public void NonEmptyCases()
{
Assert.Equal(0.8222222, Jaro.Similarity("DWAYNE", "DUANE"), 7);
Assert.Equal(0.9444444, Jaro.Similarity("MARTHA", "MARHTA"), 7);
Assert.Equal(0.7666667, Jaro.Similarity("DIXON", "DICKSONX"), 7);
Assert.Equal(0.8962963, Jaro.Similarity("JELLYFISH", "SMELLYFISH"), 7);
}
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 void Jaro_button_Click(object sender, EventArgs e)
{
JaroRez.Text = Jaro.Func(JaroText1.Text, JaroText2.Text).ToString();
}
// сравнение
private List <string[]> Sravn(string[][] data)
{
List <string[]> rezlist = new List <string[]>();
foreach (string[] str in data)
{
// количество слов в строке
if (str.Count() != 2)
{
continue;
}
else
{
string[] mass;
SimMetricsMetricUtilities.Levenstein ex_l = new SimMetricsMetricUtilities.Levenstein();
Stopwatch t = new Stopwatch();
t.Start();
double rj1 = Math.Round(Jaro.Func(str[0], str[1]), 2);
string tj1 = Math.Round(t.Elapsed.TotalMilliseconds, 2).ToString();
t = new Stopwatch();
t.Start();
double rj2 = Math.Round(ExJaro.distance(str[0], str[1]), 2);
string tj2 = Math.Round(t.Elapsed.TotalMilliseconds, 2).ToString();
// -----
t = new Stopwatch();
t.Start();
double rjv1 = Math.Round(JaroVincler.Func(str[0], str[1]), 2);
string tjv1 = Math.Round(t.Elapsed.TotalMilliseconds, 2).ToString();
t = new Stopwatch();
t.Start();
double rjv2 = Math.Round(ExJaroWincler.distance(str[0], str[1]), 2);
string tjv2 = Math.Round(t.Elapsed.TotalMilliseconds, 2).ToString();
// ----
t = new Stopwatch();
t.Start();
double rl1 = Math.Round(Levenstein.Func(str[0], str[1]), 2);
string tl1 = Math.Round(t.Elapsed.TotalMilliseconds, 2).ToString();
t = new Stopwatch();
t.Start();
double rl2 = Math.Round(ex_l.GetSimilarity(str[0], str[1]), 2);
string tl2 = Math.Round(t.Elapsed.TotalMilliseconds, 2).ToString();
rezlist.Add(new string[14] {
rj1.ToString(), tj1, rj2.ToString(), tj2,
rjv1.ToString(), tjv1, rjv2.ToString(), tjv2,
rl1.ToString(), tl1, rl2.ToString(), tl2, str[0], str[1]
});
}
}
return(rezlist);
}
public double GetSimilarity(string str1, string str2, string type)
{
IStringMetric stringMetric;
switch (type)
{
case AlgorithmTypes.BlockDistance:
stringMetric = new BlockDistance();
break;
case AlgorithmTypes.ChapmanLengthDeviation:
stringMetric = new ChapmanLengthDeviation();
break;
case AlgorithmTypes.ChapmanMeanLength:
stringMetric = new ChapmanMeanLength();
break;
case AlgorithmTypes.CosineSimilarity:
stringMetric = new CosineSimilarity();
break;
case AlgorithmTypes.DiceSimilarity:
stringMetric = new DiceSimilarity();
break;
case AlgorithmTypes.EuclideanDistance:
stringMetric = new EuclideanDistance();
break;
case AlgorithmTypes.JaccardSimilarity:
stringMetric = new JaccardSimilarity();
break;
case AlgorithmTypes.Jaro:
stringMetric = new Jaro();
break;
case AlgorithmTypes.JaroWinkler:
stringMetric = new JaroWinkler();
break;
case AlgorithmTypes.Levenstein:
stringMetric = new Levenstein();
break;
case AlgorithmTypes.MatchingCoefficient:
