public String toString() {
StringBuffer toReturn = new StringBuffer();
for (int i = 0; i < size(); i++) {
toReturn.append(((EntityConfidence) confidences.get(i)).toString() + " ");
}
return toReturn.toString();
}
public static void main(String[] args) throws Exception {
Reader trainingFile = null;
// Process arguments
int restArgs = commandOptions.processOptions(args);
// Check arguments
if (restArgs != args.length) {
commandOptions.printUsage(true);
throw new IllegalArgumentException("Unexpected arg " + args[restArgs]);
}
if (trainFileOption.value == null) {
commandOptions.printUsage(true);
throw new IllegalArgumentException("Expected --train-file FILE");
}
if (modelFileOption.value == null) {
commandOptions.printUsage(true);
throw new IllegalArgumentException("Expected --model-file FILE");
}
// Get the CRF structure specification.
ZipFile zipFile = new ZipFile(modelFileOption.value);
ZipEntry zipEntry = zipFile.getEntry("crf-info.xml");
CRFInfo crfInfo = new CRFInfo(zipFile.getInputStream(zipEntry));
StringBuffer crfInfoBuffer = new StringBuffer();
BufferedReader reader =
new BufferedReader(new InputStreamReader(zipFile.getInputStream(zipEntry)));
String line;
while ((line = reader.readLine()) != null) {
crfInfoBuffer.append(line).append('\n');
}
reader.close();
// Create the CRF, and train it.
CRF4 crf = createCRF(trainFileOption.value, crfInfo);
// Create a new zip file for our output. This will overwrite
// the file we used for input.
ZipOutputStream zos = new ZipOutputStream(new FileOutputStream(modelFileOption.value));
// Copy the CRF info xml to the output zip file.
zos.putNextEntry(new ZipEntry("crf-info.xml"));
BufferedWriter writer = new BufferedWriter(new OutputStreamWriter(zos));
writer.write(crfInfoBuffer.toString());
writer.flush();
zos.closeEntry();
// Save the CRF classifier model to the output zip file.
zos.putNextEntry(new ZipEntry("crf-model.ser"));
ObjectOutputStream oos = new ObjectOutputStream(zos);
oos.writeObject(crf);
oos.flush();
zos.closeEntry();
zos.close();
}
public String toString() {
StringBuffer toReturn = new StringBuffer();
toReturn.append(
this.entity
+ " / "
+ this.confidence
+ " / "
+ (this.correct ? "correct" : "incorrect")
+ "\n");
return toReturn.toString();
}
public EntityConfidence(double conf, boolean corr, Sequence input, int start, int end) {
this.confidence = conf;
this.correct = corr;
StringBuffer buff = new StringBuffer();
if (input != null) {
for (int j = start; j <= end; j++) {
FeatureVector fv = (FeatureVector) input.get(j);
for (int k = 0; k < fv.numLocations(); k++) {
String featureName = fv.getAlphabet().lookupObject(fv.indexAtLocation(k)).toString();
if (featureName.startsWith("W=") && featureName.indexOf("@") == -1) {
buff.append(featureName.substring(featureName.indexOf('=') + 1) + " ");
}
}
}
}
this.entity = buff.toString();
}
public String getNextLineGroup() {
StringBuffer sb = new StringBuffer();
String line;
while (true) {
try {
line = reader.readLine();
} catch (IOException e) {
throw new RuntimeException(e);
}
// System.out.println ("LineGroupIterator: got line: "+line);
if (line == null) {
break;
} else if (!line.isEmpty()) {
sb.append(line);
sb.append('\n');
break;
}
}
if (sb.length() == 0) return null;
else return sb.toString();
}