Java 类weka.core.converters.ArffLoader.ArffReader 实例源码

项目：reactive-data 文件：ARFFDataMapper.java

@Override
public Dataset mapStringToModel(JsonRequest request) throws ParseException {
  if(!(request instanceof ArffJsonRequest))
  {
    throw new ParseException("Not an instance of "+ArffJsonRequest.class, -1);
  }
  try 
  {
    ArffJsonRequest arff = (ArffJsonRequest) request;
    ArffReader ar = new ArffReader(new StringReader(request.toString()));
    Instances ins = ar.getData();
    ins.setClassIndex(arff.getClassIndex() >= 0 ? arff.getClassIndex() : ins.numAttributes()-1);
    return new Dataset(ins);
  } catch (Exception e) {
    ParseException pe = new ParseException("Cannot convert JSON stream to ARFF", -1);
    pe.initCause(e);
    throw pe;
  }
}

项目：anti-spam-weka-gui 文件：InputOutputHelper.java

public Instances loadInstancesFromArffFile(String filename) throws IOException
{
    LOGGER.trace("Loading data from ARFF file [{}].", filename);

    FileReader fileReader = new FileReader(filename);
    BufferedReader bufferedReader = new BufferedReader(fileReader);
    ArffReader arffReader = new ArffReader(bufferedReader);
    Instances data = arffReader.getData();
    data.setClassIndex(data.numAttributes() - 1);

    bufferedReader.close();
    fileReader.close();

    return data;
}

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

@Override
public Instances getDataSet() throws IOException {

  if (m_sourceReader == null) {
    throw new IOException("No source has been specified");
  }

  if (getRetrieval() == INCREMENTAL) {
    throw new IOException(
      "Cannot mix getting instances in both incremental and batch modes");
  }
  setRetrieval(BATCH);

  if (m_structure == null) {
    getStructure();
  }

  while (readData(true)) {
    ;
  }

  m_dataDumper.flush();
  m_dataDumper.close();

  // make final structure
  makeStructure();

  Reader sr = new BufferedReader(new FileReader(m_tempFile));
  ArffReader initialArff =
    new ArffReader(sr, m_structure, 0, m_fieldSeparatorAndEnclosures);

  Instances initialInsts = initialArff.getData();
  sr.close();
  initialArff = null;

  return initialInsts;
}

项目：umple 文件：CSVLoader.java

@Override
public Instances getDataSet() throws IOException {

  if (m_sourceReader == null) {
    throw new IOException("No source has been specified");
  }

  if (getRetrieval() == INCREMENTAL) {
    throw new IOException(
      "Cannot mix getting instances in both incremental and batch modes");
  }
  setRetrieval(BATCH);

  if (m_structure == null) {
    getStructure();
  }

  while (readData(true)) {
    ;
  }

  m_dataDumper.flush();
  m_dataDumper.close();

  // make final structure
  makeStructure();

  Reader sr = new BufferedReader(new FileReader(m_tempFile));
  ArffReader initialArff =
    new ArffReader(sr, m_structure, 0, m_fieldSeparatorAndEnclosures);

  Instances initialInsts = initialArff.getData();
  sr.close();
  initialArff = null;

  return initialInsts;
}

项目：weka-classifier-examples 文件：AbstractClassifier.java

protected Instances readData(String data) throws IOException{
    String trainFileName = "src/main/resources/"+data+".arff";
    BufferedReader reader = new BufferedReader(new FileReader(trainFileName));
    ArffReader arff = new ArffReader(reader);
    Instances instances = arff.getData();
    reader.close();
    return instances;
}

项目：weka-classifier-examples 文件：Learner.java

/**
 * This method loads a dataset in ARFF format. If the file does not exist,
 * or it has a wrong format, the attribute trainData is null.
 * 
 * @param fileName
 *            The name of the file that stores the dataset.
 */
public void loadDataset(String fileName) {
    try {
        BufferedReader reader = new BufferedReader(new FileReader(fileName));
        ArffReader arff = new ArffReader(reader);
        trainData = arff.getData();
        System.out.println("===== Loaded dataset: " + fileName + " =====");
        reader.close();
    } catch (IOException e) {
        System.out.println("Problem found when reading: " + fileName);
    }
}

