Java Instances.numAttributes方法代码示例

import weka.core.Instances; //导入方法依赖的package包/类
public static DMatrix instancesToDMatrix(Instances instances) throws XGBoostError {
    long[] rowHeaders = new long[instances.size()+1];
    rowHeaders[0]=0;
    List<Float> dataList = new ArrayList<>();
    List<Integer> colList = new ArrayList<>();
    float[] labels = new float[instances.size()];

    for(int i=0; i<instances.size(); i++) {
        Instance instance = instances.get(i);
        rowHeaders[i] = dataList.size();
        processInstance(instance, dataList, colList);
        labels[i] = (float) instance.classValue();
    }
    rowHeaders[rowHeaders.length - 1] = dataList.size();
    int colNum = instances.numAttributes()-1;
    DMatrix dMatrix = createDMatrix(rowHeaders, dataList, colList, colNum);

    dMatrix.setLabel(labels);
    return dMatrix;

}
 

import weka.core.Instances; //导入方法依赖的package包/类
public Filter createFilter(Instances data) throws Exception {
    Set<Integer> indexes = new HashSet<Integer>();
    for (int i = 0, cnt = this.size(); i < cnt; i++) {
        indexes.add(this.get(i).index());
    } // FOR
    
    SortedSet<Integer> to_remove = new TreeSet<Integer>(); 
    for (int i = 0, cnt = data.numAttributes(); i < cnt; i++) {
        if (indexes.contains(i) == false) {
            to_remove.add(i+1);
        }
    } // FOR
    
    Remove filter = new Remove();
    filter.setInputFormat(data);
    String options[] = { "-R", StringUtil.join(",", to_remove) };
    filter.setOptions(options);
    return (filter);
}
 

import weka.core.Instances; //导入方法依赖的package包/类
/***
	 * <p>To get 10-fold cross validation in one single arff in <b>path</b></p>
	 * <p>Use C4.5 and <b>SMOTE</b> to classify the dataset.</p>
	 * @param path dataset path
	 * @throws Exception
	 */
	public static void getEvalResultbySMOTE(String path, int index) throws Exception{
		
		Instances ins = DataSource.read(path);
		int numAttr = ins.numAttributes();
		ins.setClassIndex(numAttr - 1);
		
		SMOTE smote = new SMOTE();
		smote.setInputFormat(ins);
		
		/** classifiers setting*/
		J48 j48 = new J48();
//		j48.setConfidenceFactor(0.4f);
		j48.buildClassifier(ins);

		FilteredClassifier fc = new FilteredClassifier();
		fc.setClassifier(j48);
		fc.setFilter(smote);
			
		Evaluation eval = new Evaluation(ins);	
		eval.crossValidateModel(fc, ins, 10, new Random(1));
		
//		System.out.printf(" %4.3f %4.3f %4.3f", eval.precision(0), eval.recall(0), eval.fMeasure(0));
//		System.out.printf(" %4.3f %4.3f %4.3f", eval.precision(1), eval.recall(1), eval.fMeasure(1));
//		System.out.printf(" %4.3f \n\n", (1-eval.errorRate()));
		results[index][0] = eval.precision(0);
		results[index][1] = eval.recall(0);
		results[index][2] = eval.fMeasure(0);
		results[index][3] = eval.precision(1);
		results[index][4] = eval.recall(1);
		results[index][5] = eval.fMeasure(1);
		results[index][6] = 1-eval.errorRate();
				
