public <F> double score(Classifier<L, F> classifier, GeneralDataset<L, F> data) {
List<L> guesses = new ArrayList<L>();
List<L> labels = new ArrayList<L>();
for (int i = 0; i < data.size(); i++) {
Datum<L, F> d = data.getRVFDatum(i);
L guess = classifier.classOf(d);
guesses.add(guess);
}
int[] labelsArr = data.getLabelsArray();
labelIndex = data.labelIndex;
for (int i = 0; i < data.size(); i++) {
labels.add(labelIndex.get(labelsArr[i]));
}
labelIndex = new HashIndex<L>();
labelIndex.addAll(data.labelIndex().objectsList());
labelIndex.addAll(classifier.labels());
int numClasses = labelIndex.size();
tpCount = new int[numClasses];
fpCount = new int[numClasses];
fnCount = new int[numClasses];
negIndex = labelIndex.indexOf(negLabel);
for (int i = 0; i < guesses.size(); ++i) {
L guess = guesses.get(i);
int guessIndex = labelIndex.indexOf(guess);
L label = labels.get(i);
int trueIndex = labelIndex.indexOf(label);
if (guessIndex == trueIndex) {
if (guessIndex != negIndex) {
tpCount[guessIndex]++;
}
} else {
if (guessIndex != negIndex) {
fpCount[guessIndex]++;
}
if (trueIndex != negIndex) {
fnCount[trueIndex]++;
}
}
}
return getFMeasure();
}
public Classifier<L, F> trainClassifier(Iterable<Datum<L, F>> dataIterable) {
Minimizer<DiffFunction> minimizer = getMinimizer();
Index<F> featureIndex = Generics.newIndex();
Index<L> labelIndex = Generics.newIndex();
for (Datum<L, F> d : dataIterable) {
labelIndex.add(d.label());
featureIndex.addAll(d.asFeatures()); // If there are duplicates, it doesn't add them again.
}
System.err.println(
String.format(
"Training linear classifier with %d features and %d labels",
featureIndex.size(), labelIndex.size()));
LogConditionalObjectiveFunction<L, F> objective =
new LogConditionalObjectiveFunction<L, F>(dataIterable, logPrior, featureIndex, labelIndex);
objective.setPrior(new LogPrior(LogPrior.LogPriorType.QUADRATIC));
double[] initial = objective.initial();
double[] weights = minimizer.minimize(objective, TOL, initial);
LinearClassifier<L, F> classifier =
new LinearClassifier<L, F>(objective.to2D(weights), featureIndex, labelIndex);
return classifier;
}