public Instance pipe(Instance carrier) {
if (!(carrier.getTarget() instanceof String)) {
throw new IllegalArgumentException("Target must be of type String");
}
String featuresLine = (String) carrier.getTarget();
String[] features = featuresLine.split(",?\\s+");
double[] values = new double[features.length];
Arrays.fill(values, 1.0);
for (int i = 0; i < features.length; i++) {
// Support the syntax "FEATURE=0.000342 OTHER_FEATURE=-2.32423"
// \
if (features[i].indexOf("=") != -1) {
String[] keyValuePair = features[i].split("=");
features[i] = keyValuePair[0];
values[i] = Double.parseDouble(keyValuePair[1]);
}
// ensure that the feature has a spot in the alphabet
// \
getTargetAlphabet().lookupIndex(features[i], true);
}
FeatureVector target = new FeatureVector(getTargetAlphabet(), features, values);
carrier.setTarget(target);
return carrier;
}
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 boolean train(
InstanceList ilist, InstanceList validation, InstanceList testing, TransducerEvaluator eval) {
assert (ilist.size() > 0);
if (emissionEstimator == null) {
emissionEstimator = new Multinomial.LaplaceEstimator[numStates()];
transitionEstimator = new Multinomial.LaplaceEstimator[numStates()];
emissionMultinomial = new Multinomial[numStates()];
transitionMultinomial = new Multinomial[numStates()];
Alphabet transitionAlphabet = new Alphabet();
for (int i = 0; i < numStates(); i++)
transitionAlphabet.lookupIndex(((State) states.get(i)).getName(), true);
for (int i = 0; i < numStates(); i++) {
emissionEstimator[i] = new Multinomial.LaplaceEstimator(inputAlphabet);
transitionEstimator[i] = new Multinomial.LaplaceEstimator(transitionAlphabet);
emissionMultinomial[i] =
new Multinomial(getUniformArray(inputAlphabet.size()), inputAlphabet);
transitionMultinomial[i] =
new Multinomial(getUniformArray(transitionAlphabet.size()), transitionAlphabet);
}
initialEstimator = new Multinomial.LaplaceEstimator(transitionAlphabet);
}
for (Instance instance : ilist) {
FeatureSequence input = (FeatureSequence) instance.getData();
FeatureSequence output = (FeatureSequence) instance.getTarget();
new SumLatticeDefault(this, input, output, new Incrementor());
}
initialMultinomial = initialEstimator.estimate();
for (int i = 0; i < numStates(); i++) {
emissionMultinomial[i] = emissionEstimator[i].estimate();
transitionMultinomial[i] = transitionEstimator[i].estimate();
getState(i).setInitialWeight(initialMultinomial.logProbability(getState(i).getName()));
}
return true;
}
/**
* 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 SVM train(InstanceList trainingList) {
svm_problem problem = new svm_problem();
problem.l = trainingList.size();
problem.x = new svm_node[problem.l][];
problem.y = new double[problem.l];
for (int i = 0; i < trainingList.size(); i++) {
Instance instance = trainingList.get(i);
svm_node[] input = SVM.getSvmNodes(instance);
if (input == null) {
continue;
}
int labelIndex = ((Label) instance.getTarget()).getIndex();
problem.x[i] = input;
problem.y[i] = labelIndex;
}
int max_index = trainingList.getDataAlphabet().size();
if (param.gamma == 0 && max_index > 0) {
param.gamma = 1.0 / max_index;
}
// int numLabels = trainingList.getTargetAlphabet().size();
// int[] weight_label = new int[numLabels];
// double[] weight = trainingList.targetLabelDistribution().getValues();
// double minValue = Double.MAX_VALUE;
//
// for (int i = 0; i < weight.length; i++) {
// if (minValue > weight[i]) {
// minValue = weight[i];
// }
// }
//
// for (int i = 0; i < weight.length; i++) {
// weight_label[i] = i;
// weight[i] = weight[i] / minValue;
// }
//
// param.weight_label = weight_label;
// param.weight = weight;
String error_msg = svm.svm_check_parameter(problem, param);
if (error_msg != null) {
System.err.print("Error: " + error_msg + "\n");
System.exit(1);
}
svm_model model = svm.svm_train(problem, param);
classifier = new SVM(model, trainingList.getPipe());
return classifier;
}
private boolean[][] labelConnectionsIn(InstanceList trainingSet) {
int numLabels = outputAlphabet.size();
boolean[][] connections = new boolean[numLabels][numLabels];
for (Instance instance : trainingSet) {
FeatureSequence output = (FeatureSequence) instance.getTarget();
for (int j = 1; j < output.size(); j++) {
int sourceIndex = outputAlphabet.lookupIndex(output.get(j - 1));
int destIndex = outputAlphabet.lookupIndex(output.get(j));
assert (sourceIndex >= 0 && destIndex >= 0);
connections[sourceIndex][destIndex] = true;
}
}
return connections;
}
public Instance pipe(Instance carrier) {
Sequence data = (Sequence) carrier.getData();
Sequence target = (Sequence) carrier.getTarget();
if (data.size() != target.size())
throw new IllegalArgumentException(
"Trying to print into SimpleTagger format, where data and target lengths do not match\n"
+ "data.length = "
+ data.size()
+ ", target.length = "
+ target.size());
int N = data.size();
if (data instanceof TokenSequence) {
throw new UnsupportedOperationException("Not yet implemented.");
} else if (data instanceof FeatureVectorSequence) {
FeatureVectorSequence fvs = (FeatureVectorSequence) data;
Alphabet dict = (fvs.size() > 0) ? fvs.getFeatureVector(0).getAlphabet() : null;
for (int i = 0; i < N; i++) {
Object label = target.get(i);
writer.print(label);
FeatureVector fv = fvs.getFeatureVector(i);
for (int loc = 0; loc < fv.numLocations(); loc++) {
writer.print(' ');
String fname = dict.lookupObject(fv.indexAtLocation(loc)).toString();
double value = fv.valueAtLocation(loc);
// if (!Maths.almostEquals(value, 1.0)) {
// throw new IllegalArgumentException ("Printing to SimpleTagger format: FeatureVector
// not binary at time slice "+i+" fv:"+fv);
// }
writer.print(fname + String.valueOf(value));
}
writer.println();
}
} else {
throw new IllegalArgumentException("Don't know how to print data of type " + data);
}
writer.println();
// writer.print(getDataAlphabet());
return carrier;
}
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;
}