How to use

getOutcomeLabels

method

in

opennlp.tools.ml.model.DataIndexer

public final MaxentModel train(DataIndexer indexer) throws IOException {
 validate();
 if (indexer.getOutcomeLabels().length <= 1) {
  throw new InsufficientTrainingDataException("Training data must contain more than one outcome");
 }
 MaxentModel model = doTrain(indexer);
 addToReport(AbstractTrainer.TRAINER_TYPE_PARAM, EventTrainer.EVENT_VALUE);
 return model;
}

 private boolean compareDoubleArray(double[] expected, double[] actual,
   DataIndexer indexer, double tolerance)
 {
  double[] alignedActual = alignDoubleArrayForTestData(
    actual, indexer.getPredLabels(), indexer.getOutcomeLabels());

  if (expected.length != alignedActual.length) {
   return false;
  }

  for (int i = 0; i < alignedActual.length; i++) {
   if (Math.abs(alignedActual[i] - expected[i]) > tolerance) {
    return false;
   }
  }
  return true;
 }
}

int nPredLabels = predLabels.length;
String[] outcomeNames = indexer.getOutcomeLabels();
int nOutcomes = outcomeNames.length;

public NegLogLikelihood(DataIndexer indexer) {
 // Get data from indexer.
 if (indexer instanceof OnePassRealValueDataIndexer) {
  this.values = indexer.getValues();
 } else {
  this.values = null;
 }
 this.contexts    = indexer.getContexts();
 this.outcomeList = indexer.getOutcomeList();
 this.numTimesEventsSeen = indexer.getNumTimesEventsSeen();
 this.numOutcomes = indexer.getOutcomeLabels().length;
 this.numFeatures = indexer.getPredLabels().length;
 this.numContexts = this.contexts.length;
 this.dimension   = numOutcomes * numFeatures;
 this.expectation = new double[numOutcomes];
 this.tempSums    = new double[numOutcomes];
 this.gradient    = new double[dimension];
}

 @Test
 public void testLastLineBug() throws IOException {
  try (RealValueFileEventStream rvfes = new RealValueFileEventStream(
    "src/test/resources/data/opennlp/maxent/io/rvfes-bug-data-ok.txt")) {
   indexer.index(rvfes);
  }
  Assert.assertEquals(1, indexer.getOutcomeLabels().length);

  try (RealValueFileEventStream rvfes = new RealValueFileEventStream(
    "src/test/resources/data/opennlp/maxent/io/rvfes-bug-data-broken.txt")) {
   indexer.index(rvfes);
  }
  Assert.assertEquals(1, indexer.getOutcomeLabels().length);
 }
}

 /**
  * Evaluate the current model on training data set
  * @return model's training accuracy
  */
 @Override
 public double evaluate(double[] parameters) {
  int[][] contexts  = indexer.getContexts();
  float[][] values  = indexer.getValues();
  int[] nEventsSeen = indexer.getNumTimesEventsSeen();
  int[] outcomeList = indexer.getOutcomeList();
  int nOutcomes     = indexer.getOutcomeLabels().length;
  int nPredLabels   = indexer.getPredLabels().length;
  int nCorrect     = 0;
  int nTotalEvents = 0;
  for (int ei = 0; ei < contexts.length; ei++) {
   int[] context  = contexts[ei];
   float[] value  = values == null ? null : values[ei];
   double[] probs = new double[nOutcomes];
   QNModel.eval(context, value, probs, nOutcomes, nPredLabels, parameters);
   int outcome = ArrayMath.argmax(probs);
   if (outcome == outcomeList[ei]) {
    nCorrect += nEventsSeen[ei];
   }
   nTotalEvents += nEventsSeen[ei];
  }
  return (double) nCorrect / nTotalEvents;
 }
}

