public void Cluster_NoiseNotEmpty()
{
var matrix = new[,]
{
{0.00, 0.09, 0.22},
{0.09, 0.00, 0.30},
{0.22, 0.30, 0.00}
};
char[] objects = {'A', 'B', 'C'};
var clusterer = new DbscanClusterer<char>(o1 => objects.Where(o2 => matrix[o1 - 'A', o2 - 'A'] <= 0.2), 2);
Cluster<char>[] clusters = clusterer.GenerateClusters(objects).ToArray();
Assert.That(clusters, Is.EquivalentTo(new[] {new Cluster<char>('A', 'B'), new Cluster<char>(new[] {'C'}, true)}).Using(new ClusterEqualityComparer<char>()));
}
public void Cluster_AllObjectsInSameCluster()
{
var matrix = new[,]
{
{0.00, 0.09, 0.12},
{0.09, 0.00, 0.21},
{0.12, 0.21, 0.00}
};
char[] objects = {'A', 'B', 'C'};
var clusterer = new DbscanClusterer<char>(o1 => objects.Where(o2 => matrix[o1 - 'A', o2 - 'A'] <= 0.2), 2);
Cluster<char>[] clusters = clusterer.GenerateClusters(objects).ToArray();
Assert.That(clusters, Is.EquivalentTo(new[] {new Cluster<char>('A', 'B', 'C'), new Cluster<char>(Enumerable.Empty<char>(), true)}).Using(new ClusterEqualityComparer<char>()));
}
public void Cluster_NoiseNotEmpty()
{
var matrix = new[, ]
{
{ 0.00, 0.09, 0.22 },
{ 0.09, 0.00, 0.30 },
{ 0.22, 0.30, 0.00 }
};
char[] objects = { 'A', 'B', 'C' };
var clusterer = new DbscanClusterer <char>(o1 => objects.Where(o2 => matrix[o1 - 'A', o2 - 'A'] <= 0.2), 2);
Cluster <char>[] clusters = clusterer.GenerateClusters(objects).ToArray();
Assert.That(clusters, Is.EquivalentTo(new[] { new Cluster <char>('A', 'B'), new Cluster <char>(new[] { 'C' }, true) }).Using(new ClusterEqualityComparer <char>()));
}
public void Cluster_AllObjectsInSameCluster()
{
var matrix = new[, ]
{
{ 0.00, 0.09, 0.12 },
{ 0.09, 0.00, 0.21 },
{ 0.12, 0.21, 0.00 }
};
char[] objects = { 'A', 'B', 'C' };
var clusterer = new DbscanClusterer <char>(o1 => objects.Where(o2 => matrix[o1 - 'A', o2 - 'A'] <= 0.2), 2);
Cluster <char>[] clusters = clusterer.GenerateClusters(objects).ToArray();
Assert.That(clusters, Is.EquivalentTo(new[] { new Cluster <char>('A', 'B', 'C'), new Cluster <char>(Enumerable.Empty <char>(), true) }).Using(new ClusterEqualityComparer <char>()));
}
/* Commented out for now, because the CommandLine library doesn't like finding two Usage attributes and we already have one on VerbBase
* [Usage(ApplicationAlias = "cog-cmdline")]
* public new static IEnumerable<Example> Examples
* {
* get
* {
* yield return new Example("UPGMA clustering (specify a threshhold value)", new ClusterVerb { Method = "upgma", Threshhold = 0.2 });
* yield return new Example("DBSCAN clustering (specify epsilon and min-words values)", new ClusterVerb { Method = "dbscan", Epsilon = 0.2, MinWords = 2 });
* yield return new Example("LSDBC clustering (specify alpha and K values)", new ClusterVerb { Method = "lsdbc", Alpha = 0.2, K = 3 });
* }
* }
*/
protected override ReturnCode DoWork(TextReader inputReader, TextWriter outputWriter, TextWriter errorWriter)
{
ReturnCode retcode = ReturnCode.Okay;
SetupProject();
string lowerMethod = Method.ToLowerInvariant();
switch (lowerMethod)
{
case "dbscan":
case "lsdbc":
case "upgma":
break;
default:
Errors.Add($"Invalid clustering method {Method}. Valid values are \"upgma\", \"dbscan\", and \"lsdbc\" (not case-sensitive, e.g. \"Upgma\" also works.)");
return(ReturnCode.InputError);
}
foreach (string line in ReadLines(inputReader))
{
// Format: word1 word2 score (where score is a floating-point number with 1.0 = 100% similarity)
string[] words = line.Split(' ');
if (words.Length < 3)
{
Errors.Add(line, "Each line should contain two words and one score, separated by spaces.");
continue;
}
double score;
if (!double.TryParse(words[2], NumberStyles.Float, CultureInfo.InvariantCulture, out score))
{
Errors.Add(line, $"Could not parse score \"{words[2]}\". Scores should be a number between 0 and 1.");
continue;
}
if (score < 0.0)
{
Errors.Add(line, $"Invalid score \"{words[2]}\". Scores should not be negative, but should be a number between 0 and 1.");
continue;
}
if (score > 1.0)
{
Errors.Add(line, $"Invalid score \"{words[2]}\". Scores should not be greater than 1, but should be a number between 0 and 1.");
continue;
}
double distance = 1.0 - score;
KeepScoreForUpgmaClusterer(words[0], words[1], distance); // TODO: Since we always call this, maybe we should rename it
}
IFlatClusterer <string> clusterer;
switch (Method.ToLowerInvariant())
{
case "dbscan":
// public DbscanClusterer(Func<T, IEnumerable<T>> getNeighbors, double minPoints)
KeepScoreForDbscanClusterer();
clusterer = new DbscanClusterer <string>(word => _distanceGraph[word]
.TakeWhile(scoreWordTuple => scoreWordTuple.Item1 <= Epsilon)
.Select(scoreWordTuple => scoreWordTuple.Item2), MinWords);
break;
case "lsdbc":
// public LsdbcClusterer(double alpha, Func<T, IEnumerable<Tuple<T, double>>> getKNearestNeighbors)
KeepScoreForLsdbcClusterer();
clusterer = new LsdbcClusterer <string>(Alpha, word => _distanceGraph[word].Take(K)
.Select(tuple => new Tuple <string, double>(tuple.Item2, tuple.Item1)));
break;
default:
clusterer = new FlatUpgmaClusterer <string>((w1, w2) =>
_distanceDict[new UnorderedTuple <string, string>(w1, w2)], Threshhold);
break;
}
IEnumerable <Cluster <string> > clusters = clusterer.GenerateClusters(_allWords);
PrintResults(outputWriter, clusters);
return(retcode);
}
