SHOGUN
v2.0.0
|
Class StreamingVwCacheFile to read vector-by-vector from VW cache files.
The cache file is usually generated either by VW or by enabling the cache writing option in a CStreamingVwFile object.
This class reads the example and label into one object of VwExample type.
Definition at line 30 of file StreamingVwCacheFile.h.
Public Member Functions | |
CStreamingVwCacheFile () | |
CStreamingVwCacheFile (EVwCacheType cache_type) | |
CStreamingVwCacheFile (char *fname, char rw='r', EVwCacheType cache_type=C_NATIVE) | |
virtual | ~CStreamingVwCacheFile () |
virtual void | get_vector (VwExample *&ex, int32_t &len) |
virtual void | get_vector_and_label (VwExample *&ex, int32_t &len, float64_t &label) |
virtual const char * | get_name () const |
void | set_env (CVwEnvironment *env_to_use) |
CVwEnvironment * | get_env () |
bool | is_seekable () |
void | reset_stream () |
void | close () |
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) |
Dense Vector Access Functions | |
Functions to access dense vectors of one of several base data types. These functions are used when reading one dense vector at a time from an input source and return the vector and length of the vector by reference. | |
virtual void | get_vector (bool *&vector, int32_t &len) |
virtual void | get_vector (uint8_t *&vector, int32_t &len) |
virtual void | get_vector (char *&vector, int32_t &len) |
virtual void | get_vector (int32_t *&vector, int32_t &len) |
virtual void | get_vector (float32_t *&vector, int32_t &len) |
virtual void | get_vector (float64_t *&vector, int32_t &len) |
virtual void | get_vector (int16_t *&vector, int32_t &len) |
virtual void | get_vector (uint16_t *&vector, int32_t &len) |
virtual void | get_vector (int8_t *&vector, int32_t &len) |
virtual void | get_vector (uint32_t *&vector, int32_t &len) |
virtual void | get_vector (int64_t *&vector, int32_t &len) |
virtual void | get_vector (uint64_t *&vector, int32_t &len) |
virtual void | get_vector (floatmax_t *&vector, int32_t &len) |
Dense Vector And Label Access Functions | |
Functions to access dense vectors of one of several base data types. These functions are used when reading one dense vector at a time from an input source and return the vector, length and label of the vector by reference. | |
virtual void | get_vector_and_label (bool *&vector, int32_t &len, float64_t &label) |
virtual void | get_vector_and_label (uint8_t *&vector, int32_t &len, float64_t &label) |
virtual void | get_vector_and_label (char *&vector, int32_t &len, float64_t &label) |
virtual void | get_vector_and_label (int32_t *&vector, int32_t &len, float64_t &label) |
virtual void | get_vector_and_label (float32_t *&vector, int32_t &len, float64_t &label) |
virtual void | get_vector_and_label (float64_t *&vector, int32_t &len, float64_t &label) |
virtual void | get_vector_and_label (int16_t *&vector, int32_t &len, float64_t &label) |
virtual void | get_vector_and_label (uint16_t *&vector, int32_t &len, float64_t &label) |
virtual void | get_vector_and_label (int8_t *&vector, int32_t &len, float64_t &label) |
virtual void | get_vector_and_label (uint32_t *&vector, int32_t &len, float64_t &label) |
virtual void | get_vector_and_label (int64_t *&vector, int32_t &len, float64_t &label) |
virtual void | get_vector_and_label (uint64_t *&vector, int32_t &len, float64_t &label) |
virtual void | get_vector_and_label (floatmax_t *&vector, int32_t &len, float64_t &label) |
String Access Functions | |
Functions to access string of one of several base data types. These functions are used when reading one string vector at a time from an input source and return the vector and length of the vector by reference. | |
virtual void | get_string (bool *&vector, int32_t &len) |
virtual void | get_string (uint8_t *&vector, int32_t &len) |
virtual void | get_string (char *&vector, int32_t &len) |
virtual void | get_string (int32_t *&vector, int32_t &len) |
virtual void | get_string (float32_t *&vector, int32_t &len) |
virtual void | get_string (float64_t *&vector, int32_t &len) |
virtual void | get_string (int16_t *&vector, int32_t &len) |
virtual void | get_string (uint16_t *&vector, int32_t &len) |
virtual void | get_string (int8_t *&vector, int32_t &len) |
virtual void | get_string (uint32_t *&vector, int32_t &len) |
virtual void | get_string (int64_t *&vector, int32_t &len) |
virtual void | get_string (uint64_t *&vector, int32_t &len) |
virtual void | get_string (floatmax_t *&vector, int32_t &len) |
String And Label Access Functions | |
Functions to access strings of one of several base data types. These functions are used when reading one string vector at a time from an input source and return the vector, length and label of the vector by reference. | |
virtual void | get_string_and_label (bool *&vector, int32_t &len, float64_t &label) |
