Java Instance.getName方法代码示例

import edu.umass.cs.mallet.base.types.Instance; //导入方法依赖的package包/类
/**
  * Convert the data in the given <tt>Instance</tt> from a <tt>CharSequence</tt> 
  * of sparse feature-value pairs to a <tt>FeatureVector</tt>
  *
  * @throws IllegalStateException If <CODE>Instance.getTarget()</CODE> is
  * not a Labeling
  */
 public Instance pipe(Instance carrier) 
     throws IllegalStateException
 {
     CharSequence c = (CharSequence) carrier.getData();
     String[] pairs = c.toString().trim().split("\\s+");
     String[] keys = new String[pairs.length];
     double[] values = new double[pairs.length];

     for (int i = 0; i < pairs.length; i++) {
int delimIndex = pairs[i].lastIndexOf(":");
if (delimIndex <= 0 || delimIndex == (pairs[i].length()-1))
    throw new IllegalStateException("token is not a valid feature name-feature value pair: "
	        + pairs[i] + "\nfaulting instance name:" + carrier.getName());

keys[i] = pairs[i].substring(0, delimIndex);
values[i] = Double.parseDouble(pairs[i].substring(delimIndex+1));

dataDict.lookupIndex(keys[i], true); // add the feature name
     }
     // Sort indices beforehand to prevent the bubble sort used in
     // constructor of SparseVector from taking too much time
     int[] keyIndices = FeatureVector.getObjectIndices(keys, dataDict, true);
     java.util.Arrays.sort(keyIndices);
     FeatureVector fv = new FeatureVector(dataDict, keyIndices, values);
     // Check if we've set the target alphabet member
     if (targetDict == null) {
if (carrier.getTarget() instanceof Labeling)
    targetDict = ((Labeling)carrier.getTarget()).getLabelAlphabet();
else
    throw new IllegalStateException ("Instance target is not a " +
	         "Labeling; it is a " + 
	         carrier.getTarget().getClass().getName());
	  
     }
     
     carrier.setData( fv );
     return carrier;
 }
 

import edu.umass.cs.mallet.base.types.Instance; //导入方法依赖的package包/类
public static PipeOutputAccumulator iteratePipe (Pipe iteratedPipe,
																								 PipeOutputAccumulator accumulator,
																								 Instance carrier)
{
	PipeInputIterator iter = (PipeInputIterator) carrier.getData();
	iter.setParentInstance (carrier);
	while (iter.hasNext()) {
     // Make sure that instance.pipe field gets set when piping instance.
     Instance subInstance = iter.nextInstance();
     Instance pipedInstance = new Instance (subInstance.getData (), subInstance.getTarget (),
                                            subInstance.getName (), subInstance.getSource (), iteratedPipe);
     accumulator.pipeOutputAccumulate (pipedInstance, iteratedPipe);
   }
	return accumulator;
}
 

import edu.umass.cs.mallet.base.types.Instance; //导入方法依赖的package包/类
/**
 * 
 * @param inst input instance, with FeatureVectorSequence as data.
 * @param alphabetsPipe a Noop pipe containing the data and target alphabets for 
 * the resulting InstanceList and AugmentableFeatureVectors
 * @return list of instances, each with one AugmentableFeatureVector as data
 */
public static InstanceList convert(Instance inst, Noop alphabetsPipe)
{
	InstanceList ret = new InstanceList(alphabetsPipe);
	Object obj = inst.getData();
	assert(obj instanceof FeatureVectorSequence);

	FeatureVectorSequence fvs = (FeatureVectorSequence) obj;
	LabelSequence ls = (LabelSequence) inst.getTarget();
	assert(fvs.size() == ls.size());

	Object instName = (inst.getName() == null ? "NONAME" : inst.getName());
	
	for (int j = 0; j < fvs.size(); j++) {
		FeatureVector fv = fvs.getFeatureVector(j);
		int[] indices = fv.getIndices();
		FeatureVector data = new AugmentableFeatureVector (alphabetsPipe.getDataAlphabet(),
				indices, fv.getValues(), indices.length); 
		Labeling target = ls.getLabelAtPosition(j);
		String name = instName.toString() + "[email protected]_POS_" + (j + 1);
		Object source = inst.getSource();
		Instance toAdd = new Instance(data, target, name, source, alphabetsPipe);

		ret.add(toAdd);
	}

	return ret;
}
 

import edu.umass.cs.mallet.base.types.Instance; //导入方法依赖的package包/类
/**
 * 
 * @param instance the instance to classify
 * @param useOutOfFold whether to check the instance name and use the out-of-fold classifier
 * if the instance name matches one in the training data
 * @return the token classifier's output
 */
public Classification classify(Instance instance, boolean useOutOfFold)
{
	Object instName = instance.getName();
	
	if (! useOutOfFold || ! m_table.containsKey(instName))
		return m_tokenClassifier.classify(instance);
	
