com.wcohen.ss

Class AbstractSourcedTokenizedStringDistance

java.lang.Object

com.wcohen.ss.AbstractStringDistance

com.wcohen.ss.AbstractSourcedTokenizedStringDistance

All Implemented Interfaces:

StringDistance, StringDistanceLearner

Direct Known Subclasses:

AbstractSourcedStatisticalTokenDistance

public abstract class AbstractSourcedTokenizedStringDistance
extends AbstractStringDistance

Abstract distance metric for tokenized strings.

Field Summary

Fields

Modifier and Type	Field and Description
protected SourcedTokenizer	tokenizer

Constructor Summary

Constructors

Constructor and Description
AbstractSourcedTokenizedStringDistance()
AbstractSourcedTokenizedStringDistance(Tokenizer tokenizer)

Method Summary

Modifier and Type	Method and Description
protected com.wcohen.ss.BagOfSourcedTokens	asBagOfSourcedTokens(SourcedStringWrapper w)
StringWrapperIterator	prepare(StringWrapperIterator i0) Implements StringDistanceLearner api by providing a way to prep a StringWrapperIterator for training.
void	setStringWrapperPool(StringWrapperIterator i) Implements the StringDistanceLearner api, by providing a way to accumulate statistics for a set of related strings.
abstract void	train(StringWrapperIterator i)

Methods inherited from class com.wcohen.ss.AbstractStringDistance

addExample, doMain, explainScore, explainScore, getDistance, hasNextQuery, nextQuery, prepare, prepare, score, score, setDistanceInstancePool

Methods inherited from class java.lang.Object

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

Field Detail

tokenizer

protected SourcedTokenizer tokenizer

Constructor Detail

AbstractSourcedTokenizedStringDistance

public AbstractSourcedTokenizedStringDistance(Tokenizer tokenizer)

AbstractSourcedTokenizedStringDistance

public AbstractSourcedTokenizedStringDistance()

Method Detail

setStringWrapperPool

public final void setStringWrapperPool(StringWrapperIterator i)

Description copied from class: AbstractStringDistance

Implements the StringDistanceLearner api, by providing a way to accumulate statistics for a set of related strings. This is for distance metrics like TFIDF that use statistics on unlabeled strings to adjust a distance metric. The Default is to do nothing; override this method if it's necessary to accumulate statistics.

Specified by:

setStringWrapperPool in interface StringDistanceLearner

Overrides:

setStringWrapperPool in class AbstractStringDistance

train

public abstract void train(StringWrapperIterator i)

prepare

public final StringWrapperIterator prepare(StringWrapperIterator i0)

Description copied from class: AbstractStringDistance

Implements StringDistanceLearner api by providing a way to prep a StringWrapperIterator for training. By default this makes no changes to the iterator.

Specified by:

prepare in interface StringDistanceLearner

Overrides:

prepare in class AbstractStringDistance

asBagOfSourcedTokens

protected final com.wcohen.ss.BagOfSourcedTokens asBagOfSourcedTokens(SourcedStringWrapper w)