SHOGUN
6.0.0
|
Class TwoDistributionTest is the base class for the statistical hypothesis testing with samples from two distributions, \(mathbf{P}\) and \(\mathbf{Q}\).
Definition at line 50 of file TwoDistributionTest.h.
Public Member Functions | |
CTwoDistributionTest () | |
virtual | ~CTwoDistributionTest () |
virtual void | set_p (CFeatures *samples_from_p) |
CFeatures * | get_p () const |
virtual void | set_q (CFeatures *samples_from_q) |
CFeatures * | get_q () const |
void | set_num_samples_p (index_t num_samples_from_p) |
const index_t | get_num_samples_p () const |
void | set_num_samples_q (index_t num_samples_from_q) |
const index_t | get_num_samples_q () const |
CCustomDistance * | compute_distance (CDistance *distance) |
CCustomDistance * | compute_joint_distance (CDistance *distance) |
virtual float64_t | compute_statistic ()=0 |
virtual SGVector< float64_t > | sample_null ()=0 |
virtual const char * | get_name () const |
void | set_train_test_mode (bool on) |
void | set_train_test_ratio (float64_t ratio) |
virtual float64_t | compute_p_value (float64_t statistic) |
virtual float64_t | compute_threshold (float64_t alpha) |
bool | perform_test (float64_t alpha) |
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) |
bool | has (const std::string &name) const |
template<typename T > | |
bool | has (const Tag< T > &tag) const |
template<typename T , typename U = void> | |
bool | has (const std::string &name) const |
template<typename T > | |
void | set (const Tag< T > &_tag, const T &value) |
template<typename T , typename U = void> | |
void | set (const std::string &name, const T &value) |
template<typename T > | |
T | get (const Tag< T > &_tag) const |
template<typename T , typename U = void> | |
T | get (const std::string &name) const |
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 | |
internal::DataManager & | get_data_mgr () |
const internal::DataManager & | get_data_mgr () 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) |
template<typename T > | |
void | register_param (Tag< T > &_tag, const T &value) |
template<typename T > | |
void | register_param (const std::string &name, const T &value) |
bool | clone_parameters (CSGObject *other) |
Default constructor
Definition at line 41 of file TwoDistributionTest.cpp.
|
virtual |
Destrutor
Definition at line 45 of file TwoDistributionTest.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 630 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.
Reimplemented in CDynamicArray< T >, CDynamicArray< float64_t >, CDynamicArray< float32_t >, CDynamicArray< int32_t >, CDynamicArray< char >, CDynamicArray< bool >, CDynamicObjectArray, CAlphabet, and CMKL.
Definition at line 729 of file SGObject.cpp.
|
protectedinherited |
Definition at line 754 of file SGObject.cpp.
CCustomDistance * compute_distance | ( | CDistance * | distance | ) |
Method that pre-computes the pair-wise distance between the samples using the provided distance instance.
distance | The distance instance used for pre-computing the pair-wise distance. |
Definition at line 99 of file TwoDistributionTest.cpp.
CCustomDistance * compute_joint_distance | ( | CDistance * | distance | ) |
Method that pre-computes the pair-wise distance between the joint samples using the provided distance instance. A temporary object appending the samples from both the distributions is created in order to perform the task.
distance | The distance instance used for pre-computing the pair-wise distance. |
Definition at line 128 of file TwoDistributionTest.cpp.
Method that computes a p-value based on current method for approximating the null-distribution. The p-value is the 1-p quantile of the null- distribution where the given statistic lies in.
This method depends on the implementation of sample_null method which should be implemented by the sub-classes.
statistic | statistic value to compute the p-value for |
Reimplemented in CQuadraticTimeMMD, CBTestMMD, and CLinearTimeMMD.
Definition at line 77 of file HypothesisTest.cpp.
|
pure virtual |
Interface for computing the test-statistic for the hypothesis test.
Implements CHypothesisTest.
Implemented in CMMD, CQuadraticTimeMMD, CIndependenceTest, CTwoSampleTest, and CStreamingMMD.
Method that computes a threshold based on current method for approximating the null-distribution. The threshold is the value that a statistic has to have in ordner to reject the null-hypothesis.
This method depends on the implementation of sample_null method which should be implemented by the sub-classes.
alpha | test level to reject null-hypothesis |
Reimplemented in CQuadraticTimeMMD, CBTestMMD, and CLinearTimeMMD.
Definition at line 85 of file HypothesisTest.cpp.
|
virtualinherited |
A deep copy. All the instance variables will also be copied.
