Java 类weka.core.converters.CSVLoader 实例源码

项目：repo.kmeanspp.silhouette_score 文件：CoverTree.java

/**
 * 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();
  }
}

项目：autoweka 文件：CoverTree.java

/** 
 * 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();
  }
}

项目：umple 文件：CoverTree.java

/**
 * 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();
  }
}

项目：jbossBA 文件：CoverTree.java

/** 
 * 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();
  }
}

项目：semantic-web-scraper 文件：semanticWebScraper.java

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();
    }
}

项目：SmartBetSystem 文件：CSV2Arff.java

/**
  * 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();
}

项目：bestconf 文件：DataIOFile.java

/**
 * 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;
}

项目：BestConfig 文件：DataIOFile.java

/**
 * 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;
}

项目：wekaDeeplearning4j 文件：DatasetLoader.java

/**
 * 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;
}

项目：sequnwinder 文件：MakeArff.java

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();


}

项目：repo.kmeanspp.silhouette_score 文件：ResultsPanel.java

/**
 * 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) {

    }
  }
}

项目：SpeakerAuthentication 文件：FileUtils.java

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();
}

项目：SpeakerAuthentication 文件：Learning.java

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();
}

项目：ComplexDataObject 文件：CSVParser.java

@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;
}

项目：IReS-Platform 文件：KMeans.java

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]);
//            
//        }

    }

项目：autoweka 文件：ResultsPanel.java

/**
  * 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) {

     }
   }  
 }

项目：umple 文件：ResultsPanel.java

/**
 * 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) {

    }
  }
}

项目：jbossBA 文件：ResultsPanel.java

/**
  * 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) {

     }
   }  
 }

项目：jbossBA 文件：WekaApacheEngine.java

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;
}

项目：SmartBetSystem 文件：Neural.java

public void loadData() {
    try {
        if (useMultiple) {
            String[] loaders = {
                    "home",
                    "draw",
                    "away"
            };
            for (String str : loaders) {
                CSVLoader trainLoader = new CSVLoader();
                CSVLoader testLoader = new CSVLoader();
                trainLoader.setSource(Neural.class.getResourceAsStream("/main/resources/tsi/" + folder + "/train" + str + FILENAME_APPEND +".csv"));
                testLoader.setSource(Neural.class.getResourceAsStream("/main/resources/tsi/" + folder + "/test" + str + FILENAME_APPEND + ".csv"));

                Instances trainSet = trainLoader.getDataSet();
                trainSet.setClassIndex(0);
                //testSet = testingSource.getDataSet(0);
                Instances testSet = testLoader.getDataSet();
                testSet.setClassIndex(0);

                trainSetList.add(trainSet);
                testSetList.add(testSet);
            }
        } else {
            CSVLoader trainLoader = new CSVLoader(), testLoader = new CSVLoader();
            trainLoader.setSource(Neural.class.getResourceAsStream("/main/resources/tsi/" + folder + "/train.csv"));
            //testLoader.setSource(new File(folder+"/test.csv"));
            testLoader.setSource(Neural.class.getResourceAsStream("/main/resources/tsi/" + folder + "/test.csv"));

            trainSet = trainLoader.getDataSet();
            trainSet.setClassIndex(0);
            //testSet = testingSource.getDataSet(0);
            testSet = testLoader.getDataSet();
            testSet.setClassIndex(0);
        }
    } catch (Exception e) {
        e.printStackTrace();
    }
}

项目：seqcode-core 文件：WekaCSVLoader.java

public static void main(String[] args){
    CSVLoader loader = new CSVLoader();
    CSVLoader.runFileLoader(loader, args);
}

项目：Chordalysis 文件：RunGUI.java

/**
 * @param args
 */
public static void main(String[] args) {
    JFileChooser chooser = new JFileChooser();
    FileNameExtensionFilter filter = new FileNameExtensionFilter("CSV file", "csv");
    chooser.setFileFilter(filter);
    int returnVal = chooser.showOpenDialog(null);
    if (returnVal == JFileChooser.APPROVE_OPTION) {
        System.out.println("You chose to open this file: " + chooser.getSelectedFile().getName());
    }
    CSVLoader loader = new CSVLoader();
    File csvFile = chooser.getSelectedFile();
    if (!csvFile.exists()) {
        System.out.println("The file doesn't exist");
        return;
    }

    double pValue = Double.valueOf(JOptionPane.showInputDialog("Desired p-value ]0,1[",0.05));
    if (pValue <= 0 || 1 <= pValue) {
        System.out.println("The p-value should be between 0 and 1 excluded. ");
        return;
    }
    try {
        loader.setFile(csvFile);
        loader.setNominalAttributes("first-last");
        Instances instances = loader.getDataSet();
        String[] variablesNames = new String[instances.numAttributes()];
        for (int i = 0; i < variablesNames.length; i++) {
            variablesNames[i] = instances.attribute(i).name();
        }

        ChordalysisModeller.Data mydata = LoadWekaInstances.makeModelData(instances);
        ChordalysisModellingSMT modeller = new ChordalysisModellingSMT(mydata, pValue);
        modeller.buildModel();

