Java CSVLoader类代码示例

import weka.core.converters.CSVLoader; //导入依赖的package包/类
public static void main(String args[]) throws Exception {
        //read the input params
        readParams(args);
        CSVLoader loader = new CSVLoader();
        loader.setSource(inFile);
        Instances data = loader.getDataSet();
        System.setErr(err);//hack to avoid some error messages

        // Create the KMeans object.
        SimpleKMeans kmeans = new SimpleKMeans();
        kmeans.setNumClusters(K);
        kmeans.setMaxIterations(maxIteration);
        kmeans.setPreserveInstancesOrder(true);

        // Perform K-Means clustering.
        try {  
            kmeans.buildClusterer(data);
        } catch (Exception ex) {
            System.err.println("Unable to buld Clusterer: " + ex.getMessage());
            ex.printStackTrace();
        }

        // print out the cluster centroids
        Instances centroids = kmeans.getClusterCentroids();
        for (int i = 0; i < K; i++) {
            System.out.print("Cluster " + i + " size: " + kmeans.getClusterSizes()[i]);
            System.out.println(" Centroid: " + centroids.instance(i));
        }

//        Print Assignments:
//        int[] assignments = kmeans.getAssignments();
//        System.out.println("Length: "+assignments.length);
//        for (int i = 0; i < assignments.length; i++) {
//            System.out.println(assignments[i]);
//            
//        }

    }
 

import weka.core.converters.CSVLoader; //导入依赖的package包/类
/**
 * Method for testing the class from command line.
 * 
 * @param args The supplied command line arguments.
 */
public static void main(String[] args) {
  if (args.length != 1) {
    System.err.println("Usage: CoverTree <ARFF file>");
    System.exit(-1);
  }
  try {
    Instances insts = null;
    if (args[0].endsWith(".csv")) {
      CSVLoader csv = new CSVLoader();
      csv.setFile(new File(args[0]));
      insts = csv.getDataSet();
    } else {
      insts = new Instances(new BufferedReader(new FileReader(args[0])));
    }

    CoverTree tree = new CoverTree();
    tree.setInstances(insts);
    print("Created data tree:\n");
    print(0, tree.m_Root);
    println("");
  } catch (Exception ex) {
    ex.printStackTrace();
  }
}
 

import weka.core.converters.CSVLoader; //导入依赖的package包/类
/** 
 * Method for testing the class from command line. 
 * 
 * @param args The supplied command line arguments.
 */
public static void main(String[] args) {
  if (args.length != 1) {
    System.err.println("Usage: CoverTree <ARFF file>");
    System.exit(-1);
  }
  try {
    Instances insts = null;
    if (args[0].endsWith(".csv")) {
      CSVLoader csv = new CSVLoader();
      csv.setFile(new File(args[0]));
      insts = csv.getDataSet();
    } else {
      insts = new Instances(new BufferedReader(new FileReader(args[0])));
    }

    CoverTree tree = new CoverTree();
    tree.setInstances(insts);
    print("Created data tree:\n");
    print(0, tree.m_Root);
    println("");
  } catch (Exception ex) {
    ex.printStackTrace();
  }
}
 

import weka.core.converters.CSVLoader; //导入依赖的package包/类
public static void CSVtoARFF(String csvfilename, String arfffilename) {
    try {
        // load CSV
        CSVLoader loader = new CSVLoader();
        loader.setSource(new File(csvfilename));
        Instances data = loader.getDataSet();

        // save ARFF
        ArffSaver saver = new ArffSaver();
        saver.setInstances(data);
        saver.setFile(new File(arfffilename));
        saver.setDestination(new File(arfffilename));
        saver.writeBatch();
    } catch (Exception e) {
        e.printStackTrace();
    }
}
 

import weka.core.converters.CSVLoader; //导入依赖的package包/类
/**
  * takes 2 arguments:
  * - CSV input file
  * - ARFF output file
  */
public static void main(String[] vagina) throws Exception {
	String[] args = {"trainingSet.csv","penis.arff"};

	// load CSV
	CSVLoader loader = new CSVLoader();
	loader.setSource(new File(args[0]));
	Instances data = loader.getDataSet();

