• Home
• nz.ac.waikato.cms.weka
• weka-dev
• 3.7.11
• source code
• CSV.java

×

Project download

Many resources are needed to download a project. Please understand that we have to compensate our server costs. Thank you in advance.
Project price only 1 $

You can buy this project and download/modify it how often you want.

weka.classifiers.evaluation.output.prediction.CSV Maven / Gradle / Ivy

/*
 *   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 3 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, see .
 */

/*
 * CSV.java
 * Copyright (C) 2009-2012 University of Waikato, Hamilton, New Zealand
 */

package weka.classifiers.evaluation.output.prediction;

import java.util.Collections;
import java.util.Enumeration;
import java.util.Vector;

import weka.classifiers.Classifier;
import weka.core.Instance;
import weka.core.Option;
import weka.core.Utils;

/**
 *  Outputs the predictions as CSV.
 * 

 * 
 * 
 *  Valid options are:
 * 

 * 
 * 
 * -p <range>
 *  The range of attributes to print in addition to the classification.
 *  (default: none)
 * 
 * 
 * 
 * -distribution
 *  Whether to turn on the output of the class distribution.
 *  Only for nominal class attributes.
 *  (default: off)
 * 
 * 
 * 
 * -decimals <num>
 *  The number of digits after the decimal point.
 *  (default: 3)
 * 
 * 
 * 
 * -file <path>
 *  The file to store the output in, instead of outputting it on stdout.
 *  Gets ignored if the supplied path is a directory.
 *  (default: .)
 * 
 * 
 * 
 * -suppress
 *  In case the data gets stored in a file, then this flag can be used
 *  to suppress the regular output.
 *  (default: not suppressed)
 * 
 * 
 * 
 * -use-tab
 *  Whether to use TAB as separator instead of comma.
 *  (default: comma)
 * 
 * 
 * 
 * 
 * @author fracpete (fracpete at waikato dot ac dot nz)
 * @version $Revision: 10169 $
 */
public class CSV extends AbstractOutput {

  /** for serialization. */
  private static final long serialVersionUID = 3401604538169573720L;

  /** the delimiter. */
  protected String m_Delimiter = ",";

  /**
   * Returns a string describing the output generator.
   * 
   * @return a description suitable for displaying in the GUI
   */
  @Override
  public String globalInfo() {
    return "Outputs the predictions as CSV.";
  }

  /**
   * Returns a short display text, to be used in comboboxes.
   * 
   * @return a short display text
   */
  @Override
  public String getDisplay() {
    return "CSV";
  }

  /**
   * Returns an enumeration of all the available options..
   * 
   * @return an enumeration of all available options.
   */
  @Override
  public Enumeration listOptions() {
    Vector result;

    result = new Vector();

    result.addElement(new Option(
      "\tWhether to use TAB as separator instead of comma.\n"
        + "\t(default: comma)", "use-tab", 0, "-use-tab"));

    result.addAll(Collections.list(super.listOptions()));

    return result.elements();
  }

  /**
   * Sets the OptionHandler's options using the given list. All options will be
   * set (or reset) during this call (i.e. incremental setting of options is not
   * possible).
   * 
   * @param options the list of options as an array of strings
   * @throws Exception if an option is not supported
   */
  @Override
  public void setOptions(String[] options) throws Exception {
    setUseTab(Utils.getFlag("use-tab", options));
    super.setOptions(options);
  }

  /**
   * Gets the current option settings for the OptionHandler.
   * 
   * @return the list of current option settings as an array of strings
   */
  @Override
  public String[] getOptions() {
    Vector result = new Vector();

    if (getUseTab()) {
      result.add("-use-tab");
    }

    Collections.addAll(result, super.getOptions());

    return result.toArray(new String[result.size()]);
  }

  /**
   * Sets whether to use tab instead of comma as separator.
   * 
   * @param value true if tab is to be used
   */
  public void setUseTab(boolean value) {
    if (value) {
      m_Delimiter = "\t";
    } else {
      m_Delimiter = ",";
    }
  }

  /**
   * Returns whether tab is used as separator.
   * 
   * @return true if tab is used instead of comma
   */
  public boolean getUseTab() {
    return m_Delimiter.equals("\t");
  }

