Java DenseInstance类代码示例

import weka.core.DenseInstance; //导入依赖的package包/类
public Main() {
    try {
        BufferedReader datafile;
        datafile = readDataFile("camping.txt");
        Instances data = new Instances(datafile);
        data.setClassIndex(data.numAttributes() - 1);

        Instances trainingData = new Instances(data, 0, 14);
        Instances testingData = new Instances(data, 14, 5);
        Evaluation evaluation = new Evaluation(trainingData);

        SMO smo = new SMO();
        smo.buildClassifier(data);

        evaluation.evaluateModel(smo, testingData);
        System.out.println(evaluation.toSummaryString());

        // Test instance 
        Instance instance = new DenseInstance(3);
        instance.setValue(data.attribute("age"), 78);
        instance.setValue(data.attribute("income"), 125700);
        instance.setValue(data.attribute("camps"), 1);            
        instance.setDataset(data);
        System.out.println("The instance: " + instance);
        System.out.println(smo.classifyInstance(instance));
    } catch (Exception ex) {
        ex.printStackTrace();
    }
}
 

import weka.core.DenseInstance; //导入依赖的package包/类
public SentenceType classifySentence(Sentence sentence) {
	SpeechActsClassifier.Features features = speechActsClassifier.classifyFeatures(sentence);

	Instance inst = new DenseInstance(6);
	inst.setDataset(dataSet);

	inst.setValue(0, features.getSentenceLength());
	inst.setValue(1, features.getNumberOfNouns());
	inst.setValue(2, (features.isEndingInNounOrAdjective() ? 1 : 0));
	inst.setValue(3, (features.isBeginningInVerb() ? 1 : 0));
	inst.setValue(4, features.getCountOfWhMarkers());
	inst.setValue(5, Utils.missingValue());

	try {
		return SentenceType.valueOf(classifier.classifyInstance(inst));
	} catch (Exception e) {
		throw new RuntimeException("Can't classify");
	}
}
 

import weka.core.DenseInstance; //导入依赖的package包/类
public QuestionType classifyQuestion(Sentence sentence) {
	if (!sentence.isQuestion()) {
		return QuestionType.NA;
	}

	QuestionTypeClassifier.Features features = questionTypeClassifier.classifyFeatures(sentence);

	Instance inst = new DenseInstance(5);
	inst.setDataset(dataSet);

	inst.setValue(0, features.getWhWord());
	inst.setValue(1, features.getWhWordPos());
	inst.setValue(2, features.getPosOfNext());
	inst.setValue(3, features.getRootPos());
	inst.setValue(4, Utils.missingValue());

	try {
		int ndx = (int) classifier.classifyInstance(inst);
		 return QuestionType.valueOf(ndx);
	} catch (Exception e) {
		throw new RuntimeException("Not classified");
	}
}
 

import weka.core.DenseInstance; //导入依赖的package包/类
public Instance createInstance(List<String> featureNames, I key) {
	double[] vals = new double[featureNames.size()];
	for (int i = 0; i < featureNames.size(); i++) {
		Feature<Object> f = this.featureValues.get(key).get(featureNames.get(i));
		if (f != null)
			vals[i] = f.getDoubleValue();
		else {
			Class<Object> type = features.get(featureNames.get(i));
			if (type.equals(Double.class) || type.equals(Float.class) || type.equals(Integer.class))
				vals[i] = Double.NaN;
			if (type.equals(Boolean.class) || type.equals(String.class))
				vals[i] = 0;
		}
	}
	return new DenseInstance(1.0, vals);
}
 

import weka.core.DenseInstance; //导入依赖的package包/类
public static Instances createXInstances(XYForRegression xy) {
  // build attributes
  ArrayList<Attribute> attributes = new ArrayList<Attribute>();
  for (String attrName : xy.getAttrNames() ) {
    // attribute name is the polynomial power
    Attribute xattr = new Attribute(attrName); 
    attributes.add(xattr);
  }    

  double[][] Xarr = xy.getX();
  int numInstances = Xarr.length;
  int numAttr = Xarr[0].length;
  Instances Xinst = new Instances("X", attributes, numInstances);

  // fill instances 
  for (int i = 0; i < numInstances; ++i) {
    Instance row = new DenseInstance(numAttr);
    for (int j = 0; j < numAttr; ++j) {
      row.setValue(j, Xarr[i][j]);
    }
    Xinst.add(row);
  }
  return Xinst; 
}
 

import weka.core.DenseInstance; //导入依赖的package包/类
public Instances createArff(String comment) {

