/**
* The examples are assumed to be a list of RFVDatum. The datums are assumed to contain the zeroes
* as well.
*/
@Override
@Deprecated
public NaiveBayesClassifier<L, F> trainClassifier(List<RVFDatum<L, F>> examples) {
RVFDatum<L, F> d0 = examples.get(0);
int numFeatures = d0.asFeatures().size();
int[][] data = new int[examples.size()][numFeatures];
int[] labels = new int[examples.size()];
labelIndex = new HashIndex<L>();
featureIndex = new HashIndex<F>();
for (int d = 0; d < examples.size(); d++) {
RVFDatum<L, F> datum = examples.get(d);
Counter<F> c = datum.asFeaturesCounter();
for (F feature : c.keySet()) {
if (featureIndex.add(feature)) {
int fNo = featureIndex.indexOf(feature);
int value = (int) c.getCount(feature);
data[d][fNo] = value;
}
}
labelIndex.add(datum.label());
labels[d] = labelIndex.indexOf(datum.label());
}
int numClasses = labelIndex.size();
return trainClassifier(data, labels, numFeatures, numClasses, labelIndex, featureIndex);
}
private int add(AmbiguityClass a) {
if (classes.contains(a)) {
return classes.indexOf(a);
}
classes.add(a);
return classes.indexOf(a);
}
public Index<IntPair> createIndex() {
Index<IntPair> index = new HashIndex<>();
for (int x = 0; x < px.length; x++) {
int numberY = numY(x);
for (int y = 0; y < numberY; y++) {
index.add(new IntPair(x, y));
}
}
return index;
}
protected void read(DataInputStream file) {
try {
int size = file.readInt();
index = new HashIndex<String>();
for (int i = 0; i < size; i++) {
String tag = file.readUTF();
boolean inClosed = file.readBoolean();
index.add(tag);
if (inClosed) closed.add(tag);
}
} catch (IOException e) {
e.printStackTrace();
}
}
@Override
public void train(List<TaggedWord> sentence) {
lex.train(sentence, 1.0);
String last = null;
for (TaggedWord tagLabel : sentence) {
String tag = tagLabel.tag();
tagIndex.add(tag);
if (last == null) {
initial.incrementCount(tag);
} else {
ruleCounter.incrementCount2D(last, tag);
}
last = tag;
}
}
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;
}
static {
binaryIndex = new HashIndex<>();
binaryIndex.add(POS_LABEL);
binaryIndex.add(NEG_LABEL);
posIndex = binaryIndex.indexOf(POS_LABEL);
}