SHOGUN
4.1.0
|
Dynamic Programming Class.
Structure and Function collection. This Class implements a Dynamic Programming functions.
Public Member Functions | |
CDynProg (int32_t p_num_svms=8) | |
virtual | ~CDynProg () |
void | set_num_states (int32_t N) |
int32_t | get_num_states () |
int32_t | get_num_svms () |
void | init_content_svm_value_array (const int32_t p_num_svms) |
void | init_tiling_data (int32_t *probe_pos, float64_t *intensities, const int32_t num_probes) |
void | precompute_tiling_plifs (CPlif **PEN, const int32_t *tiling_plif_ids, const int32_t num_tiling_plifs) |
void | resize_lin_feat (int32_t num_new_feat) |
void | set_p_vector (SGVector< float64_t > p) |
void | set_q_vector (SGVector< float64_t > q) |
void | set_a (SGMatrix< float64_t > a) |
void | set_a_id (SGMatrix< int32_t > a) |
void | set_a_trans_matrix (SGMatrix< float64_t > a_trans) |
void | init_mod_words_array (SGMatrix< int32_t > p_mod_words_array) |
bool | check_svm_arrays () |
void | set_observation_matrix (SGNDArray< float64_t > seq) |
int32_t | get_num_positions () |
void | set_content_type_array (SGMatrix< float64_t > seg_path) |
void | set_pos (SGVector< int32_t > pos) |
void | set_orf_info (SGMatrix< int32_t > orf_info) |
void | set_gene_string (SGVector< char > genestr) |
void | set_dict_weights (SGMatrix< float64_t > dictionary_weights) |
void | best_path_set_segment_loss (SGMatrix< float64_t > segment_loss) |
void | best_path_set_segment_ids_mask (int32_t *segment_ids, float64_t *segment_mask, int32_t m) |
void | set_sparse_features (CSparseFeatures< float64_t > *seq_sparse1, CSparseFeatures< float64_t > *seq_sparse2) |
void | set_plif_matrices (CPlifMatrix *pm) |
SGVector< float64_t > | get_scores () |
SGMatrix< int32_t > | get_states () |
SGMatrix< int32_t > | get_positions () |
void | compute_nbest_paths (int32_t max_num_signals, bool use_orf, int16_t nbest, bool with_loss, bool with_multiple_sequences) |
void | best_path_trans_deriv (int32_t *my_state_seq, int32_t *my_pos_seq, int32_t my_seq_len, const float64_t *seq_array, int32_t max_num_signals) |
void | set_my_state_seq (int32_t *my_state_seq) |
void | set_my_pos_seq (int32_t *my_pos_seq) |
void | get_path_scores (float64_t **my_scores, int32_t *seq_len) |
void | get_path_losses (float64_t **my_losses, int32_t *seq_len) |
T_STATES | get_N () const |
access function for number of states N More... | |
void | set_q (T_STATES offset, float64_t value) |
void | set_p (T_STATES offset, float64_t value) |
void | set_a (T_STATES line_, T_STATES column, float64_t value) |
float64_t | get_q (T_STATES offset) const |
float64_t | get_q_deriv (T_STATES offset) const |
float64_t | get_p (T_STATES offset) const |
float64_t | get_p_deriv (T_STATES offset) const |
void | precompute_content_values () |
float64_t * | get_lin_feat (int32_t &dim1, int32_t &dim2) |
void | set_lin_feat (float64_t *p_lin_feat, int32_t p_num_svms, int32_t p_seq_len) |
void | create_word_string () |
void | precompute_stop_codons () |
float64_t | get_a (T_STATES line_, T_STATES column) const |
float64_t | get_a_deriv (T_STATES line_, T_STATES column) const |
void | set_intron_list (CIntronList *intron_list, int32_t num_plifs) |
CSegmentLoss * | get_segment_loss_object () |
void | long_transition_settings (bool use_long_transitions, int32_t threshold, int32_t max_len) |
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 | |
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 | |
void | lookup_content_svm_values (const int32_t from_state, const int32_t to_state, const int32_t from_pos, const int32_t to_pos, float64_t *svm_values, int32_t frame) |
void | lookup_tiling_plif_values (const int32_t from_state, const int32_t to_state, const int32_t len, float64_t *svm_values) |
int32_t | find_frame (const int32_t from_state) |
int32_t | raw_intensities_interval_query (const int32_t from_pos, const int32_t to_pos, float64_t *intensities, int32_t type) |
bool | extend_orf (int32_t orf_from, int32_t orf_to, int32_t start, int32_t &last_pos, int32_t to) |
virtual const char * | get_name () const |
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) |
Static Protected Attributes | |
static int32_t | word_degree_default [4] ={3,4,5,6} |
static int32_t | cum_num_words_default [5] ={0,64,320,1344,5440} |
static int32_t | frame_plifs [3] ={4,5,6} |
static int32_t | num_words_default [4] = {64,256,1024,4096} |
static int32_t | mod_words_default [32] |
static bool | sign_words_default [16] |
static int32_t | string_words_default [16] |
CDynProg | ( | int32_t | p_num_svms = 8 | ) |
|
virtual |
Definition at line 142 of file DynProg.cpp.