stringMetric = new MatchingCoefficient();
break;
case AlgorithmTypes.MongeElkan:
stringMetric = new MongeElkan();
break;
case AlgorithmTypes.NeedlemanWunch:
stringMetric = new NeedlemanWunch();
break;
case AlgorithmTypes.OverlapCoefficient:
stringMetric = new OverlapCoefficient();
break;
case AlgorithmTypes.QGramsDistance:
stringMetric = new QGramsDistance();
break;
case AlgorithmTypes.SmithWaterman:
stringMetric = new SmithWaterman();
break;
case AlgorithmTypes.SmithWatermanGotoh:
stringMetric = new SmithWatermanGotoh();
break;
case AlgorithmTypes.SmithWatermanGotohWindowedAffine:
stringMetric = new SmithWatermanGotohWindowedAffine();
break;
default:
stringMetric = new SmithWatermanGotoh();
break;
}
var similarity = stringMetric.GetSimilarity(str1.Trim(), str2.Trim());
return(similarity);
}
// [SetUp]
public JaroAndJaroWinklerUnitTests()
{
LoadData();
_myJaro = new Jaro();
_myJaroWinkler = new JaroWinkler();
}
private void button1_Click(object sender, EventArgs e)
{
Existing_Method ex_m = new Existing_Method();
Jaro m1;
JaroVincler m2;
Levenstein m3;
Stopwatch t = new Stopwatch();
double[] rez_mas = new double[20];
if (System.IO.File.Exists("data.txt"))
{
string[] mass = System.IO.File.ReadAllLines("data.txt");
System.IO.File.WriteAllText("ex_m.txt", "");
// Существующий тест
t.Start();
foreach (string s in mass)
{
string[] str = s.Split(' ');
System.IO.File.AppendAllText("ex_m.txt", ex_m.IndistinctMatching(4, str[0], str[1]).ToString() + Environment.NewLine);
}
t.Stop();
System.IO.File.AppendAllText("ex_m.txt", t.Elapsed.ToString());
System.IO.File.WriteAllText("m1.txt", "");
// Метод 1
t = new Stopwatch();
t.Start();
foreach (string s in mass)
{
string[] str = s.Split(' ');
m1 = new Jaro(str[0], str[1]);
System.IO.File.AppendAllText("m1.txt", (m1.Func() * 100).ToString() + Environment.NewLine);
}
t.Stop();
System.IO.File.AppendAllText("m1.txt", t.Elapsed.ToString());
System.IO.File.WriteAllText("m2.txt", "");
// Метод 2
t = new Stopwatch();
t.Start();
foreach (string s in mass)
{
string[] str = s.Split(' ');
m2 = new JaroVincler(str[0], str[1]);
if (m2.Func())
{
System.IO.File.AppendAllText("m2.txt", "100" + Environment.NewLine);
}
else
{
System.IO.File.AppendAllText("m2.txt", "0" + Environment.NewLine);
}
}
t.Stop();
System.IO.File.AppendAllText("m2.txt", t.Elapsed.ToString());
// Метод 3
System.IO.File.WriteAllText("m3.txt", "");
t = new Stopwatch();
t.Start();
foreach (string s in mass)
{
string[] str = s.Split(' ');
m3 = new Levenstein(str[0], str[1]);
System.IO.File.AppendAllText("m3.txt", (100 - m3.Func() * 100).ToString() + Environment.NewLine);
}
t.Stop();
System.IO.File.AppendAllText("m3.txt", t.Elapsed.ToString());
MessageBox.Show("Выполнено");
}
}
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();
}
public void Initialize()
{
_jaro = new Jaro();
}
public void EmptyCases()
{
Assert.Equal(1, Jaro.Similarity("", ""));
Assert.Equal(0, Jaro.Similarity("", "AB"));
Assert.Equal(0, Jaro.Similarity("AB", ""));
}
