Uses of Class
netkit.classifiers.DataSplit

Packages that use DataSplit

netkit.classifiers
netkit.classifiers.active
netkit.classifiers.nonrelational
netkit.classifiers.relational
netkit.graph.edgecreator

Uses of DataSplit in netkit.classifiers

Methods in netkit.classifiers that return DataSplit

DataSplit[]	DataView.crossValidate(int numSplits)
DataSplit	NetworkLearner.getSplit()
DataSplit	DataView.getSplit(Classification known)
DataSplit	DataView.getSplit(Classification known, Classification test)
DataSplit	DataView.getSplit(double trainRatio)
DataSplit	DataView.getSplit(double trainRatio, double testRatio)
DataSplit	DataView.getSplit(int trainSize)
DataSplit	DataView.getSplit(int trainSize, int testSize)
DataSplit	DataView.getSplit(NodeFilter trainFilter)
DataSplit[]	NetworkLearning.getSplits()
DataSplit[]	DataView.getSplits(int numSplits, double trainRatio)
DataSplit[]	DataView.getSplits(int numSplits, double trainRatio, double testRatio)
DataSplit[]	DataView.getSplits(int numSplits, int trainSize)
DataSplit[]	DataView.getSplits(int numSplits, int trainSize, int testSize)

Methods in netkit.classifiers with parameters of type DataSplit

void	Estimate.applyCMN(DataSplit split) Apply class mass normalization.
void	NetworkLearning.augmentGraph(DataSplit split, GraphView gv, EdgeCreator[] ecs)
void	ClassifierImp.induceModel(Graph graph, DataSplit split)
void	Classifier.induceModel(Graph graph, DataSplit split)
Estimate	NetworkLearner.runActiveLearner(PickLabelStrategy ps, DataSplit split) See fully parameterized method for details.
Estimate	NetworkLearner.runActiveLearner(PickLabelStrategy ps, DataSplit split, int picksPerIteration, int maxPicks, boolean learnWithTruth, int depth) Run active learning using the given parameters.
Estimate	NetworkLearning.runInference(DataSplit split)
Estimate	NetworkLearner.runInference(DataSplit split)
Estimate	NetworkLearner.runInference(DataSplit split, boolean showItAcc, boolean learnWithTruth, int depth)
Estimate	NetworkLearner.runLeaveOneOut(DataSplit split)
Estimate	NetworkLearner.runLeaveOneOut(DataSplit split, boolean learnWithTruth, int depth)
void	NetworkLearning.setSplits(DataSplit[] s)

Uses of DataSplit in netkit.classifiers.active

Methods in netkit.classifiers.active that return DataSplit

DataSplit

PickLabelStrategyImp.getSplit()

Methods in netkit.classifiers.active with parameters of type DataSplit

PickLabelStrategy.LabelNode[]	PickLabelStrategyImp.getNodesToLabel(DataSplit currentSplit, Estimate currentPredictions, int maxPicks) Get the list of nodes to get labels for.
PickLabelStrategy.LabelNode[]	PickLabelStrategy.getNodesToLabel(DataSplit currentSplit, Estimate currentPredictions, int maxPicks) Get the list of nodes to get labels for.
double	UncertaintyLabeling.getRank(DataSplit split, Estimate predictions, Node node)
double	PickLabelStrategyImp.getRank(DataSplit currentSplit, Estimate currentPredictions, Node node)
double	PickLabelStrategy.getRank(DataSplit currentSplit, Estimate currentPredictions, Node node) Get the rank of the given node if the strategy were to pick the node.
double	GreedyTruth.getRank(DataSplit split, Estimate predictions, Node node)
double	GraphCentralityLabeling.getRank(DataSplit split, Estimate predictions, Node node)
double	EmpiricalRiskMinimizationHarmonic.getRank(DataSplit split, Estimate predictions, Node node)
void	PickLabelStrategyImp.initialize(NetworkLearner nl, DataSplit split)
void	PickLabelStrategy.initialize(NetworkLearner nl, DataSplit split) Initialize the label strategy by providing a reference to the NetworkLeaner object that calls the strategy, thereby giving it access to all information it is likely to need.
void	GreedyTruth.initialize(NetworkLearner nl, DataSplit split)
void	GraphCentralityLabeling.initialize(NetworkLearner nl, DataSplit split)
void	ERMHybrid.initialize(NetworkLearner nl, DataSplit split)
void	EmpiricalRiskMinimizationHarmonic.initialize(NetworkLearner nl, DataSplit split)
void	ComparatorLabeler.initialize(NetworkLearner nl, DataSplit split)
PickLabelStrategy.LabelNode[]	UncertaintyLabeling.peek(DataSplit split, Estimate predictions, int maxPicks)
PickLabelStrategy.LabelNode[]	PickLabelStrategyImp.peek(DataSplit currentSplit, Estimate currentPredictions, int numPeek)
PickLabelStrategy.LabelNode[]	PickLabelStrategy.peek(DataSplit currentSplit, Estimate currentPredictions, int numPeek) Get the list of nodes to get labels for...
PickLabelStrategy.LabelNode[]	GreedyTruth.peek(DataSplit split, Estimate predictions, int maxPicks)
PickLabelStrategy.LabelNode[]	GraphCentralityLabeling.peek(DataSplit split, Estimate predictions, int maxPicks)
PickLabelStrategy.LabelNode[]	EmpiricalRiskMinimizationHarmonic.peek(DataSplit split, Estimate predictions, int maxPicks)

