// TODO check clusters vs dailyClusters, there's a problem in this method
private List<ClusterDendogram> clusterToDate(
List<ClusterDendogram> clusters,
List<ClusterDendogram> dailyClusters,
Cluster.distType type) {
// System.out.printf("Clustering clusters (%d) with new day's clusters (%d)\n", clusters.size(),
// dailyClusters.size());
// outer for loop loops over clusters in a day
// inner for loop loops over clusters built up to the current day
/*
* clustering between days uses just correlations
*/
// System.out.printf("\n***clustering to date***\n");
for (ClusterDendogram newClusterDend : dailyClusters) {
Cluster newCluster = newClusterDend.getCluster();
// double minDist = Double.MAX_VALUE;
double maxSimilarity = 0;
int closeClusterNdx = -1;
for (int clustNdx = 0; clustNdx < clusters.size(); clustNdx++) {
Cluster currClust = clusters.get(clustNdx).getCluster();
double clustDist = newCluster.corrDistance(currClust, type);
/*
System.out.printf("\n\nnewCluster: \n\t%s\n\ncurrClust:\n\t%s\n\n", newCluster, currClust);
System.out.printf("clustDist: %.03f\n", clustDist);
*/
// if (clustDist < minDist && clustDist < mLowerThreshold) {
// System.out.println("cluster to date ward's distance: " + clustDist);
// if (clustDist < minDist && clustDist >= mUpperThreshold) {
/*
System.out.printf("is %.03f > %.03f? %s\n\n", clustDist, maxSimilarity, (clustDist > maxSimilarity));
System.out.printf("mThreshold = %.03f\n", mThresholding);
*/
// if (clustDist > maxSimilarity && clustDist > mThresholding) {
if (mClusterPreference.equals("structure")) {
if (clustDist > maxSimilarity && !newCluster.isDifferent(currClust)) {
maxSimilarity = clustDist;
// System.out.printf("maxSimilarity: %.03f\n", maxSimilarity);
closeClusterNdx = clustNdx;
}
} else if (mClusterPreference.equals("similarity")) {
if (clustDist > maxSimilarity && newCluster.isSimilar(currClust)) {
maxSimilarity = clustDist;
// System.out.printf("maxSimilarity: %.03f\n", maxSimilarity);
closeClusterNdx = clustNdx;
}
}
}
// replace the cluster closest to the new Cluster with the
// oldCluster U newCluster
if (closeClusterNdx != -1) {
Cluster closeCluster = clusters.get(closeClusterNdx).getCluster();
Dendogram newDendogram =
new DendogramNode(
maxSimilarity,
newClusterDend.getDendogram(),
clusters.get(closeClusterNdx).getDendogram());
ClusterDendogram newClustDend =
new ClusterDendogram(closeCluster.unionWith(newCluster), newDendogram);
clusters.set(closeClusterNdx, newClustDend);
} else {
clusters.add(newClusterDend);
}
}
// System.out.printf("clusters combined into size %d\n", clusters.size());
// System.out.printf("\n***Finished clustering new day's clusters***\n");
return clusters;
}
private List<ClusterDendogram> clusterIsolates(
Cluster.distType type, Map<Connectivity, IsolateSimilarityMatrix> isolateNetworks) {
/*
IsolateRegion region = settings.getRegion();
double distanceThreshold = settings.getDistanceThreshold();
double lowerThreshold = settings.getLowerThreshold();
double upperThreshold = settings.getUpperThreshold();
Cluster.distType type = settings.getDistanceType();
*/
// mappings represent days to isolates
Map<String, Map<Integer, List<Isolate>>> technicianIsolateMap = null;
// list of all constructed clusters
List<ClusterDendogram> clusters = new ArrayList<ClusterDendogram>();
List<ClusterDendogram> technicianClusters = new ArrayList<ClusterDendogram>();
/*
* Marker
*/
// MARKER new code. get the isolateMap from the similarity matrix now
// also, multiple similarity matrices are stored in the isolate networks
// map so that it is possible to iterate on correlations based on their
// strength instead of just going all willy nilly
IsolateSimilarityMatrix similarityMatrix = isolateNetworks.get(Connectivity.STRONG);
technicianIsolateMap = similarityMatrix.getIsolateMap();
for (String technician : technicianIsolateMap.keySet()) {
System.out.printf("clustering technician %s's dataset...\n", technician);
Map<Integer, List<Isolate>> isolateMap = technicianIsolateMap.get(technician);
for (int sampleDay : isolateMap.keySet()) {
System.out.printf("clustering day %d...\n", sampleDay);
// Cluster the list of isolates in this day
List<ClusterDendogram> currClusters =
clusterIsolateList(similarityMatrix, isolateMap.get(sampleDay), type);
IsolateOutputWriter.outputClustersByDay(similarityMatrix, sampleDay, currClusters);
/*
System.err.println("currClusters length: " + currClusters.size());
/*
for (ClusterDendogram clustDend : currClusters) {
System.out.println(clustDend.getDendogram().getXML());
}
*/
// System.err.printf("on day %d there are a total of %d clusters", sampleDay,
// clusters.size());
// Cluster all previous days with this day
clusters = clusterToDate(clusters, currClusters, type);
}
technicianClusters.addAll(clusters);
clusters = new ArrayList<ClusterDendogram>();
}
clusters = clusterGroup(technicianClusters, type);
System.out.printf(
"\n\n================\nFINISHED STAGE 1. CLUSTERING SQUISHIES\n"
+ "===================\n\n");
similarityMatrix = isolateNetworks.get(Connectivity.WEAK);
technicianIsolateMap = similarityMatrix.getIsolateMap();
/*
* this is so that when doing the second pass through all of the clusters
* squishy correlations will also be known
*/
for (ClusterDendogram clust : clusters) {
clust.getCluster().setSimilarityMatrix(similarityMatrix);
}
for (String technician : technicianIsolateMap.keySet()) {
System.out.printf("clustering technician %s's dataset...\n", technician);
Map<Integer, List<Isolate>> isolateMap = technicianIsolateMap.get(technician);
for (int sampleDay : isolateMap.keySet()) {
System.out.printf("clustering day %d...\n", sampleDay);
for (Isolate isolate : isolateMap.get(sampleDay)) {
// clusters = clusterWeakIsolates(similarityMatrix, clusters, isolate, type);
if (!isolate.hasBeenClustered()) {
Cluster newCluster = new Cluster(similarityMatrix, isolate);
Dendogram newDendogram = new DendogramLeaf(isolate);
clusters.add(new ClusterDendogram(newCluster, newDendogram));
}
}
}
}
clusters = clusterGroup(clusters, type);
System.out.printf("\n\n==================\nFINISHED STAGE 2.\n======================\n\n");
return clusters;
}