virtual void | get_string_and_label (uint8_t *&vector, int32_t &len, float64_t &label) |
virtual void | get_string_and_label (char *&vector, int32_t &len, float64_t &label) |
virtual void | get_string_and_label (int32_t *&vector, int32_t &len, float64_t &label) |
virtual void | get_string_and_label (float32_t *&vector, int32_t &len, float64_t &label) |
virtual void | get_string_and_label (float64_t *&vector, int32_t &len, float64_t &label) |
virtual void | get_string_and_label (int16_t *&vector, int32_t &len, float64_t &label) |
virtual void | get_string_and_label (uint16_t *&vector, int32_t &len, float64_t &label) |
virtual void | get_string_and_label (int8_t *&vector, int32_t &len, float64_t &label) |
virtual void | get_string_and_label (uint32_t *&vector, int32_t &len, float64_t &label) |
virtual void | get_string_and_label (int64_t *&vector, int32_t &len, float64_t &label) |
virtual void | get_string_and_label (uint64_t *&vector, int32_t &len, float64_t &label) |
virtual void | get_string_and_label (floatmax_t *&vector, int32_t &len, float64_t &label) |
Sparse Vector Access Functions | |
Functions to access sparse vectors of one of several base data types. These functions are used when reading one sparse vector at a time from an input source and return the vector and length of the vector by reference. | |
virtual void | get_sparse_vector (SGSparseVectorEntry< bool > *&vector, int32_t &len) |
virtual void | get_sparse_vector (SGSparseVectorEntry< uint8_t > *&vector, int32_t &len) |
virtual void | get_sparse_vector (SGSparseVectorEntry< char > *&vector, int32_t &len) |
virtual void | get_sparse_vector (SGSparseVectorEntry< int32_t > *&vector, int32_t &len) |
virtual void | get_sparse_vector (SGSparseVectorEntry< float32_t > *&vector, int32_t &len) |
virtual void | get_sparse_vector (SGSparseVectorEntry< float64_t > *&vector, int32_t &len) |
virtual void | get_sparse_vector (SGSparseVectorEntry< int16_t > *&vector, int32_t &len) |
virtual void | get_sparse_vector (SGSparseVectorEntry< uint16_t > *&vector, int32_t &len) |
virtual void | get_sparse_vector (SGSparseVectorEntry< int8_t > *&vector, int32_t &len) |
virtual void | get_sparse_vector (SGSparseVectorEntry< uint32_t > *&vector, int32_t &len) |
virtual void | get_sparse_vector (SGSparseVectorEntry< int64_t > *&vector, int32_t &len) |
virtual void | get_sparse_vector (SGSparseVectorEntry< uint64_t > *&vector, int32_t &len) |
virtual void | get_sparse_vector (SGSparseVectorEntry< floatmax_t > *&vector, int32_t &len) |
Sparse Vector And Label Access Functions | |
Functions to access sparse vectors of one of several base data types. These functions are used when reading one sparse vector at a time from an input source and return the vector, length and label of the vector by reference. | |
virtual void | get_sparse_vector_and_label (SGSparseVectorEntry< bool > *&vector, int32_t &len, float64_t &label) |
virtual void | get_sparse_vector_and_label (SGSparseVectorEntry< uint8_t > *&vector, int32_t &len, float64_t &label) |
virtual void | get_sparse_vector_and_label (SGSparseVectorEntry< char > *&vector, int32_t &len, float64_t &label) |
virtual void | get_sparse_vector_and_label (SGSparseVectorEntry< int32_t > *&vector, int32_t &len, float64_t &label) |
virtual void | get_sparse_vector_and_label (SGSparseVectorEntry< float32_t > *&vector, int32_t &len, float64_t &label) |
virtual void | get_sparse_vector_and_label (SGSparseVectorEntry< float64_t > *&vector, int32_t &len, float64_t &label) |
virtual void | get_sparse_vector_and_label (SGSparseVectorEntry< int16_t > *&vector, int32_t &len, float64_t &label) |
virtual void | get_sparse_vector_and_label (SGSparseVectorEntry< uint16_t > *&vector, int32_t &len, float64_t &label) |
virtual void | get_sparse_vector_and_label (SGSparseVectorEntry< int8_t > *&vector, int32_t &len, float64_t &label) |
virtual void | get_sparse_vector_and_label (SGSparseVectorEntry< uint32_t > *&vector, int32_t &len, float64_t &label) |
virtual void | get_sparse_vector_and_label (SGSparseVectorEntry< int64_t > *&vector, int32_t &len, float64_t &label) |
virtual void | get_sparse_vector_and_label (SGSparseVectorEntry< uint64_t > *&vector, int32_t &len, float64_t &label) |
virtual void | get_sparse_vector_and_label (SGSparseVectorEntry< floatmax_t > *&vector, int32_t &len, float64_t &label) |
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 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 | |
CVwCacheReader * | cache_reader |
Cache reader. | |
CVwEnvironment * | env |
Environment used for vw. | |
EVwCacheType | cache_format |
Cache type. | |
CIOBuffer * | buf |
Buffer to hold stuff in memory. | |
char | task |
Task. | |
char * | filename |
Name of the handled file. |
Default constructor. Assumes cache file is of type C_NATIVE
Definition at line 14 of file StreamingVwCacheFile.cpp.
