/// <summary>
/// Create test data in known clusters, perform unattended clustering, time the process.
/// Make no attempt to verify the correctness of the result.
/// The timing does not include the creation of the test data, just the clustering.
/// </summary>
/// <param name="numPoints">Number of points to cluster.</param>
/// <param name="clusterCount">Cluster count.</param>
/// <param name="dimensions">Dimensions per point.</param>
/// <param name="clusterSizeVariation">Cluster size variation.
/// The average number of points per cluster is numPoints/clusterCount.
/// The actual size of a given cluster will be permitted to vary by as much as ± clusterSizeVariation.
/// </param>
/// <param name="maxCoordinate">All points will have coordinate values in the range 0 to maxCoordinate.</param>
/// <returns>Time in seconds and an Boolean which is false if the clustering did not produce perfect results.</returns>
private Tuple <double, bool> ClassifyPerformance(int numPoints, int clusterCount, int dimensions,
int clusterSizeVariation = 0, int maxCoordinate = 1000)
{
var minClusterSize = (numPoints / clusterCount) - clusterSizeVariation;
var maxClusterSize = (numPoints / clusterCount) + clusterSizeVariation;
var data = new GaussianClustering
{
ClusterCount = clusterCount,
Dimensions = dimensions,
MaxCoordinate = maxCoordinate,
MinClusterSize = minClusterSize,
MaxClusterSize = maxClusterSize
};
var expectedClusters = data.MakeClusters();
var timer = new Stopwatch();
timer.Start();
var classifier = new HilbertClassifier(expectedClusters.Points(), 10);
classifier.IndexConfig.UseSample = true;
var actualClusters = classifier.Classify();
timer.Stop();
var success = expectedClusters.IsSimilarTo(actualClusters);
if (!success)
{
Console.WriteLine($"Clustering was not perfect. # of Clusters actual/expected: {actualClusters.NumPartitions}/{expectedClusters.NumPartitions}");
}
var seconds = timer.ElapsedMilliseconds / 1000.0;
return(new Tuple <double, bool>(seconds, success));
}
private void ClusterCore(GaussianClustering data, double acceptableBCubed)
{
var expectedClusters = data.MakeClusters();
var classifier = new HilbertClassifier(expectedClusters.Points(), 10);
classifier.IndexConfig.UseSample = true;
var actualClusters = classifier.Classify();
var comparison = expectedClusters.Compare(actualClusters);
var message = $" Comparison of clusters: {comparison}.\n Clusters expected/actual: {expectedClusters.NumPartitions}/{actualClusters.NumPartitions}.";
Console.WriteLine(message);
Console.WriteLine($" Large clusters: {actualClusters.NumLargePartitions(classifier.OutlierSize)}");
Assert.GreaterOrEqual(comparison.BCubed, acceptableBCubed, $"Clustering was not good enough. BCubed = {comparison.BCubed}");
}
public void ClusterNetflixData()
{
throw new Exception("Test not fully written");
var classifier = new HilbertClassifier(AllNetflixData.Points, 3);
classifier.IndexConfig.IndexCount = 1;
Timer.Start("Clustering Netflix data");
var actualClusters = classifier.Classify();
Timer.Stop("Clustering Netflix data");
//TODO: Design a measure of success.
LogCLusterStats(actualClusters);
Timer.Log();
}
private void ClassifyCase(Classification <UnsignedPoint, string> expectedClusters, double acceptableBCubed = 0.99)
{
var maxCoordinate = expectedClusters.Points().Select(p => p.MaxCoordinate).Max();
var bitsPerDimension = ((int)maxCoordinate).SmallestPowerOfTwo();
var classifier = new HilbertClassifier(expectedClusters.Points(), bitsPerDimension);
classifier.IndexConfig.UseSample = true;
var actualClusters = classifier.Classify();
var comparison = expectedClusters.Compare(actualClusters);
var message = $" Comparison of clusters: {comparison}.\n Clusters expected/actual: {expectedClusters.NumPartitions}/{actualClusters.NumPartitions}.";
Console.WriteLine(message);
Console.WriteLine($" Large clusters: {actualClusters.NumLargePartitions(classifier.OutlierSize)}");
Assert.GreaterOrEqual(comparison.BCubed, acceptableBCubed, $"Clustering was not good enough. BCubed = {comparison.BCubed}");
}
private void ClusterChainCore(GaussianClustering data, double acceptableBCubed, int chainLength)
{
var expectedClusters = data.MakeChains(chainLength);
var classifier = new HilbertClassifier(expectedClusters.Points(), 10);
classifier.IndexConfig.UseSample = true;
var actualClusters = classifier.Classify();
var comparison = expectedClusters.Compare(actualClusters);
var message = $" Comparison of clusters: {comparison}.\n Clusters expected/actual: {expectedClusters.NumPartitions}/{actualClusters.NumPartitions}.";
Logger.Info(message);
var message2 = $" Large clusters: {actualClusters.NumLargePartitions(classifier.OutlierSize)}";
Logger.Info(message2);
var pointsInOutliers = actualClusters.LabelToPoints.Values
.Select(values => values.Count())
.Where(count => count < classifier.OutlierSize)
.Sum();
var message3 = $" Points in Outliers/Total Point: {pointsInOutliers} / {actualClusters.NumPoints}";
Logger.Info(message3);
Assert.GreaterOrEqual(comparison.BCubed, acceptableBCubed, $"Clustering was not good enough. BCubed = {comparison.BCubed}");
}
/// <summary>
/// Perform a classification of two clusters that are near enough to each other to partially overlap, causing problems.