	}
 

import weka.core.Instances; //导入方法依赖的package包/类
public static Instance findBestPerf(Instances data){
	int idx = data.numAttributes()-1;
	double bestPerf = data.attributeStats(idx).numericStats.max;
	for(int i=0;i<data.numInstances();i++)
		if(data.get(i).value(idx)==bestPerf)
			return data.get(i);
	return null;//should never return NULL
}
 

import weka.core.Instances; //导入方法依赖的package包/类
public static int findBestPerfIndex(Instances data){
	int idx = data.numAttributes()-1;
	double bestPerf = data.attributeStats(idx).numericStats.max;
	for(int i=0;i<data.numInstances();i++)
		if(data.get(i).value(idx)==bestPerf)
			return i;
	return -1;//should never return -1
}
 

import weka.core.Instances; //导入方法依赖的package包/类
/***
	 * <p>To get 10-fold cross validation in one single arff in <b>path</b></p>
	 * <p>Only use C4.5 to classify the dataset.</p>
	 * @param path dataset path
	 * @throws Exception
	 */
	public static void getEvalResultbyNo(String path, int index) throws Exception{
		
		Instances ins = DataSource.read(path);
		int numAttr = ins.numAttributes();
		ins.setClassIndex(numAttr - 1);
		
		/** classifiers setting*/
		J48 j48 = new J48();
//		j48.setConfidenceFactor(0.4f);
		j48.buildClassifier(ins);
		
		Evaluation eval = new Evaluation(ins);	
		eval.crossValidateModel(j48, ins, 10, new Random(1));
		
//		System.out.printf(" %4.3f %4.3f %4.3f", eval.precision(0), eval.recall(0), eval.fMeasure(0));
//		System.out.printf(" %4.3f %4.3f %4.3f", eval.precision(1), eval.recall(1), eval.fMeasure(1));
//		System.out.printf(" %4.3f \n\n", (1-eval.errorRate()));
		results[index][0] = eval.precision(0);
		results[index][1] = eval.recall(0);
		results[index][2] = eval.fMeasure(0);
		results[index][3] = eval.precision(1);
		results[index][4] = eval.recall(1);
		results[index][5] = eval.fMeasure(1);
		results[index][6] = 1-eval.errorRate();
			
	}
 

import weka.core.Instances; //导入方法依赖的package包/类
/***
	 * <p>To get 10-fold cross validation in one single arff in <b>path</b></p>
	 * <p>Use C4.5 and <b>Resampling</b> to classify the dataset.</p>
	 * @param path dataset path
	 * @throws Exception
	 */
	public static void getEvalResultbyResampling(String path, int index) throws Exception{
		
		Instances ins = DataSource.read(path);
		int numAttr = ins.numAttributes();
		ins.setClassIndex(numAttr - 1);
		
		Resample resample = new Resample();
		resample.setInputFormat(ins);
		
		/** classifiers setting*/
		J48 j48 = new J48();
//		j48.setConfidenceFactor(0.4f);
		j48.buildClassifier(ins);

		FilteredClassifier fc = new FilteredClassifier();
		fc.setClassifier(j48);
		fc.setFilter(resample);
			
		Evaluation eval = new Evaluation(ins);	
		eval.crossValidateModel(fc, ins, 10, new Random(1));
		
//		System.out.printf(" %4.3f %4.3f %4.3f", eval.precision(0), eval.recall(0), eval.fMeasure(0));
//		System.out.printf(" %4.3f %4.3f %4.3f", eval.precision(1), eval.recall(1), eval.fMeasure(1));
//		System.out.printf(" %4.3f \n\n", (1-eval.errorRate()));
		results[index][0] = eval.precision(0);
		results[index][1] = eval.recall(0);
		results[index][2] = eval.fMeasure(0);
		results[index][3] = eval.precision(1);
		results[index][4] = eval.recall(1);
		results[index][5] = eval.fMeasure(1);
		results[index][6] = 1-eval.errorRate();
			
	}
 

import weka.core.Instances; //导入方法依赖的package包/类
/***
	 * <p>To get 10-fold cross validation in one single arff in <b>path</b></p>
	 * <p>Use C4.5 and <b>Cost-sensitive learning</b> to classify the dataset.</p>
	 * @param path dataset path
	 * @throws Exception
	 */
	public static void getEvalResultbyCost(String path, int index) throws Exception{
		
