SHOGUN
4.1.0
|
Class KNN, an implementation of the standard k-nearest neigbor classifier.
An example is classified to belong to the class of which the majority of the k closest examples belong to. Formally, kNN is described as
\[ label for x = \arg \max_{l} \sum_{i=1}^{k} [label of i-th example = l] \]
This class provides a capability to do weighted classfication using:
\[ label for x = \arg \max_{l} \sum_{i=1}^{k} [label of i-th example = l] q^{i}, \]
where \(|q|<1\).
To avoid ties, k should be an odd number. To define how close examples are k-NN requires a CDistance object to work with (e.g., CEuclideanDistance ).
Note that k-NN has zero training time but classification times increase dramatically with the number of examples. Also note that k-NN is capable of multi-class-classification. And finally, in case of k=1 classification will take less time with an special optimization provided.
Public Member Functions | |
CKNN () | |
CKNN (int32_t k, CDistance *d, CLabels *trainlab) | |
virtual | ~CKNN () |
virtual EMachineType | get_classifier_type () |
SGMatrix< index_t > | nearest_neighbors () |
virtual CMulticlassLabels * | apply_multiclass (CFeatures *data=NULL) |
virtual float64_t | apply_one (int32_t vec_idx) |
get output for example "vec_idx" More... | |
SGMatrix< int32_t > | classify_for_multiple_k () |
virtual bool | load (FILE *srcfile) |
virtual bool | save (FILE *dstfile) |
void | set_k (int32_t k) |
int32_t | get_k () |
void | set_q (float64_t q) |
float64_t | get_q () |
void | set_use_covertree (bool use_covertree) |
bool | get_use_covertree () const |
virtual const char * | get_name () const |
void | set_distance (CDistance *d) |
CDistance * | get_distance () const |
void | distances_lhs (float64_t *result, int32_t idx_a1, int32_t idx_a2, int32_t idx_b) |
void | distances_rhs (float64_t *result, int32_t idx_b1, int32_t idx_b2, int32_t idx_a) |
virtual bool | train (CFeatures *data=NULL) |
virtual CLabels * | apply (CFeatures *data=NULL) |
virtual CBinaryLabels * | apply_binary (CFeatures *data=NULL) |
virtual CRegressionLabels * | apply_regression (CFeatures *data=NULL) |
virtual CStructuredLabels * | apply_structured (CFeatures *data=NULL) |
virtual CLatentLabels * | apply_latent (CFeatures *data=NULL) |
virtual void | set_labels (CLabels *lab) |
virtual CLabels * | get_labels () |
void | set_max_train_time (float64_t t) |
float64_t | get_max_train_time () |
void | set_solver_type (ESolverType st) |
ESolverType | get_solver_type () |
virtual void | set_store_model_features (bool store_model) |
virtual bool | train_locked (SGVector< index_t > indices) |
virtual CLabels * | apply_locked (SGVector< index_t > indices) |
virtual CBinaryLabels * | apply_locked_binary (SGVector< index_t > indices) |
virtual CRegressionLabels * | apply_locked_regression (SGVector< index_t > indices) |
virtual CMulticlassLabels * | apply_locked_multiclass (SGVector< index_t > indices) |
virtual CStructuredLabels * | apply_locked_structured (SGVector< index_t > indices) |
virtual CLatentLabels * | apply_locked_latent (SGVector< index_t > indices) |
virtual void | data_lock (CLabels *labs, CFeatures *features) |
virtual void | post_lock (CLabels *labs, CFeatures *features) |
virtual void | data_unlock () |
virtual bool | supports_locking () const |
bool | is_data_locked () const |
virtual EProblemType | get_machine_problem_type () const |
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 | |
virtual void | store_model_features () |
virtual CMulticlassLabels * | classify_NN () |
void | init_distance (CFeatures *data) |
virtual bool | train_machine (CFeatures *data=NULL) |
virtual bool | is_label_valid (CLabels *lab) const |
virtual bool | train_require_labels () 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 Member Functions | |
static void * | run_distance_thread_lhs (void *p) |
static void * | run_distance_thread_rhs (void *p) |
Protected Attributes | |
int32_t | m_k |
the k parameter in KNN More... | |
float64_t | m_q |
parameter q of rank weighting More... | |
bool | m_use_covertree |
parameter to enable cover tree support More... | |
int32_t | m_num_classes |
number of classes (i.e. number of values labels can take) More... | |
int32_t | m_min_label |
smallest label, i.e. -1 More... | |
SGVector< int32_t > | m_train_labels |
CDistance * | distance |
float64_t | m_max_train_time |
CLabels * | m_labels |
ESolverType | m_solver_type |
bool | m_store_model_features |
bool | m_data_locked |
apply machine to data if data is not specified apply to the current features
data | (test)data to be classified |
Definition at line 152 of file Machine.cpp.
