org.aksw.limes.core.ml.algorithm

Class WombatSimple

java.lang.Object

org.aksw.limes.core.ml.algorithm.ACoreMLAlgorithm

org.aksw.limes.core.ml.algorithm.wombat.AWombat

org.aksw.limes.core.ml.algorithm.WombatSimple

public class WombatSimple
extends AWombat

Simple implementation of the Wombat algorithm Fast implementation, that is not complete

Version:

Jun 7, 2016

Author:

Mohamed Sherif (sherif@informatik.uni-leipzig.de)

Field Summary

Fields inherited from class org.aksw.limes.core.ml.algorithm.wombat.AWombat

isUnsupervised, PARAMETER_ATOMIC_MEASURES, PARAMETER_CHILDREN_PENALTY_WEIGHT, PARAMETER_COMPLEXITY_PENALTY_WEIGHT, PARAMETER_EXECUTION_TIME_IN_MINUTES, PARAMETER_FMEASURE_BETA, PARAMETER_MAX_FITNESS_THRESHOLD, PARAMETER_MAX_ITERATION_TIME_IN_MINUTES, PARAMETER_MAX_ITERATIONS_NUMBER, PARAMETER_MAX_REFINEMENT_TREE_SIZE, PARAMETER_MIN_PROPERTY_COVERAGE, PARAMETER_OVERALL_PENALTY_WEIGHT, PARAMETER_PROPERTY_LEARNING_RATE, PARAMETER_SAVE_MAPPING, PARAMETER_VERBOSE, pseudoFMeasure, sourcePropertiesCoverageMap, sourceSample, sourceUris, sourceVariable, targetPropertiesCoverageMap, targetSample, targetUris, targetVariable, trainingData, wombatParameterNames

Fields inherited from class org.aksw.limes.core.ml.algorithm.ACoreMLAlgorithm

configuration, learningParameters, sourceCache, targetCache

Constructor Summary

Constructors

Modifier	Constructor and Description
protected	WombatSimple() WombatSimple constructor.

Method Summary

Modifier and Type	Method and Description
protected MLResults	activeLearn() Learning method for supervised active core ML algorithm implementations Normally, it is used as a first step to initialize the ML model before going through the active learning process
protected MLResults	activeLearn(AMapping oracleMapping) Learning method for supervised active core ML algorithm implementations.
protected void	createRefinementTreeRoot() initiate the refinement tree as a root node with set of children nodes containing all initial classifiers
RefinementNode	findBestSolution()
protected List<RefinementNode>	getBestKNodes(Tree<RefinementNode> r, int k)
protected String	getName() Name of the core ML algorithm.
protected AMapping	getNextExamples(int size) Get a set of examples to be added to the mapping.
protected TreeSet<RefinementNode>	getSortedNodes(Tree<RefinementNode> r, double penaltyWeight, TreeSet<RefinementNode> result)
protected void	init(List<LearningParameter> lp, ACache sourceCache, ACache targetCache) Initialize the core ML algorithm.
protected MLResults	learn(AMapping trainingData) Learning method for supervised core ML algorithm implementations, where the confidence values for each pair in the trainingData determine its truth degree.
protected MLResults	learn(PseudoFMeasure pfm) Learning method for unsupervised core ML algorithm implementations.
protected boolean	supports(MLImplementationType mlType) Check whether the mlType is supported.
protected void	updateScores(Tree<RefinementNode> r) update F-Measure of the refinement tree r based on either training data or PFM

Methods inherited from class org.aksw.limes.core.ml.algorithm.wombat.AWombat

createNode, fillSampleSourceTargetCaches, findInitialClassifiers, fMeasure, getAtomicMeasures, getBestNode, getBeta, getChildrenPenaltyWeight, getComplexityPenaltyWeight, getExcutionTimeInMinutes, getIterationTimeInMinutes, getMappingOfMetricExpression, getMaxFitnessThreshold, getMaxIterationNumber, getMaxRefinmentTreeSize, getMinPropertyCoverage, getMostPromisingNode, getOverAllPenaltyWeight, getPropertyLearningRate, isUnsupervised, isVerbose, precision, predict, recall, saveMapping, setDefaultParameters

Methods inherited from class org.aksw.limes.core.ml.algorithm.ACoreMLAlgorithm

getConfiguration, getParameter, getParameters, getSourceCache, getTargetCache, setConfiguration, setParameter

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

WombatSimple

protected WombatSimple()

WombatSimple constructor.