        DecomposableModel bestModel = modeller.getModel();
        System.out.println("The model selected is:");
        System.out.println(bestModel.toString(variablesNames));
        PrintableModel.display(bestModel, variablesNames);
    } catch (IOException e) {
        System.out.println("I/O error while loading csv file");
        e.printStackTrace();
    }

}

项目：Chordalysis 文件：RunDot.java

/**
 * @param args
 */
public static void main(String[] args) {
    if (args.length != 3) {         
        System.out.println("Usage:\tjava -Xmx1g -jar Chordalysis.jar dataFile pvalue dotOutputFile");
        System.out.println("Example:\tjava -Xmx1g -jar Chordalysis.jar dataset.csv 0.05 graph.dot");
        System.out.println("\nNote:\t'1g' means that you authorize 1GB of memory. " +
                "\nNote:\tIt should be adjusted depending upon the size of your data set (mostly required to load the data set).");
        return;
    }
    System.out.println();
    CSVLoader loader = new CSVLoader();
    File csvFile = new File(args[0]);
    if (!csvFile.exists()) {
        System.out.println("The file doesn't exist");
        return;
    }else{
        System.out.println("Info:\tUsing the dataset file "+csvFile.getAbsolutePath());
    }

    double pValue = Double.valueOf(args[1]);
    if(pValue<=0 || 1<=pValue){
        System.out.println("The p-value should be between 0 and 1 excluded. ");
        return;
    }else{
        System.out.println("Info:\tUsing p="+pValue);
    }

    File outPutFile = new File(args[2]);
    String []splitted = outPutFile.getName().split("\\.");
    if(splitted.length<2){
        System.out.println("The image output file should declare a \".dot\" extension");
        return;
    }

    try {
        loader.setFile(csvFile);
        loader.setNominalAttributes("first-last");
        Instances instances = loader.getDataSet();
        String[] variablesNames = new String[instances.numAttributes()];
        for (int i = 0; i < variablesNames.length; i++) {
            variablesNames[i] = instances.attribute(i).name();
        }
        long start = System.currentTimeMillis();

        ChordalysisModeller.Data mydata = LoadWekaInstances.makeModelData(instances);
        ChordalysisModellingSMT modeller = new ChordalysisModellingSMT(mydata, pValue);
        modeller.buildModel();

        DecomposableModel bestModel = modeller.getModel();

        System.out.println("The model selected is: (selected in " + (System.currentTimeMillis() - start) + "ms)");
        System.out.println(bestModel.toString(variablesNames));
        bestModel.exportDOT(outPutFile, variablesNames);
        System.out.println("DOT file exported - note that the variables with no neighbors won't be included in the graph");
    } catch (IOException e) {
        System.out.println("I/O error while loading csv file");
        e.printStackTrace();
    } 
}

项目：Chordalysis 文件：Run.java

/**
 * @param args
 */
public static void main(String[] args) {
    if (args.length != 4) {         
        System.out.println("Usage:\tjava -Xmx1g -jar Chordalysis.jar dataFile pvalue imageOutputFile useGUI?");
        System.out.println("Example:\tjava -Xmx1g -jar Chordalysis.jar dataset.csv 0.05 graph.png false");
        System.out.println("\nNote:\t'1g' means that you authorize 1GB of memory. " +
                "\nNote:\tIt should be adjusted depending upon the size of your data set (mostly required to load the data set).");
        return;
    }
    System.out.println();
    CSVLoader loader = new CSVLoader();
    File csvFile = new File(args[0]);
    if (!csvFile.exists()) {
        System.out.println("The file doesn't exist");
        return;
    }else{
        System.out.println("Info:\tUsing the dataset file "+csvFile.getAbsolutePath());
    }

    double pValue = Double.valueOf(args[1]);
    if(pValue<=0 || 1<=pValue){
        System.out.println("The p-value should be between 0 and 1 excluded. ");
        return;
    }else{
        System.out.println("Info:\tUsing p="+pValue);
    }

    File outPutFile = new File(args[2]);
    String []splitted = outPutFile.getName().split("\\.");
    if(splitted.length<2){
        System.out.println("The image output file should declare an extension among \".jpg\", \".png\" or \".gif\"");
        return;
    }
    String extension = splitted[splitted.length-1];
    if(!extension.equals("jpg") && !extension.equals("png")&&!extension.equals("gif")){
        System.out.println("The format for the graphical representation of the model should be either jpg, png or gif. ");
        return;
    }else{
        System.out.println("Info:\tExporting result as a "+extension+" file");
    }

    boolean gui = Boolean.parseBoolean(args[3]);

    if(gui){
        System.out.println("Info:\tUsing a graphical user interface");
    }else{
        System.out.println("Info:\tNot using a graphical user interface");
    }

    try {
        loader.setFile(csvFile);
        loader.setNominalAttributes("first-last");
        Instances instances = loader.getDataSet();
        String[] variablesNames = new String[instances.numAttributes()];
        for (int i = 0; i < variablesNames.length; i++) {
            variablesNames[i] = instances.attribute(i).name();
        }
        long start = System.currentTimeMillis();

