/**
* Initialise a CTMain before usage with a first tree, going through and setting up the hash table
* etc.
*
* @param root Root of the initial tree to initialise with
* @param noOfSamples Current number of samples taken
*/
public void initialize(TreeNode root, int noOfSamples) {
// Parameter initialisation
this.noOfSamples = noOfSamples;
noOfTrees = 0;
// TaxaMap initialisation
List<TreeNode> leaves = root.getLeaves();
noOfTaxa = leaves.size();
// Hash initialisation
hashUtils = new HashUtils();
hashUtils.initialize(noOfTaxa, noOfSamples, C, seed);
hashTable = new HashTable(hashUtils.m1);
// Taxamap initialisation
taxa = new TaxaMap(noOfTaxa);
for (int i = 0; i < leaves.size(); i++) {
taxa.put(leaves.get(i).name, i);
}
leafEdgeLengths = new double[noOfTaxa];
// Adds a single star partition, once and for all.
BitSet star = new BitSet(noOfTaxa);
star.flip(0, noOfTaxa);
HashEntry entry = new HashEntry(-1, star, 0.0d);
entry.count = noOfSamples + 1;
partitions.add(entry);
// Majority threshold initialisation
updateInterestThreshold();
}
/**
* Create partitions from an input tree - recursive so will be called by many nodes, beginning
* with root but with calculations actually beginning on leaves.
*
* @param partitions Partitions in the form of entries in the hash table
* @param curInterestPercentage Current percentage of interest that we want splits to occur above
* to view in the network later
*/
private ArrayList<Cluster> constructClusters(
LinkedList<HashEntry> partitions, double curInterestPercentage) {
ArrayList<Cluster> clusters = new ArrayList<Cluster>();
// Thresholds for the current run of the cluster builder (c.f. the threshold for the partitions
// list).
double curInterestThreshold = (double) (noOfTrees * (curInterestPercentage / 100.0d));
int majInterestThreshold = (int) (noOfTrees * (50.0 / 100.0d));
for (Iterator<HashEntry> it = partitions.iterator(); it.hasNext(); ) {
HashEntry entry = it.next();
// Checks if this partition is still above threshold... partition.
// If not: remove it - O(1).
if ((double) entry.count <= curInterestThreshold) {
// correct the isMajority flag to now refer to majority not if of interest or not..
if (entry.count <= majInterestThreshold) {
entry.isMajority = false;
}
it.remove();
continue;
}
// Constructs clusters (list of TreeNode's for each set bit) from each partition.
if ((double) entry.count > curInterestThreshold) {
Cluster cluster = new Cluster();
if (entry.count > majInterestThreshold) {
cluster.isMajority = true;
}
cluster.aboveSplit = entry.partition;
cluster.noOfOccurrences = entry.count;
cluster.edgeLength = entry.edgeLengthsSum / entry.count;
for (int i = 0; i < entry.partition.size(); i++) {
if (entry.partition.get(i)) {
TreeNode node = new TreeNode(taxa.getName(i));
node.edgeLength = leafEdgeLengths[i] / noOfTrees;
cluster.add(node);
}
}
clusters.add(cluster);
}
}
// Sort by number of taxa.
// TODO: This might obviously be optimized a bit, e.g. with a PriorityQueue. - Eiriksson
Collections.sort(clusters);
return clusters;
}
/**
* FOR TESTING ONLY Function called to initialise the Network Tester hash table & rest of CTMain
*
* @param noOfTestTaxa Number of taxa
* @param noOfTestSamples number of trees input
*/
public void InitialiseNetworkTester(int noOfTestTaxa, int noOfTestSamples) {
// TaxaMap initialisation
noOfTrees = 0;
noOfTaxa = noOfTestTaxa;
noOfSamples = noOfTestSamples;
// Hash initialisation
hashUtils = new HashUtils();
hashUtils.initialize(noOfTaxa, noOfSamples, C, seed);
hashTable = new HashTable(hashUtils.m1);
leafEdgeLengths = new double[noOfTaxa];
taxa = new TaxaMap(noOfTaxa);
for (int i = 0; i < noOfTaxa; i++) {
taxa.put("" + i, i);
leafEdgeLengths[i] = 1;
}
// Adds a single star partition, once and for all.
BitSet star = new BitSet(noOfTaxa);
star.flip(0, noOfTaxa);
HashEntry entry = new HashEntry(-1, star, 0.0d);
entry.count = noOfSamples + 1;
partitions.add(entry);
updateInterestThreshold();
}