private void computeEmpiricalStatistics(List<F> geFeatures) {
// allocate memory to the containers and initialize them
geFeature2EmpiricalDist = new double[geFeatures.size()][labeledDataset.labelIndex.size()];
geFeature2DatumList = new ArrayList<List<Integer>>(geFeatures.size());
Map<F, Integer> geFeatureMap = Generics.newHashMap();
Set<Integer> activeUnlabeledExamples = Generics.newHashSet();
for (int n = 0; n < geFeatures.size(); n++) {
F geFeature = geFeatures.get(n);
geFeature2DatumList.add(new ArrayList<Integer>());
Arrays.fill(geFeature2EmpiricalDist[n], 0);
geFeatureMap.put(geFeature, n);
}
// compute the empirical label distribution for each GE feature
for (int i = 0; i < labeledDataset.size(); i++) {
Datum<L, F> datum = labeledDataset.getDatum(i);
int labelID = labeledDataset.labelIndex.indexOf(datum.label());
for (F feature : datum.asFeatures()) {
if (geFeatureMap.containsKey(feature)) {
int geFnum = geFeatureMap.get(feature);
geFeature2EmpiricalDist[geFnum][labelID]++;
}
}
}
// now normalize and smooth the label distribution for each feature.
for (int n = 0; n < geFeatures.size(); n++) {
ArrayMath.normalize(geFeature2EmpiricalDist[n]);
smoothDistribution(geFeature2EmpiricalDist[n]);
}
// now build the inverted index from each GE feature to unlabeled datums that contain it.
for (int i = 0; i < unlabeledDataList.size(); i++) {
Datum<L, F> datum = unlabeledDataList.get(i);
for (F feature : datum.asFeatures()) {
if (geFeatureMap.containsKey(feature)) {
int geFnum = geFeatureMap.get(feature);
geFeature2DatumList.get(geFnum).add(i);
activeUnlabeledExamples.add(i);
}
}
}
System.out.println("Number of active unlabeled examples:" + activeUnlabeledExamples.size());
}
private static void smoothDistribution(double[] dist) {
// perform Laplace smoothing
double epsilon = 1e-6;
for (int i = 0; i < dist.length; i++) dist[i] += epsilon;
ArrayMath.normalize(dist);
}