///
/// From this we can deduce which of six cases obtain (the SplitQuality).
/// </summary>
/// <returns>A Tuple with these parts:
/// 1) comparison of actual to expected (with its BCubed),
/// 2) the expected number of clusters
/// 3) the actual number of clusters
/// 4) a qualitative assessment of the results.
/// </returns>
/// <param name="numPoints">Number of points.</param>
/// <param name="dimensions">Number of Dimensions.</param>
/// <param name="overlapPercent">Overlap percent.</param>
/// <param name="clusterSizeVariation">Cluster size variation.</param>
/// <param name="maxCoordinate">Max value of any coordinate.</param>
/// <param name="acceptablePrecision">Acceptable precision</param>
/// <param name="useDensityClassifier">If set to <c>true</c> use density classifier.</param>
private Tuple <ClusterMetric <UnsignedPoint, string>, int, int, SplitQuality> ClassifyTwoClustersHelper(int numPoints, int dimensions, double overlapPercent,
int clusterSizeVariation = 0, int maxCoordinate = 1000, double acceptablePrecision = 0.98, bool useDensityClassifier = true)
{
Logger.SetupForTests();
var bitsPerDimension = maxCoordinate.SmallestPowerOfTwo();
var clusterCount = 2;
var minClusterSize = (numPoints / clusterCount) - clusterSizeVariation;
var maxClusterSize = (numPoints / clusterCount) + clusterSizeVariation;
var outlierSize = 5;
var radiusShrinkage = 0.6; // 0.7 merges too many that belong apart!
var data = new GaussianClustering
{
ClusterCount = clusterCount,
Dimensions = dimensions,
MaxCoordinate = maxCoordinate,
MinClusterSize = minClusterSize,
MaxClusterSize = maxClusterSize
};
var expectedClusters = data.TwoClusters(overlapPercent);
Classification <UnsignedPoint, string> actualClusters;
if (useDensityClassifier)
{
var hIndex = new HilbertIndex(expectedClusters, bitsPerDimension);
var cc = new ClusterCounter {
NoiseSkipBy = 10, OutlierSize = outlierSize, ReducedNoiseSkipBy = 1
};
var count = cc.Count(hIndex.SortedPoints);
var unmergeableSize = expectedClusters.NumPoints / 6;
var densityClassifier = new DensityClassifier(hIndex, count.MaximumSquareDistance, unmergeableSize)
{
MergeableShrinkage = radiusShrinkage
};
actualClusters = densityClassifier.Classify();
}
else
{
var classifier = new HilbertClassifier(expectedClusters.Points(), 10)
{
OutlierSize = outlierSize
};
//classifier.IndexConfig.NoiseSkipBy = 0;
classifier.IndexConfig.UseSample = false;
actualClusters = classifier.Classify();
}
var comparison = expectedClusters.Compare(actualClusters);
SplitQuality qualitativeResult = SplitQuality.Unsplit;
if (comparison.BCubed >= 1.0)
{
qualitativeResult = SplitQuality.PerfectSplit;
}
else if (actualClusters.NumPartitions == 1)
{
qualitativeResult = SplitQuality.Unsplit;
}
else if (actualClusters.NumPartitions > expectedClusters.NumPartitions && comparison.Precision >= 1.0)
{
qualitativeResult = SplitQuality.GoodOverSplit;
}
else if (actualClusters.NumPartitions > expectedClusters.NumPartitions && comparison.Precision >= acceptablePrecision)
{
qualitativeResult = SplitQuality.FairOverSplit;
}
else if (actualClusters.NumPartitions == expectedClusters.NumPartitions && comparison.Precision >= acceptablePrecision)
{
qualitativeResult = SplitQuality.GoodSplit;
}
else if (actualClusters.NumPartitions > expectedClusters.NumPartitions && comparison.Precision < 1.0)
{
qualitativeResult = SplitQuality.BadOverSplit;
}
else // Assume correct number of clusters.
{
qualitativeResult = SplitQuality.BadSplit;
}
Logger.Info($" Quality: {qualitativeResult} Comparison: {comparison}");
return(new Tuple <ClusterMetric <UnsignedPoint, string>, int, int, SplitQuality>(
comparison,
expectedClusters.NumPartitions,
actualClusters.NumPartitions,
qualitativeResult
));
}
