private double GetActualSimilarity(Collection <string> firstTokens, Collection <string> secondTokens)
{
Collection <string> collection = _tokenUtilities.CreateMergedSet(firstTokens, secondTokens);
int num = 0;
foreach (string str in collection)
{
int num2 = 0;
for (int i = 0; i < firstTokens.Count; i++)
{
if (firstTokens[i].Equals(str))
{
num2++;
}
}
int num4 = 0;
for (int j = 0; j < secondTokens.Count; j++)
{
if (secondTokens[j].Equals(str))
{
num4++;
}
}
if (num2 > num4)
{
num += num2 - num4;
}
else
{
num += num4 - num2;
}
}
return(num);
}
public override double GetSimilarity(string firstWord, string secondWord)
{
if (firstWord != null && secondWord != null && _tokenUtilities.CreateMergedSet(_tokeniser.Tokenize(firstWord), _tokeniser.Tokenize(secondWord)).Count > 0)
{
return(_tokenUtilities.CommonSetTerms() / (Math.Pow(_tokenUtilities.FirstSetTokenCount, 0.5) * Math.Pow(_tokenUtilities.SecondSetTokenCount, 0.5)));
}
return(0.0);
}
public override double GetSimilarity(string firstWord, string secondWord)
{
if (firstWord != null && secondWord != null)
{
_tokenUtilities.CreateMergedSet(_tokeniser.Tokenize(firstWord), _tokeniser.Tokenize(secondWord));
return(_tokenUtilities.CommonSetTerms() / (double)Math.Min(_tokenUtilities.FirstSetTokenCount, _tokenUtilities.SecondSetTokenCount));
}
return(DefaultMismatchScore);
}
public override double GetSimilarity(string firstWord, string secondWord)
{
if (firstWord != null && secondWord != null)
{
Collection <string> collection = _tokenUtilities.CreateMergedSet(_tokeniser.Tokenize(firstWord), _tokeniser.Tokenize(secondWord));
if (collection.Count > 0)
{
return(_tokenUtilities.CommonSetTerms() / (double)collection.Count);
}
}
return(DefaultMismatchScore);
}
/// <summary>
/// gets the similarity of the two strings using OverlapCoefficient
/// </summary>
/// <param name="firstWord"></param>
/// <param name="secondWord"></param>
/// <returns>a value between 0-1 of the similarity</returns>
/// <remarks>overlap_coefficient(q,r) = ( | q and r | ) / min{ | q | , | r | }.</remarks>
public override double GetSimilarity(string firstWord, string secondWord)
{
if ((firstWord != null) && (secondWord != null))
{
//Collection<string> allTokens =
tokenUtilities.CreateMergedSet(tokeniser.Tokenize(firstWord), tokeniser.Tokenize(secondWord));
return
(tokenUtilities.CommonSetTerms() /
(double)Math.Min(tokenUtilities.FirstSetTokenCount, tokenUtilities.SecondSetTokenCount));
}
return(defaultMismatchScore);
}
/// <summary>
/// gets the similarity of the two strings using DiceSimilarity
/// </summary>
/// <param name="firstWord"></param>
/// <param name="secondWord"></param>
/// <returns>a value between 0-1 of the similarity</returns>
/// <remarks>Dices coefficient = (2*Common Terms) / (Number of terms in String1 + Number of terms in String2).</remarks>
public override double GetSimilarity(string firstWord, string secondWord)
{
if ((firstWord != null) && (secondWord != null))
{
if (tokenUtilities.CreateMergedSet(tokeniser.Tokenize(firstWord), tokeniser.Tokenize(secondWord)).Count > 0)
{
return
((2.0 * tokenUtilities.CommonSetTerms()) /
(tokenUtilities.FirstSetTokenCount + tokenUtilities.SecondSetTokenCount));
}
}
return(0.0);
}
/// <summary>
/// gets the similarity of the two strings using JaccardSimilarity.
/// </summary>
/// <param name="firstWord"></param>
/// <param name="secondWord"></param>
/// <returns>a value between 0-1 of the similarity</returns>
/// <remarks>Each instance is represented as a Jaccard vector similarity function. The Jaccard between two vectors X and Y is
/// (X*Y) / (|X||Y|-(X*Y))
/// where (X*Y) is the inner product of X and Y, and |X| = (X*X)^1/2, i.e. the Euclidean norm of X.
/// This can more easily be described as ( |X and Y| ) / ( | X or Y | )</remarks>
public override double GetSimilarity(string firstWord, string secondWord)
{
if ((firstWord != null) && (secondWord != null))
{
Collection <string> allTokens =
tokenUtilities.CreateMergedSet(tokeniser.Tokenize(firstWord), tokeniser.Tokenize(secondWord));
if (allTokens.Count > 0)
{
return((double)tokenUtilities.CommonSetTerms() / (double)allTokens.Count);
}
}
return(defaultMismatchScore);
}
double GetActualSimilarity(Collection <string> firstTokens, Collection <string> secondTokens)
{
Collection <string> allTokens = tokenUtilities.CreateMergedSet(firstTokens, secondTokens);
int difference = 0;
foreach (string token in allTokens)
{
int matchingQGrams1 = 0;
for (int i = 0; i < firstTokens.Count; i++)
{
if (firstTokens[i].Equals(token))
{
matchingQGrams1++;
}
}
int matchingQGrams2 = 0;
for (int i = 0; i < secondTokens.Count; i++)
{
if (secondTokens[i].Equals(token))
{
matchingQGrams2++;
}
}
if (matchingQGrams1 > matchingQGrams2)
{
difference += matchingQGrams1 - matchingQGrams2;
}
else
{
difference += matchingQGrams2 - matchingQGrams1;
}
}
return(difference);
}
