Java InstanceList.size方法代码示例

import cc.mallet.types.InstanceList; //导入方法依赖的package包/类
public void induceFeatures (InstanceList ilist, boolean withFeatureShrinkage, boolean inducePerClassFeatures)
	{
		if (inducePerClassFeatures) {
			int numClasses = ilist.getTargetAlphabet().size();
//			int numFeatures = ilist.getDataAlphabet().size();
			FeatureSelection[] pcfs = new FeatureSelection[numClasses];
			for (int j = 0; j < numClasses; j++)
				pcfs[j] = (FeatureSelection) ilist.getPerLabelFeatureSelection()[j].clone();
			for (int i = 0; i < ilist.size(); i++) {
				Object data = ilist.get(i).getData();
				AugmentableFeatureVector afv = (AugmentableFeatureVector) data;
				root.induceFeatures (afv, null, pcfs, ilist.getFeatureSelection(), ilist.getPerLabelFeatureSelection(),
														 withFeatureShrinkage, inducePerClassFeatures, addFeaturesClassEntropyThreshold);
			}
		} else {
			throw new UnsupportedOperationException ("Not yet implemented");
		}
	}
 

import cc.mallet.types.InstanceList; //导入方法依赖的package包/类
public void printInstanceLists ()
{
	for (int i = 0; i < memm.numStates(); i++) {
		State state = (State) memm.getState (i);
		InstanceList training = state.trainingSet;
		System.out.println ("State "+i+" : "+state.getName());
		if (training == null) {
			System.out.println ("No data");
			continue;
		}
		for (int j = 0; j < training.size(); j++) {
			Instance inst = training.get (j);
			System.out.println ("From : "+state.getName()+" To : "+inst.getTarget());
			System.out.println ("Instance "+j);
			System.out.println (inst.getTarget());
			System.out.println (inst.getData());
		}
	}
}
 

import cc.mallet.types.InstanceList; //导入方法依赖的package包/类
public BitSet preProcess(InstanceList data) {
  // count
  int ii = 0;
  int fi;
  FeatureVector fv;
  BitSet bitSet = new BitSet(data.size());
  for (Instance instance : data) {
    FeatureVectorSequence fvs = (FeatureVectorSequence)instance.getData();
    for (int ip = 0; ip < fvs.size(); ip++) {
      fv = fvs.get(ip);
      for (int loc = 0; loc < fv.numLocations(); loc++) {
        fi = fv.indexAtLocation(loc);
        if (constraints.containsKey(fi)) {
          constraints.get(fi).count += 1;
          bitSet.set(ii);
        }
      }
    }
    ii++;
  }
  return bitSet;
}
 

import cc.mallet.types.InstanceList; //导入方法依赖的package包/类
public CRFOptimizableByGE(CRF crf, ArrayList<GEConstraint> constraints, InstanceList data, StateLabelMap map, int numThreads, double weight) {
  this.crf = crf;
  this.constraints = constraints;
  this.cache = Integer.MAX_VALUE;
  this.cachedValue = Double.NaN;
  this.cachedGradient = new CRF.Factors(crf);
  this.data = data;
  this.numThreads = numThreads;
  this.weight = weight;
  
  instancesWithConstraints = new BitSet(data.size());
  
  for (GEConstraint constraint : constraints) {
    constraint.setStateLabelMap(map);
    BitSet bitset = constraint.preProcess(data);
    instancesWithConstraints.or(bitset);
  }
  this.gpv = DEFAULT_GPV;
  
  if (numThreads > 1) {
    this.executor = (ThreadPoolExecutor)Executors.newFixedThreadPool(numThreads);
  }
  
  createReverseTransitionMatrices(crf);
}
 

import cc.mallet.types.InstanceList; //导入方法依赖的package包/类
public BitSet preProcess(InstanceList data) {
  // count
  BitSet bitSet = new BitSet(data.size());
  int ii = 0;
  for (Instance instance : data) {
    FeatureVectorSequence fvs = (FeatureVectorSequence)instance.getData();
    for (int ip = 1; ip < fvs.size(); ip++) {
      for (int fi : constraintsMap.keys()) {
        // binary constraint features
        if (fvs.get(ip).location(fi) >= 0) {
          constraintsList.get(constraintsMap.get(fi)).count += 1;
          bitSet.set(ii);
        }
      }
    }
    ii++;
  }
  return bitSet;
}
 

import cc.mallet.types.InstanceList; //导入方法依赖的package包/类
/**
 * Runs inference across all the instances and returns the average token
 * accuracy.
 */
public double averageTokenAccuracy (InstanceList ilist)
{
	double accuracy = 0;
	for (int i = 0; i < ilist.size(); i++) {
		Instance instance = ilist.get(i);
		Sequence input = (Sequence) instance.getData();
		Sequence output = (Sequence) instance.getTarget();
		assert (input.size() == output.size());
		Sequence predicted = maxLatticeFactory.newMaxLattice(this, input).bestOutputSequence();
		double pathAccuracy = Sequences.elementwiseAccuracy(output, predicted); 
		accuracy += pathAccuracy;
		logger.fine ("Transducer path accuracy = "+pathAccuracy);
	}
	return accuracy/ilist.size();
}
 

import cc.mallet.types.InstanceList; //导入方法依赖的package包/类
/** This method is deprecated. */
// But it is here as a reminder to do something about induceFeaturesFor(). */
@Deprecated
public Sequence[] predict (InstanceList testing) {
	testing.setFeatureSelection(this.globalFeatureSelection);
	for (int i = 0; i < featureInducers.size(); i++) {
		FeatureInducer klfi = (FeatureInducer)featureInducers.get(i);
		klfi.induceFeaturesFor (testing, false, false);
	}
	Sequence[] ret = new Sequence[testing.size()];
	for (int i = 0; i < testing.size(); i++) {
		Instance instance = testing.get(i);
		Sequence input = (Sequence) instance.getData();
		Sequence trueOutput = (Sequence) instance.getTarget();
		assert (input.size() == trueOutput.size());
		Sequence predOutput = new MaxLatticeDefault(this, input).bestOutputSequence();
		assert (predOutput.size() == trueOutput.size());
		ret[i] = predOutput;
	}
	return ret;
}
 

