SGObject.cpp.
|
virtual |
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 296 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 |
Definition at line 369 of file SGObject.cpp.
|
protectedvirtualinherited |
Can (optionally) be overridden to post-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::LOAD_SERIALIZABLE_POST is called.
ShogunException | will be thrown if an error occurs. |
Reimplemented in CKernel, CWeightedDegreePositionStringKernel, CList, CAlphabet, CLinearHMM, CGaussianKernel, CInverseMultiQuadricKernel, CCircularKernel, and CExponentialKernel.
Definition at line 426 of file SGObject.cpp.
|
protectedvirtualinherited |
Can (optionally) be overridden to pre-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::LOAD_SERIALIZABLE_PRE is called.
ShogunException | will be thrown if an error occurs. |
Reimplemented in CDynamicArray< T >, CDynamicArray< float64_t >, CDynamicArray< float32_t >, CDynamicArray< int32_t >, CDynamicArray< char >, CDynamicArray< bool >, and CDynamicObjectArray.
Definition at line 421 of file SGObject.cpp.
|
virtualinherited |
Definition at line 262 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 474 of file SGObject.cpp.
|
virtualinherited |
prints registered parameters out
prefix | prefix for members |
Definition at line 308 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 |
Definition at line 314 of file SGObject.cpp.
|
protectedvirtualinherited |
Can (optionally) be overridden to post-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::SAVE_SERIALIZABLE_POST is called.
ShogunException | will be thrown if an error occurs. |
Reimplemented in CKernel.
Definition at line 436 of file SGObject.cpp.
|
protectedvirtualinherited |
Can (optionally) be overridden to pre-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::SAVE_SERIALIZABLE_PRE is called.
ShogunException | will be thrown if an error occurs. |
Reimplemented in CKernel, CDynamicArray< T >, CDynamicArray< float64_t >, CDynamicArray< float32_t >, CDynamicArray< int32_t >, CDynamicArray< char >, CDynamicArray< bool >, and CDynamicObjectArray.
Definition at line 431 of file SGObject.cpp.
void set_degree | ( | int32_t | d | ) |
|
inherited |
Definition at line 41 of file SGObject.cpp.
|
inherited |
Definition at line 46 of file SGObject.cpp.
|
inherited |
Definition at line 51 of file SGObject.cpp.
|
inherited |
Definition at line 56 of file SGObject.cpp.
|
inherited |
Definition at line 61 of file SGObject.cpp.
|
inherited |
Definition at line 66 of file SGObject.cpp.
|
inherited |
Definition at line 71 of file SGObject.cpp.
|
inherited |
Definition at line 76 of file SGObject.cpp.
|
inherited |
Definition at line 81 of file SGObject.cpp.
|
inherited |
Definition at line 86 of file SGObject.cpp.
|
inherited |
Definition at line 91 of file SGObject.cpp.
|
inherited |
Definition at line 96 of file SGObject.cpp.
|
inherited |
Definition at line 101 of file SGObject.cpp.
|
inherited |
Definition at line 106 of file SGObject.cpp.
|
inherited |
Definition at line 111 of file SGObject.cpp.
|
inherited |
set generic type to T
|
inherited |
|
inherited |
set the parallel object
parallel | parallel object to use |
Definition at line 241 of file SGObject.cpp.
|
inherited |
set the version object
version | version object to use |
Definition at line 283 of file SGObject.cpp.
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 192 of file SGObject.cpp.
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 303 of file SGObject.cpp.
|
virtualinherited |
Updates the hash of current parameter combination
Definition at line 248 of file SGObject.cpp.
|
inherited |
io
Definition at line 369 of file SGObject.h.
|
inherited |
parameters wrt which we can compute gradients
Definition at line 384 of file SGObject.h.
|
inherited |
Hash of parameter values
Definition at line 387 of file SGObject.h.
|
inherited |
model selection parameters
Definition at line 381 of file SGObject.h.
|
inherited |
parameters
Definition at line 378 of file SGObject.h.
|
inherited |
parallel
Definition at line 372 of file SGObject.h.
|
protected |
|
inherited |
version
Definition at line 375 of file SGObject.h.