项目：ctwt 文件：Actions.java

public static void mergeAndWrite(String relationName, String destPath, String... dataSetPaths) throws IOException {
    ArffSaver saver = new ArffSaver();
    saver.setFile(new File(destPath));
    saver.setRetrieval(Saver.INCREMENTAL);
    boolean first = true;

    for (String p : dataSetPaths) {
        ArffReader reader = new ArffReader(new BufferedReader(new FileReader(p)));
        Instances dataSet = reader.getData();

        if (first) {
            dataSet.setRelationName(relationName);
            saver.setStructure(dataSet);


            first = false;
        }
        for (int i = 0; i < dataSet.numInstances(); ++i) {
            saver.writeIncremental(dataSet.instance(i));
        }

    }
    saver.getWriter().flush();



}

项目：Chordalysis 文件：LoadWekaInstances.java

/** Make a lattice over the given variables of the dataset.*/
public static ChordalysisModeller.Data makeModelData(Instances structure, ArffReader loader) throws IOException {
  return makeModelData(structure, loader, true);
}

项目：Chordalysis 文件：LoadWekaInstances.java

/** Make a lattice over the given variables of the dataset.*/
public static ChordalysisModeller.Data makeModelData(Instances structure, ArffReader loader, boolean hasMissingValues)
  throws IOException {

  // Access the size:
  int nbInstances = 0;
  int nbVariables = structure.numAttributes();

  // Create the array for the model
  int[] variables = new int[nbVariables];

  // Create the bitset for the lattice
  int[] nbValuesForAttribute            = new int[nbVariables];       // Also used by the model
  BitSet[][] presence                   = new BitSet[nbVariables][];

  // --- 1 ---
  // For each attribute:
  for (int a = 0; a < nbVariables; a++) {
    // --- For the model:
    variables[a] = a;

    // --- For the lattice:
    nbValuesForAttribute[a] = structure.attribute(a).numValues();
    // --- --- Handle the case of missing values:  +1 for missing
    if (hasMissingValues) { nbValuesForAttribute[a]++; }
    // --- --- Build the bitset
    presence[a] = new BitSet[nbValuesForAttribute[a]];
    for (int v = 0; v < presence[a].length; v++) { presence[a][v] = new BitSet(); }
  }

  // --- 2 ---
  // For each instance (only for the lattice)...
  Instance row;
  while ((row = loader.readInstance(structure)) != null) {
    boolean skipRow = false;
    for (int a = 0; a < nbVariables; a++) {
      int indexOfValue;
      if (row.isMissing(a)) {
        if (hasMissingValues) {
          indexOfValue = structure.attribute(a).numValues() ;
        } else {
          System.err.println("Found missing while I was told I wouldn't; ignoring whole row");
          skipRow = true;
          break;
        }
      } else {
        String value = row.stringValue(a);
        indexOfValue = row.attribute(a).indexOfValue(value);
      }
      presence[a][indexOfValue].set(nbInstances);
    }
    if (!skipRow) { nbInstances++; }
  }

  // --- 3 ---
  // Create the data:
  return new ChordalysisModeller.Data(
      new DecomposableModel(variables, nbValuesForAttribute),
      new Lattice(nbVariables, nbInstances, nbValuesForAttribute, presence) );
}

项目：ctwt 文件：Actions.java

public static Instances loadDataSet(File dataSetPath) throws IOException, FileNotFoundException {
    ArffReader reader = new ArffReader(new BufferedReader(new FileReader(dataSetPath)));
    Instances dataSet = reader.getData();
    dataSet.setClassIndex(dataSet.numAttributes() - 1);
    return dataSet;
}