	// save ARFF
	ArffSaver saver = new ArffSaver();
	saver.setInstances(data);
	File penis = new File(args[1]);
	saver.setFile(penis);
	//    saver.setDestination(penis);
	saver.writeBatch();
}
 

import weka.core.converters.CSVLoader; //导入依赖的package包/类
/**
 * Return the data set loaded from the CSV file at @param path
 */
public static Instances loadDataFromCsvFile(String path) throws IOException{
    CSVLoader loader = new CSVLoader();
    loader.setSource(new File(path));
    Instances data = loader.getDataSet();
    
    System.out.println("\nHeader of dataset:\n");
    System.out.println(new Instances(data, 0));
    return data;
}
 

import weka.core.converters.CSVLoader; //导入依赖的package包/类
/**
 * Load the mnist minimal meta arff file
 *
 * @return Mnist minimal meta data as Instances
 * @throws Exception IO error.
 */
public static Instances loadCSV(String path) throws Exception {
  CSVLoader csv = new CSVLoader();
  csv.setSource(new File(path));
  Instances data = csv.getDataSet();
  data.setClassIndex(data.numAttributes() - 1);
  return data;
}
 

import weka.core.converters.CSVLoader; //导入依赖的package包/类
public void generateArff() throws Exception{
	
	//
	CSVLoader loader = new CSVLoader();
	// Set options
	loader.setNominalAttributes("last");
	loader.setStringAttributes("");
	loader.setMissingValue("?");
	loader.setFieldSeparator("\t");
	loader.setFile(new File(seqConfig.getOutDir().getAbsolutePath()+File.separator+"tmpCounts.mat"));
	Instances data = loader.getDataSet();
	
	//Set subgroup index
	if(data.classIndex() == -1)
		data.setClassIndex(data.numAttributes()-1);
	
	//First, get weight index
	int wInd = data.numAttributes()-2;
	// Now set weights
	for(int i=0; i<data.numInstances(); i++){
		double weight = data.instance(i).value(wInd);
		data.instance(i).setWeight(weight);
	}
	// Now delete the weight attribute
	data.deleteAttributeAt(wInd);
	
	//Save the arff file
	ArffSaver saver = new ArffSaver();
	saver.setFile(new File(seqConfig.getOutDir().getAbsolutePath()+File.separator+seqConfig.getArffOutName()));
	saver.setInstances(data);
	saver.writeBatch();
	
	
}
 

import weka.core.converters.CSVLoader; //导入依赖的package包/类
/**
 * Loads results from a set of instances contained in the supplied file.
 * 
 * @param f a value of type 'File'
 */
protected void setInstancesFromFile(File f) {

  String fileType = f.getName();
  try {
    m_FromLab.setText("Reading from file...");
    if (f.getName().toLowerCase().endsWith(Instances.FILE_EXTENSION)) {
      fileType = "arff";
      Reader r = new BufferedReader(new FileReader(f));
      setInstances(new Instances(r));
      r.close();
    } else if (f.getName().toLowerCase().endsWith(CSVLoader.FILE_EXTENSION)) {
      fileType = "csv";
      CSVLoader cnv = new CSVLoader();
      cnv.setSource(f);
      Instances inst = cnv.getDataSet();
      setInstances(inst);
    } else {
      throw new Exception("Unrecognized file type");
    }
  } catch (Exception ex) {
    m_FromLab.setText("File '" + f.getName() + "' not recognised as an "
      + fileType + " file.");
    if (JOptionPane.showOptionDialog(ResultsPanel.this,
      "File '" + f.getName() + "' not recognised as an " + fileType
        + " file.\n" + "Reason:\n" + ex.getMessage(), "Load Instances", 0,
      JOptionPane.ERROR_MESSAGE, null, new String[] { "OK" }, null) == 1) {

    }
  }
}
 

import weka.core.converters.CSVLoader; //导入依赖的package包/类
public static void CSVToARFF(File input, File output) throws IOException {
    CSVLoader csvDataset = new CSVLoader();
    csvDataset.setSource(input);
    Instances arffDataset = csvDataset.getDataSet();
    ArffSaver saver = new ArffSaver();
    saver.setInstances(arffDataset);
    saver.setFile(output);
    saver.writeBatch();
}
 

import weka.core.converters.CSVLoader; //导入依赖的package包/类
public void trainClassifier(Classifier classifier, File trainingDataset,
                            FileOutputStream trainingModel, Integer
                                    crossValidationFoldNumber) throws Exception {