Uses of DataSplit in netkit.classifiers.nonrelational

Methods in netkit.classifiers.nonrelational with parameters of type DataSplit

void	UniformPrior.induceModel(Graph graph, DataSplit split) Makes a uniform prediction array---all classes are equally likely
void	MetaMultiplicative.induceModel(Graph graph, DataSplit split) Induce the model.
void	LocalWeka.induceModel(Graph graph, DataSplit split) Induce the weka classifier by creating a training Instances object according to the schema of the nodes to be classified.
void	LocalMetaClassifier.induceModel(Graph graph, DataSplit split) This induces each of the local classifiers individually.
void	ExternalPrior.induceModel(Graph graph, DataSplit split) Inducing this model simply means to read the estimates from the input file.

Uses of DataSplit in netkit.classifiers.relational

Methods in netkit.classifiers.relational with parameters of type DataSplit

void	WeightedVoteRelationalNeighbor.induceModel(Graph graph, DataSplit split) wvRN has no model, so this only initializes what needs to be done for laplace correction (in addition to whatever the superclass does).
void	NetworkWeka.induceModel(Graph graph, DataSplit split) Induce the weka classifier by creating a training Instances object according to the schema of the nodes to be classified.
void	NetworkOnlyBayes.induceModel(Graph graph, DataSplit split) Induce the model by computing the counts for Prob(classIdx | neighborClassIdx)
void	NetworkMetaClassifier.induceModel(Graph graph, DataSplit split) This separately induces all the non-relational and relational classifiers in addition to any setup the super-class needs to do.
void	NetworkClassifierImp.induceModel(Graph graph, DataSplit split) This method induces a new prediction model.
void	MetaMultiplicative.induceModel(Graph graph, DataSplit split) Induce the model.
void	Harmonic.induceModel(Graph graph, DataSplit split) Harmonic has no model per se as its learning consists of computing the harmonic function which results in the predictions.
void	ClassDistribRelNeighbor.induceModel(Graph graph, DataSplit split) Induce the cdRN model by finding the 'prototypical' neighborhood for each class of nodes.

Uses of DataSplit in netkit.graph.edgecreator

Fields in netkit.graph.edgecreator declared as DataSplit

protected DataSplit

EdgeCreatorImp.split

Methods in netkit.graph.edgecreator with parameters of type DataSplit

void	MahalanobisDistanceEdgeCreator.buildModel(DataSplit split)
void	GaussianNumericEdgeCreator.buildModel(DataSplit split)
void	EuclideanDistanceEdgeCreator.buildModel(DataSplit split)
void	EdgeCreatorImp.buildModel(DataSplit split)
void	EdgeCreator.buildModel(DataSplit split) Build a model of edge creation based on the data split.
void	CosineDistanceEdgeCreator.buildModel(DataSplit split)
void	BayesCategoricalEdgeCreator.buildModel(DataSplit split)
Classification	EdgeCreatorImp.getLabeledNodes(DataSplit split, boolean useTrueAssort) Get a classification object which contains all the nodes to be used to calculate assortativity