csvloader.java

Java 编写的多种数据挖掘算法 包括聚类、分类、预处理等

/*
 *    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 Mark Hall
 *
 */

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.StreamTokenizer;
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: 1.10 $
 * @see Loader
 */
public class CSVLoader 
  extends AbstractLoader 
  implements FileSourcedConverter, BatchConverter {

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

  /** the file */
  protected String m_File = 
    (new File(System.getProperty("user.dir"))).getAbsolutePath();

  /**
   * Holds the determined structure (header) of the data set.
   */
  //@ protected depends: model_structureDetermined -> m_structure;
  //@ protected represents: model_structureDetermined <- (m_structure != null);
  protected Instances m_structure = null;

  /**
   * Holds the source of the data set.
   */
  //@ protected depends: model_sourceSupplied -> m_sourceFile;
  //@ protected represents: model_sourceSupplied <- (m_sourceFile != null);
  protected File m_sourceFile = null;

  /**
   * Describe variable <code>m_tokenizer</code> here.
   */
  //  private StreamTokenizer m_tokenizer = null;

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

  /**
   * Holds instances accumulated so far
   */
  private FastVector m_cumulativeInstances;
  
  /**
   * 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";
  }

  /**
   * get the File specified as the source
   *
   * @return the source file
   */
  public File retrieveFile() {
    return new File(m_File);
  }

  /**
   * sets the source File
   *
   * @param file the source file
   * @exception IOException if an error occurs
   */
  public void setFile(File file) throws IOException {
    m_File = file.getAbsolutePath();
    setSource(file);
  }

  /**
   * 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 ready to read a new data set
   */
  public void reset() {
    m_structure = null;
    setRetrieval(NONE);
  }

  /**
   * 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 {
    reset();

    if (file == null) {
      throw new IOException("Source file object is null!");
    }

    m_sourceFile = file;
    try {
      BufferedReader br = new BufferedReader(new FileReader(file));
      br.close();
    } catch (FileNotFoundException ex) {
      throw new IOException("File not found");
    }
  }

  /**
   * 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) {
      throw new IOException("No source has been specified");
    }

    if (m_structure == null) {
      try {
	BufferedReader br = new BufferedReader(new FileReader(m_sourceFile));
     
	// assumes that the first line of the file is the header
	/*m_tokenizer = new StreamTokenizer(br);
	initTokenizer(m_tokenizer);
	readHeader(m_tokenizer); */
	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) {
      throw new IOException("No source has been specified");
    }
    //    m_sourceReader.close();
    setSource(m_sourceFile);
    BufferedReader br = new BufferedReader(new FileReader(m_sourceFile));
    //    getStructure();
    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));
      }
    }