Java Instances.setClass方法代码示例

import weka.core.Instances; //导入方法依赖的package包/类
/**
 * Create a new, smaller data Instances that contains only the attributes the user selected.
 *
 * It does this by counting out the indices that the user wanted and removing anything that doesn't match.
 * If it were elegant, it wouldn't be java. :/
 *
 * @return Instances newData
 */
public Instances getUserSpecifiedDataset(){
    Instances newData = new Instances(this.master);
    newData.setClass(newData.attribute(this.classIndex));
    //need to reverse sort them so our array doesn't get screwed up.
    Integer[] keepAttributes = new Integer[this.userAttributeSelectionIndices.length];
    for (int i = 0; i < this.userAttributeSelectionIndices.length; i++) {
        keepAttributes[i] = Integer.valueOf(this.userAttributeSelectionIndices[i]);
    }
    Arrays.sort(keepAttributes, Collections.reverseOrder());
    for(Integer i = this.userAttributeSelectionIndices.length; i >= 0; --i){
        if(! Arrays.asList(keepAttributes).contains(i)){
            newData.deleteAttributeAt(i);
        }
    }
    return(newData);
}
 

import weka.core.Instances; //导入方法依赖的package包/类
public static Instances convertToArff(List<Document> dataSet, List<String> vocabulary, String fileName) {
    int dataSetSize = dataSet.size();
    /* Create features */
    ArrayList<Attribute> attributes = new ArrayList<>();
    for (int i = 0; i < vocabulary.size(); i++) {
        attributes.add(new Attribute("word_" + i));
    }
    Attribute classAttribute = new Attribute("Class");
    attributes.add(classAttribute);

    /* Add examples */
    System.out.println("Building instances...");
    Instances trainingDataSet = new Instances(fileName, attributes, 0);
    for (int k = 0; k < dataSetSize; k++) {
        Document document = dataSet.get(k);
        Instance example = new DenseInstance(attributes.size());
        for (int i = 0; i < vocabulary.size(); i++) {
            String word = vocabulary.get(i);
            example.setValue(i, Collections.frequency(document.getTerms(), word));
        }
        example.setValue(classAttribute, document.getDocumentClass());
        trainingDataSet.add(example);
        int progress = (int) ((k * 100.0) / dataSetSize);
        System.out.printf("\rPercent completed: %3d%%", progress);
    }
    trainingDataSet.setClass(classAttribute);
    System.out.println();

    System.out.println("Writing to file ...");
    try {
        ArffSaver saver = new ArffSaver();
        saver.setInstances(trainingDataSet);
        saver.setFile(new File(fileName));
        saver.writeBatch();
    } catch (IOException e) {
        e.printStackTrace();
    }

    return trainingDataSet;
}
 

import weka.core.Instances; //导入方法依赖的package包/类
protected Classifier generateDecisionTree(AbstractClusterer clusterer, MarkovAttributeSet aset, Instances data) throws Exception {
    // We need to create a new Attribute that has the ClusterId
    Instances newData = data; // new Instances(data);
    newData.insertAttributeAt(new Attribute("ClusterId"), newData.numAttributes());
    Attribute cluster_attr = newData.attribute(newData.numAttributes()-1);
    assert(cluster_attr != null);
    assert(cluster_attr.index() > 0);
    newData.setClass(cluster_attr);
    
    // We will then tell the Classifier to predict that ClusterId based on the MarkovAttributeSet
    ObjectHistogram<Integer> cluster_h = new ObjectHistogram<Integer>();
    for (int i = 0, cnt = newData.numInstances(); i < cnt; i++) {
        // Grab the Instance and throw it at the the clusterer to get the target cluster
        Instance inst = newData.instance(i);
        int c = (int)clusterer.clusterInstance(inst);
        inst.setClassValue(c);
        cluster_h.put(c);
    } // FOR
    System.err.println("Number of Elements: " + cluster_h.getValueCount());
    System.err.println(cluster_h);

    NumericToNominal filter = new NumericToNominal();
    filter.setInputFormat(newData);
    newData = Filter.useFilter(newData, filter);
    
    String output = this.catalog_proc.getName() + "-labeled.arff";
    FileUtil.writeStringToFile(output, newData.toString());
    LOG.info("Wrote labeled data set to " + output);
    
    // Decision Tree
    J48 j48 = new J48();
    String options[] = {
        "-S", Integer.toString(this.rand.nextInt()),
        
    };
    j48.setOptions(options);

    // Make sure we add the ClusterId attribute to a new MarkovAttributeSet so that
    // we can tell the Classifier to classify that!
    FilteredClassifier fc = new FilteredClassifier();
    MarkovAttributeSet classifier_aset = new MarkovAttributeSet(aset);
    classifier_aset.add(cluster_attr);
    fc.setFilter(classifier_aset.createFilter(newData));
    fc.setClassifier(j48);
    
    // Bombs away!
    fc.buildClassifier(newData);
    
    return (fc);
}