		ArrayList<Attribute> atts = new ArrayList<Attribute>();
		ArrayList<String> classes = new ArrayList<String>();
		classes.add("good");
		classes.add("bad");

		atts.add(new Attribute("text", (ArrayList<String>) null));

		// make sure that the name of the class attribute is unlikely to
		// clash with any attribute created via the StringToWordVector filter
		atts.add(new Attribute("@@[email protected]@", classes));
		Instances data = new Instances("weka_SO_comments_model", atts, 0);
		data.setClassIndex(data.numAttributes() - 1);

		DenseInstance instance = new DenseInstance(2);
		Attribute messageAtt = data.attribute("text");
		instance.setValue(messageAtt, messageAtt.addStringValue(comment));

		data.add(instance);

		// System.out.println(data.toString());

		return data;
	}
 

import weka.core.DenseInstance; //导入依赖的package包/类
public void train(TrainData data, TermVocabulary vocab) throws Exception {
	this.vocab = vocab;
	Instances trainset = buildInstances();

	for (Pair<String, BytecodeData.MethodData> p : data.data()) {

		double[] instV = seqToFeats(p.getRight().getExtOpcodeSeq());
		instV[instV.length - 1] = (double) vocab.termToPos(p.getKey());

		Instance inst = new DenseInstance(1.0, instV);
		inst.setDataset(trainset);
		trainset.add(inst);
	}

	nb = new NaiveBayes();
	nb.buildClassifier(trainset);
}
 

import weka.core.DenseInstance; //导入依赖的package包/类
public Map<String, Double> predict(BytecodeData.MethodData method) throws Exception {
	if (testHeader == null)
		testHeader = buildInstances();

	double[] instV = seqToFeats(method.getExtOpcodeSeq());
	instV[instV.length - 1] = 0.0;

	Instance inst = new DenseInstance(1.0, instV);
	inst.setDataset(testHeader);
	testHeader.add(inst);

	double[] probs = nb.distributionForInstance(inst);
	Map<String, Double> result = new HashMap<>();
	int i = 0;
	for (String term : vocab.terms()) {
		result.put(term, probs[i]);
		i++;
	}

	testHeader.clear();

	return result;
}
 

import weka.core.DenseInstance; //导入依赖的package包/类
public void train(TrainData data, TermVocabulary vocab) throws Exception {
    this.vocab = vocab;
    Instances trainset = buildInstances();

    for (Pair<String, BytecodeData.MethodData> p : data.data()) {

        double[] instV = seqToFeats(p.getRight().getExtOpcodeSeq());
        instV[instV.length - 1] = (double) vocab.termToPos(p.getKey());

        Instance inst = new DenseInstance(1.0, instV);
        inst.setDataset(trainset);
        trainset.add(inst);
    }

    frf = new FastRandomForest();
    frf.setSeed(1993);
    // frf.setMaxDepth(20);
    // frf.setNumThreads(1);
    frf.setNumTrees(numTrees);
    frf.buildClassifier(trainset);
}
 

import weka.core.DenseInstance; //导入依赖的package包/类
public Map<String, Double> predict(BytecodeData.MethodData method) throws Exception {
    if (testHeader == null)
        testHeader = buildInstances();

    double[] instV = seqToFeats(method.getExtOpcodeSeq());
    instV[instV.length - 1] = 0.0;

    Instance inst = new DenseInstance(1.0, instV);
    inst.setDataset(testHeader);
    testHeader.add(inst);

    double[] probs = frf.distributionForInstance(inst);
    Map<String, Double> result = new HashMap<>();
    int i = 0;
    for (String term : vocab.terms()) {
        result.put(term, probs[i]);
        i++;
    }

    testHeader.clear();

    return result;
}
 

import weka.core.DenseInstance; //导入依赖的package包/类
/**
 * Launch the move centroids tasks
 * 
 * @param clusters the cluster centroids
 * @return the number of empty clusters
 */
protected int launchMoveCentroids(Instances[] clusters) {
  int emptyClusterCount = 0;
  List<Future<double[]>> results = new ArrayList<Future<double[]>>();

  for (int i = 0; i < m_NumClusters; i++) {
    if (clusters[i].numInstances() == 0) {
      emptyClusterCount++;
    } else {
      Future<double[]> futureCentroid =
        m_executorPool.submit(new KMeansComputeCentroidTask(i, clusters[i]));
      results.add(futureCentroid);
    }
  }