@Test
public void testDomainDimensionSanity() throws IOException {
 // given
 RealValueFileEventStream rvfes1 = new RealValueFileEventStream(
   "src/test/resources/data/opennlp/maxent/real-valued-weights-training-data.txt", "UTF-8");
 testDataIndexer.index(rvfes1);
 NegLogLikelihood objectFunction = new NegLogLikelihood(testDataIndexer);
 // when
 int correctDomainDimension = testDataIndexer.getPredLabels().length
   * testDataIndexer.getOutcomeLabels().length;
 // then
 Assert.assertEquals(correctDomainDimension, objectFunction.getDimension());
}

outcomeLabels = di.getOutcomeLabels();
omap = new HashMap<>();
for (int oli = 0; oli < outcomeLabels.length; oli++) {

Assert.assertEquals("opennlp.tools.ml.model.OnePassDataIndexer", di.getClass().getName());
Assert.assertEquals(3, di.getNumEvents());
Assert.assertEquals(2, di.getOutcomeLabels().length);
Assert.assertEquals(6, di.getPredLabels().length);

di.index(eventStream);
Assert.assertEquals(3, di.getNumEvents());
Assert.assertEquals(2, di.getOutcomeLabels().length);
Assert.assertEquals(6, di.getPredLabels().length);
di.index(eventStream);
Assert.assertEquals(3, di.getNumEvents());
Assert.assertEquals(2, di.getOutcomeLabels().length);
Assert.assertEquals(6, di.getPredLabels().length);

@Test
public void testValueAtNonInitialPoint02() throws IOException {
 // given
 RealValueFileEventStream rvfes1 = new RealValueFileEventStream(
   "src/test/resources/data/opennlp/maxent/real-valued-weights-training-data.txt", "UTF-8");
 testDataIndexer.index(rvfes1);
 NegLogLikelihood objectFunction = new NegLogLikelihood(testDataIndexer);
 // when
 double[] nonInitialPoint = new double[] { 3, 2, 3, 2, 3, 2, 3, 2, 3, 2 };
 double value = objectFunction.valueAt(dealignDoubleArrayForTestData(nonInitialPoint,
   testDataIndexer.getPredLabels(),
   testDataIndexer.getOutcomeLabels()));
 double expectedValue = 53.163219721099026;
 // then
 Assert.assertEquals(expectedValue, value, TOLERANCE02);
}

public AbstractModel trainModel(DataIndexer di) {
 display("Incorporating indexed data for training...  \n");
 contexts = di.getContexts();
 values = di.getValues();
 numTimesEventsSeen = di.getNumTimesEventsSeen();
 numEvents = di.getNumEvents();
 numUniqueEvents = contexts.length;
 outcomeLabels = di.getOutcomeLabels();
 outcomeList = di.getOutcomeList();
 predLabels = di.getPredLabels();
 numPreds = predLabels.length;
 numOutcomes = outcomeLabels.length;
 display("done.\n");
 display("\tNumber of Event Tokens: " + numUniqueEvents + "\n");
 display("\t    Number of Outcomes: " + numOutcomes + "\n");
 display("\t  Number of Predicates: " + numPreds + "\n");
 display("Computing model parameters...\n");
 MutableContext[] finalParameters = findParameters();
 display("...done.\n");
 /* Create and return the model ****/
 return new NaiveBayesModel(finalParameters, predLabels, outcomeLabels);
}

public AbstractModel trainModel(int iterations, DataIndexer di, int cutoff, boolean useAverage) {
 display("Incorporating indexed data for training...  \n");
 contexts = di.getContexts();
 values = di.getValues();
 numTimesEventsSeen = di.getNumTimesEventsSeen();
 numEvents = di.getNumEvents();
 numUniqueEvents = contexts.length;
 outcomeLabels = di.getOutcomeLabels();
 outcomeList = di.getOutcomeList();
 predLabels = di.getPredLabels();
 numPreds = predLabels.length;
 numOutcomes = outcomeLabels.length;
 display("done.\n");
 display("\tNumber of Event Tokens: " + numUniqueEvents + "\n");
 display("\t    Number of Outcomes: " + numOutcomes + "\n");
 display("\t  Number of Predicates: " + numPreds + "\n");
 display("Computing model parameters...\n");
 MutableContext[] finalParameters = findParameters(iterations, useAverage);
 display("...done.\n");
 /* Create and return the model *************/
 return new PerceptronModel(finalParameters, predLabels, outcomeLabels);
}

