Modifier and Type | Class and Description |
---|---|
class |
BCC
BCC.java - Bayesian Classifier Chains.
|
class |
BPNN
BPNN.java - Back Propagation Neural Network.
|
class |
BR |
class |
BRq
BRq.java - Random Subspace ('quick') Version.
|
class |
CC
CC.java - The Classifier Chains Method.
|
class |
CCq
The Classifier Chains Method - Random Subspace ('quick') Version.
|
class |
CDN
CDN.java - Conditional Dependency Networks.
|
class |
CDT
CDT.java - Conditional Dependency Trellis.
|
class |
CT
CT - Classifier Trellis.
|
class |
DBPNN
DBPNN.java - Deep Back-Propagation Neural Network.
|
class |
FW
FW.java Four-class pairWise classification.
|
class |
HASEL
HASEL - Partitions labels into subsets based on the dataset defined hierarchy.
|
class |
LC
LC.java - The LC (Label Combination) aka LP (Laber Powerset) Method.
|
class |
MajorityLabelset
MajorityLabelset.java - The most simplest multi-label classifier.
|
class |
MCC
MCC.java - CC with Monte Carlo optimisation.
|
class |
MULAN
MULAN.java - A wrapper for MULAN classifiers MULAN.
|
class |
PCC
PCC.java - (Bayes Optimal) Probabalistic Classifier Chains.
|
class |
PMCC
PMCC.java - Like MCC but creates a population of M chains at training time (from Is candidate chains, using Monte Carlo sampling), and uses this population for inference at test time; If you are looking for a 'more typical' majority-vote ensemble method, use something like EnsembleML or BaggingML with MCC.
|
class |
PS
PS.java - The Pruned Sets Method.
|
class |
PSt
PSt.java - Pruned Sets with a a threshold so as to be able to predict sets not seen in the training set.
|
class |
RAkEL
RAkEL.java - Draws M subsets of size k from the set of labels, and trains PS upon each one, then combines label votes from these PS classifiers to get a label-vector prediction.
|
class |
RAkELd
RAkELd - Takes RAndom partition of labELs; like RAkEL but labelsets are disjoint / non-overlapping subsets.
|
class |
RT
RT.java - The 'Ranking + Threshold' classifier.
|
Modifier and Type | Method and Description |
---|---|
static MultilabelClassifier[] |
MultilabelClassifier.makeCopies(MultilabelClassifier model,
int num)
Creates a given number of deep copies of the given multi-label classifier using serialization.
|
Modifier and Type | Method and Description |
---|---|
static Result[] |
Evaluation.cvModel(MultilabelClassifier h,
weka.core.Instances D,
int numFolds,
java.lang.String top)
CVModel - Split D into train/test folds, and then train and evaluate on each one.
|
static Result[] |
Evaluation.cvModel(MultilabelClassifier h,
weka.core.Instances D,
int numFolds,
java.lang.String top,
java.lang.String vop)
CVModel - Split D into train/test folds, and then train and evaluate on each one.
|
static Result |
Evaluation.evaluateModel(MultilabelClassifier h,
weka.core.Instances D_train,
weka.core.Instances D_test)
EvaluateModel - Build model 'h' on 'D_train', test it on 'D_test'.
|
static Result |
Evaluation.evaluateModel(MultilabelClassifier h,
weka.core.Instances D_train,
weka.core.Instances D_test,
java.lang.String top)
EvaluateModel - Build model 'h' on 'D_train', test it on 'D_test', threshold it according to 'top', using default verbosity option.
|
static Result |
Evaluation.evaluateModel(MultilabelClassifier h,
weka.core.Instances D_train,
weka.core.Instances D_test,
java.lang.String top,
java.lang.String vop)
EvaluateModel - Build model 'h' on 'D_train', test it on 'D_test', threshold it according to 'top', verbosity 'vop'.
|
static Result |
Evaluation.evaluateModel(MultilabelClassifier h,
weka.core.Instances D_test,
java.lang.String tal,
java.lang.String vop)
EvaluateModel - Assume 'h' is already built, test it on 'D_test', threshold it according to 'top', verbosity 'vop'.
|
static void |
MultilabelClassifier.evaluation(MultilabelClassifier h,
java.lang.String[] args)
Called by classifier's main() method upon initialisation from the command line.