  try {
    for (Future<double[]> d : results) {
      m_ClusterCentroids.add(new DenseInstance(1.0, d.get()));
    }
  } catch (Exception ex) {
    ex.printStackTrace();
  }

  return emptyClusterCount;
}
 

import weka.core.DenseInstance; //导入依赖的package包/类
/**
 * Adds a training instance to our dataset, based on the coordinates of the
 * mouse on the panel. This method sets the x and y attributes and the class
 * (as defined by classAttIndex), and sets all other values as Missing.
 * 
 * @param mouseX the x coordinate of the mouse, in pixels.
 * @param mouseY the y coordinate of the mouse, in pixels.
 * @param classAttIndex the index of the attribute that is currently selected
 *          as the class attribute.
 * @param classValue the value to set the class to in our new point.
 */
public void addTrainingInstanceFromMouseLocation(int mouseX, int mouseY,
  int classAttIndex, double classValue) {
  // convert to coordinates in the training instance space.
  double x = convertFromPanelX(mouseX);
  double y = convertFromPanelY(mouseY);

  // build the training instance
  Instance newInstance = new DenseInstance(m_trainingData.numAttributes());
  for (int i = 0; i < newInstance.numAttributes(); i++) {
    if (i == classAttIndex) {
      newInstance.setValue(i, classValue);
    } else if (i == m_xAttribute) {
      newInstance.setValue(i, x);
    } else if (i == m_yAttribute) {
      newInstance.setValue(i, y);
    } else {
      newInstance.setMissing(i);
    }
  }

  // add it to our data set.
  addTrainingInstance(newInstance);
}
 

import weka.core.DenseInstance; //导入依赖的package包/类
/**
 * Make an output instance given an input one
 *
 * @param inputI the input instance to process
 * @return the output instance with substrings replaced
 */
public Instance makeOutputInstance(Instance inputI) {
  double[] vals = new double[m_outputStructure.numAttributes()];
  String[] stringVals = new String[m_outputStructure.numAttributes()];
  for (int i = 0; i < inputI.numAttributes(); i++) {
    if (inputI.attribute(i).isString() && !inputI.isMissing(i)) {
      stringVals[i] = inputI.stringValue(i);
    } else {
      vals[i] = inputI.value(i);
    }
  }

  for (SubstringReplacerMatchRule mr : m_matchRules) {
    mr.apply(stringVals);
  }

  for (int i = 0; i < m_outputStructure.numAttributes(); i++) {
    if (m_outputStructure.attribute(i).isString() && stringVals[i] != null) {
      m_outputStructure.attribute(i).setStringValue(stringVals[i]);
    }
  }

  Instance result = new DenseInstance(inputI.weight(), vals);
  result.setDataset(m_outputStructure);
  return result;
}
 

import weka.core.DenseInstance; //导入依赖的package包/类
public Instance fillFeatureVector(NGGFeatureVector vSource, Instances data) {
    
    double[] values = new double[data.numAttributes()];
    
    values[0] = vSource.getContainmentSimilarityArrayAtIndex(0);
    values[1] = vSource.getSizeSimilarityArrayAtIndex(0);
    values[2] = vSource.getValueSimilarityArrayAtIndex(0);
    values[3] = vSource.getNVSArrayAtIndex(0);
    values[4] = vSource.getContainmentSimilarityArrayAtIndex(1);
    values[5] = vSource.getSizeSimilarityArrayAtIndex(1);
    values[6] = vSource.getValueSimilarityArrayAtIndex(1);
    values[7] = vSource.getNVSArrayAtIndex(1);
    values[8] = data.attribute(8).indexOfValue(vSource.getLabel());
    
    Instance inst = new DenseInstance(1.0, values);
    
    return inst;
}
 

import weka.core.DenseInstance; //导入依赖的package包/类
public Instance decideCentroid(double[] vals,Instances members){
	Instance inst=new DenseInstance(vals.length);
	int q;
	for(q=0;q<vals.length;q++){
		inst.setValue(q, vals[q]);
	}
	
	double minDistance=Double.MAX_VALUE;
	double tempDistance;
	int instanceID=0;
	int i;
	for(i=0;i<members.numInstances();i++){
		tempDistance=myDistance(inst,members.instance(i));
		if(tempDistance<minDistance ){
			minDistance=tempDistance;
			instanceID=i;
		}
	}
	return members.instance(instanceID);
}