	Classifier classifier = (Classifier) m_table.get(instName);

	return classifier.classify(instance);
}
 

import edu.umass.cs.mallet.base.types.Instance; //导入方法依赖的package包/类
public Instance nextInstance ()
{
  final Instance instance = iter.nextInstance ();
  Instance ret = new Instance (instance.getData(), instance.getTarget(), instance.getName(), instance.getSource());
  ret.setPropertyList (instance.getPropertyList ());
  return ret;
}
 

import edu.umass.cs.mallet.base.types.Instance; //导入方法依赖的package包/类
public TagList output (Transducer crf, InstanceList eval, java.util.Vector spans) throws IOException
{   
  //String toReturn="";
  //for (int i = 0; i < eval.size(); i++) {
    Instance instance = eval.getInstance(eval.size()-1);
    Sequence input = (Sequence) instance.getData();
    Sequence predOutput = crf.viterbiPath(input).output();
    String[] tokens = (String[])instance.getName();
    
    Tag currentTag = null;
    TagList tagList = new TagList();
    for(int j = 0; j < tokens.length; j++) {
        boolean foundTag = false;
        for(int s = 0; s < segmentStartTags.length; s++) {
            if(((String)predOutput.get(j)).equals(segmentStartTags[s])) {
                foundTag = true;
                currentTag = new Tag(segmentStartTags[s].substring(2,segmentStartTags[s].length()));
                currentTag.addSegment(tokens[j], j);
                if(spans!=null) {
          currentTag.updateOffset(((int[])spans.get(j))[0],((int[])spans.get(j))[1]);
                }
        //toReturn+="<"+segmentStartTags[s].substring(2,segmentStartTags[s].length())+">" + tokens[j];
                for(int j1 = j+1; j1 < tokens.length && ((String)predOutput.get(j1)).equals(segmentContinueTags[s]); j1++) {
                    currentTag.addSegment(tokens[j1], j1);
                    if(spans!=null) {
            currentTag.updateOffset(((int[])spans.get(j1))[0],((int[])spans.get(j1))[1]);
          }
                    //toReturn+=" " + tokens[j1];
                    j=j1;
                }
                tagList.addTag(currentTag);
                currentTag = null;
                //toReturn+="</"+segmentStartTags[s].substring(2,segmentStartTags[s].length())+">";
                break;
            }
        }
        //if(!foundTag)
        //    toReturn+=tokens[j];
        
        //if(j < tokens.length-1)
        //    toReturn+=" ";
    }
    //toReturn+="\n";
  //}   
  return tagList;//toReturn;
}
 

import edu.umass.cs.mallet.base.types.Instance; //导入方法依赖的package包/类
public TagList output (Transducer crf, InstanceList eval, java.util.Vector spans) throws IOException
{   
  //String toReturn="";
  //for (int i = 0; i < eval.size(); i++) {
    Instance instance = eval.getInstance(eval.size()-1);
    Sequence input = (Sequence) instance.getData();
    Sequence predOutput = crf.viterbiPath(input).output();
    String[] tokens = (String[])instance.getName();
    
    Tag currentTag = null;
    TagList tagList = new TagList();
    for(int j = 0; j < tokens.length; j++) {
        boolean foundTag = false;
        for(int s = 0; s < segmentStartTags.length; s++) {
            if(((String)predOutput.get(j)).equals(segmentStartTags[s])) {
                foundTag = true;
                currentTag = new Tag(segmentStartTags[s].substring(2,segmentStartTags[s].length()));
                currentTag.addSegment(tokens[j], j);
                if(spans!=null) {
			  currentTag.updateOffset(((int[])spans.get(j))[0],((int[])spans.get(j))[1]);
                }
		  //toReturn+="<"+segmentStartTags[s].substring(2,segmentStartTags[s].length())+">" + tokens[j];
                for(int j1 = j+1; j1 < tokens.length && ((String)predOutput.get(j1)).equals(segmentContinueTags[s]); j1++) {
                    currentTag.addSegment(tokens[j1], j1);
                    if(spans!=null) {
				  currentTag.updateOffset(((int[])spans.get(j1))[0],((int[])spans.get(j1))[1]);
			  }
                    //toReturn+=" " + tokens[j1];
                    j=j1;
                }
                tagList.addTag(currentTag);
                currentTag = null;
                //toReturn+="</"+segmentStartTags[s].substring(2,segmentStartTags[s].length())+">";
                break;
            }
        }
        //if(!foundTag)
        //    toReturn+=tokens[j];
        
        //if(j < tokens.length-1)
        //    toReturn+=" ";
    }
    //toReturn+="\n";
  //}   
  return tagList;//toReturn;
}