Package ai.libs.jaicore.ml.dyadranking.activelearning

Class ARandomlyInitializingDyadRanker

java.lang.Object

ai.libs.jaicore.ml.dyadranking.activelearning.ActiveDyadRanker

ai.libs.jaicore.ml.dyadranking.activelearning.ARandomlyInitializingDyadRanker

Direct Known Subclasses:

ConfidenceIntervalClusteringBasedActiveDyadRanker, PrototypicalPoolBasedActiveDyadRanker, RandomPoolBasedActiveDyadRanker, UCBPoolBasedActiveDyadRanker

public abstract class ARandomlyInitializingDyadRanker
extends ActiveDyadRanker

Field Summary

Fields inherited from class ai.libs.jaicore.ml.dyadranking.activelearning.ActiveDyadRanker

poolProvider, ranker

Constructor Summary

Constructors

Constructor	Description
ARandomlyInitializingDyadRanker(PLNetDyadRanker ranker, IDyadRankingPoolProvider poolProvider, int seed, int numberRandomQueriesAtStart, int minibatchSize)

Method Summary

Modifier and Type	Method	Description
void	activelyTrain(int numberOfQueries)	Actively trains the ranker for a certain number of queries.
abstract void	activelyTrainWithOneInstance()
java.util.Map<Dyad,org.apache.commons.math3.stat.descriptive.SummaryStatistics>	getDyadStats()
java.util.List<ai.libs.jaicore.math.linearalgebra.Vector>	getInstanceFeatures()
int	getIteration()
int	getMinibatchSize()
int	getNumberRandomQueriesAtStart()
java.util.Random	getRandom()
void	updateRanker(java.util.Set<IDyadRankingInstance> minibatch)

Methods inherited from class ai.libs.jaicore.ml.dyadranking.activelearning.ActiveDyadRanker

getPoolProvider, getRanker, setPoolProvider, setRanker

Methods inherited from class java.lang.Object

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

Constructor Detail

ARandomlyInitializingDyadRanker

public ARandomlyInitializingDyadRanker(PLNetDyadRanker ranker,
                                       IDyadRankingPoolProvider poolProvider,
                                       int seed,
                                       int numberRandomQueriesAtStart,
                                       int minibatchSize)

Method Detail

activelyTrain

public void activelyTrain(int numberOfQueries)
                   throws TrainingException

Description copied from class: ActiveDyadRanker

Actively trains the ranker for a certain number of queries.

Overrides:

activelyTrain in class ActiveDyadRanker

Parameters:

numberOfQueries - Number of queries the ranker conducts

Throws:

TrainingException

getNumberRandomQueriesAtStart

public int getNumberRandomQueriesAtStart()

getIteration

public int getIteration()

getDyadStats

public java.util.Map<Dyad,org.apache.commons.math3.stat.descriptive.SummaryStatistics> getDyadStats()

getInstanceFeatures

public java.util.List<ai.libs.jaicore.math.linearalgebra.Vector> getInstanceFeatures()

getRandom

public java.util.Random getRandom()

getMinibatchSize

public int getMinibatchSize()

activelyTrainWithOneInstance

public abstract void activelyTrainWithOneInstance()
                                           throws TrainingException

Specified by:

activelyTrainWithOneInstance in class ActiveDyadRanker

Throws:

TrainingException

updateRanker

public void updateRanker(java.util.Set<IDyadRankingInstance> minibatch)
                  throws TrainingException

Throws:

TrainingException