CStreamingVwCacheFile | ( | EVwCacheType | cache_type | ) |
Constructor taking cache type as an argument.
cache_type | cache type - C_NATIVE or C_PROTOBUF |
Definition at line 20 of file StreamingVwCacheFile.cpp.
CStreamingVwCacheFile | ( | char * | fname, |
char | rw = 'r' , |
||
EVwCacheType | cache_type = C_NATIVE |
||
) |
Constructor taking file name and cache type as arguments
fname | file name |
rw | read/write mode |
cache_type | type of cache - C_NATIVE or C_PROTOBUF |
Definition at line 26 of file StreamingVwCacheFile.cpp.
|
virtual |
Destructor
Definition at line 32 of file StreamingVwCacheFile.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 |
Closes the file
Definition at line 58 of file StreamingFile.h.
|
virtualinherited |
A deep copy. All the instance variables will also be copied.
Definition at line 131 of file SGObject.h.
CVwEnvironment* get_env | ( | ) |
Return the environment
Definition at line 102 of file StreamingVwCacheFile.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 |
Reimplemented from CStreamingFile.
Definition at line 85 of file StreamingVwCacheFile.h.
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtual |
Returns the parsed example.
The example contains the label if available, and also contains length of the feature vector. These parameters, passed separately are redundant.
ex | examples as VwExample*, set by reference |
len | length of vector, untouched |
Reimplemented from CStreamingFile.
Definition at line 38 of file StreamingVwCacheFile.cpp.
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
Returns the parsed example.
TODO: Make this fail if examples are found to be unlabelled.
ex | example as VwExample*, set by reference |
len | length of vector, untouched |
label | label, untouched |
Reimplemented from CStreamingFile.
Definition at line 46 of file StreamingVwCacheFile.cpp.
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
virtualinherited |
|
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.
|
virtual |
Whether this stream is seekable
Reimplemented from CStreamingFile.
Definition at line 113 of file StreamingVwCacheFile.h.
|
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.
|
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.
|
virtual |
Reset cache file back to first example.
Used when multiple passes are to be performed
Reimplemented from CStreamingFile.
Definition at line 76 of file StreamingVwCacheFile.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_env | ( | CVwEnvironment * | env_to_use | ) |
Set environment for vw
env_to_use | CVwEnvironment* environment |
Definition at line 54 of file StreamingVwCacheFile.cpp.
|
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.
|
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.
|
protectedvirtualinherited |
Updates the hash of current parameter combination.
Definition at line 237 of file SGObject.cpp.
|
protectedinherited |
Buffer to hold stuff in memory.
Definition at line 295 of file StreamingFile.h.
|
protected |
Cache type.
Definition at line 138 of file StreamingVwCacheFile.h.
|
protected |
Cache reader.
Definition at line 132 of file StreamingVwCacheFile.h.
|
protected |
Environment used for vw.
Definition at line 135 of file StreamingVwCacheFile.h.
|
protectedinherited |
Name of the handled file.
Definition at line 299 of file StreamingFile.h.
|
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.
|
protectedinherited |
Task.
Definition at line 297 of file StreamingFile.h.
|
inherited |
version
Definition at line 468 of file SGObject.h.