Definition at line 231 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 651 of file SGObject.cpp.
|
inherited |
Getter for a class parameter, identified by a Tag. Throws an exception if the class does not have such a parameter.
_tag | name and type information of parameter |
Definition at line 376 of file SGObject.h.
|
inherited |
Getter for a class parameter, identified by a name. Throws an exception if the class does not have such a parameter.
name | name of the parameter |
Definition at line 399 of file SGObject.h.
|
protectedinherited |
Definition at line 104 of file HypothesisTest.cpp.
|
protectedinherited |
Definition at line 109 of file HypothesisTest.cpp.
|
inherited |
|
inherited |
|
inherited |
|
inherited |
Definition at line 531 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 555 of file SGObject.cpp.
|
inherited |
Returns index of model selection parameter with provided index
param_name | name of model selection parameter |
Definition at line 568 of file SGObject.cpp.
|
virtual |
Reimplemented from CHypothesisTest.
Reimplemented in CQuadraticTimeMMD, CMMD, CIndependenceTest, CTwoSampleTest, CStreamingMMD, CBTestMMD, and CLinearTimeMMD.
Definition at line 159 of file TwoDistributionTest.cpp.
const index_t get_num_samples_p | ( | ) | const |
Definition at line 81 of file TwoDistributionTest.cpp.
const index_t get_num_samples_q | ( | ) | const |
Definition at line 93 of file TwoDistributionTest.cpp.
CFeatures * get_p | ( | ) | const |
Definition at line 56 of file TwoDistributionTest.cpp.
CFeatures * get_q | ( | ) | const |
Definition at line 69 of file TwoDistributionTest.cpp.
|
inherited |
Checks if object has a class parameter identified by a name.
name | name of the parameter |
Definition at line 299 of file SGObject.h.
|
inherited |
Checks if object has a class parameter identified by a Tag.
tag | tag of the parameter containing name and type information |
Definition at line 310 of file SGObject.h.
|
inherited |
Checks if a type exists for a class parameter identified by a name.
name | name of the parameter |
Definition at line 321 of file SGObject.h.
|
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 329 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 402 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 459 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 454 of file SGObject.cpp.
|
virtualinherited |
Definition at line 295 of file SGObject.cpp.
|
inherited |
Method that performs the complete hypothesis test on current data and returns a binary answer: wheter null hypothesis is rejected or not.
This is just a wrapper for the above compute_p_value() method that returns a p-value. If this p-value lies below the test level alpha, the null hypothesis is rejected.
Should not be overwritten in subclasses. (Therefore not virtual)
alpha | test level alpha. |
Definition at line 92 of file HypothesisTest.cpp.
|
inherited |
prints all parameter registered for model selection and their type
Definition at line 507 of file SGObject.cpp.
|
virtualinherited |
prints registered parameters out
prefix | prefix for members |
Definition at line 341 of file SGObject.cpp.
|
protectedinherited |
Registers a class parameter which is identified by a tag. This enables the parameter to be modified by set() and retrieved by get(). Parameters can be registered in the constructor of the class.
_tag | name and type information of parameter |
value | value of the parameter |
Definition at line 450 of file SGObject.h.
|
protectedinherited |
Registers a class parameter which is identified by a name. This enables the parameter to be modified by set() and retrieved by get(). Parameters can be registered in the constructor of the class.
name | name of the parameter |
value | value of the parameter along with type information |
Definition at line 463 of file SGObject.h.
Interface for computing the samples under the null-hypothesis.
Implements CHypothesisTest.
Implemented in CMMD, CQuadraticTimeMMD, CIndependenceTest, CTwoSampleTest, and CStreamingMMD.
|
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 347 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 469 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 464 of file SGObject.cpp.
|
inherited |
Setter for a class parameter, identified by a Tag. Throws an exception if the class does not have such a parameter.
