public void addInstance(SingleDecision decision, FeatureVector featureVector)
throws MaltChainedException {
if (featureVector == null) {
throw new LibException("The feature vector cannot be found");
} else if (decision == null) {
throw new LibException("The decision cannot be found");
}
try {
sb.append(decision.getDecisionCode() + "\t");
final int n = featureVector.size();
for (int i = 0; i < n; i++) {
FeatureValue featureValue = featureVector.getFeatureValue(i);
if (featureValue == null || (excludeNullValues == true && featureValue.isNullValue())) {
sb.append("-1");
} else {
if (featureValue instanceof SingleFeatureValue) {
SingleFeatureValue singleFeatureValue = (SingleFeatureValue) featureValue;
if (singleFeatureValue.getValue() == 1) {
sb.append(singleFeatureValue.getIndexCode());
} else if (singleFeatureValue.getValue() == 0) {
sb.append("-1");
} else {
sb.append(singleFeatureValue.getIndexCode());
sb.append(":");
sb.append(singleFeatureValue.getValue());
}
} else if (featureValue instanceof MultipleFeatureValue) {
Set<Integer> values = ((MultipleFeatureValue) featureValue).getCodes();
int j = 0;
for (Integer value : values) {
sb.append(value.toString());
if (j != values.size() - 1) {
sb.append("|");
}
j++;
}
} else {
throw new LibException(
"Don't recognize the type of feature value: " + featureValue.getClass());
}
}
sb.append('\t');
}
sb.append('\n');
instanceOutput.write(sb.toString());
instanceOutput.flush();
increaseNumberOfInstances();
sb.setLength(0);
} catch (IOException e) {
throw new LibException("The learner cannot write to the instance file. ", e);
}
}
public boolean predict(FeatureVector featureVector, SingleDecision decision)
throws MaltChainedException {
if (featureVector == null) {
throw new LibException(
"The learner cannot predict the next class, because the feature vector cannot be found. ");
}
final FeatureList featureList = new FeatureList();
final int size = featureVector.size();
for (int i = 1; i <= size; i++) {
final FeatureValue featureValue = featureVector.getFeatureValue(i - 1);
if (featureValue != null && !(excludeNullValues == true && featureValue.isNullValue())) {
if (featureValue instanceof SingleFeatureValue) {
SingleFeatureValue singleFeatureValue = (SingleFeatureValue) featureValue;
int index = featureMap.getIndex(i, singleFeatureValue.getIndexCode());
if (index != -1 && singleFeatureValue.getValue() != 0) {
featureList.add(index, singleFeatureValue.getValue());
}
} else if (featureValue instanceof MultipleFeatureValue) {
for (Integer value : ((MultipleFeatureValue) featureValue).getCodes()) {
int v = featureMap.getIndex(i, value);
if (v != -1) {
featureList.add(v, 1);
}
}
}
}
}
try {
decision.getKBestList().addList(model.predict(featureList.toArray()));
// decision.getKBestList().addList(prediction(featureList));
} catch (OutOfMemoryError e) {
throw new LibException("Out of memory. Please increase the Java heap size (-Xmx<size>). ", e);
}
return true;
}
/**
* Initialize the feature split parameters and the split feature vector and master feature vector
* according to the behavior strategy.
*
* @param featureVector the parent guide model's feature vector.
* @throws MaltChainedException
*/
protected void initSplitParam(FeatureVector featureVector) throws MaltChainedException {
if (getGuide().getConfiguration().getOptionValue("guide", "data_split_column") == null
|| getGuide()
.getConfiguration()
.getOptionValue("guide", "data_split_column")
.toString()
.length()
== 0) {
throw new GuideException(
"The option '--guide-data_split_column' cannot be found, when initializing the data split. ");
}
if (getGuide().getConfiguration().getOptionValue("guide", "data_split_structure") == null
|| getGuide()
.getConfiguration()
.getOptionValue("guide", "data_split_structure")
.toString()
.length()
== 0) {
throw new GuideException(
"The option '--guide-data_split_structure' cannot be found, when initializing the data split. ");
}
try {
final String spec =
"InputColumn("
+ getGuide()
.getConfiguration()
.getOptionValue("guide", "data_split_column")
.toString()
.trim()
+ ", "
+ getGuide()
.getConfiguration()
.getOptionValue("guide", "data_split_structure")
.toString()
.trim()
+ ")";
divideFeature = featureVector.getFeatureModel().identifyFeature(spec);
} catch (FeatureException e) {
throw new GuideException(
"The data split feature 'InputColumn("
+ getGuide()
.getConfiguration()
.getOptionValue("guide", "data_split_column")
.toString()
+ ", "
+ getGuide()
.getConfiguration()
.getOptionValue("guide", "data_split_structure")
.toString()
+ ") cannot be initialized. ",
e);
}
if (!(divideFeature instanceof Modifiable)) {
throw new GuideException(
"The data split feature 'InputColumn("
+ getGuide()
.getConfiguration()
.getOptionValue("guide", "data_split_column")
.toString()
+ ", "
+ getGuide()
.getConfiguration()
.getOptionValue("guide", "data_split_structure")
.toString()
+ ") does not implement Modifiable interface. ");
}
divideFeatureIndexVector = new ArrayList<Integer>();
for (int i = 0; i < featureVector.size(); i++) {
if (featureVector.get(i).equals(divideFeature)) {
divideFeatureIndexVector.add(i);
}
}
// if ((Boolean)getGuide().getConfiguration().getOptionValue("malt0.4", "behavior") == true) {
// /* MaltParser 0.4 removes the divide feature for all divide models. For the "Sum-up" model
// or
// * master model adds the divide feature in the end of the feature vector.
// */
// masterFeatureVector = (FeatureVector)featureVector.clone();
// for (Integer i : divideFeatureIndexVector) {
// masterFeatureVector.remove(masterFeatureVector.get(i));
// }
// for (Integer i : divideFeatureIndexVector) {
// masterFeatureVector.add(featureVector.get(i));
// }
//
// divideFeatureVector = (FeatureVector)featureVector.clone();
// for (Integer i : divideFeatureIndexVector) {
// divideFeatureVector.remove(divideFeatureVector.get(i));
// }
// } else {
masterFeatureVector = featureVector;
divideFeatureVector = (FeatureVector) featureVector.clone();
for (Integer i : divideFeatureIndexVector) {
divideFeatureVector.remove(divideFeatureVector.get(i));
}
// }
try {
if (getGuide().getConfiguration().getOptionValue("guide", "data_split_threshold").toString()
!= null) {
divideThreshold =
Integer.parseInt(
getGuide()
.getConfiguration()
.getOptionValue("guide", "data_split_threshold")
.toString());
} else {
divideThreshold = 0;
}
} catch (NumberFormatException e) {
throw new GuideException(
"The --guide-data_split_threshold option is not an integer value. ", e);
}
}