		Instances ins = DataSource.read(path);
		int numAttr = ins.numAttributes();
		ins.setClassIndex(numAttr - 1);
		
		/**Classifier setting*/
		J48 j48 = new J48();
//		j48.setConfidenceFactor(0.4f);
		j48.buildClassifier(ins);
		
		CostSensitiveClassifier csc = new CostSensitiveClassifier();
		csc.setClassifier(j48);
		csc.setCostMatrix(new CostMatrix(new BufferedReader(new FileReader("files/costm"))));
		
		Evaluation eval = new Evaluation(ins);
		
		eval.crossValidateModel(csc, ins, 10, new Random(1));
		
//		System.out.printf(" %4.3f %4.3f %4.3f", eval.precision(0), eval.recall(0), eval.fMeasure(0));
//		System.out.printf(" %4.3f %4.3f %4.3f", eval.precision(1), eval.recall(1), eval.fMeasure(1));
//		System.out.printf(" %4.3f \n\n", (1-eval.errorRate()));
		results[index][0] = eval.precision(0);
		results[index][1] = eval.recall(0);
		results[index][2] = eval.fMeasure(0);
		results[index][3] = eval.precision(1);
		results[index][4] = eval.recall(1);
		results[index][5] = eval.fMeasure(1);
		results[index][6] = 1-eval.errorRate();
			
	}
 

import weka.core.Instances; //导入方法依赖的package包/类
/***
	 * <p>To get 10-fold cross validation in one single arff in <b>path</b></p>
	 * <p>Use C4.5 and <b>SMOTE</b> to classify the dataset.</p>
	 * @param path dataset path
	 * @throws Exception
	 */
	public static void getEvalResultbyDefault(String path, int index) throws Exception{
		
		Instances ins = DataSource.read(path);
		int numAttr = ins.numAttributes();
		ins.setClassIndex(numAttr - 1);
		
		SMOTE smote = new SMOTE();
		smote.setInputFormat(ins);
		
		/** classifiers setting*/
		J48 j48 = new J48();
//		j48.setConfidenceFactor(0.4f);
		j48.buildClassifier(ins);

		FilteredClassifier fc = new FilteredClassifier();
		fc.setClassifier(j48);
		fc.setFilter(smote);
			
		Evaluation eval = new Evaluation(ins);	
		eval.crossValidateModel(fc, ins, 10, new Random(1));
		
//		System.out.printf(" %4.3f %4.3f %4.3f", eval.precision(0), eval.recall(0), eval.fMeasure(0));
//		System.out.printf(" %4.3f %4.3f %4.3f", eval.precision(1), eval.recall(1), eval.fMeasure(1));
//		System.out.printf(" %4.3f \n\n", (1-eval.errorRate()));
		results[index][0] = eval.precision(0);
		results[index][1] = eval.recall(0);
		results[index][2] = eval.fMeasure(0);
		results[index][3] = eval.precision(1);
		results[index][4] = eval.recall(1);
		results[index][5] = eval.fMeasure(1);
		results[index][6] = 1-eval.errorRate();
				
	}
 

import weka.core.Instances; //导入方法依赖的package包/类
public static DMatrix instancesToDenseDMatrix(Instances instances) throws XGBoostError {
    int colNum = instances.numAttributes()-1;
    int rowNum = instances.size();

    float[] data = new float[colNum*rowNum];
    float[] labels = new float[instances.size()];
    Attribute classAttribute = instances.classAttribute();
    int classAttrIndex = classAttribute.index();

    for(int i=0, dataIndex = 0; i<instances.size(); i++) {
        Instance instance = instances.get(i);

        labels[i] = (float) instance.classValue();
        Enumeration<Attribute> attributeEnumeration = instance.enumerateAttributes();
        while (attributeEnumeration.hasMoreElements()) {
            Attribute attribute = attributeEnumeration.nextElement();
            int attrIndex = attribute.index();
            if(attrIndex == classAttrIndex){
                continue;
            }
            data[dataIndex]= (float) instance.value(attribute);
            dataIndex++;
        }
    }