|
static MultilabelClassifier[] |
MultilabelClassifier.makeCopies(MultilabelClassifier model,
int num)
Creates a given number of deep copies of the given multi-label classifier using serialization.
|
static void |
MultilabelClassifier.runClassifier(MultilabelClassifier h,
java.lang.String[] args)
Called by classifier's main() method upon initialisation from the command line.
|
static void |
Evaluation.runExperiment(MultilabelClassifier h,
java.lang.String[] options)
RunExperiment - Build and evaluate a model with command-line options.
|
static Result |
Evaluation.testClassifier(MultilabelClassifier h,
weka.core.Instances D_test)
TestClassifier - test classifier h on D_test
|
Modifier and Type | Class and Description |
---|---|
class |
BRUpdateable
BRUpdateable.java - Updateable BR.
|
class |
CCUpdateable
CCUpdateable.java - Updateable version of CC.
|
class |
MajorityLabelsetUpdateable
MajorityLabelsetUpdateable.java - Updateable version of MajorityLabelset.
|
class |
PSUpdateable
PSUpdateable.java - Pruned Sets Updateable.
|
class |
RTUpdateable
RTUpdateable.java - Updateable RT.
|
Modifier and Type | Method and Description |
---|---|
static Result[] |
IncrementalEvaluation.evaluateModel(MultilabelClassifier h,
weka.core.Instances D)
EvaluateModel - over 20 windows.
|
static Result[] |
IncrementalEvaluation.evaluateModel(MultilabelClassifier h,
weka.core.Instances D,
int numWindows,
double rLabeled,
java.lang.String Top,
java.lang.String Vop)
EvaluateModel - Evaluate a multi-label data-stream model over a moving window.
|
static Result |
IncrementalEvaluation.evaluateModel(MultilabelClassifier h,
java.lang.String[] options)
EvaluateModel - Build and evaluate.
|
static void |
IncrementalEvaluation.runExperiment(MultilabelClassifier h,
java.lang.String[] args)
RunExperiment - Build and evaluate a model with command-line options.
|
Modifier and Type | Class and Description |
---|---|
class |
BaggingMLUpdateable
BaggingMLUpdatable.java - Using the OzaBag scheme (see OzaBag.java from MOA)).
|
class |
BaggingMLUpdateableADWIN
BaggingMLUpdatableUpdateableADWIN.java - Using the OzaBag scheme (see OzaBag.java from MOA)).
|
Modifier and Type | Class and Description |
---|---|
class |
BaggingML
BaggingML.java - Combining several multi-label classifiers using Bootstrap AGGregatING.
|
class |
BaggingMLdup
BaggingMLdup.java - A version of BaggingML where Instances are duplicated instead of assigned higher weighs.
|
class |
CM
CM.java - Classification Maximization using any multi-label classifier.
|
class |
DeepML
DeepML.java - Deep Multi-label Classification.
|
class |
EM
EM.java - Expectation Maximization using any multi-label classifier.
|
class |
EnsembleML
EnsembleML.java - Combines several multi-label classifiers in a simple-subset ensemble.
|
class |
MBR
MBR.java - Meta BR: BR stacked with feature outputs into another BR.
|
class |
MultilabelMetaClassifier
MultilabelMetaClassifier.java - For ensembles of multi-label methods.
|
class |
RandomSubspaceML
RandomSubspaceML.java - Subsample the attribute space and instance space randomly for each ensemble member.
|
class |
SubsetMapper
Maps the output of a multi-label classifier to a known label combination using the hamming distance.
|
Modifier and Type | Class and Description |
---|---|
class |
AbstractDeepNeuralNet
AbstractDeepNeuralNet.java - Extends AbstractNeuralNet with depth options.
|
class |
AbstractNeuralNet
AbstractNeuralNet.java - Provides common options, constants, and other functions for NNs.
|
Modifier and Type | Class and Description |
---|---|
class |
CCp
CCp.java - Multitarget CC with probabilistic output.
|
class |
CR |
class |
NSR
NSR.java - The Nearest Set Relpacement (NSR) method.
|
class |
SCC
SCC.java - Super Class Classifier (aka Super Node Classifier).
|
Modifier and Type | Class and Description |
---|---|
class |
BaggingMT
BaggingMT.java - The Multi-Target Version of BaggingML.
|
class |
EnsembleMT
The Multi-Target Version of EnsembleML.
|