public void TestSimilarity()
{
var instance = new NormalizedLevenshtein();
NullEmptyTests.TestSimilarity(instance);
// TODO: regular (non-null/empty) similarity tests
}
public void TestSimilarity()
{
var instance = new Cosine();
var result = instance.Similarity("ABC", "ABCE");
Assert.Equal(
expected: 0.71,
actual: result,
precision: 2 // 0.01
);
NullEmptyTests.TestSimilarity(instance);
}
public void TestSimilarity()
{
var instance = new Jaccard(k: 2);
// AB BC CD DE DF
// 1 1 1 1 0
// 1 1 1 0 1
// => 3 / 5 = 0.6
var result = instance.Similarity("ABCDE", "ABCDF");
Assert.Equal(expected: 0.6, actual: result);
NullEmptyTests.TestSimilarity(instance);
}
public void TestSimilarity()
{
var instance = new JaroWinkler();
Assert.Equal(
expected: 0.974074,
actual: instance.Similarity("My string", "My tsring"),
precision: 6 // 0.000001
);
Assert.Equal(
expected: 0.896296,
actual: instance.Similarity("My string", "My ntrisg"),
precision: 6 // 0.000001
);
NullEmptyTests.TestSimilarity(instance);
}
public void TestSimilarity()
{
var instance = new SorensenDice(2);
// AB BC CD DE DF FG
// 1 1 1 1 0 0
// 1 1 1 0 1 1
// => 2 x 3 / (4 + 5) = 6/9 = 0.6666
var result = instance.Similarity("ABCDE", "ABCDFG");
Assert.Equal(
expected: 0.6667, // last digit should be 7 because of rounding
actual: result,
precision: 4 //0.0001
);
NullEmptyTests.TestSimilarity(instance);
}
public void TestSimilarity()
{
var instance = new RatcliffObershelp();
/// test data from other algorithms
/// "My string" vs "My tsring"
/// Substrings:
/// "ring" ==> 4, "My s" ==> 3, "s" ==> 1
/// Ratcliff-Obershelp = 2*(sum of substrings)/(length of s1 + length of s2)
/// = 2*(4 + 3 + 1) / (9 + 9)
/// = 16/18
/// = 0.888888888888889
Assert.Equal(
expected: 0.888888888888889,
actual: instance.Similarity("My string", "My tsring"),
precision: 15 /// 0.000000000000001
);
/// test data from other algorithms
/// "My string" vs "My tsring"
/// Substrings:
/// "My " ==> 3, "tri" ==> 3, "g" ==> 1
/// Ratcliff-Obershelp = 2*(sum of substrings)/(length of s1 + length of s2)
/// = 2*(3 + 3 + 1) / (9 + 9)
/// = 14/18
/// = 0.777777777777778
Assert.Equal(
expected: 0.777777777777778,
actual: instance.Similarity("My string", "My ntrisg"),
precision: 15 /// 0.000000000000001
);
/// test data from essay by Ilya Ilyankou
/// "Comparison of Jaro-Winkler and Ratcliff/Obershelp algorithms
/// in spell check"
/// https://ilyankou.files.wordpress.com/2015/06/ib-extended-essay.pdf
/// p13, expected result is 0.857
Assert.Equal(
expected: 0.857,
actual: instance.Similarity("MATEMATICA", "MATHEMATICS"),
precision: 3 /// 0.001
);
/// test data from stringmetric
/// https://github.com/rockymadden/stringmetric
/// expected output is 0.736842105263158
Assert.Equal(
expected: 0.736842105263158,
actual: instance.Similarity("aleksander", "alexandre"),
precision: 15 /// 0.000000000000001
);
/// test data from stringmetric
/// https://github.com/rockymadden/stringmetric
/// expected output is 0.666666666666667
Assert.Equal(
expected: 0.666666666666667,
actual: instance.Similarity("pennsylvania", "pencilvaneya"),
precision: 15 /// 0.000000000000001
);
/// test data from wikipedia
/// https://en.wikipedia.org/wiki/Gestalt_Pattern_Matching
/// expected output is 14/18 = 0.777777777777778
Assert.Equal(
expected: 0.777777777777778,
actual: instance.Similarity("WIKIMEDIA", "WIKIMANIA"),
precision: 15 /// 0.000000000000001
);
/// test data from wikipedia
/// https://en.wikipedia.org/wiki/Gestalt_Pattern_Matching
/// expected output is 24/40 = 0.6
Assert.Equal(
expected: 0.6,
actual: instance.Similarity("GESTALT PATTERN MATCHING", "GESTALT PRACTICE"),
precision: 15 /// 0.000000000000001
);
NullEmptyTests.TestSimilarity(instance);
}