Java FeatureVectorSequence.get方法代码示例

import cc.mallet.types.FeatureVectorSequence; //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.FeatureVectorSequence; //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.FeatureVectorSequence; //导入方法依赖的package包/类
public TransitionIterator (State source,
		FeatureVectorSequence inputSeq,
		int inputPosition,
		String output, CRF crf)
{
	this (source, inputSeq.get(inputPosition), output, crf);
}
 

import cc.mallet.types.FeatureVectorSequence; //导入方法依赖的package包/类
/** returns unnormalized scores, corresponding to the score an
 * element of the InstanceList being the "top" instance
 * @param instance instance with data field a {@link InstanceList}.
 * @param scores has length = number of Instances in Instance.data,
 * which is of type InstanceList */
public void getUnnormalizedClassificationScores (Instance instance, double[] scores)
{
	FeatureVectorSequence fvs = (FeatureVectorSequence)instance.getData();
	assert (scores.length == fvs.size());
	int numFeatures = instance.getDataAlphabet().size()+1;

	for (int instanceNumber=0; instanceNumber < fvs.size(); instanceNumber++) {
		FeatureVector fv = (FeatureVector)fvs.get(instanceNumber);
		// Make sure the feature vector's feature dictionary matches
		// what we are expecting from our data pipe (and thus our notion
		// of feature probabilities.
		assert (fv.getAlphabet ()
						== this.instancePipe.getDataAlphabet ());
		
		// Include the feature weights according to each label xxx is
		// this correct ? we only calculate the dot prod of the feature
		// vector with the "positiveLabel" weights
		// xxx include multiple labels
		scores[instanceNumber] = parameters[0*numFeatures + defaultFeatureIndex]
															 + MatrixOps.rowDotProduct (parameters, numFeatures,
																													0, fv,
																													defaultFeatureIndex,
																													(perClassFeatureSelection == null
																													 ? featureSelection
																													 : perClassFeatureSelection[0]));
	}
}
 

import cc.mallet.types.FeatureVectorSequence; //导入方法依赖的package包/类
public void getClassificationScores (Instance instance, double[] scores)
{
	FeatureVectorSequence fvs = (FeatureVectorSequence)instance.getData();
	int numFeatures = instance.getDataAlphabet().size()+1;
	int numLabels = fvs.size();
	assert (scores.length == fvs.size());

	for (int instanceNumber=0; instanceNumber < fvs.size(); instanceNumber++) {
		FeatureVector fv = (FeatureVector)fvs.get(instanceNumber);
		// Make sure the feature vector's feature dictionary matches
		// what we are expecting from our data pipe (and thus our notion
		// of feature probabilities.
		assert (fv.getAlphabet ()
						== this.instancePipe.getDataAlphabet ());
		
		// Include the feature weights according to each label
		scores[instanceNumber] = parameters[0*numFeatures + defaultFeatureIndex]
															 + MatrixOps.rowDotProduct (parameters, numFeatures,
																													0, fv,
																													defaultFeatureIndex,
																													(perClassFeatureSelection == null
																													 ? featureSelection
																													 : perClassFeatureSelection[0]));
	}

	// Move scores to a range where exp() is accurate, and normalize
	double max = MatrixOps.max (scores);
	double sum = 0;
	for (int li = 0; li < numLabels; li++)
		sum += (scores[li] = Math.exp (scores[li] - max));
	for (int li = 0; li < numLabels; li++) {
		scores[li] /= sum;
		// xxxNaN assert (!Double.isNaN(scores[li]));
	}
}
 

import cc.mallet.types.FeatureVectorSequence; //导入方法依赖的package包/类
@Override
public Instance pipe(Instance inst) {
	FeatureVectorSequence vs = (FeatureVectorSequence) inst.getData();
	for (int i = 0; i < vs.size(); i++) {
		AugmentableFeatureVector v = (AugmentableFeatureVector) vs.get(i);
		// System.out.println("Before augment: " + v.numLocations());
		double[] values = scl.transform(v);
		for (int j = 0; j < values.length; j++) {
			String key = "SCL_AUG" + j;
			// if (values[j] != 0)
			// v.add("SCL_AUG" + j, values[j]);
			// if (values[j] < -1) {
			// v.add(key + "(<-1)", 1);
			// } else if (values[j] < -0.5) {
			// v.add(key + "(<-0.5)", 1);
			// } else if (values[j] < 0) {
			// v.add(key + "(<0)", 1);
			// } else if (values[j] > 1) {
			// v.add(key + "(>1)", 1);
			// } else if (values[j] > 0.5) {
			// v.add(key + "(>0.5)", 1);
			// } else if (values[j] > 0) {
			// v.add(key + "(>0)", 1);
			// } else {
			// v.add(key + "(=0)", 1);
			// }
			// if (values[j] > 0) {
			// v.add(key + "(>0)", 1);
			// } else if (values[j] < 0) {
			// v.add(key + "(<0)", 1);
			// }
			if (values[j] != 0)
				v.add(key, values[j]);
		}
		// System.out.println(v);
		// System.out.println("After augment: " + v.numLocations());
	}

	return inst;
}
 

import cc.mallet.types.FeatureVectorSequence; //导入方法依赖的package包/类
/** returns unnormalized scores, corresponding to the score an
 * element of the InstanceList being the "top" instance
 * @param instance instance with data field a {@link cc.mallet.types.InstanceList}.
 * @param scores has length = number of Instances in Instance.data,
 * which is of type InstanceList */
public void getUnnormalizedClassificationScores (Instance instance, double[] scores)
{
	FeatureVectorSequence fvs = (FeatureVectorSequence)instance.getData();
	assert (scores.length == fvs.size());
	int numFeatures = instance.getDataAlphabet().size()+1;

	for (int instanceNumber=0; instanceNumber < fvs.size(); instanceNumber++) {
		FeatureVector fv = (FeatureVector)fvs.get(instanceNumber);
		// Make sure the feature vector's feature dictionary matches
		// what we are expecting from our data pipe (and thus our notion
		// of feature probabilities.
		assert (fv.getAlphabet ()
						== this.instancePipe.getDataAlphabet ());
		
		// Include the feature weights according to each label xxx is
		// this correct ? we only calculate the dot prod of the feature
		// vector with the "positiveLabel" weights
		// xxx include multiple labels
		scores[instanceNumber] = parameters[0*numFeatures + defaultFeatureIndex]
															 + MatrixOps.rowDotProduct (parameters, numFeatures,
																													0, fv,
																													defaultFeatureIndex,
																													(perClassFeatureSelection == null
																													 ? featureSelection
																													 : perClassFeatureSelection[0]));
	}
}