/** * NeedlemanWunsch distance is a measure of the similarity between two strings, which we will refer to as the source * string (s) and the target string (t). The distance is the number of deletions, insertions, or substitutions * required to transform s into t. */ public static Long getNeedlemanWunsch_Distance( ValueMetaInterface metaA, Object dataA, ValueMetaInterface metaB, Object dataB ) { if ( dataA == null || dataB == null ) { return null; } return new Long( (int) new NeedlemanWunsch().score( dataA.toString(), dataB.toString() ) ); }
csimilarity = new Jaro().score( cacheValue, lookupvalue ); break; case FuzzyMatchMeta.OPERATION_TYPE_JARO_WINKLER: csimilarity = new JaroWinkler().score( cacheValue, lookupvalue ); break; default:
public CombinedStringDistanceLearner() { innerLearners = new StringDistanceLearner[] { new JaroWinkler() ,new ScaledLevenstein() ,new Jaccard() ,new TFIDF() ,new JaroWinklerTFIDF() }; delim = null; }
final public StringWrapper prepare(String s) { MultiStringWrapper ms = asMultiStringWrapper(new BasicStringWrapper(s)); ms.prepare( innerDistances ); return ms; }
public LevenshteinSecondStringComparator() { secondStringMeasureL1 = new Levenstein(); secondStringMeasureL2 = new Level2Levenstein(); } }
public JaroSecondStringComparator() { secondStringMeasureL1 = new Jaro(); secondStringMeasureL2 = new Level2Jaro(); } }
public String explainScore(StringWrapper s,StringWrapper t) { MatrixTrio mat = new MatrixTrio( s, t ); double d = score(s,t,mat); return mat.toString() + "\nScore = "+d; }
public UnitVector(BagOfTokens bag) { this(bag.unwrap(), bag.getTokens()); termFreq2TFIDF(); } /** convert term frequency weights to unit-length TFIDF weights */
public CombinedStringDistanceLearner() { innerLearners = new StringDistanceLearner[] { new JaroWinkler() ,new ScaledLevenstein() ,new Jaccard() ,new TFIDF() ,new JaroWinklerTFIDF() }; delim = null; }
final public StringWrapper prepare(String s) { MultiStringWrapper ms = asMultiStringWrapper(new BasicStringWrapper(s)); ms.prepare( innerDistances ); return ms; }
break; case FuzzyMatchMeta.OPERATION_TYPE_NEEDLEMAN_WUNSH: cdistance = Math.abs( (int) new NeedlemanWunsch().score( usecacheValue, uselookupvalue ) ); break; default:
public CombinedStringDistanceLearner() { innerLearners = new StringDistanceLearner[] { new JaroWinkler() ,new ScaledLevenstein() ,new Jaccard() ,new TFIDF() ,new JaroWinklerTFIDF() }; delim = null; }
final public StringWrapper prepare(String s) { MultiStringWrapper ms = asMultiStringWrapper(new BasicStringWrapper(s)); ms.prepare( innerDistances ); return ms; }