public class LearnNSE extends AbstractClassifier implements MultiClassClassifier
Ensemble of classifiers-based approach for incremental learning of concept drift, characterized by nonstationary environments (NSEs), where the underlying data distributions change over time. It learns from consecutive batches of data that experience constant or variable rate of drift, addition or deletion of concept classes, as well as cyclical drift.
Based on: Ryan Elwell and Robi Polikar. Incremental learning of concept drift in non-stationary environments. IEEE Transactions on Neural Networks, 22(10):1517-1531, October 2011. ISSN 1045-9227. URL http://dx.doi.org/10.1109/TNN.2011.2160459
Modifier and Type | Field and Description |
---|---|
ClassOption |
baseLearnerOption |
protected List<ArrayList<Double>> |
bkts |
protected Instances |
buffer |
protected double |
crossingPoint |
protected List<Classifier> |
ensemble |
protected int |
ensembleSize |
IntOption |
ensembleSizeOption |
protected List<Double> |
ensembleWeights |
protected long |
index |
IntOption |
periodOption |
protected int |
pruning |
MultiChoiceOption |
pruningStrategyOption |
FloatOption |
sigmoidCrossingPointOption |
FloatOption |
sigmoidSlopeOption |
protected double |
slope |
protected List<ArrayList<Double>> |
wkts |
classifierRandom, modelContext, randomSeed, randomSeedOption, trainingWeightSeenByModel
config
Constructor and Description |
---|
LearnNSE() |
Modifier and Type | Method and Description |
---|---|
void |
getModelDescription(StringBuilder out,
int indent)
Returns a string representation of the model.
|
protected Measurement[] |
getModelMeasurementsImpl()
Gets the current measurements of this classifier.
The reason for ...Impl methods: ease programmer burden by not requiring them to remember calls to super in overridden methods. |
double[] |
getVotesForInstance(Instance inst)
Predicts the class memberships for a given instance.
|
boolean |
isRandomizable()
Gets whether this learner needs a random seed.
|
void |
resetLearningImpl()
Resets this classifier.
|
void |
trainOnInstanceImpl(Instance inst)
Trains this classifier incrementally using the given instance.
The reason for ...Impl methods: ease programmer burden by not requiring them to remember calls to super in overridden methods. |
contextIsCompatible, copy, correctlyClassifies, getAttributeNameString, getAWTRenderer, getClassLabelString, getClassNameString, getDescription, getModel, getModelContext, getModelMeasurements, getNominalValueString, getPredictionForInstance, getPredictionForInstance, getPurposeString, getSubClassifiers, getSublearners, getVotesForInstance, modelAttIndexToInstanceAttIndex, modelAttIndexToInstanceAttIndex, prepareForUseImpl, resetLearning, setModelContext, setRandomSeed, trainingHasStarted, trainingWeightSeenByModel, trainOnInstance, trainOnInstance
getCLICreationString, getOptions, getPreparedClassOption, prepareClassOptions, prepareForUse, prepareForUse
copy, measureByteSize, measureByteSize, toString
clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait
getCLICreationString, getOptions, prepareForUse, prepareForUse
measureByteSize
public ClassOption baseLearnerOption
public IntOption periodOption
public FloatOption sigmoidSlopeOption
public FloatOption sigmoidCrossingPointOption
public IntOption ensembleSizeOption
public MultiChoiceOption pruningStrategyOption
protected List<Classifier> ensemble
protected Instances buffer
protected long index
protected double slope
protected double crossingPoint
protected int pruning
protected int ensembleSize
public void resetLearningImpl()
AbstractClassifier
resetLearningImpl
in class AbstractClassifier
public void trainOnInstanceImpl(Instance inst)
AbstractClassifier
trainOnInstanceImpl
in class AbstractClassifier
inst
- the instance to be used for trainingpublic boolean isRandomizable()
Learner
isRandomizable
in interface Learner<Example<Instance>>
public double[] getVotesForInstance(Instance inst)
Classifier
getVotesForInstance
in interface Classifier
getVotesForInstance
in class AbstractClassifier
inst
- the instance to be classifiedpublic void getModelDescription(StringBuilder out, int indent)
AbstractClassifier
getModelDescription
in class AbstractClassifier
out
- the stringbuilder to add the descriptionindent
- the number of characters to indentprotected Measurement[] getModelMeasurementsImpl()
AbstractClassifier
getModelMeasurementsImpl
in class AbstractClassifier
Copyright © 2019 University of Waikato, Hamilton, NZ. All Rights Reserved.