/// <summary>
/// Returns the distance matrix for a set of peaks.
/// </summary>
public static DistanceMatrix Create(Core core, IntensityMatrix valueMatrix, ConfigurationMetric metric, ProgressReporter prog)
{
int n = valueMatrix.NumRows;
int bytesRequired = (n * n) * 8;
int mbRequired = bytesRequired / (1024 * 1024);
int limit = core.Options.ObjectSizeLimit * 1024 * 1024;
if (bytesRequired > limit)
{
// It ain't gonna happen. I'm not creating a distance matrix over 500Mb
throw new InvalidOperationException("n = " + n + " input vectors. n * n = " + (n * n) + " elements in the distance matrix. 8 bytes per element gives " + (n * n * 8) + " bytes, or " + mbRequired + " megabytes. ObjectSizeLimit is " + core.Options.ObjectSizeLimit + " Mb. Reduce the number of input vectors by filtering the data, or change the limit from the preferences menu. Some algorithms also have the option to disable the distance matrix.");
}
double[,] s = new double[n, n];
prog.Enter("Calculating distance matrix");
for (int i = 0; i < n; i++)
{
prog.SetProgress(i, n);
for (int j = 0; j < n; j++)
{
s[i, j] = metric.Calculate(valueMatrix.Vectors[i], valueMatrix.Vectors[j]);
}
}
prog.Leave();
return(new DistanceMatrix(s, valueMatrix));
}
/// <summary>
/// Thread operation fo calculate statistics for [stat].
///
/// [stat] is guarenteed to be unique, however stat.Assignment is not, hence stat.Assignment must be locked.
///
/// Currently only stat.Assignment.AssignmentStatistics is the only member to be R/W locked, since that is all
/// that is modified.
/// </summary>
private static void Thread_CalculateAssignmentStatistics([Const] EClustererStatistics statistics, [MutableUnsafe] ForStat stat, [Const] Cluster[] realClusters, [Const] ConfigurationMetric metric, [MutableSafe] ProgressParallelHandler prog)
{
prog.SafeIncrement();
// STATS: Distance from avg
if (stat.ClusterVector != null)
{
// Euclidean
if (statistics.HasFlag(EClustererStatistics.EuclideanFromAverage))
{
double ed = Maths.Euclidean(stat.AssignmentVector.Values, stat.ClusterVector);
stat.Assignment.AssignmentStatistics.ThreadSafeIndex(CreatePartialKey(stat.ObsFilter, STAT_ASSIGNMENT_EUCLIDEAN_FROM_AVG), ed);
stat.Assignment.AssignmentStatistics.ThreadSafeIndex(CreatePartialKey(stat.ObsFilter, STAT_ASSIGNMENT_EUCLIDEAN_FROM_AVG_SQUARED), ed * ed);
}
// Custom (if applicable)
if (metric != null &&
statistics.HasFlag(EClustererStatistics.DistanceFromAverage) &&
!(metric.Args.Id == Algo.ID_METRIC_EUCLIDEAN && statistics.HasFlag(EClustererStatistics.EuclideanFromAverage)))
{
string key1 = metric.ToString() + STAT_ASSIGNMENT_DISTANCE_FROM_AVG;
string key2 = metric.ToString() + STAT_ASSIGNMENT_DISTANCE_FROM_AVG_SQUARED;
double dd = metric.Calculate(stat.AssignmentVector.Values, stat.ClusterVector);
stat.Assignment.AssignmentStatistics.ThreadSafeIndex(CreatePartialKey(stat.ObsFilter, key1), dd);
stat.Assignment.AssignmentStatistics.ThreadSafeIndex(CreatePartialKey(stat.ObsFilter, key2), dd * dd);
}
}
// STATS: Silhouette
Cluster nextNearestCluster = null;
if (statistics.HasFlag(EClustererStatistics.SilhouetteWidth))
{
double silhouetteWidth;
double nextNearestClusterId;
ClustererStatisticsHelper.CalculateSilhouette(stat, realClusters, out silhouetteWidth, out nextNearestCluster);
if (!double.TryParse(nextNearestCluster.ShortName, out nextNearestClusterId))
{
nextNearestClusterId = double.NaN;
}
// Silhouette
stat.Assignment.AssignmentStatistics.ThreadSafeIndex(CreatePartialKey(stat.ObsFilter, STAT_ASSIGNMENT_SILHOUETTE_WIDTH), silhouetteWidth);
stat.Assignment.AssignmentStatistics.ThreadSafeIndex(CreatePartialKey(stat.ObsFilter, STAT_ASSIGNMENT_NEXT_NEAREST_CLUSTER), nextNearestClusterId);
}
// STATS: Score
if (stat.ObsFilter == null)
{
// Score
stat.Assignment.AssignmentStatistics.ThreadSafeIndex(STAT_ASSIGNMENT_SCORE, stat.Assignment.Score);
// Next nearest cluster
stat.Assignment.NextNearestCluster = nextNearestCluster; // Only one ForStat per Assignment has ObsFilter == null so thread safe not required
}
}
/// <summary>
/// Calculates the score for variable v against this cluster.
/// The centres must have been called first by calling [SetCentre].
/// </summary>
public double CalculateScore(IReadOnlyList <double> vector, EDistanceMode distanceMode, ConfigurationMetric distanceMetric)
{
switch (distanceMode)
{
case EDistanceMode.ClosestCentre:
return(this.Centres.Count == 0
? double.NaN
: (this.Centres.Cast <double[]>().Select(centre => distanceMetric.Calculate(vector, centre))).Min());
case EDistanceMode.AverageToAllCentres:
double totalDistance = this.Centres.Cast <double[]>().Sum(centre => distanceMetric.Calculate(vector, centre));
return(totalDistance / this.Centres.Count);
default:
throw new InvalidOperationException("Invalid switch: " + distanceMode.ToString());
}
}
