public void EmptyTargetArtifactsTest()
{
TLArtifactsCollection sourceArtifacts = new TLArtifactsCollection();
sourceArtifacts.Add(new TLArtifact("id", "text"));
TLArtifactsCollection targetArtifacts = new TLArtifactsCollection();
TLDictionaryIndex dictionary = new TLDictionaryIndex();
dictionary.AddTermEntry("term", 1, 1, 1);
Workspace.Store("sourceArtifacts", sourceArtifacts);
Workspace.Store("targetArtifacts", targetArtifacts);
Workspace.Store("dictionaryIndex", dictionary);
((TracerConfig)TestComponent.Configuration).SimilarityMetric = SimilarityMetricMethod.SimpleMatching;
TestComponent.Compute();
TLSimilarityMatrix simMat = (TLSimilarityMatrix)Workspace.Load("similarityMatrix");
if (simMat == null || simMat.Count != 0)
{
Assert.Fail("Similarity Matrix should still be created but have nothing in it");
}
}
public void TestTracingOfComponent()
{
TLArtifactsCollection sourceArtifacts = new TLArtifactsCollection();
TLArtifactsCollection targetArtifacts = new TLArtifactsCollection();
TLDictionaryIndex dictionary = new TLDictionaryIndex();
// TODO: add inputs that matter
sourceArtifacts.Add(new TLArtifact("id1", "first text"));
sourceArtifacts.Add(new TLArtifact("id2", "words to do stuff with"));
sourceArtifacts.Add(new TLArtifact("id3", "some more text"));
targetArtifacts.Add(new TLArtifact("id1", "hello world"));
targetArtifacts.Add(new TLArtifact("id2", "very very random yes indeed"));
targetArtifacts.Add(new TLArtifact("id3", "yep"));
targetArtifacts.Add(new TLArtifact("id4", "chickens in the coop"));
dictionary.AddTermEntry("term", 3, 3, 0.2);
Workspace.Store("sourceArtifacts", sourceArtifacts);
Workspace.Store("targetArtifacts", targetArtifacts);
Workspace.Store("dictionaryIndex", dictionary);
((TracerConfig)TestComponent.Configuration).SimilarityMetric = SimilarityMetricMethod.SimpleMatching;
TestComponent.Compute();
TLSimilarityMatrix simMat = (TLSimilarityMatrix)Workspace.Load("similarityMatrix");
// TODO: add tests to make sure the output is correctly formatted
Assert.Fail();
}
public void IncorrectInputSourceArtifactsType()
{
TLArtifactsCollection targetArtifacts = new TLArtifactsCollection();
targetArtifacts.Add(new TLArtifact("id1", "text2"));
TLDictionaryIndex dictionary = new TLDictionaryIndex();
dictionary.AddTermEntry("term", 1, 1, 1);
Workspace.Store("sourceArtifacts", "incorrect type");
Workspace.Store("targetArtifacts", targetArtifacts);
Workspace.Store("dictionaryIndex", dictionary);
((TracerConfig)TestComponent.Configuration).SimilarityMetric = SimilarityMetricMethod.SimpleMatching;
TestComponent.Compute();
}
/**
* input is a map of artifact.Id and processed text of each artifact
*
*/
public static TLDictionaryIndex build(TLArtifactsCollection setOfProcessedDocuments, ComponentLogger logger)
{
// Variables
TLTermEntry termEntry;
TLPosting posting;
double vectorLength;
// Stores the vector lenght of each document - this is used to normalize the term weights
// The vector length is the square root of the sum of the squares of all the term weights.
Dictionary <string, double> documentVectorLength = new Dictionary <string, double>();
// Creates the dictionary
TLDictionaryIndex dict = new TLDictionaryIndex();
// Iterates over all the documents
foreach (TLArtifact artifact in setOfProcessedDocuments.Values)
{
string[] terms = artifact.Text.Split(new char[] { ' ' }, StringSplitOptions.RemoveEmptyEntries);
if (terms.Length == 0)
{
logger.Warn(String.Format("Artifact Id {0} is empty.", artifact.Id));
}
// Iterates over all the terms
foreach (string t in terms)
{
// Checks if that term has already a posting
if (!dict.ContainsTermEntry(t))
{
// New term
termEntry = dict.AddTermEntry(t, 1, 1, 1.0);
posting = termEntry.AddPosting(artifact.Id, 1, 1.0);
}
else
{
// Existing term
termEntry = dict.GetTermEntry(t);
termEntry.TotalFrequencyAcrossArtifacts += 1;
termEntry.Weight = 1.0;
// Checks if there is already a posting for this document
if (!termEntry.ContainsPosting(artifact.Id))
{
// New posting
termEntry.NumberOfArtifactsContainingTerm += 1;
posting = termEntry.AddPosting(artifact.Id, 1, 1.0);
}
else
{
// Existing posting
posting = termEntry.GetPosting(artifact.Id);
posting.Frequency += 1;
posting.Weight += 1.0;
}
}
}
}
string artId;
// Now that all the counts are in, it calculates the document vector weights
foreach (TLTermEntry t in dict.TermEntries)
{
foreach (TLPosting p in t.Postings)
{
artId = p.ArtifactId;
vectorLength = Math.Pow(p.Frequency, 2);
if (documentVectorLength.ContainsKey(artId))
{
// The document has other terms
vectorLength += documentVectorLength[artId];
}
documentVectorLength[artId] = vectorLength;
}
}
// Finally, we need to get the square root of all entries in the document vector length
foreach (TLArtifact artifact in setOfProcessedDocuments.Values)
{
if (documentVectorLength.ContainsKey(artifact.Id))
{
vectorLength = Math.Sqrt(documentVectorLength[artifact.Id]);
// Here we update the document vector length of the dictionary - not the internal structure any more
dict.SetDocumentVectorWeight(artifact.Id, vectorLength);
}
}
return(dict);
}