void best_path_set_segment_ids_mask | ( | int32_t * | segment_ids, |
float64_t * | segment_mask, | ||
int32_t | m | ||
) |
set best path segmend ids mask
segment_ids | segment ids |
segment_mask | segment mask |
m | dimension m |
Definition at line 815 of file DynProg.cpp.
set best path segment loss
segment_loss | segment loss |
Definition at line 798 of file DynProg.cpp.
void best_path_trans_deriv | ( | int32_t * | my_state_seq, |
int32_t * | my_pos_seq, | ||
int32_t | my_seq_len, | ||
const float64_t * | seq_array, | ||
int32_t | max_num_signals | ||
) |
given a path though the state model and the corresponding positions compute the features. This can be seen as the derivative of the score (output of dynamic program) with respect to the parameters
my_state_seq | state sequence of the path |
my_pos_seq | sequence of positions |
my_seq_len | length of state and position sequences |
seq_array | array of features |
max_num_signals | maximal number of signals |
Definition at line 2052 of file DynProg.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 597 of file SGObject.cpp.
bool check_svm_arrays | ( | ) |
check SVM arrays call this function to check consistency
Definition at line 601 of file DynProg.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.
void compute_nbest_paths | ( | int32_t | max_num_signals, |
bool | use_orf, | ||
int16_t | nbest, | ||
bool | with_loss, | ||
bool | with_multiple_sequences | ||
) |
run the viterbi algorithm to compute the n best viterbi paths
max_num_signals | maximal number of signals for a single state |
use_orf | whether orf shall be used |
nbest | number of best paths (n) |
with_loss | use loss |
with_multiple_sequences | !!!not functional set to false!!! |
Definition at line 944 of file DynProg.cpp.
void create_word_string | ( | ) |
create word string from char* Jonas
Definition at line 361 of file DynProg.cpp.
|
virtualinherited |
A deep copy. All the instance variables will also be copied.
Definition at line 198 of file SGObject.cpp.
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.
|
protected |
extend orf
orf_from | orf from |
orf_to | orf to |
start | start |
last_pos | last position |
to | to |
Definition at line 893 of file DynProg.cpp.
|
protected |
find frame
from_state | from state |
|
inherited |
|
inherited |
|
inherited |
float64_t* get_lin_feat | ( | int32_t & | dim1, |
int32_t & | dim2 | ||
) |
|
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.
T_STATES get_N | ( | ) | const |
|
protectedvirtual |
int32_t get_num_positions | ( | ) |
get number of positions; the dynamic program is sparse encoded and this function gives the number of positions that can actually be part of a predicted path
Definition at line 679 of file DynProg.cpp.
int32_t get_num_states | ( | ) |
get num states
Definition at line 234 of file DynProg.cpp.
int32_t get_num_svms | ( | ) |
get num svms
Definition at line 191 of file DynProg.cpp.
void get_path_losses | ( | float64_t ** | my_losses, |
int32_t * | seq_len | ||
) |
get path losses
best_path_trans_deriv result retrieval functions
my_losses | my losses |
seq_len | length of sequence |
Definition at line 877 of file DynProg.cpp.
void get_path_scores | ( | float64_t ** | my_scores, |
int32_t * | seq_len | ||
) |
get path scores
best_path_trans_deriv result retrieval functions
my_scores | scores |
seq_len | length of sequence |
Definition at line 863 of file DynProg.cpp.
SGMatrix< int32_t > get_positions | ( | ) |
CSegmentLoss* get_segment_loss_object | ( | ) |
SGMatrix< int32_t > get_states | ( | ) |
void init_content_svm_value_array | ( | const int32_t | p_num_svms | ) |
init CDynamicArray for precomputed content svm values with size seq_len x num_svms
p_num_svms | number of svm weight vectors for content prediction |
Definition at line 269 of file DynProg.cpp.
void init_mod_words_array | ( | SGMatrix< int32_t > | p_mod_words_array | ) |
init mod words array
p_mod_words_array | new mod words array |
Definition at line 579 of file DynProg.cpp.
void init_tiling_data | ( | int32_t * | probe_pos, |
float64_t * | intensities, | ||
const int32_t | num_probes | ||
) |
init CDynamicArray for precomputed tiling intensitie-plif-values with size seq_len x num_svms
probe_pos | local positions of probes |
intensities | intensities of probes |
num_probes | number of probes |
Definition at line 239 of file DynProg.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 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.
