public void ComputeLSA()
{
TLArtifactsCollection source = TermDocumentMatrix.Load(@"../../Data/LSA/source.txt").ToTLArtifactsCollection();
TLArtifactsCollection target = TermDocumentMatrix.Load(@"../../Data/LSA/target.txt").ToTLArtifactsCollection();
REngine engine = new REngine(Settings.Default.RScriptEXE);
TLSimilarityMatrix matrix = (TLSimilarityMatrix)engine.Execute(new LSAScript(source, target, new LSAConfig {
Dimensions = 3
}));
TLSimilarityMatrix correct = Similarities.Import(@"../../Data/LSA/correct.txt");
foreach (TLSingleLink link in matrix.AllLinks)
{
Assert.AreEqual(correct.GetScoreForLink(link.SourceArtifactId, link.TargetArtifactId),
link.Score,
Settings.Default.DoublePrecision
);
}
}
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);
}
}
}
public override void Compute()
{
Workspace.Store("Artifacts", TermDocumentMatrix.Load(_config.CorpusDocument.Absolute));
}