import cc.mallet.types.InstanceList; //导入方法依赖的package包/类
private double trainSample(InstanceList trainingSample, int numIterations,
		double rate) {
	double lambda = trainingSample.size();
	double t = 1 / (lambda * rate);

	double loglik = Double.NEGATIVE_INFINITY;
	for (int i = 0; i < numIterations; i++) {
		loglik = 0.0;
		for (int j = 0; j < trainingSample.size(); j++) {
			rate = 1 / (lambda * t);
			loglik += trainIncrementalLikelihood(trainingSample.get(j),
					rate);
			t += 1.0;
		}
	}

	return loglik;
}
 

import cc.mallet.types.InstanceList; //导入方法依赖的package包/类
/**
 * Sample a InstanceList and its true clustering.
 * @param alph
 * @return
 */
private Clustering sampleClustering (Alphabet alph) {
	InstanceList instances =
		new InstanceList(random,
										 alph,
										 new String[]{"foo", "bar"},
										 30).subList(0, 20);
	Clustering singletons = ClusterUtils.createSingletonClustering(instances);
	// Merge instances that both have feature0
	for (int i = 0; i < instances.size(); i++) {
		FeatureVector fvi = (FeatureVector)instances.get(i).getData();
		for (int j = i + 1; j < instances.size(); j++) {
			FeatureVector fvj = (FeatureVector)instances.get(j).getData();
			if (fvi.contains("feature0") && fvj.contains("feature0")) {
				singletons = ClusterUtils.mergeClusters(singletons,
																								singletons.getLabel(i),
																								singletons.getLabel(j));
			} else if (!(fvi.contains("feature0") || fvj.contains("feature0"))
								 && random.nextUniform() < noise) {
				// Random noise.
				singletons = ClusterUtils.mergeClusters(singletons,
																								singletons.getLabel(i),
																								singletons.getLabel(j));					
			}
		}
	}
	return singletons;
}
 

import cc.mallet.types.InstanceList; //导入方法依赖的package包/类
public Trial (Classifier c, InstanceList ilist)
{
	super (ilist.size());
	this.classifier = c;
	for (Instance instance : ilist)
		this.add (c.classify (instance));
}
 

import cc.mallet.types.InstanceList; //导入方法依赖的package包/类
public void collectConstraints (InstanceList ilist)
{
  for (int inum = 0; inum < ilist.size(); inum++) {
    logger.finest ("*** Collecting constraints for instance "+inum);
    Instance inst = ilist.get (inum);
    ACRF.UnrolledGraph unrolled = new ACRF.UnrolledGraph (inst, templates, null, true);
    Assignment assn = unrolled.getAssignment ();
    collectConstraintsForGraph (unrolled, assn);
  }
}
 

import cc.mallet.types.InstanceList; //导入方法依赖的package包/类
public static void main(String[] args) {
	String htmldir = args[0];
	Pipe pipe = new SerialPipes(new Pipe[] { new Input2CharSequence(),
			new CharSequenceRemoveHTML() });
	InstanceList list = new InstanceList(pipe);
	list.addThruPipe(new FileIterator(htmldir, FileIterator.STARTING_DIRECTORIES));

	for (int index = 0; index < list.size(); index++) {
		Instance inst = list.get(index);
		System.err.println(inst.getData());
	}

}
 

import cc.mallet.types.InstanceList; //导入方法依赖的package包/类
public BitSet preProcess(InstanceList data) {
  // count
  int ii = 0;
  int fi;
  FeatureVector fv;
  BitSet bitSet = new BitSet(data.size());
  for (Instance instance : data) {
    FeatureVectorSequence fvs = (FeatureVectorSequence)instance.getData();
    for (int ip = 0; ip < fvs.size(); ip++) {
      fv = fvs.get(ip);
      for (int loc = 0; loc < fv.numLocations(); loc++) {
        fi = fv.indexAtLocation(loc);
        if (constraints.containsKey(fi)) {
          constraints.get(fi).count += 1;
          bitSet.set(ii);
        }
      }
      if (constraints.containsKey(fv.getAlphabet().size())) {
        bitSet.set(ii);
        constraints.get(fv.getAlphabet().size()).count += 1;
      }
    }

    ii++;
  }
  return bitSet;
}
 

import cc.mallet.types.InstanceList; //导入方法依赖的package包/类
public BitSet preProcess(InstanceList data) {
  // count number of tokens
  BitSet bitSet = new BitSet(data.size());
  bitSet.set(0, data.size(), true);
  for (Instance instance : data) {
    FeatureVectorSequence fvs = (FeatureVectorSequence)instance.getData();
    this.numTokens += fvs.size();
  } 
  return bitSet;
}
 

import cc.mallet.types.InstanceList; //导入方法依赖的package包/类
public static Clustering mergeInstancesWithSameLabel (Clustering clustering) {
	InstanceList list = clustering.getInstances();
	for (int i = 0; i < list.size(); i++) {
		Instance ii = list.get(i);
		int li = clustering.getLabel(i);
		for (int j = i + 1; j < list.size(); j++) {
			Instance ij = list.get(j);
			int lj = clustering.getLabel(j);
			if (li != lj && ii.getLabeling().equals(ij.getLabeling()))
				clustering = ClusterUtils.mergeClusters(clustering, li, lj);
		}
	}	
	return clustering;
}