void long_transition_settings | ( | bool | use_long_transitions, |
int32_t | threshold, | ||
int32_t | max_len | ||
) |
|
protected |
lookup content SVM values
from_state | from state |
to_state | to state |
from_pos | from position |
to_pos | to position |
svm_values | SVM values |
frame | frame |
Definition at line 2482 of file DynProg.cpp.
|
protected |
lookup tiling Plif values
from_state | from state |
to_state | to state |
len | length |
svm_values | SVM values |
|
virtualinherited |
Definition at line 262 of file SGObject.cpp.
void precompute_content_values | ( | ) |
create array of precomputed content svm values
Definition at line 392 of file DynProg.cpp.
void precompute_stop_codons | ( | ) |
precompute stop codons
Definition at line 196 of file DynProg.cpp.
void precompute_tiling_plifs | ( | CPlif ** | PEN, |
const int32_t * | tiling_plif_ids, | ||
const int32_t | num_tiling_plifs | ||
) |
precompute tiling Plifs
PEN | Plif PEN |
tiling_plif_ids | tiling plif id's |
num_tiling_plifs | number of tiling plifs |
Definition at line 312 of file DynProg.cpp.
|
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.
|
protected |
raw intensities interval query
from_pos | from position |
to_pos | to position |
intensities | intensities |
type | type |
Definition at line 2456 of file DynProg.cpp.
void resize_lin_feat | ( | int32_t | num_new_feat | ) |
append rows to linear features array
num_new_feat | number of new rows to add |
Definition at line 279 of file DynProg.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_a_id | ( | SGMatrix< int32_t > | a | ) |
set a transition matrix
a_trans | transition matrix a |
Definition at line 478 of file DynProg.cpp.
set an array of length #(candidate positions) which specifies the content type of each pos and a mask that determines to which extend the loss should be applied to this position; this is a way to encode label confidence via weights between zero and one
seg_path | seg path |
Definition at line 684 of file DynProg.cpp.
set best path dict weights
dictionary_weights | dictionary weights |
Definition at line 779 of file DynProg.cpp.
void set_gene_string | ( | SGVector< char > | genestr | ) |
|
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_intron_list | ( | CIntronList * | intron_list, |
int32_t | num_plifs | ||
) |
set intron list
intron_list | |
num_plifs | number of intron plifs |
Definition at line 2535 of file DynProg.cpp.
void set_lin_feat | ( | float64_t * | p_lin_feat, |
int32_t | p_num_svms, | ||
int32_t | p_seq_len | ||
) |
void set_my_pos_seq | ( | int32_t * | my_pos_seq | ) |
set best path my position sequence
my_pos_seq | my position sequence |
Definition at line 771 of file DynProg.cpp.
void set_my_state_seq | ( | int32_t * | my_state_seq | ) |
set best path my state sequence
my_state_seq | my state sequence |
Definition at line 763 of file DynProg.cpp.
void set_num_states | ( | int32_t | N | ) |
set number of states use this to set N first
N | new N |
Definition at line 219 of file DynProg.cpp.
void set_orf_info | ( | SGMatrix< int32_t > | orf_info | ) |
set best path orf info only for compute_nbest_paths
orf_info | the orf info |
Definition at line 723 of file DynProg.cpp.
void set_plif_matrices | ( | CPlifMatrix * | pm | ) |
void set_pos | ( | SGVector< int32_t > | pos | ) |
void set_sparse_features | ( | CSparseFeatures< float64_t > * | seq_sparse1, |
CSparseFeatures< float64_t > * | seq_sparse2 | ||
) |
set sparse feature matrices
Definition at line 732 of file DynProg.cpp.
|
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.
|
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.
|
staticprotected |
|
staticprotected |
|
inherited |
io
Definition at line 369 of file SGObject.h.
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
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.
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
inherited |
model selection parameters
Definition at line 381 of file SGObject.h.
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
inherited |
parameters
Definition at line 378 of file SGObject.h.
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
wordstr is a vector of L n-gram indices, with wordstr(i) representing a number betweeen 0 and 4095 corresponding to the 6-mer in genestr(i-5:i) pos is a vector of candidate transition positions (it is input to compute_nbest_paths) t_end is some index in pos
svs has been initialized by init_svm_values
At the end of this procedure, svs.svm_values[i+s*svs.seqlen] has the value of the s-th SVM on genestr(pos(t_end-i):pos(t_end)) for every i satisfying pos(t_end)-pos(t_end-i) <= svs.maxlookback
The SVM weights are precomputed in m_dict_weights
|
staticprotected |
|
staticprotected |
|
inherited |
parallel
Definition at line 372 of file SGObject.h.
|
staticprotected |
|
staticprotected |
|
inherited |
version
Definition at line 375 of file SGObject.h.
|
staticprotected |