public static double ApproximatelyEquals(this string firstWord, string secondWord, SimMetricType simMetricType = SimMetricType.Levenstein)
{
switch (simMetricType)
{
case SimMetricType.BlockDistance:
var sim2 = new BlockDistance();
return(sim2.GetSimilarity(firstWord, secondWord));
case SimMetricType.ChapmanLengthDeviation:
var sim3 = new ChapmanLengthDeviation();
return(sim3.GetSimilarity(firstWord, secondWord));
case SimMetricType.CosineSimilarity:
var sim4 = new CosineSimilarity();
return(sim4.GetSimilarity(firstWord, secondWord));
case SimMetricType.DiceSimilarity:
var sim5 = new DiceSimilarity();
return(sim5.GetSimilarity(firstWord, secondWord));
case SimMetricType.EuclideanDistance:
var sim6 = new EuclideanDistance();
return(sim6.GetSimilarity(firstWord, secondWord));
case SimMetricType.JaccardSimilarity:
var sim7 = new JaccardSimilarity();
return(sim7.GetSimilarity(firstWord, secondWord));
case SimMetricType.Jaro:
var sim8 = new Jaro();
return(sim8.GetSimilarity(firstWord, secondWord));
case SimMetricType.JaroWinkler:
var sim9 = new JaroWinkler();
return(sim9.GetSimilarity(firstWord, secondWord));
case SimMetricType.MatchingCoefficient:
var sim10 = new MatchingCoefficient();
return(sim10.GetSimilarity(firstWord, secondWord));
case SimMetricType.MongeElkan:
var sim11 = new MongeElkan();
return(sim11.GetSimilarity(firstWord, secondWord));
case SimMetricType.NeedlemanWunch:
var sim12 = new NeedlemanWunch();
return(sim12.GetSimilarity(firstWord, secondWord));
case SimMetricType.OverlapCoefficient:
var sim13 = new OverlapCoefficient();
return(sim13.GetSimilarity(firstWord, secondWord));
case SimMetricType.QGramsDistance:
var sim14 = new QGramsDistance();
return(sim14.GetSimilarity(firstWord, secondWord));
case SimMetricType.SmithWaterman:
var sim15 = new SmithWaterman();
return(sim15.GetSimilarity(firstWord, secondWord));
case SimMetricType.SmithWatermanGotoh:
var sim16 = new SmithWatermanGotoh();
return(sim16.GetSimilarity(firstWord, secondWord));
case SimMetricType.SmithWatermanGotohWindowedAffine:
var sim17 = new SmithWatermanGotohWindowedAffine();
return(sim17.GetSimilarity(firstWord, secondWord));
case SimMetricType.ChapmanMeanLength:
var sim18 = new ChapmanMeanLength();
return(sim18.GetSimilarity(firstWord, secondWord));
default:
var sim1 = new Levenstein();
return(sim1.GetSimilarity(firstWord, secondWord));
}
}
private static void Main(string[] args)
{
/****************************************************/
/* BagOfTokensSimilarity */
/****************************************************/
// the recommend method for complex similarity on more words
var bagOfTokens = new BagOfWordsSimilarity();
const string pattern = "John Smith";
const string targetText = "Mr. John Smith, Jr.";
// using normalized string and tokenizer returns score 1.0
var resultingSim = bagOfTokens.GetSimilarity(new Tokenizer(new NormalizedString(pattern)),
new Tokenizer(new NormalizedString(targetText)));
/****************************************************/
/* Levenshtein */
/****************************************************/
const string nameCorrect = "martha";
const string nameError = "marhta";
// Levenshtein distance (implements interface IDistance)
// & similarity (implements interface ISimilarity)
var lev = new Levenshtein();
// returns edit distance 2
var distLev = lev.GetDistance(nameCorrect, nameError);
// normalized string removes special symbols, diacritics and make case insensitivity
// returns score 0.67
var simLev = lev.GetSimilarity(new NormalizedString(nameCorrect), new NormalizedString(nameError));
/****************************************************/
/* Damerau-Levenshtein */
/****************************************************/
// DamerauLevenshtein implements IDistance and ISimilarity
var damLev = new DamerauLevenshtein();
// returns edit distance 1
var distDamLev = damLev.GetDistance(nameCorrect, nameError);
// returns score 0.83
var simDamLev = damLev.GetSimilarity(nameCorrect, nameError);
/****************************************************/
/* Jaro, Jaro-Winler */
/****************************************************/
// Jaro, Jaro-Winkler implements only ISimilarity
var nameFirst = new Token("dwayne");
var nameSecond = new Token("duane");
var jaro = new Jaro();
var jaroWinkler = new JaroWinkler();
jaroWinkler.GetSimilarity(nameFirst, nameSecond);
/****************************************************/
/* Q-grams coefficient */
/****************************************************/
// q-grams similarity coefficient - Dice, Jaccard, Overlap
// with different q-grams type
var diceUnigrams = new DiceCoefficient <Bigram>();
var jaccardBigrams = new JaccardCoefficient <Bigram>();
var overlapTrigrams = new OverlapCoefficient <Bigram>();
// returns score 0.5
var jaccardSim = jaccardBigrams.GetSimilarity(pattern, targetText);
// returns score 0.67
var diceSim = diceUnigrams.GetSimilarity(pattern, targetText);
// returns score 1.0
var overlapSim = overlapTrigrams.GetSimilarity(pattern, targetText);
Console.ReadKey();
}