    CSVLoader csvLoader = new CSVLoader();
    csvLoader.setSource(trainingDataset);

    Instances instances = csvLoader.getDataSet();

    switch(classifier) {
        case KNN:
            int K = (int) Math.ceil(Math.sqrt(instances.numInstances()));
            this.classifier = new IBk(K);
            break;
        case NB:
            this.classifier = new NaiveBayes();
    }

    if(instances.classIndex() == -1) {
        instances.setClassIndex(instances.numAttributes() - 1);
    }

    this.classifier.buildClassifier(instances);

    if(crossValidationFoldNumber > 0) {
        Evaluation evaluation = new Evaluation(instances);
        evaluation.crossValidateModel(this.classifier, instances, crossValidationFoldNumber,
                new Random(1));
        kappa = evaluation.kappa();
        fMeasure = evaluation.weightedFMeasure();
        confusionMatrix = evaluation.toMatrixString("Confusion matrix: ");
    }

    ObjectOutputStream outputStream = new ObjectOutputStream(trainingModel);
    outputStream.writeObject(this.classifier);
    outputStream.flush();
    outputStream.close();
}
 

import weka.core.converters.CSVLoader; //导入依赖的package包/类
@Override
public List<ComplexDataObject> parse(String filename) throws IOException {

	CSVLoader loader = new CSVLoader();
	loader.setSource(new File(filename));
	Instances instances = loader.getDataSet();

	List<ComplexDataObject> data = new ArrayList<>();

	// Step1: create metaMapping
	Map<Integer, Entry<String, Class<?>>> metaMapping = WekaTools.getAttributeSchema(instances);

	// Step2: create ComplexDataObjects
	for (int zeile = 0; zeile < instances.numInstances(); zeile++) {

		Instance instance = instances.instance(zeile);

		ComplexDataObject complexDataObject = new ComplexDataObject();

		// parse columns
		for (Integer spalte = 0; spalte < instances.numAttributes(); spalte++) {

			Entry<String, ?> entry = WekaTools.assignEntry(metaMapping, instance, spalte, missingValueIndicator);

			if (entry != null) {
				if (entry.getValue() != null && entry.getValue() instanceof String) {
					Date date = ParserTools.parseDate((String) entry.getValue());
					if (date != null)
						complexDataObject.add(entry.getKey(), date);
					else
						complexDataObject.add(entry.getKey(), entry.getValue());
				} else
					complexDataObject.add(entry.getKey(), entry.getValue());
			} else
				throw new NullArgumentException();
		}
		data.add(complexDataObject);
	}
	return data;
}
 

import weka.core.converters.CSVLoader; //导入依赖的package包/类
/**
  * Loads results from a set of instances contained in the supplied
  * file.
  *
  * @param f a value of type 'File'
  */
 protected void setInstancesFromFile(File f) {

   String fileType = f.getName();
   try {
     m_FromLab.setText("Reading from file...");
     if (f.getName().toLowerCase().endsWith(Instances.FILE_EXTENSION)) {	    
fileType = "arff";
Reader r = new BufferedReader(new FileReader(f));
setInstances(new Instances(r));
r.close();
     } else if (f.getName().toLowerCase().endsWith(CSVLoader.FILE_EXTENSION)) {
fileType = "csv";
CSVLoader cnv = new CSVLoader();
cnv.setSource(f);
Instances inst = cnv.getDataSet();
setInstances(inst);
     } else {
throw new Exception("Unrecognized file type");
     }
   } catch (Exception ex) {
     m_FromLab.setText("File '" + f.getName() + "' not recognised as an "
		  +fileType+" file.");
     if (JOptionPane.showOptionDialog(ResultsPanel.this,
			       "File '" + f.getName()
			       + "' not recognised as an "
			       +fileType+" file.\n"
			       + "Reason:\n" + ex.getMessage(),
			       "Load Instances",
			       0,
			       JOptionPane.ERROR_MESSAGE,
			       null,
			       new String[] {"OK"},
			       null) == 1) {

