dragon.ml.seqmodel.feature

Class AbstractFeatureType

java.lang.Object

dragon.ml.seqmodel.feature.AbstractFeatureType

All Implemented Interfaces:

FeatureType

Direct Known Subclasses:

FeatureTypeConcatRegex, FeatureTypeEdge, FeatureTypeEnd, FeatureTypeKnownWord, FeatureTypePOSPattern, FeatureTypePrior, FeatureTypeRegexCount, FeatureTypeSegmentLength, FeatureTypeSegmentLengthPoly, FeatureTypeStart, FeatureTypeUnknownWord, FeatureTypeWord, FeatureTypeWordScore

public abstract class AbstractFeatureType
extends Object
implements FeatureType

Abstract class for feature type

Copyright: Copyright (c) 2005

Company: IST, Drexel University

Version:

1.0

Author:

Davis Zhou

Field Summary

Fields

Modifier and Type	Field and Description
protected String	idPrefix

Constructor Summary

Constructors

Constructor and Description
AbstractFeatureType(boolean needTraining)

Method Summary

Modifier and Type	Method and Description
int	getTypeID() Gets the unique id of the current feature type.
boolean	needTraining() Tests if the current feature type needs training
boolean	readTrainingResult() Reads the training result in testing mode
boolean	saveTrainingResult() Saves the training results in training mode
void	setTypeID(int typeID) Sets the id of the current feature type
boolean	startScanFeaturesAt(DataSequence data, int pos)
boolean	supportSegment() Tests if the feature type supports generating features for segments.
boolean	train(Dataset data) Trains the feature types with the labeled training dataset

Methods inherited from class java.lang.Object

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

Methods inherited from interface dragon.ml.seqmodel.feature.FeatureType

hasNext, next, startScanFeaturesAt

Field Detail

idPrefix

protected String idPrefix

Constructor Detail

AbstractFeatureType

public AbstractFeatureType(boolean needTraining)

Method Detail

needTraining

public boolean needTraining()

Description copied from interface: FeatureType

Tests if the current feature type needs training

Specified by:

needTraining in interface FeatureType

Returns:

true if the feature type needs training

train

public boolean train(Dataset data)

Description copied from interface: FeatureType

Trains the feature types with the labeled training dataset

Specified by:

train in interface FeatureType

Parameters:

data - the dataset for training

Returns:

true if trained successfully

saveTrainingResult

public boolean saveTrainingResult()

Description copied from interface: FeatureType

Saves the training results in training mode

Specified by:

saveTrainingResult in interface FeatureType

Returns:

true if saved successfully

readTrainingResult

public boolean readTrainingResult()

Description copied from interface: FeatureType

Reads the training result in testing mode

Specified by:

readTrainingResult in interface FeatureType

Returns:

training result

getTypeID

public int getTypeID()

Description copied from interface: FeatureType

Gets the unique id of the current feature type.

Specified by:

getTypeID in interface FeatureType

Returns:

type ID

setTypeID

public void setTypeID(int typeID)

Description copied from interface: FeatureType

Sets the id of the current feature type

Specified by:

setTypeID in interface FeatureType

Parameters:

typeID - the type id

startScanFeaturesAt

public boolean startScanFeaturesAt(DataSequence data,
                                   int pos)

supportSegment

public boolean supportSegment()

Description copied from interface: FeatureType

Tests if the feature type supports generating features for segments.

Specified by:

supportSegment in interface FeatureType

Returns:

true if supported