|
virtualinherited |
apply machine to data in means of binary classification problem
Reimplemented in CKernelMachine, COnlineLinearMachine, CWDSVMOcas, CNeuralNetwork, CLinearMachine, CGaussianProcessClassification, CDomainAdaptationSVMLinear, CDomainAdaptationSVM, CPluginEstimate, and CBaggingMachine.
Definition at line 208 of file Machine.cpp.
|
virtualinherited |
apply machine to data in means of latent problem
Reimplemented in CLinearLatentMachine.
Definition at line 232 of file Machine.cpp.
Applies a locked machine on a set of indices. Error if machine is not locked
indices | index vector (of locked features) that is predicted |
Definition at line 187 of file Machine.cpp.
|
virtualinherited |
applies a locked machine on a set of indices for binary problems
Reimplemented in CKernelMachine, and CMultitaskLinearMachine.
Definition at line 238 of file Machine.cpp.
|
virtualinherited |
applies a locked machine on a set of indices for latent problems
Definition at line 266 of file Machine.cpp.
|
virtualinherited |
applies a locked machine on a set of indices for multiclass problems
Definition at line 252 of file Machine.cpp.
|
virtualinherited |
applies a locked machine on a set of indices for regression problems
Reimplemented in CKernelMachine.
Definition at line 245 of file Machine.cpp.
|
virtualinherited |
applies a locked machine on a set of indices for structured problems
Definition at line 259 of file Machine.cpp.
|
virtual |
classify objects
data | (test)data to be classified |
Reimplemented from CDistanceMachine.
|
virtual |
get output for example "vec_idx"
Reimplemented from CDistanceMachine.
|
virtualinherited |
apply machine to data in means of regression problem
Reimplemented in CKernelMachine, CWDSVMOcas, COnlineLinearMachine, CNeuralNetwork, CCHAIDTree, CStochasticGBMachine, CCARTree, CLinearMachine, CGaussianProcessRegression, and CBaggingMachine.
Definition at line 214 of file Machine.cpp.
|
virtualinherited |
apply machine to data in means of SO classification problem
Reimplemented in CLinearStructuredOutputMachine.
Definition at line 226 of file Machine.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.
SGMatrix< int32_t > classify_for_multiple_k | ( | ) |
|
protectedvirtual |
|
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.
Locks the machine on given labels and data. After this call, only train_locked and apply_locked may be called
Only possible if supports_locking() returns true
labs | labels used for locking |
features | features used for locking |
Reimplemented in CKernelMachine.
Definition at line 112 of file Machine.cpp.
|
virtualinherited |
Unlocks a locked machine and restores previous state
Reimplemented in CKernelMachine.
Definition at line 143 of file Machine.cpp.
|
virtualinherited |
A deep copy. All the instance variables will also be copied.
