/**
* converts the sentence based instance list into a token based one This is needed for the
* ME-version of JET (JetMeClassifier)
*
* @param METrainerDummyPipe
* @param inst just the features for one sentence to be transformed
* @return
*/
public static InstanceList convertFeatsforClassifier(
final Pipe METrainerDummyPipe, final Instance inst) {
final InstanceList iList = new InstanceList(METrainerDummyPipe);
final FeatureVectorSequence fvs = (FeatureVectorSequence) inst.getData();
final LabelSequence ls = (LabelSequence) inst.getTarget();
final LabelAlphabet ldict = (LabelAlphabet) ls.getAlphabet();
final Object source = inst.getSource();
final Object name = inst.getName();
if (ls.size() != fvs.size()) {
System.err.println(
"failed making token instances: size of labelsequence != size of featue vector sequence: "
+ ls.size()
+ " - "
+ fvs.size());
System.exit(-1);
}
for (int j = 0; j < fvs.size(); j++) {
final Instance I =
new Instance(fvs.getFeatureVector(j), ldict.lookupLabel(ls.get(j)), name, source);
iList.add(I);
}
return iList;
}
public static InstanceList copy(InstanceList instances) {
InstanceList ret = (InstanceList) instances.clone();
// LabelAlphabet labelDict = (LabelAlphabet) ret.getTargetAlphabet();
Alphabet featDict = ret.getDataAlphabet();
for (int i = 0; i < ret.size(); i++) {
Instance instance = ret.get(i);
Instance clone = (Instance) instance.clone();
FeatureVector fv = (FeatureVector) clone.getData();
int[] indices = fv.getIndices();
double[] values = fv.getValues();
int[] newIndices = new int[indices.length];
System.arraycopy(indices, 0, newIndices, 0, indices.length);
double[] newValues = new double[indices.length];
System.arraycopy(values, 0, newValues, 0, indices.length);
FeatureVector newFv = new FeatureVector(featDict, newIndices, newValues);
Instance newInstance =
new Instance(newFv, instance.getTarget(), instance.getName(), instance.getSource());
ret.set(i, newInstance);
}
return ret;
}
public Instance pipe(Instance carrier) {
TokenSequence ts = (TokenSequence) carrier.getData();
TokenSequence targets =
carrier.getTarget() instanceof TokenSequence ? (TokenSequence) carrier.getTarget() : null;
TokenSequence source =
carrier.getSource() instanceof TokenSequence ? (TokenSequence) carrier.getSource() : null;
StringBuffer sb = new StringBuffer();
if (prefix != null) sb.append(prefix);
sb.append("name: " + carrier.getName() + "\n");
for (int i = 0; i < ts.size(); i++) {
if (source != null) {
sb.append(source.get(i).getText());
sb.append(' ');
}
if (carrier.getTarget() instanceof TokenSequence) {
sb.append(((TokenSequence) carrier.getTarget()).get(i).getText());
sb.append(' ');
}
if (carrier.getTarget() instanceof FeatureSequence) {
sb.append(((FeatureSequence) carrier.getTarget()).getObjectAtPosition(i).toString());
sb.append(' ');
}
PropertyList pl = ts.get(i).getFeatures();
if (pl != null) {
PropertyList.Iterator iter = pl.iterator();
while (iter.hasNext()) {
iter.next();
double v = iter.getNumericValue();
if (v == 1.0) sb.append(iter.getKey());
else sb.append(iter.getKey() + '=' + v);
sb.append(' ');
}
}
sb.append('\n');
}
System.out.print(sb.toString());
return carrier;
}
public Instance pipe(Instance carrier) {
Object inputData = carrier.getData();
Alphabet features = getDataAlphabet();
LabelAlphabet labels;
LabelSequence target = null;
String[][] tokens;
if (inputData instanceof String) tokens = parseSentence((String) inputData);
else if (inputData instanceof String[][]) tokens = (String[][]) inputData;
else throw new IllegalArgumentException("Not a String or String[][]; got " + inputData);
FeatureVector[] fvs = new FeatureVector[tokens.length];
if (isTargetProcessing()) {
labels = (LabelAlphabet) getTargetAlphabet();
target = new LabelSequence(labels, tokens.length);
}
for (int l = 0; l < tokens.length; l++) {
int nFeatures;
if (isTargetProcessing()) {
if (tokens[l].length < 1)
throw new IllegalStateException(
"Missing label at line " + l + " instance " + carrier.getName());
nFeatures = tokens[l].length - 1;
target.add(tokens[l][nFeatures]);
} else nFeatures = tokens[l].length;
int featureIndices[] = new int[nFeatures];
for (int f = 0; f < nFeatures; f++) featureIndices[f] = features.lookupIndex(tokens[l][f]);
fvs[l] =
featureInductionOption.value
? new AugmentableFeatureVector(
features, featureIndices, null, featureIndices.length)
: new FeatureVector(features, featureIndices);
}
carrier.setData(new FeatureVectorSequence(fvs));
if (isTargetProcessing()) carrier.setTarget(target);
else carrier.setTarget(new LabelSequence(getTargetAlphabet()));
return carrier;
}
