org.tribuo.sequence

Class HashingSequenceTrainer<T extends Output<T>>

java.lang.Object

org.tribuo.sequence.HashingSequenceTrainer<T>

Type Parameters:

T - The type of the output.

All Implemented Interfaces:

com.oracle.labs.mlrg.olcut.config.Configurable, com.oracle.labs.mlrg.olcut.provenance.Provenancable<TrainerProvenance>, SequenceTrainer<T>

public final class HashingSequenceTrainer<T extends Output<T>>
extends Object
implements SequenceTrainer<T>

A SequenceTrainer that hashes all the feature names on the way in.

It wraps another SequenceTrainer which actually builds the SequenceModel.

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	HashingSequenceTrainer.HashingSequenceTrainerProvenance Provenance for HashingSequenceTrainer.

Constructor Summary

Constructors

Constructor and Description
HashingSequenceTrainer(SequenceTrainer<T> trainer, Hasher hasher)

Method Summary

Modifier and Type	Method and Description
int	getInvocationCount() Returns the number of times the train method has been invoked.
TrainerProvenance	getProvenance()
String	toString()
SequenceModel<T>	train(SequenceDataset<T> sequenceExamples, Map<String,com.oracle.labs.mlrg.olcut.provenance.Provenance> instanceProvenance) This clones the SequenceDataset, hashes each of the examples and rewrites their feature ids before passing it to the inner trainer.

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.tribuo.sequence.SequenceTrainer

train

Methods inherited from interface com.oracle.labs.mlrg.olcut.config.Configurable

postConfig

Constructor Detail

HashingSequenceTrainer

public HashingSequenceTrainer(SequenceTrainer<T> trainer,
                              Hasher hasher)

Method Detail

train

public SequenceModel<T> train(SequenceDataset<T> sequenceExamples,
                              Map<String,com.oracle.labs.mlrg.olcut.provenance.Provenance> instanceProvenance)

This clones the SequenceDataset, hashes each of the examples and rewrites their feature ids before passing it to the inner trainer.

This ensures the Trainer sees the data after the collisions, and thus builds the correct size data structures.

Specified by:

train in interface SequenceTrainer<T extends Output<T>>

Parameters:

sequenceExamples - The input dataset.

instanceProvenance - Training run specific provenance information.

Returns:

A trained SequenceModel.

getInvocationCount

public int getInvocationCount()

Description copied from interface: SequenceTrainer

Returns the number of times the train method has been invoked.

Specified by:

getInvocationCount in interface SequenceTrainer<T extends Output<T>>

Returns:

The number of times train has been invoked.

toString

public String toString()

Overrides:

toString in class Object

getProvenance

public TrainerProvenance getProvenance()

Specified by:

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