@Test
public void testGradientAtNonInitialPoint() throws IOException {
 // given
 RealValueFileEventStream rvfes1 = new RealValueFileEventStream(
   "src/test/resources/data/opennlp/maxent/real-valued-weights-training-data.txt", "UTF-8");
 testDataIndexer.index(rvfes1);
 NegLogLikelihood objectFunction = new NegLogLikelihood(testDataIndexer);
 // when
 double[] nonInitialPoint = new double[] { 0.2, 0.5, 0.2, 0.5, 0.2, 0.5, 0.2, 0.5, 0.2, 0.5 };
 double[] gradientAtNonInitialPoint =
   objectFunction.gradientAt(dealignDoubleArrayForTestData(nonInitialPoint,
     testDataIndexer.getPredLabels(),
     testDataIndexer.getOutcomeLabels()));
 double[] expectedGradient =
   new double[] { -12.755042847945553, -21.227127506102434,
     -72.57790706276435,   38.03525795198456,
     15.348650889354925,  12.755042847945557,
     21.22712750610244,   72.57790706276438,
     -38.03525795198456,  -15.348650889354925 };
 // then
 Assert.assertTrue(compareDoubleArray(expectedGradient, gradientAtNonInitialPoint,
   testDataIndexer, TOLERANCE01));
}

outcomeLabels = di.getOutcomeLabels();
outcomeList = di.getOutcomeList();
numOutcomes = outcomeLabels.length;

public final MaxentModel train(DataIndexer indexer) throws IOException {
 validate();
 if (indexer.getOutcomeLabels().length <= 1) {
  throw new InsufficientTrainingDataException("Training data must contain more than one outcome");
 }
 MaxentModel model = doTrain(indexer);
 addToReport(AbstractTrainer.TRAINER_TYPE_PARAM, EventTrainer.EVENT_VALUE);
 return model;
}

Assert.assertArrayEquals(new int[]{3, 1, 1}, indexer.getNumTimesEventsSeen());
Assert.assertArrayEquals(new String[]{"ppo=other"}, indexer.getPredLabels());
Assert.assertArrayEquals(new String[]{"other", "org-start", "org-cont"}, indexer.getOutcomeLabels());
Assert.assertArrayEquals(new int[]{5}, indexer.getPredCounts());

Assert.assertArrayEquals(new int[]{3, 1, 1}, indexer.getNumTimesEventsSeen());
Assert.assertArrayEquals(new String[]{"ppo=other"}, indexer.getPredLabels());
Assert.assertArrayEquals(new String[]{"other", "org-start", "org-cont"}, indexer.getOutcomeLabels());
Assert.assertArrayEquals(new int[]{5}, indexer.getPredCounts());

Assert.assertArrayEquals(new int[]{3, 1, 1}, indexer.getNumTimesEventsSeen());
Assert.assertArrayEquals(new String[]{"ppo=other"}, indexer.getPredLabels());
Assert.assertArrayEquals(new String[]{"other", "org-start", "org-cont"}, indexer.getOutcomeLabels());
Assert.assertArrayEquals(new int[]{5}, indexer.getPredCounts());

Assert.assertArrayEquals(new int[]{3, 1, 1}, indexer.getNumTimesEventsSeen());
Assert.assertArrayEquals(new String[]{"ppo=other"}, indexer.getPredLabels());
Assert.assertArrayEquals(new String[]{"other", "org-start", "org-cont"}, indexer.getOutcomeLabels());
Assert.assertArrayEquals(new int[]{5}, indexer.getPredCounts());