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

/**
 * Reads a single instance from the reader and appends it to the dataset.
 * Automatically expands the dataset if it is not large enough to hold the
 * instance. This method does not check for carriage return at the end of the
 * line.
 * 
 * @param reader the reader
 * @return false if end of file has been reached
 * @throws IOException if the information is not read successfully
 * @deprecated instead of using this method in conjunction with the
 *             <code>readInstance(Reader)</code> method, one should use the
 *             <code>ArffLoader</code> or <code>DataSource</code> class
 *             instead.
 * @see weka.core.converters.ArffLoader
 * @see weka.core.converters.ConverterUtils.DataSource
 */
@Deprecated
public boolean readInstance(Reader reader) throws IOException {

  ArffReader arff = new ArffReader(reader, this, m_Lines, 1);
  Instance inst = arff.readInstance(arff.getData(), false);
  m_Lines = arff.getLineNo();
  if (inst != null) {
    add(inst);
    return true;
  } else {
    return false;
  }
}

项目：autoweka 文件：Instances.java

/**
 * Reads a single instance from the reader and appends it
 * to the dataset.  Automatically expands the dataset if it
 * is not large enough to hold the instance. This method does
 * not check for carriage return at the end of the line.
 *
 * @param reader the reader 
 * @return false if end of file has been reached
 * @throws IOException if the information is not read 
 * successfully
 * @deprecated instead of using this method in conjunction with the
 * <code>readInstance(Reader)</code> method, one should use the 
 * <code>ArffLoader</code> or <code>DataSource</code> class instead.
 * @see weka.core.converters.ArffLoader
 * @see weka.core.converters.ConverterUtils.DataSource
 */ 
@Deprecated public boolean readInstance(Reader reader) throws IOException {

  ArffReader arff = new ArffReader(reader, this, m_Lines, 1);
  Instance inst = arff.readInstance(arff.getData(), false);
  m_Lines = arff.getLineNo();
  if (inst != null) {
    add(inst);
    return true;
  }
  else {
    return false;
  }
}

项目：umple 文件：Instances.java

/**
 * Reads a single instance from the reader and appends it to the dataset.
 * Automatically expands the dataset if it is not large enough to hold the
 * instance. This method does not check for carriage return at the end of the
 * line.
 * 
 * @param reader the reader
 * @return false if end of file has been reached
 * @throws IOException if the information is not read successfully
 * @deprecated instead of using this method in conjunction with the
 *             <code>readInstance(Reader)</code> method, one should use the
 *             <code>ArffLoader</code> or <code>DataSource</code> class
 *             instead.
 * @see weka.core.converters.ArffLoader
 * @see weka.core.converters.ConverterUtils.DataSource
 */
@Deprecated
public boolean readInstance(Reader reader) throws IOException {

  ArffReader arff = new ArffReader(reader, this, m_Lines, 1);
  Instance inst = arff.readInstance(arff.getData(), false);
  m_Lines = arff.getLineNo();
  if (inst != null) {
    add(inst);
    return true;
  } else {
    return false;
  }
}

项目：jbossBA 文件：Instances.java

/**
 * Reads a single instance from the reader and appends it to the dataset.
 * Automatically expands the dataset if it is not large enough to hold the
 * instance. This method does not check for carriage return at the end of the
 * line.
 *
 * @param reader the reader
 * @return false if end of file has been reached
 * @throws IOException if the information is not read successfully
 * @see weka.core.converters.ArffLoader
 * @see weka.core.converters.ConverterUtils.DataSource
 * @deprecated instead of using this method in conjunction with the
 * <code>readInstance(Reader)</code> method, one should use the
 * <code>ArffLoader</code> or <code>DataSource</code> class
 * instead.
 */
@Deprecated
public boolean readInstance(Reader reader) throws IOException {

    ArffReader arff = new ArffReader(reader, this, m_Lines, 1);
    Instance inst = arff.readInstance(arff.getData(), false);
    m_Lines = arff.getLineNo();
    if (inst != null) {
        add(inst);
        return true;
    } else {
        return false;
    }
}