csvloader.java

矩阵的QR分解算法

/*
 *    This program is free software; you can redistribute it and/or modify
 *    it under the terms of the GNU General Public License as published by
 *    the Free Software Foundation; either version 2 of the License, or
 *    (at your option) any later version.
 *
 *    This program is distributed in the hope that it will be useful,
 *    but WITHOUT ANY WARRANTY; without even the implied warranty of
 *    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *    GNU General Public License for more details.
 *
 *    You should have received a copy of the GNU General Public License
 *    along with this program; if not, write to the Free Software
 *    Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 */

/*
 *    CSVLoader.java
 *    Copyright (C) 2000 University of Waikato, Hamilton, New Zealand
 *
 */

package weka.core.converters;

import weka.core.Attribute;
import weka.core.FastVector;
import weka.core.Instance;
import weka.core.Instances;

import java.io.BufferedReader;
import java.io.File;
import java.io.FileNotFoundException;
import java.io.FileReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.StreamTokenizer;
import java.io.StringReader;
import java.util.Enumeration;
import java.util.Hashtable;

/**
 <!-- globalinfo-start -->
 * Reads a source that is in comma separated or tab separated format. Assumes that the first row in the file determines the number of and names of the attributes.
 * <p/>
 <!-- globalinfo-end -->
 *
 * @author Mark Hall ([e-mail])
 * @version $Revision: 1.16 $
 * @see Loader
 */
public class CSVLoader 
  extends AbstractFileLoader 
  implements BatchConverter {

  /** for serialization */
  static final long serialVersionUID = 5607529739745491340L;
  
  /** the file extension */
  public static String FILE_EXTENSION = ".csv";

  /**
   * A list of hash tables for accumulating nominal values during parsing.
   */
  private FastVector m_cumulativeStructure;

  /**
   * Holds instances accumulated so far
   */
  private FastVector m_cumulativeInstances;
  
  /** the data collected from an InputStream */
  private StringBuffer m_StreamBuffer;
  
  /**
   * default constructor
   */
  public CSVLoader() {
    // No instances retrieved yet
    setRetrieval(NONE);
  }

  /**
   * Get the file extension used for arff files
   *
   * @return the file extension
   */
  public String getFileExtension() {
    return FILE_EXTENSION;
  }

  /**
   * Returns a description of the file type.
   *
   * @return a short file description
   */
  public String getFileDescription() {
    return "CSV data files";
  }

  /**
   * Gets all the file extensions used for this type of file
   *
   * @return the file extensions
   */
  public String[] getFileExtensions() {
    return new String[]{getFileExtension()};
  }

  /**
   * Returns a string describing this attribute evaluator
   * @return a description of the evaluator suitable for
   * displaying in the explorer/experimenter gui
   */
  public String globalInfo() {
    return "Reads a source that is in comma separated or tab separated format. "
      +"Assumes that the first row in the file determines the number of "
      +"and names of the attributes.";
  }
  
  /**
   * Resets the Loader object and sets the source of the data set to be 
   * the supplied Stream object.
   *
   * @param input the input stream
   * @exception IOException if an error occurs
   */
  public void setSource(InputStream input) throws IOException {
    BufferedReader	reader;
    String		line;
    
    m_structure    = null;
    m_sourceFile   = null;
    m_File         = null;

    m_StreamBuffer = new StringBuffer();
    reader         = new BufferedReader(new InputStreamReader(input));
    while ((line = reader.readLine()) != null)
      m_StreamBuffer.append(line + "\n");
  }

  /**
   * Resets the Loader object and sets the source of the data set to be 
   * the supplied File object.
   *
   * @param file the source file.
   * @exception IOException if an error occurs
   */
  public void setSource(File file) throws IOException {
    super.setSource(file);
    
    m_StreamBuffer = null;
  }

  /**
   * Determines and returns (if possible) the structure (internally the 
   * header) of the data set as an empty set of instances.
   *
   * @return the structure of the data set as an empty set of Instances
   * @exception IOException if an error occurs
   */
  public Instances getStructure() throws IOException {
    if ((m_sourceFile == null) && (m_StreamBuffer == null)) {
      throw new IOException("No source has been specified");
    }

    if (m_structure == null) {
      try {
	BufferedReader br;
	if (m_StreamBuffer != null)
	  br = new BufferedReader(new StringReader(m_StreamBuffer.toString()));
	else
	  br = new BufferedReader(new FileReader(m_sourceFile));
	StreamTokenizer st = new StreamTokenizer(br);
	initTokenizer(st);
	readStructure(st);
      } catch (FileNotFoundException ex) {
      }
    }
    
    return m_structure;
  }

  /**
   * reads the structure
   * 
   * @param st the stream tokenizer to read from
   * @throws IOException if reading fails
   */
  private void readStructure(StreamTokenizer st) throws IOException {
    readHeader(st);
  }

  /**
   * Return the full data set. If the structure hasn't yet been determined
   * by a call to getStructure then method should do so before processing
   * the rest of the data set.
   *
   * @return the structure of the data set as an empty set of Instances
   * @exception IOException if there is no source or parsing fails
   */
  public Instances getDataSet() throws IOException {
    if ((m_sourceFile == null) && (m_StreamBuffer == null)) {
      throw new IOException("No source has been specified");
    }
    BufferedReader br;
    if (m_sourceFile != null) {
      setSource(m_sourceFile);
      br = new BufferedReader(new FileReader(m_sourceFile));
    }
    else {
      br = new BufferedReader(new StringReader(m_StreamBuffer.toString()));
    }
    StreamTokenizer st = new StreamTokenizer(br);
    initTokenizer(st);
    readStructure(st);
    
    st.ordinaryChar(',');
    st.ordinaryChar('\t');
    
    m_cumulativeStructure = new FastVector(m_structure.numAttributes());
    for (int i = 0; i < m_structure.numAttributes(); i++) {
      m_cumulativeStructure.addElement(new Hashtable());
    }
    

    // Instances result = new Instances(m_structure);
    m_cumulativeInstances = new FastVector();
    FastVector current;
    while ((current = getInstance(st)) != null) {
      m_cumulativeInstances.addElement(current);
    }
    br.close();
    // now determine the true structure of the data set
    FastVector atts = new FastVector(m_structure.numAttributes());
    for (int i = 0; i < m_structure.numAttributes(); i++) {
      String attname = m_structure.attribute(i).name();
      Hashtable tempHash = ((Hashtable)m_cumulativeStructure.elementAt(i));
      if (tempHash.size() == 0) {
	atts.addElement(new Attribute(attname));
      } else {
	FastVector values = new FastVector(tempHash.size());
	// add dummy objects in order to make the FastVector's size == capacity
	for (int z = 0; z < tempHash.size(); z++) {
	  values.addElement("dummy");
	}
	Enumeration e = tempHash.keys();
	while (e.hasMoreElements()) {
	  Object ob = e.nextElement();
	  //	  if (ob instanceof Double) {
	  int index = ((Integer)tempHash.get(ob)).intValue();
	  values.setElementAt(new String(ob.toString()), index);
	  //	  }
	}
	atts.addElement(new Attribute(attname, values));
      }
    }

    // make the instances
    String relationName;
    if (m_sourceFile != null)
      relationName = (m_sourceFile.getName()).replaceAll("\\.[cC][sS][vV]$","");
    else
      relationName = "stream";
    Instances dataSet = new Instances(relationName,