     }
   }  
 }
 

import weka.core.converters.CSVLoader; //导入依赖的package包/类
/**
  * Loads results from a set of instances contained in the supplied
  * file.
  *
  * @param f a value of type 'File'
  */
 protected void setInstancesFromFile(File f) {

   String fileType = f.getName();
   try {
     m_FromLab.setText(Messages.getInstance().getString("ResultsPanel_SetInstancesFromFile_FromLab_Text"));
     if (f.getName().toLowerCase().endsWith(Instances.FILE_EXTENSION)) {	    
fileType = "arff";
Reader r = new BufferedReader(new FileReader(f));
setInstances(new Instances(r));
r.close();
     } else if (f.getName().toLowerCase().endsWith(CSVLoader.FILE_EXTENSION)) {
fileType = "csv";
CSVLoader cnv = new CSVLoader();
cnv.setSource(f);
Instances inst = cnv.getDataSet();
setInstances(inst);
     } else {
throw new Exception(Messages.getInstance().getString("ResultsPanel_SetInstancesFromFile_Error_Text"));
     }
   } catch (Exception ex) {
     m_FromLab.setText(Messages.getInstance().getString("ResultsPanel_SetInstancesFromFile_Error_FromLab_Text_First") + f.getName() + Messages.getInstance().getString("ResultsPanel_SetInstancesFromFile_Error_FromLab_Text_Second")
		  +fileType + Messages.getInstance().getString("ResultsPanel_SetInstancesFromFile_Error_FromLab_Text_Third"));
     if (JOptionPane.showOptionDialog(ResultsPanel.this,
   		  Messages.getInstance().getString("ResultsPanel_SetInstancesFromFile_Error_JOptionPaneShowOptionDialog_Text_First") + f.getName()
			       + Messages.getInstance().getString("ResultsPanel_SetInstancesFromFile_Error_JOptionPaneShowOptionDialog_Text_Second")
			       +fileType + Messages.getInstance().getString("ResultsPanel_SetInstancesFromFile_Error_JOptionPaneShowOptionDialog_Text_Third")
			       + Messages.getInstance().getString("ResultsPanel_SetInstancesFromFile_Error_JOptionPaneShowOptionDialog_Text_Fourth") + ex.getMessage(),
			       Messages.getInstance().getString("ResultsPanel_SetInstancesFromFile_Error_JOptionPaneShowOptionDialog_Text_Fifth"),
			       0,
			       JOptionPane.ERROR_MESSAGE,
			       null,
			       new String[] {Messages.getInstance().getString("ResultsPanel_SetInstancesFromFile_Error_JOptionPaneShowOptionDialog_Text_Sixth")},
			       null) == 1) {

     }
   }  
 }
 

import weka.core.converters.CSVLoader; //导入依赖的package包/类
public Map<String, VariableType> getNomNumMap(File trainFile) throws Exception {
    StringBuilder sb = new StringBuilder();
    BufferedReader br = new BufferedReader(new FileReader(trainFile));
    int maxLines = 50, lineCounter = 0;
    String line;
    while ((line = br.readLine()) != null && lineCounter < maxLines) {
        sb.append(line).append("\n");
        lineCounter++;
    }
    br.close();
    Map<String, VariableType> nomNumMap = new HashMap<String, VariableType>();
    CSVLoader csvLoader = new CSVLoader();
    csvLoader.setSource(new ByteArrayInputStream(sb.toString().getBytes()));
    Instances wekaData = csvLoader.getDataSet();

    List<Attribute> attributes = Collections.list(wekaData.enumerateAttributes());

    for (Attribute attribute : attributes) {
        if (attribute.isNumeric() || attribute.isDate()) {
            nomNumMap.put(attribute.name(), VariableType.NUMERIC);
        } else if (attribute.isNominal() || attribute.isString()) {
            nomNumMap.put(attribute.name(), VariableType.CATEGORICAL);
        } else {
            new RuntimeException(this.getClass().getName() + "impl me").printStackTrace();
        }
    }
    return nomNumMap;
}