/// <summary>
/// Thread operation to calculate statistics for [cluster].
///
/// [cluster] is guarenteed to be unique, so needn't be locked.
/// </summary>
private static void Thread_CalculateClusterStatistics([Const] Core core, [Const] EClustererStatistics statistics, [MutableSafe] Cluster cluster, [MutableSafe] ProgressParallelHandler prog)
{
prog.SafeIncrement();
cluster.CalculateAveragedStatistics();
cluster.CalculateCommentFlags();
Dictionary <string, double> clusterStatistics = cluster.ClusterStatistics;
List <Assignment> assignments = cluster.Assignments.List;
int hcomp, numcomp, hpeak, numpath;
ClustererStatisticsHelper.CalculateHighestCompounds(cluster, out hcomp, out numcomp);
ClustererStatisticsHelper.CalculateHighestPeaks(cluster, out hpeak, out numpath);
clusterStatistics[STAT_CLUSTER_AVERAGE_HIGHEST_NUM_COMPOUNDS] = hcomp;
clusterStatistics[STAT_CLUSTER_AVERAGE_NUM_COMPOUNDS] = numcomp;
clusterStatistics[STAT_CLUSTER_AVERAGE_HIGHEST_NUM_PEAKS] = hpeak;
clusterStatistics[STAT_CLUSTER_AVERAGE_NUM_PATHWAYS] = numpath;
//////////////////////////
// GROUP STATS (cluster)
if (statistics.HasFlag(EClustererStatistics.ClusterAverages))
{
AddAveragedStatistics(core, clusterStatistics, assignments);
}
}
/// <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>
/// Determines what needs calculating.
/// </summary>
private void Thread_AddFilterToCalculationList([Const] Core core, [Const] ConfigurationMetric metric, [Const] IntensityMatrix vmatrix, [Const] DistanceMatrix dmatrix, [Const] EClustererStatistics statistics, [Const] Cluster[] realClusters, [Const] ObsFilter obsFilter, [MutableUnsafe] List <ForStat> needsCalculating, [MutableSafe] ProgressParallelHandler progP)
{
progP.SafeIncrement();
IntensityMatrix vmatFiltered;
DistanceMatrix dmatFiltered;
int[] filteredIndices;
if (obsFilter == null)
{
vmatFiltered = vmatrix;
dmatFiltered = dmatrix;
filteredIndices = null;
}
else
{
filteredIndices = vmatrix.Columns.Which(z => obsFilter.Test(z.Observation)).ToArray(); // TODO: Multuple iteration
vmatFiltered = vmatrix.Subset(null, obsFilter, ESubsetFlags.None);
dmatFiltered = null;
}
Dictionary <Cluster, IReadOnlyList <double> > centreVectors = new Dictionary <Cluster, IReadOnlyList <double> >();
foreach (Cluster cluster in realClusters)
{
/////////////////////
// ASSIGNMENT STATS
var centre = cluster.GetCentre(ECentreMode.Average, ECandidateMode.Assignments);
IReadOnlyList <double> centreVector = centre.Count != 0 ? centre[0] : null;
if (filteredIndices != null)
{
centreVector = centreVector.Extract(filteredIndices);
}
centreVectors.Add(cluster, centreVector);
}
foreach (Assignment ass in Assignments)
{
ForStat f = new ForStat();
f.Assignment = ass;
f.ObsFilter = obsFilter;
if (filteredIndices != null)
{
f.AssignmentVector = vmatFiltered.Vectors[ass.Vector.Index];
}
else
{
f.AssignmentVector = ass.Vector;
}
f.ClusterVector = centreVectors[ass.Cluster];
if (statistics.HasFlag(EClustererStatistics.SilhouetteWidth))
{
if (dmatFiltered == null)
{
dmatFiltered = DistanceMatrix.Create(core, vmatrix, metric, ProgressReporter.GetEmpty());
}
}
f.DistanceMatrix = dmatFiltered;
lock (needsCalculating)
{
needsCalculating.Add(f);
}
}
}