    DMatrix dMatrix = new DMatrix(data, rowNum, colNum);

    dMatrix.setLabel(labels);
    return dMatrix;

}
 

import weka.core.Instances; //导入方法依赖的package包/类
private void loadWekaInstance(String path) {
    try {
        this.wekaInstance.loadInstanceFromPath(path);
    } catch (Exception e) {
        MiniMLLogger.INSTANCE.exception(e);
    }

    Instances data = (Instances) this.wekaInstance.getValue();
    for (int i = 0; i < data.numAttributes(); i++)
    {
        String name = data.attribute(i).name();
        this.attributes.add(i, name);
        this.classifierSelect.addItem(name);
    }
}
 

import weka.core.Instances; //导入方法依赖的package包/类
public void loadInstanceFromPath(String path) throws Exception {
    DataSource source = new DataSource(path);
    Instances data = source.getDataSet();
    if (data.classIndex() == -1) {
        data.setClassIndex(data.numAttributes() - 1);
    }
    this.value = data;
    MiniMLLogger.INSTANCE.info("Dataset loaded with these attributes");
    for (int i = 0; i < data.numAttributes(); i++)
    {
        MiniMLLogger.INSTANCE.info(data.attribute(i));
    }
}
 

import weka.core.Instances; //导入方法依赖的package包/类
/***
	 * <p>To get 10-fold cross validation in one single arff in <b>path</b></p>
	 * <p>Use C4.5 and <b>SMOTE</b>, combined with <b>Chi-Square</b> to classify the dataset.</p>
	 * @param path dataset path
	 * @throws Exception
	 */
	public static void getEvalResultbyChiSquare(String path, int index) throws Exception{
		
		Instances ins = DataSource.read(path);
		int numAttr = ins.numAttributes();
		ins.setClassIndex(numAttr - 1);
		
		/**chi-squared filter to process the whole dataset first*/
		ChiSquaredAttributeEval evall = new ChiSquaredAttributeEval();	
		Ranker ranker = new Ranker();
		AttributeSelection selector = new AttributeSelection();
		
		selector.setEvaluator(evall);
		selector.setSearch(ranker);
		selector.setInputFormat(ins);
		ins = Filter.useFilter(ins, selector);
		
		SMOTE smote = new SMOTE();
		smote.setInputFormat(ins);
		
		/** classifiers setting*/
		J48 j48 = new J48();
//		j48.setConfidenceFactor(0.4f);
		j48.buildClassifier(ins);

		FilteredClassifier fc = new FilteredClassifier();
		fc.setClassifier(j48);
		fc.setFilter(smote);
			
		Evaluation eval = new Evaluation(ins);	
		eval.crossValidateModel(fc, ins, 10, new Random(1));
		
//		System.out.printf(" %4.3f %4.3f %4.3f", eval.precision(0), eval.recall(0), eval.fMeasure(0));
//		System.out.printf(" %4.3f %4.3f %4.3f", eval.precision(1), eval.recall(1), eval.fMeasure(1));
//		System.out.printf(" %4.3f \n\n", (1-eval.errorRate()));
		results[index][0] = eval.precision(0);
		results[index][1] = eval.recall(0);
		results[index][2] = eval.fMeasure(0);
		results[index][3] = eval.precision(1);
		results[index][4] = eval.recall(1);
		results[index][5] = eval.fMeasure(1);
		results[index][6] = 1-eval.errorRate();
				
	}
 

import weka.core.Instances; //导入方法依赖的package包/类
/***
	 * <p>To get 10-fold cross validation in one single arff in <b>path</b></p>
	 * <p>Use C4.5 and <b>SMOTE</b>, combined with <b>Information Gain</b> to classify the dataset.</p>
	 * @param path dataset path
	 * @throws Exception
	 */
	public static void getEvalResultbyInfoGain(String path, int index) throws Exception{
		
