Package org.tribuo.classification.ensemble

Class AdaBoostTrainer

java.lang.Object

org.tribuo.classification.ensemble.AdaBoostTrainer

All Implemented Interfaces:

com.oracle.labs.mlrg.olcut.config.Configurable, com.oracle.labs.mlrg.olcut.provenance.Provenancable<TrainerProvenance>, Trainer<Label>

public class AdaBoostTrainer
extends Object
implements Trainer<Label>

Implements Adaboost.SAMME one of the more popular algorithms for multiclass boosting. Based on this paper.

If the trainer implements WeightedExamples then it performs boosting by weighting, otherwise it uses a weighted bootstrap sample.

See:

 J. Zhu, S. Rosset, H. Zou, T. Hastie.
 "Multi-class Adaboost"
 2006.
 

Field Summary

Fields

Modifier and Type	Field	Description
protected Trainer<Label>	innerTrainer
protected int	numMembers
protected SplittableRandom	rng
protected long	seed
protected int	trainInvocationCounter

Fields inherited from interface org.tribuo.Trainer

DEFAULT_SEED, INCREMENT_INVOCATION_COUNT

Constructor Summary

Constructors

Constructor	Description
AdaBoostTrainer(Trainer<Label> trainer, int numMembers)	Constructs an adaboost trainer using the supplied weak learner trainer and the specified number of boosting rounds.
AdaBoostTrainer(Trainer<Label> trainer, int numMembers, long seed)	Constructs an adaboost trainer using the supplied weak learner trainer, the specified number of boosting rounds and the supplied seed.

Method Summary

Modifier and Type	Method	Description
int	getInvocationCount()
TrainerProvenance	getProvenance()
void	postConfig()	Used by the OLCUT configuration system, and should not be called by external code.
void	setInvocationCount(int invocationCount)
String	toString()
Model<Label>	train(Dataset<Label> examples, Map<String,com.oracle.labs.mlrg.olcut.provenance.Provenance> runProvenance)	If the trainer implements WeightedExamples then do boosting by weighting, otherwise do boosting by sampling.
Model<Label>	train(Dataset<Label> examples, Map<String,com.oracle.labs.mlrg.olcut.provenance.Provenance> runProvenance, int invocationCount)

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.tribuo.Trainer

train

Field Details

innerTrainer

@Config(mandatory=true,
        description="The trainer to use to build each weak learner.")
protected Trainer<Label> innerTrainer

numMembers

@Config(mandatory=true,
        description="The number of ensemble members to train.")
protected int numMembers

seed

@Config(mandatory=true,
        description="The seed for the RNG.")
protected long seed

rng

protected SplittableRandom rng

trainInvocationCounter

protected int trainInvocationCounter

Constructor Details

AdaBoostTrainer

public AdaBoostTrainer(Trainer<Label> trainer,
 int numMembers)

Constructs an adaboost trainer using the supplied weak learner trainer and the specified number of boosting rounds. Uses the default seed.

Parameters:

trainer - The weak learner trainer.

numMembers - The maximum number of boosting rounds.

AdaBoostTrainer

public AdaBoostTrainer(Trainer<Label> trainer,
 int numMembers,
 long seed)

Constructs an adaboost trainer using the supplied weak learner trainer, the specified number of boosting rounds and the supplied seed.

Parameters:

trainer - The weak learner trainer.

numMembers - The maximum number of boosting rounds.

seed - The RNG seed.

Method Details

postConfig

public void postConfig()

Used by the OLCUT configuration system, and should not be called by external code.

Specified by:

postConfig in interface com.oracle.labs.mlrg.olcut.config.Configurable

toString

public String toString()

Overrides:

toString in class Object

train

public Model<Label> train(Dataset<Label> examples,
 Map<String,com.oracle.labs.mlrg.olcut.provenance.Provenance> runProvenance)

If the trainer implements WeightedExamples then do boosting by weighting, otherwise do boosting by sampling.

Specified by:

train in interface Trainer<Label>

Parameters:

examples - the data set containing the examples.

Returns:

A WeightedEnsembleModel.

train

public Model<Label> train(Dataset<Label> examples,
 Map<String,com.oracle.labs.mlrg.olcut.provenance.Provenance> runProvenance,
 int invocationCount)

Specified by:

train in interface Trainer<Label>

getInvocationCount

public int getInvocationCount()

Specified by:

getInvocationCount in interface Trainer<Label>

setInvocationCount

public void setInvocationCount(int invocationCount)

Specified by:

setInvocationCount in interface Trainer<Label>

getProvenance

public TrainerProvenance getProvenance()

Specified by:

getProvenance in interface com.oracle.labs.mlrg.olcut.provenance.Provenancable<TrainerProvenance>