Method Detail

getName

protected String getName()

Description copied from class: ACoreMLAlgorithm

Name of the core ML algorithm.

Specified by:

getName in class ACoreMLAlgorithm

Returns:

Name of the core ML algorithm.

init

protected void init(List<LearningParameter> lp,
                    ACache sourceCache,
                    ACache targetCache)

Description copied from class: ACoreMLAlgorithm

Initialize the core ML algorithm.

Overrides:

init in class AWombat

Parameters:

lp - learning parameters

sourceCache - the source cache

targetCache - the target cache

learn

protected MLResults learn(AMapping trainingData)

Description copied from class: ACoreMLAlgorithm

Learning method for supervised core ML algorithm implementations, where the confidence values for each pair in the trainingData determine its truth degree.

Specified by:

learn in class ACoreMLAlgorithm

Parameters:

trainingData - used for learning

Returns:

wrap with results

learn

protected MLResults learn(PseudoFMeasure pfm)

Description copied from class: ACoreMLAlgorithm

Learning method for unsupervised core ML algorithm implementations.

Specified by:

learn in class ACoreMLAlgorithm

Parameters:

pfm - pseudo F-measure for unsupervised learning

Returns:

wrap with results

supports

protected boolean supports(MLImplementationType mlType)

Description copied from class: ACoreMLAlgorithm

Check whether the mlType is supported.

Specified by:

supports in class ACoreMLAlgorithm

Parameters:

mlType - machine learning implementation type

Returns:

a boolean value

getNextExamples

protected AMapping getNextExamples(int size)
                            throws UnsupportedMLImplementationException

Description copied from class: ACoreMLAlgorithm

Get a set of examples to be added to the mapping.

Specified by:

getNextExamples in class ACoreMLAlgorithm

Parameters:

size - of the examples

Returns:

the mapping

Throws:

UnsupportedMLImplementationException - Exception

activeLearn

protected MLResults activeLearn()

Description copied from class: ACoreMLAlgorithm

Learning method for supervised active core ML algorithm implementations Normally, it is used as a first step to initialize the ML model before going through the active learning process

Specified by:

activeLearn in class ACoreMLAlgorithm

Returns:

wrap with results

activeLearn

protected MLResults activeLearn(AMapping oracleMapping)

Description copied from class: ACoreMLAlgorithm

Learning method for supervised active core ML algorithm implementations.

Specified by:

activeLearn in class ACoreMLAlgorithm

Parameters:

oracleMapping - mapping from the oracle

Returns:

wrap with results

updateScores

protected void updateScores(Tree<RefinementNode> r)

update F-Measure of the refinement tree r based on either training data or PFM

Parameters:

r - refinement tree

findBestSolution

public RefinementNode findBestSolution()

Returns:

RefinementNode containing the best over all solution

getBestKNodes

protected List<RefinementNode> getBestKNodes(Tree<RefinementNode> r,
                                             int k)

Parameters:

r - the root of the refinement tree

k - number of best nodes

Returns:

sorted list of best k tree nodes

getSortedNodes

protected TreeSet<RefinementNode> getSortedNodes(Tree<RefinementNode> r,
                                                 double penaltyWeight,
                                                 TreeSet<RefinementNode> result)

Parameters:

r - the root of the refinement tree

penaltyWeight - from 0 to 1

result - refinment tree

Returns:

sorted list of tree nodes

createRefinementTreeRoot

protected void createRefinementTreeRoot()

initiate the refinement tree as a root node with set of children nodes containing all initial classifiers