        ChordalysisModeller.Data mydata = LoadWekaInstances.makeModelData(instances);
        ChordalysisModellingSMT modeller = new ChordalysisModellingSMT(mydata, pValue);
        modeller.buildModel();
        DecomposableModel bestModel = modeller.getModel();

        if(gui){PrintableModel.display(bestModel, variablesNames);}

        System.out.println("The model selected is: (selected in " + (System.currentTimeMillis() - start) + "ms)");
        System.out.println(bestModel.toString(variablesNames));

        ImageIO.write(PrintableModel.getImage(bestModel, variablesNames),extension, outPutFile);
    } catch (IOException e) {
        System.out.println("I/O error while loading csv file");
        e.printStackTrace();
    } 
}

项目：multimedia-indexing 文件：CodebookLearning.java

/**
 * @param args
 *            [0] path to the arff or csv formated (without header) file containing a set the local
 *            features
 * @param args
 *            [1] the number of clusters to create (e.g. 64)
 * @param args
 *            [2] the maximum number of k-means iterations (e.g. 100)
 * @param args
 *            [3] the seed given to k-means (e.g. 1)
 * @param args
 *            [4] the number of execution slots to use (>1 = parallel execution)
 * @param args
 *            [5] the type of normalization to apply on the local features (no/l2/power+l2)
 * @param args
 *            [6] whether to use kmeans++ for the initialization of the centroids (true/false)
 * @throws Exception
 */
public static void main(String[] args) throws Exception {
    String filepath = args[0];
    int numClusters = Integer.parseInt(args[1]);
    int maxIterations = Integer.parseInt(args[2]);
    int seed = Integer.parseInt(args[3]);
    int numSlots = Integer.parseInt(args[4]);
    String normalization = args[5];
    boolean kMeansPlusPlus = Boolean.parseBoolean(args[6]);

    Instances data;
    System.out.println("--Loading descriptors--");
    if (filepath.endsWith(".arff")) { // loading instances from arff file
        BufferedReader reader = new BufferedReader(new FileReader(filepath));
        // Using the Instances class of WEKA to read the dataset
        data = new Instances(reader);
        reader.close();
    } else if (filepath.endsWith(".csv")) { // loading instances from csv file
        CSVLoader loader = new CSVLoader();
        loader.setNoHeaderRowPresent(true);
        loader.setSource(new File(filepath));
        data = loader.getDataSet();
    } else {
        throw new Exception("Wrong dataset format!");
    }

    if (!normalization.equals("no")) { // apply normalization on the features
        System.out.println("--Normalizing descriptors--");
        for (int i = 0; i < data.numInstances(); i++) {
            double[] vector = data.instance(i).toDoubleArray();
            if (normalization.equals("l2")) {
                vector = Normalization.normalizeL2(vector);
            }
            if (normalization.equals("power+l2")) {
                vector = Normalization.normalizePower(vector, power);
                vector = Normalization.normalizeL2(vector);
            }
            for (int j = 0; j < vector.length; j++) {
                data.instance(i).setValue(j, vector[j]);
            }
        }
    }

    String outFilename = filepath + "_codebook-" + data.numAttributes() + "A-" + numClusters + "C-"
            + maxIterations + "I-" + seed + "S" + "_" + normalization + ".csv";
    AbstractQuantizerLearning.learnAndWriteQuantizer(outFilename, data, numClusters, maxIterations, seed,
            numSlots, kMeansPlusPlus);
}

项目：java-examples 文件：DataImport.java

public static Instances getInstancesFromCSV(String filePath) throws IOException {
    CSVLoader loader = new CSVLoader();
    loader.setSource(new File(filePath));

    return loader.getDataSet();

}

项目：java-examples 文件：WekaMultiLayerPerceptron.java

public static void main(String[] args) {
    try {


        CSVLoader loader = new CSVLoader();
        loader.setSource(new File(OJOSECO_FILEPATH));



        Instances data = loader.getDataSet();

        Normalize normalize = new Normalize();
        normalize.setInputFormat(data);
        data = Filter.useFilter(data, normalize);

        data.setClassIndex(data.numAttributes() - 1);

        System.out.println(data.toSummaryString());



        data.randomize(new Random(0));

        int trainSize = Math.toIntExact(Math.round(data.numInstances() * RATIO_TEST));
        int testSize = data.numInstances() - trainSize;

        Instances train = new Instances(data, 0, trainSize);
        Instances test = new Instances(data, trainSize, testSize);



        MultilayerPerceptron mlp = new MultilayerPerceptron();
        mlp.setOptions(Utils.splitOptions("-L 0.3 -M 0.2 -N 500 -V 0 -S 0 -E 20 -H a"));
        mlp.buildClassifier(train);

        System.out.println(mlp.toString());



        Evaluation eval = new Evaluation(test);
        eval.evaluateModel(mlp, test);

        System.out.println(eval.toSummaryString());


    } catch (Exception e) {
        e.printStackTrace();
    }

}