/**
* Populate the FeatureVector with Bag of Words.
*
* @param c
* @param fv
*/
protected void populateFV(String text, FeatureVector<E> fv) {
List<String> unnormalized = tokenizer.tokenize(text);
Multiset<String> terms = HashMultiset.create();
for (String token : unnormalized) {
String norm = Util.normalize(token);
if (!norm.isEmpty()) {
terms.add(norm);
}
}
// sparse representation... no need to put in 0's
for (String term : terms.elementSet()) {
// rare words don't get included, so check first
if (!integerFeatureNames && train.getMetadata().containsKey(term)) {
DoubleFeature bagFeat = new DoubleFeature(term, (double) terms.count(term));
fv.put(term, bagFeat);
} else if (integerFeatureNames
&& train.getMetadata().containsKey(String.valueOf(wordIndexMap.get(term)))) {
String featureName = String.valueOf(wordIndexMap.get(term));
DoubleFeature bagFeat = new DoubleFeature(featureName, (double) terms.count(term));
fv.put(featureName, bagFeat);
}
}
}
/**
* Convert to the Mallet format.
*
* @param train
* @return
* @throws IOException
*/
public static InstanceList convert(Relation<?> train) {
boolean isTrain = (train instanceof TrainRelation) ? true : false;
StringBuffer sb = new StringBuffer();
for (FeatureVector<?> fv : train) {
sb.append(fv.getId() + "\t");
if (isTrain) {
sb.append(((LabeledFeatureVector<?>) fv).getLabel().toString() + "\t");
} else {
sb.append("X\t");
}
for (String feature : train.getMetadata().keySet()) {
if (fv.containsKey(feature)) {
sb.append(feature + "=" + fv.get(feature).getValue() + " ");
}
}
sb.append("\n");
}
InstanceList il = loadInstances(sb.toString());
return il;
}
/**
* Train the classifier with this instance.
*
* @param fv
* @param clazz
*/
public void train(FeatureVector<E> fv, E clazz) {
if (!trained.contains(fv.getId())) {
LabeledFeatureVector<E> lfv = new LabeledFeatureVector<E>(clazz, fv.getId());
lfv.putAll(fv);
lfv.setQid(fv.getQid());
lfv.setRank(fv.getRank());
train.add(lfv);
trained.add(fv.getId());
}
}
/**
* Convert to the Mallet format.
*
* @param fv
* @param m
* @return
*/
public static Instance convert(FeatureVector<?> fv, Metadata m) {
boolean isTrain = (fv instanceof LabeledFeatureVector) ? true : false;
StringBuffer sb = new StringBuffer(fv.getId() + "\t");
if (isTrain) {
sb.append(((LabeledFeatureVector<?>) fv).getLabel().toString() + "\t");
} else {
sb.append("1\t");
}
for (String feature : m.keySet()) {
if (fv.containsKey(feature)) {
sb.append(feature + "=" + fv.get(feature).getValue() + " ");
}
}
InstanceList il = loadInstances(sb.toString());
return il.get(0);
}