Definition at line 198 of file SGObject.cpp.
|
inherited |
get distance functions for lhs feature vectors going from a1 to a2 and rhs feature vector b
result | array of distance values |
idx_a1 | first feature vector a1 at idx_a1 |
idx_a2 | last feature vector a2 at idx_a2 |
idx_b | feature vector b at idx_b |
Definition at line 52 of file DistanceMachine.cpp.
|
inherited |
get distance functions for rhs feature vectors going from b1 to b2 and lhs feature vector a
result | array of distance values |
idx_b1 | first feature vector a1 at idx_b1 |
idx_b2 | last feature vector a2 at idx_b2 |
idx_a | feature vector a at idx_a |
Definition at line 114 of file DistanceMachine.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.
|
virtual |
|
inherited |
|
inherited |
|
inherited |
|
inherited |
|
virtualinherited |
|
virtualinherited |
returns type of problem machine solves
Reimplemented in CNeuralNetwork, CRandomForest, CCHAIDTree, CCARTree, and CBaseMulticlassMachine.
|
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 |
|
inherited |
bool get_use_covertree | ( | ) | const |
|
protected |
|
inherited |
|
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.
|
protectedvirtualinherited |
check whether the labels is valid.
Subclasses can override this to implement their check of label types.
lab | the labels being checked, guaranteed to be non-NULL |
Reimplemented in CNeuralNetwork, CCARTree, CCHAIDTree, CGaussianProcessRegression, and CBaseMulticlassMachine.
|
virtual |
|
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.
for each example in the rhs features of the distance member, find the m_k nearest neighbors among the vectors in the lhs features
|
virtualinherited |
Definition at line 262 of file SGObject.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.
|
staticprotectedinherited |
thread function for computing distance values
p | thread parameter |
Definition at line 176 of file DistanceMachine.cpp.
|
staticprotectedinherited |
thread function for computing distance values
p | thread parameter |
Definition at line 192 of file DistanceMachine.cpp.
|
virtual |
|
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.
|
inherited |
|
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.
|
virtualinherited |
set labels
lab | labels |
Reimplemented in CNeuralNetwork, CGaussianProcessMachine, CCARTree, CStructuredOutputMachine, CRelaxedTree, and CMulticlassMachine.
Definition at line 65 of file Machine.cpp.
|
inherited |
set maximum training time
t | maximimum training time |
Definition at line 82 of file Machine.cpp.
|
inherited |
|
virtualinherited |
Setter for store-model-features-after-training flag
store_model | whether model should be stored after training |
Definition at line 107 of file Machine.cpp.
void set_use_covertree | ( | bool | use_covertree | ) |
|
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.
|
protectedvirtual |
Stores feature data of underlying model.
Replaces lhs and rhs of underlying distance with copies of themselves
Reimplemented from CDistanceMachine.
|
virtualinherited |
Reimplemented in CKernelMachine, and CMultitaskLinearMachine.
|
virtualinherited |
train machine
data | training data (parameter can be avoided if distance or kernel-based classifiers are used and distance/kernels are initialized with train data). If flag is set, model features will be stored after training. |
Reimplemented in CRelaxedTree, CAutoencoder, CSGDQN, and COnlineSVMSGD.
Definition at line 39 of file Machine.cpp.
Trains a locked machine on a set of indices. Error if machine is not locked
NOT IMPLEMENTED
indices | index vector (of locked features) that is used for training |
Reimplemented in CKernelMachine, and CMultitaskLinearMachine.
|
protectedvirtual |
|
protectedvirtualinherited |
returns whether machine require labels for training
Reimplemented in COnlineLinearMachine, CHierarchical, CLinearLatentMachine, CVwConditionalProbabilityTree, CConditionalProbabilityTree, and CLibSVMOneClass.
|
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.
|
protectedinherited |
the distance
Definition at line 130 of file DistanceMachine.h.
|
inherited |
io
Definition at line 369 of file SGObject.h.
|
protectedinherited |
|
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.
|
protectedinherited |
|
inherited |
model selection parameters
Definition at line 381 of file SGObject.h.
|
protected |
|
inherited |
parameters
Definition at line 378 of file SGObject.h.
|
protectedinherited |
|
protectedinherited |
|
protected |
|
protected |
|
inherited |
parallel
Definition at line 372 of file SGObject.h.
|
inherited |
version
Definition at line 375 of file SGObject.h.