[TestCase(" ", " ", 0)] // Doesn't contain shingles and should therefore have 0 similarity
public void FullImplementationSimilarityTest(string first, string second, double expectedSimilarity)
{
List <string> firstList = InitializeListWithWords(first);
List <string> secondList = InitializeListWithWords(second);
var test = new JaccardSimilarity(firstList, secondList);
Assert.AreEqual(expectedSimilarity, test.Similarity);
}
[TestCase("We could also try with two equal sentences", "We could also try with two equal sentences", 5)] // Equal sentences
public void AllElementsTest(string first, string second, int expectedResult)
{
List <string> firstList = InitializeListWithWords(first);
List <string> secondList = InitializeListWithWords(second);
var test = new JaccardSimilarity(firstList, secondList);
Assert.AreEqual(expectedResult, test.AllElements.Count());
}
[Test()] // Check that the first text are handled correctly
public void InitializeTextATest()
{
List <string> first = InitializeListWithWords("This is a test");
var test = new JaccardSimilarity(first, new List <string>()
{
"Can't be empty"
});
CollectionAssert.AreEqual(first, test.TextA);
}
// We expect no shingles to be generated from the 2 above standing texts input
public void GetShinglesBExpectNoShinglesInGivenTextTest(string text)
{
var listOfWords = InitializeListWithWords(text);
var test = new JaccardSimilarity(new List <string>()
{
"Can't be empty"
}, listOfWords);
Assert.IsFalse(test.shinglesB.Any());
}
[Test()] // Check that the second text are handled correctly
public void InitializeTextBTest()
{
List <string> Second = InitializeListWithWords("This is a test");
var test = new JaccardSimilarity(new List <string>()
{
"Can't be empty"
}, Second);
CollectionAssert.AreEqual(Second, test.TextB);
}
[Test()] // Method that insert stopwords to HashSet
public void AmountOfStopwordsTest()
{
var test = new JaccardSimilarity(new List <string>()
{
"Can't be empty"
}, new List <string>()
{
"Can't be empty"
});
Assert.AreEqual(464, test.stopWords.Count);
}
[Test()] // Load of stopwords from textfile
public void TemporaryStopwordsTest()
{
var test = new JaccardSimilarity(new List <string>()
{
"Can't be empty"
}, new List <string>()
{
"Can't be empty"
});
Assert.AreEqual(464, test.tempStopWords.Count());
}
"to check for", "for generated shingles")] // Regular sentence
public void GetShinglesBShinglesInGivenTextTest(string text, params string[] shingles)
{
List <string> listOfWords = InitializeListWithWords(text);
List <string> expectedResult = InitiaizeListWithShingles(shingles);
var test = new JaccardSimilarity(new List <string>()
{
"Can't be empty"
}, listOfWords);
CollectionAssert.AreEqual(expectedResult, test.shinglesB);
}
static void Main(string[] args)
{
Stopwatch stopwatch = new Stopwatch();
Console.WriteLine(Stopwatch.IsHighResolution);
stopwatch.Start();
#region LevenshteinDistance
//Indlæser hver linje af teksten til en liste af strings
LoadStringToList tekstA = new LoadStringToList(@"C:\Users\Patri\Dropbox\Projekt\P2\Program\Nyheder_Database\Koran_Bible_Same1.txt");
LoadStringToList tekstB = new LoadStringToList(@"C:\Users\Patri\Dropbox\Projekt\P2\Program\Nyheder_Database\Koran_Bible_Same2.txt");
// Beregner LevenshteinDistance
LevenshteinDistance levDis = new LevenshteinDistance(tekstA.Lines, tekstB.Lines, tekstA.GetAmountOfChars(),
tekstB.GetAmountOfChars(), tekstA.LinesInText, tekstB.LinesInText);
levDis.Print(); // Printer LevenshteinDistance mellem de to tekster
#endregion
Console.WriteLine(stopwatch.ElapsedMilliseconds);
stopwatch.Restart();
#region CosineDistance
//Indlæser hvert ord fra teksten til en liste af strings
LoadEachWordToList TextA = new LoadEachWordToList(@"C:\Users\Patri\Dropbox\Projekt\P2\Program\Nyheder_Database\Koran_Bible_Same1.txt");
LoadEachWordToList TextB = new LoadEachWordToList(@"C:\Users\Patri\Dropbox\Projekt\P2\Program\Nyheder_Database\Koran_Bible_Same2.txt");
CalculateCosine CalcCos = new CalculateCosine(TextA.Words, TextB.Words); // Beregner CosineDistance
CalcCos.Print(); // Printer CosineSimilarity mellem de to tekster
#endregion
Console.WriteLine(stopwatch.ElapsedMilliseconds);
stopwatch.Restart();
#region JaccardDistance
JaccardSimilarity nytekstA = new JaccardSimilarity(TextA.Words, TextB.Words); // TextA og TextB er indlæst i #region CosineDistance - (LoadEachWordToList)
nytekstA.Print(); // Printer JaccardSimilarity mellem de to tekster
#endregion
Console.WriteLine(stopwatch.ElapsedMilliseconds);
stopwatch.Stop();
#region TryDiffrentLoadMethod (Resources)
//var TekstA = new List<string>();
//var TekstB = new List<string>();