_tag | name and type information of parameter |
value | value of the parameter |
Definition at line 337 of file SGObject.h.
|
inherited |
Setter for a class parameter, identified by a name. Throws an exception if the class does not have such a parameter.
name | name of the parameter |
value | value of the parameter along with type information |
Definition at line 363 of file SGObject.h.
|
inherited |
Definition at line 74 of file SGObject.cpp.
|
inherited |
Definition at line 79 of file SGObject.cpp.
|
inherited |
Definition at line 84 of file SGObject.cpp.
|
inherited |
Definition at line 89 of file SGObject.cpp.
|
inherited |
Definition at line 94 of file SGObject.cpp.
|
inherited |
Definition at line 99 of file SGObject.cpp.
|
inherited |
Definition at line 104 of file SGObject.cpp.
|
inherited |
Definition at line 109 of file SGObject.cpp.
|
inherited |
Definition at line 114 of file SGObject.cpp.
|
inherited |
Definition at line 119 of file SGObject.cpp.
|
inherited |
Definition at line 124 of file SGObject.cpp.
|
inherited |
Definition at line 129 of file SGObject.cpp.
|
inherited |
Definition at line 134 of file SGObject.cpp.
|
inherited |
Definition at line 139 of file SGObject.cpp.
|
inherited |
Definition at line 144 of file SGObject.cpp.
|
inherited |
set generic type to T
|
inherited |
|
inherited |
set the parallel object
parallel | parallel object to use |
Definition at line 274 of file SGObject.cpp.
|
inherited |
set the version object
version | version object to use |
Definition at line 316 of file SGObject.cpp.
void set_num_samples_p | ( | index_t | num_samples_from_p | ) |
Method that initializes the number of samples to be drawn from distribution \(\mathbf{P}\). Please ensure to call this method if you are intending to use streaming data generators that generate the samples on the fly. For other types of features, the number of samples is set internally from the features object itself, therefore this method should not be used.
num_samples_from_p | The CFeatures instance representing the samples from \(\mathbf{P}\). |
Definition at line 75 of file TwoDistributionTest.cpp.
void set_num_samples_q | ( | index_t | num_samples_from_q | ) |
Method that initializes the number of samples to be drawn from distribution \(\mathbf{Q}\). Please ensure to call this method if you are intending to use streaming data generators that generate the samples on the fly. For other types of features, the number of samples is set internally from the features object itself, therefore this method should not be used.
num_samples_from_q | The CFeatures instance representing the samples from \(\mathbf{Q}\). |
Definition at line 87 of file TwoDistributionTest.cpp.
|
virtual |
Method that initializes the samples from \(\mathbf{P}\). This method is kept virtual for the sub-classes to perform additional initialization tasks that have to be performed every time features are set/updated.
samples_from_p | The CFeatures instance representing the samples from \(\mathbf{P}\). |
Reimplemented in CQuadraticTimeMMD.
Definition at line 49 of file TwoDistributionTest.cpp.
|
virtual |
Method that initializes the samples from \(\mathbf{Q}\). This method is kept virtual for the sub-classes to perform additional initialization tasks that have to be performed every time features are set/updated.
samples_from_q | The CFeatures instance representing the samples from \(\mathbf{Q}\). |
Reimplemented in CQuadraticTimeMMD.
Definition at line 62 of file TwoDistributionTest.cpp.
|
inherited |
Method that enables/disables the training-testing mode. If this option is turned on, then the samples would be split in two pieces: one chunk would be used for training algorithms and the other chunk would be used for performing tests. If this option is turned off, the entire data would be used for performing the test. Before running any training algorithms, make sure to turn this mode on.
By default, the training-testing mode is turned off.
on | Whether to enable/disable the training-testing mode |
Definition at line 66 of file HypothesisTest.cpp.
|
inherited |
Method that specifies the ratio of training-testing data split for the algorithms. Note that this is NOT the percentage of samples to be used for training, rather the ratio of the number of samples to be used for training and that of testing.
By default, an equal 50-50 split (ratio = 1) is made.
ratio | The ratio of the number of samples to be used for training and that of testing |
Definition at line 71 of file HypothesisTest.cpp.
|
virtualinherited |
A shallow copy. All the SGObject instance variables will be simply assigned and SG_REF-ed.
Reimplemented in CGaussianKernel.
Definition at line 225 of file SGObject.cpp.
|
inherited |
unset generic type
this has to be called in classes specializing a template class
Definition at line 336 of file SGObject.cpp.
|
virtualinherited |
Updates the hash of current parameter combination
Definition at line 281 of file SGObject.cpp.
|
inherited |
io
Definition at line 558 of file SGObject.h.
|
inherited |
parameters wrt which we can compute gradients
Definition at line 573 of file SGObject.h.
|
inherited |
Hash of parameter values
Definition at line 576 of file SGObject.h.
|
inherited |
model selection parameters
Definition at line 570 of file SGObject.h.
|
inherited |
parameters
Definition at line 567 of file SGObject.h.
|
inherited |
parallel
Definition at line 561 of file SGObject.h.
|
inherited |
version
Definition at line 564 of file SGObject.h.