		Instances ins = DataSource.read(path);
		int numAttr = ins.numAttributes();
		ins.setClassIndex(numAttr - 1);
		
		/**information gain filter to process the whole dataset first*/
		InfoGainAttributeEval evall = new InfoGainAttributeEval();
		Ranker ranker = new Ranker();
		AttributeSelection selector = new AttributeSelection();
		
		selector.setEvaluator(evall);
		selector.setSearch(ranker);
		selector.setInputFormat(ins);
		ins = Filter.useFilter(ins, selector);
		
		SMOTE smote = new SMOTE();
		smote.setInputFormat(ins);
		
		/** classifiers setting*/
		J48 j48 = new J48();
//		j48.setConfidenceFactor(0.4f);
		j48.buildClassifier(ins);

		FilteredClassifier fc = new FilteredClassifier();
		fc.setClassifier(j48);
		fc.setFilter(smote);
			
		Evaluation eval = new Evaluation(ins);	
		eval.crossValidateModel(fc, ins, 10, new Random(1));
		
//		System.out.printf(" %4.3f %4.3f %4.3f", eval.precision(0), eval.recall(0), eval.fMeasure(0));
//		System.out.printf(" %4.3f %4.3f %4.3f", eval.precision(1), eval.recall(1), eval.fMeasure(1));
//		System.out.printf(" %4.3f \n\n", (1-eval.errorRate()));
		results[index][0] = eval.precision(0);
		results[index][1] = eval.recall(0);
		results[index][2] = eval.fMeasure(0);
		results[index][3] = eval.precision(1);
		results[index][4] = eval.recall(1);
		results[index][5] = eval.fMeasure(1);
		results[index][6] = 1-eval.errorRate();
				
	}
 

import weka.core.Instances; //导入方法依赖的package包/类
/***
	 * <p>To get 10-fold cross validation in one single arff in <b>path</b></p>
	 * <p>Use C4.5 and <b>SMOTE</b>, combined with <b>Information Gain Ratio</b> to classify the dataset.</p>
	 * @param path dataset path
	 * @throws Exception
	 */
	public static void getEvalResultbyGainRatio(String path, int index) throws Exception{
		
		Instances ins = DataSource.read(path);
		int numAttr = ins.numAttributes();
		ins.setClassIndex(numAttr - 1);
		
		/**information gain ratio filter to process the whole dataset first*/
		GainRatioAttributeEval evall = new GainRatioAttributeEval();
		Ranker ranker = new Ranker();
		AttributeSelection selector = new AttributeSelection();
		
		selector.setEvaluator(evall);
		selector.setSearch(ranker);
		selector.setInputFormat(ins);
		ins = Filter.useFilter(ins, selector);
		
		SMOTE smote = new SMOTE();
		smote.setInputFormat(ins);
		
		/** classifiers setting*/
		J48 j48 = new J48();
//		j48.setConfidenceFactor(0.4f);
		j48.buildClassifier(ins);

		FilteredClassifier fc = new FilteredClassifier();
		fc.setClassifier(j48);
		fc.setFilter(smote);
			
		Evaluation eval = new Evaluation(ins);	
		eval.crossValidateModel(fc, ins, 10, new Random(1));
		
//		System.out.printf(" %4.3f %4.3f %4.3f", eval.precision(0), eval.recall(0), eval.fMeasure(0));
//		System.out.printf(" %4.3f %4.3f %4.3f", eval.precision(1), eval.recall(1), eval.fMeasure(1));
//		System.out.printf(" %4.3f \n\n", (1-eval.errorRate()));
		results[index][0] = eval.precision(0);
		results[index][1] = eval.recall(0);
		results[index][2] = eval.fMeasure(0);
		results[index][3] = eval.precision(1);
		results[index][4] = eval.recall(1);
		results[index][5] = eval.fMeasure(1);
		results[index][6] = 1-eval.errorRate();
				
	}