//string[] stringSeparators = { ",", ".", "!", "?", ";", ":", " ", "-", "\"", "(", ")" };
//TekstA = Resources.Pizzagate1.Split(stringSeparators, StringSplitOptions.RemoveEmptyEntries).ToList();
//TekstB = Resources.Pizzagate2.Split(stringSeparators, StringSplitOptions.RemoveEmptyEntries).ToList();
//CalculateCosine CalcCos2 = new CalculateCosine(TekstA, TekstB); // Beregner CosineDistance
//CalcCos2.Print(); // Printer CosineDistance mellem de to tekster
#endregion
Console.ReadLine();
}
[Test()] // Test for two hole text1s in reverse order (added as resources)
public void SimilarityBetweenTwoRealTextstInReverseOrderTest()
{
List <string> firstText;
List <string> secondText;
InitializeListWithWordsFromText(out firstText, out secondText);
var test = new JaccardSimilarity(secondText, firstText);
decimal similarity = Math.Round(test.Similarity, 6);
Assert.AreEqual(0.008997, similarity);
}
// Returns the greatest JaccardSimilarity optained by comparing the text to texts in the directory
public override decimal CompareWithTexts(List <string> paths)
{
decimal greatestSimilarity = 0;
foreach (string path in paths) // Gets JaccardSimilarity for all false articles
{
var databaseText = new LoadEachWordToList(path);
var compareTexts = new JaccardSimilarity(TextToBeCompared, databaseText.Words);
// Happens if the jaccardSimilarity between the two current texts are the greatest so far
if (compareTexts.Similarity > greatestSimilarity)
{
greatestSimilarity = compareTexts.Similarity;
}
}
return(greatestSimilarity);
}
public void GetSimilarity_TwoDifferentVectors_ExpectedResult()
{
JaccardSimilarity js = new JaccardSimilarity();
Article x = new Article();
Article y = new Article();
x.Vector[1] = 1;
x.Vector[2] = 3;
x.Vector[3] = 5;
y.Vector[1] = 2;
y.Vector[2] = 4;
y.Vector[5] = 3;
double expected = 0.28571428571428571428571428571429;
double actual = js.GetSimilarity(x, y);
Assert.IsTrue(Math.Abs(expected - actual) < 0.001);
}
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));
}
}
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);
}
public IEnumerable <GameDTO> GetGamesByCollaborative(Guid gamekey, UserDTO userDTO = null)
{
//var user = _unitOfWork.Users.Get(x => x.IsWoman == userDTO.IsWoman && x.Adulthood == userDTO.Adulthood);
var user = _unitOfWork.Users.GetAll();
UserProfile currentUserProfile = new UserProfile(Guid.NewGuid(), new Guid[] { gamekey });
var profiles = new List <UserProfile>();
for (int i = 0; i < user.Count(); i++)
{
var orders = _unitOfWork.Orders.Get(u => u.UserId == user.ToArray()[i].Id);
var orderDet = _unitOfWork.OrderDetails.Get(od => orders.Any(o => od.OrderId == o.Id));
var games = _unitOfWork.Games.Get(g => orderDet.Any(o => g.Id == o.GameId));
var gamesId = new Guid[games.Count()];
for (int j = 0; j < games.Count(); j++)
{
gamesId[j] = games.ToArray()[j].Id;
}
if (user.ToArray()[i].Id == userDTO.Id)
{
var gamesIds = new Guid[games.Count() + 1];
for (int j = 0; j < gamesId.Count(); j++)
{
gamesIds[j] = gamesId[j];
}
gamesIds[games.Count()] = gamekey;
currentUserProfile = new UserProfile(user.ToArray()[i].Id, gamesId);
}
profiles.Add(new UserProfile(user.ToArray()[i].Id, gamesId));
}
var simiarity = new JaccardSimilarity();
var engine = new CollaborativeFiltering();
var results = engine.recommend(profiles, simiarity, currentUserProfile);
var games3 = _unitOfWork.Games.Get(x => results.Any(r => x.Id == r.Key));
if (results.ElementAt(0).Value == 0)
{
var user2 = user.Where(x => x.IsWoman == userDTO.IsWoman && x.Adulthood == userDTO.Adulthood);
var profiles2 = new List <UserProfile>();
for (int i = 0; i < user2.Count(); i++)
{
var orders = _unitOfWork.Orders.Get(u => u.UserId == user.ToArray()[i].Id);
var orderDet = _unitOfWork.OrderDetails.Get(od => orders.Any(o => od.OrderId == o.Id));
var games = _unitOfWork.Games.Get(g => orderDet.Any(o => g.Id == o.GameId));
var gamesId = new Guid[games.Count()];
for (int j = 0; j < games.Count(); j++)
{
gamesId[j] = games.ToArray()[j].Id;
}
if (user2.ToArray()[i].Id == userDTO.Id)
{
currentUserProfile = new UserProfile(user.ToArray()[i].Id, gamesId);
}
profiles.Add(new UserProfile(user.ToArray()[i].Id, gamesId));
}
var simiarity2 = new JaccardSimilarity();
var engine2 = new CollaborativeFiltering();
var results2 = engine.recommend(profiles, simiarity, currentUserProfile);
var games2 = _unitOfWork.Games.Get(x => results.Any(r => x.Id == r.Key));
return(_mapper.Map <IEnumerable <GameDTO> >(games3));
}
return(_mapper.Map <IEnumerable <GameDTO> >(games3));
}
// [SetUp]
public JaccardSimilarityUnitTests()
{
LoadData();
_myJaccardSimilarity = new JaccardSimilarity();
}