@Override
public void processNewResult(ResultHierarchy hier, Result newResult) {
// We may just have added this result.
if (newResult instanceof Clustering && isReferenceResult((Clustering<?>) newResult)) {
return;
}
Database db = ResultUtil.findDatabase(hier);
List<Clustering<?>> crs = ResultUtil.getClusteringResults(newResult);
if (crs == null || crs.size() < 1) {
return;
}
// Compute the reference clustering
Clustering<?> refc = null;
// Try to find an existing reference clustering (globally)
{
Collection<Clustering<?>> cs = ResultUtil.filterResults(hier, db, Clustering.class);
for (Clustering<?> test : cs) {
if (isReferenceResult(test)) {
refc = test;
break;
}
}
}
// Try to find an existing reference clustering (locally)
if (refc == null) {
Collection<Clustering<?>> cs = ResultUtil.filterResults(hier, newResult, Clustering.class);
for (Clustering<?> test : cs) {
if (isReferenceResult(test)) {
refc = test;
break;
}
}
}
if (refc == null) {
LOG.debug("Generating a new reference clustering.");
Result refres = referencealg.run(db);
List<Clustering<?>> refcrs = ResultUtil.getClusteringResults(refres);
if (refcrs.size() == 0) {
LOG.warning("Reference algorithm did not return a clustering result!");
return;
}
if (refcrs.size() > 1) {
LOG.warning("Reference algorithm returned more than one result!");
}
refc = refcrs.get(0);
} else {
LOG.debug("Using existing clustering: " + refc.getLongName() + " " + refc.getShortName());
}
for (Clustering<?> c : crs) {
if (c == refc) {
continue;
}
evaluteResult(db, c, refc);
}
}
/**
* Generates {@code d+1}-dimensional subspace candidates from the specified {@code d}-dimensional
* subspaces.
*
* @param subspaces the {@code d}-dimensional subspaces
* @return the {@code d+1}-dimensional subspace candidates
*/
private List<Subspace> generateSubspaceCandidates(List<Subspace> subspaces) {
List<Subspace> candidates = new ArrayList<>();
if (subspaces.isEmpty()) {
return candidates;
}
// Generate (d+1)-dimensional candidate subspaces
int d = subspaces.get(0).dimensionality();
StringBuilder msgFine = new StringBuilder("\n");
if (LOG.isDebuggingFiner()) {
msgFine.append("subspaces ").append(subspaces).append('\n');
}
for (int i = 0; i < subspaces.size(); i++) {
Subspace s1 = subspaces.get(i);
for (int j = i + 1; j < subspaces.size(); j++) {
Subspace s2 = subspaces.get(j);
Subspace candidate = s1.join(s2);
if (candidate != null) {
if (LOG.isDebuggingFiner()) {
msgFine.append("candidate: ").append(candidate.dimensonsToString()).append('\n');
}
// prune irrelevant candidate subspaces
List<Subspace> lowerSubspaces = lowerSubspaces(candidate);
if (LOG.isDebuggingFiner()) {
msgFine.append("lowerSubspaces: ").append(lowerSubspaces).append('\n');
}
boolean irrelevantCandidate = false;
for (Subspace s : lowerSubspaces) {
if (!subspaces.contains(s)) {
irrelevantCandidate = true;
break;
}
}
if (!irrelevantCandidate) {
candidates.add(candidate);
}
}
}
}
if (LOG.isDebuggingFiner()) {
LOG.debugFiner(msgFine.toString());
}
if (LOG.isDebugging()) {
StringBuilder msg = new StringBuilder();
msg.append(d + 1).append("-dimensional candidate subspaces: ");
for (Subspace candidate : candidates) {
msg.append(candidate.dimensonsToString()).append(' ');
}
LOG.debug(msg.toString());
}
return candidates;
}
protected void autoEvaluateOutliers(ResultHierarchy hier, Result newResult) {
Collection<OutlierResult> outliers =
ResultUtil.filterResults(hier, newResult, OutlierResult.class);
if (LOG.isDebugging()) {
LOG.debug("Number of new outlier results: " + outliers.size());
}
if (outliers.size() > 0) {
Database db = ResultUtil.findDatabase(hier);
ResultUtil.ensureClusteringResult(db, db);
Collection<Clustering<?>> clusterings = ResultUtil.filterResults(hier, db, Clustering.class);
if (clusterings.size() == 0) {
LOG.warning(
"Could not find a clustering result, even after running 'ensureClusteringResult'?!?");
return;
}
Clustering<?> basec = clusterings.iterator().next();
// Find minority class label
int min = Integer.MAX_VALUE;
int total = 0;
String label = null;
if (basec.getAllClusters().size() > 1) {
for (Cluster<?> c : basec.getAllClusters()) {
final int csize = c.getIDs().size();
total += csize;
if (csize < min) {
min = csize;
label = c.getName();
}
}
}
if (label == null) {
LOG.warning("Could not evaluate outlier results, as I could not find a minority label.");
return;
}
if (min == 1) {
LOG.warning(
"The minority class label had a single object. Try using 'ClassLabelFilter' to identify the class label column.");
}
if (min > 0.05 * total) {
LOG.warning(
"The minority class I discovered (labeled '"
+ label
+ "') has "
+ (min * 100. / total)
+ "% of objects. Outlier classes should be more rare!");
}
LOG.verbose("Evaluating using minority class: " + label);
Pattern pat = Pattern.compile("^" + Pattern.quote(label) + "$");
// Evaluate rankings.
new OutlierRankingEvaluation(pat).processNewResult(hier, newResult);
// Compute ROC curve
new OutlierROCCurve(pat).processNewResult(hier, newResult);
// Compute Precision at k
new OutlierPrecisionAtKCurve(pat, min << 1).processNewResult(hier, newResult);
// Compute ROC curve
new OutlierPrecisionRecallCurve(pat).processNewResult(hier, newResult);
// Compute outlier histogram
new ComputeOutlierHistogram(pat, 50, new LinearScaling(), false)
.processNewResult(hier, newResult);
}
}
