Package org.tribuo.classification.sequence.viterbi

Class DefaultFeatureExtractor

java.lang.Object

org.tribuo.classification.sequence.viterbi.DefaultFeatureExtractor

All Implemented Interfaces:

com.oracle.labs.mlrg.olcut.config.Configurable, com.oracle.labs.mlrg.olcut.provenance.Provenancable<com.oracle.labs.mlrg.olcut.provenance.ConfiguredObjectProvenance>, Serializable, LabelFeatureExtractor, ProtoSerializable<org.tribuo.classification.protos.LabelFeatureExtractorProto>

public class DefaultFeatureExtractor
extends Object
implements LabelFeatureExtractor

A label feature extractor that produces several kinds of label-based features.

The options are: the most recent output, the least recent output, recent bigrams, recent trigrams, recent 4-grams.

See Also:

• Serialized Form

Field Summary

Fields

Modifier and Type	Field	Description
static final int	CURRENT_VERSION	Protobuf serialization version.

Fields inherited from interface org.tribuo.protos.ProtoSerializable

DESERIALIZATION_METHOD_NAME, PROVENANCE_SERIALIZER

Constructor Summary

Constructors

Constructor	Description
DefaultFeatureExtractor()	Constructs a default feature extractor for bigrams and trigrams using the past 3 outcomes.
DefaultFeatureExtractor(int mostRecentOutcome, int leastRecentOutcome, boolean useBigram, boolean useTrigram, boolean use4gram)	Constructs a default feature extractor using the supplied parameters.

Method Summary

Modifier and Type	Method	Description
static DefaultFeatureExtractor	deserializeFromProto(int version, String className, com.google.protobuf.Any message)	Deserialization factory.
List<Feature>	extractFeatures(List<Label> previousOutcomes, double value)	Generates features based on the previously produced labels.
com.oracle.labs.mlrg.olcut.provenance.ConfiguredObjectProvenance	getProvenance()
org.tribuo.classification.protos.LabelFeatureExtractorProto	serialize()	Serializes this object to a protobuf.
String	toString()

Methods inherited from class java.lang.Object

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

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

postConfig

Field Details

CURRENT_VERSION

public static final int CURRENT_VERSION

Protobuf serialization version.

See Also:

• Constant Field Values

Constructor Details

DefaultFeatureExtractor

public DefaultFeatureExtractor()

Constructs a default feature extractor for bigrams and trigrams using the past 3 outcomes.

DefaultFeatureExtractor

public DefaultFeatureExtractor(int mostRecentOutcome,
 int leastRecentOutcome,
 boolean useBigram,
 boolean useTrigram,
 boolean use4gram)

Constructs a default feature extractor using the supplied parameters.

Parameters:

mostRecentOutcome - The most recent outcome to include as a feature.

leastRecentOutcome - The least recent outcome to include as a feature.

useBigram - Use bigrams of the outcomes.

useTrigram - Use trigrams of the outcomes.

use4gram - Use 4-grams of the outcomes.

Method Details

deserializeFromProto

public static DefaultFeatureExtractor deserializeFromProto(int version,
 String className,
 com.google.protobuf.Any message)
                                                    throws com.google.protobuf.InvalidProtocolBufferException

Deserialization factory.

Parameters:

version - The serialized object version.

className - The class name.

message - The serialized data.

Returns:

The deserialized object.

Throws:

com.google.protobuf.InvalidProtocolBufferException - If the protobuf could not be parsed from the message.

toString

public String toString()

Overrides:

toString in class Object

extractFeatures

public List<Feature> extractFeatures(List<Label> previousOutcomes,
 double value)

Description copied from interface: LabelFeatureExtractor

Generates features based on the previously produced labels.

Specified by:

extractFeatures in interface LabelFeatureExtractor

Parameters:

previousOutcomes - The previous step's labels.

value - The value to give to the features.

Returns:

Features.

getProvenance

public com.oracle.labs.mlrg.olcut.provenance.ConfiguredObjectProvenance getProvenance()

Specified by:

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

serialize

public org.tribuo.classification.protos.LabelFeatureExtractorProto serialize()

Description copied from interface: ProtoSerializable

Serializes this object to a protobuf.

Specified by:

serialize in interface ProtoSerializable<org.tribuo.classification.protos.LabelFeatureExtractorProto>

Returns:

The protobuf.