/// <summary>
/// Computes cosine similarities between two TermDocumentMatrices.
/// Cosine similarity is defined as (dot product) / (length * length)
/// </summary>
/// <param name="m1">Binary document matrix</param>
/// <param name="m2">tf-idf weighted document matrix</param>
/// <returns>Similarity matrix</returns>
public static TLSimilarityMatrix ComputeCosine(TermDocumentMatrix m1, TermDocumentMatrix m2)
{
TLSimilarityMatrix sims = new TLSimilarityMatrix();
List <TermDocumentMatrix> matrices = TermDocumentMatrix.Equalize(m1, m2);
for (int i = 0; i < m1.NumDocs; i++)
{
TLLinksList links = new TLLinksList();
for (int j = 0; j < m2.NumDocs; j++)
{
double lengthProduct = ComputeLength(matrices[0].GetDocument(i)) * ComputeLength(matrices[1].GetDocument(j));
if (lengthProduct == 0.0)
{
links.Add(new TLSingleLink(m1.GetDocumentName(i), m2.GetDocumentName(j), 0.0));
}
else
{
links.Add(new TLSingleLink(m1.GetDocumentName(i), m2.GetDocumentName(j), ComputeDotProduct(matrices[0].GetDocument(i), matrices[1].GetDocument(j)) / lengthProduct));
}
}
links.Sort();
foreach (TLSingleLink link in links)
{
sims.AddLink(link.SourceArtifactId, link.TargetArtifactId, link.Score);
}
}
return(sims);
}
/// <summary>
/// Computes cosine similarities between two TermDocumentMatrices.
/// Cosine similarity is defined as (dot product) / (length * length)
/// </summary>
/// <param name="m1">Binary document matrix</param>
/// <param name="m2">tf-idf weighted document matrix</param>
/// <returns>Similarity matrix</returns>
public static TLSimilarityMatrix ComputeCosine(TermDocumentMatrix m1, TermDocumentMatrix m2)
{
TLSimilarityMatrix sims = new TLSimilarityMatrix();
List<TermDocumentMatrix> matrices = TermDocumentMatrix.Equalize(m1, m2);
for (int i = 0; i < m1.NumDocs; i++)
{
TLLinksList links = new TLLinksList();
for (int j = 0; j < m2.NumDocs; j++)
{
double lengthProduct = ComputeLength(matrices[0].GetDocument(i)) * ComputeLength(matrices[1].GetDocument(j));
if (lengthProduct == 0.0)
{
links.Add(new TLSingleLink(m1.GetDocumentName(i), m2.GetDocumentName(j), 0.0));
}
else
{
links.Add(new TLSingleLink(m1.GetDocumentName(i), m2.GetDocumentName(j), ComputeDotProduct(matrices[0].GetDocument(i), matrices[1].GetDocument(j)) / lengthProduct));
}
}
links.Sort();
foreach (TLSingleLink link in links)
{
sims.AddLink(link.SourceArtifactId, link.TargetArtifactId, link.Score);
}
}
return sims;
}
public void ConstructorTest_Artifacts()
{
string data = @"../../Data/SimpleCorpus.";
TermDocumentMatrix matrix = new TermDocumentMatrix(Artifacts.Import(data + "input.target.txt"));
TermDocumentMatrix answer = TermDocumentMatrix.Load(data + "output.target.matrix.txt");
// counts
Assert.AreEqual(matrix.NumDocs, answer.NumDocs);
Assert.AreEqual(matrix.NumTerms, answer.NumTerms);
// matrix
for (int i = 0; i < answer.NumDocs; i++)
{
Assert.AreEqual(matrix.GetDocumentName(i), answer.GetDocumentName(i));
Assert.AreEqual(matrix.GetDocument(i).Length, answer.NumTerms);
for (int j = 0; j < answer.NumTerms; j++)
{
Assert.AreEqual(matrix.GetTermName(j), answer.GetTermName(j));
Assert.AreEqual(matrix[i, j], answer[i, j], 0.0);
}
}
}
public void ConstructorTest_Artifacts()
{
string inputData = Settings.Default.SimpleCorpusDir;
string outputData = Path.Combine(inputData, "TermDocumentMatrix");
TermDocumentMatrix matrix = new TermDocumentMatrix(Artifacts.ImportFile(Path.Combine(inputData, "target.txt")));
TermDocumentMatrix answer = TermDocumentMatrix.Load(Path.Combine(outputData, "output.txt"));
// counts
Assert.AreEqual(matrix.NumDocs, answer.NumDocs);
Assert.AreEqual(matrix.NumTerms, answer.NumTerms);
// matrix
for (int i = 0; i < answer.NumDocs; i++)
{
Assert.AreEqual(matrix.GetDocumentName(i), answer.GetDocumentName(i));
Assert.AreEqual(matrix.GetDocument(i).Length, answer.NumTerms);
for (int j = 0; j < answer.NumTerms; j++)
{
Assert.AreEqual(matrix.GetTermName(j), answer.GetTermName(j));
Assert.AreEqual(matrix[i, j], answer[i, j], 0.0);
}
}
}