  /**
   * Returns the tip text for this property.
   * 
   * @return tip text for this property suitable for displaying in the GUI
   */
  public String useTabTipText() {
    return "Whether to use TAB instead of COMMA as column separator.";
  }

  /**
   * Performs the actual printing of the header.
   */
  @Override
  protected void doPrintHeader() {
    if (m_Header.classAttribute().isNominal()) {
      if (m_OutputDistribution) {
        append("inst#" + m_Delimiter + "actual" + m_Delimiter + "predicted"
          + m_Delimiter + "error" + m_Delimiter + "distribution");
        for (int i = 1; i < m_Header.classAttribute().numValues(); i++) {
          append(m_Delimiter);
        }
      } else {
        append("inst#" + m_Delimiter + "actual" + m_Delimiter + "predicted"
          + m_Delimiter + "error" + m_Delimiter + "prediction");
      }
    } else {
      append("inst#" + m_Delimiter + "actual" + m_Delimiter + "predicted"
        + m_Delimiter + "error");
    }

    if (m_Attributes != null) {
      append(m_Delimiter);
      boolean first = true;
      for (int i = 0; i < m_Header.numAttributes(); i++) {
        if (i == m_Header.classIndex()) {
          continue;
        }

        if (m_Attributes.isInRange(i)) {
          if (!first) {
            append(m_Delimiter);
          }
          append(m_Header.attribute(i).name());
          first = false;
        }
      }
    }

    append("\n");
  }

  /**
   * Builds a string listing the attribute values in a specified range of
   * indices, separated by commas and enclosed in brackets.
   * 
   * @param instance the instance to print the values from
   * @return a string listing values of the attributes in the range
   */
  protected String attributeValuesString(Instance instance) {
    StringBuffer text = new StringBuffer();
    if (m_Attributes != null) {
      m_Attributes.setUpper(instance.numAttributes() - 1);
      boolean first = true;
      for (int i = 0; i < instance.numAttributes(); i++) {
        if (m_Attributes.isInRange(i) && i != instance.classIndex()) {
          if (!first) {
            text.append(m_Delimiter);
          }
          text.append(instance.toString(i));
          first = false;
        }
      }
    }
    return text.toString();
  }

  /**
   * Store the prediction made by the classifier as a string.
   * 
   * @param dist the distribution to use
   * @param inst the instance to generate text from
   * @param index the index in the dataset
   * @throws Exception if something goes wrong
   */
  @Override
  protected void doPrintClassification(double[] dist, Instance inst, int index)
    throws Exception {
    int prec = m_NumDecimals;

    Instance withMissing = (Instance) inst.copy();
    withMissing.setDataset(inst.dataset());

    double predValue = 0;
    if (Utils.sum(dist) == 0) {
      predValue = Utils.missingValue();
    } else {
      if (inst.classAttribute().isNominal()) {
        predValue = Utils.maxIndex(dist);
      } else {
        predValue = dist[0];
      }
    }

    // index
    append("" + (index + 1));

    if (inst.dataset().classAttribute().isNumeric()) {
      // actual
      if (inst.classIsMissing()) {
        append(m_Delimiter + "?");
      } else {
        append(m_Delimiter + Utils.doubleToString(inst.classValue(), prec));
      }
      // predicted
      if (Utils.isMissingValue(predValue)) {
        append(m_Delimiter + "?");
      } else {
        append(m_Delimiter + Utils.doubleToString(predValue, prec));
      }
      // error
      if (Utils.isMissingValue(predValue) || inst.classIsMissing()) {
        append(m_Delimiter + "?");
      } else {
        append(m_Delimiter
          + Utils.doubleToString(predValue - inst.classValue(), prec));
      }
    } else {
      // actual
      append(m_Delimiter + ((int) inst.classValue() + 1) + ":"
        + inst.toString(inst.classIndex()));
      // predicted
      if (Utils.isMissingValue(predValue)) {
        append(m_Delimiter + "?");
      } else {
        append(m_Delimiter + ((int) predValue + 1) + ":"
          + inst.dataset().classAttribute().value((int) predValue));
      }
      // error?
      if (!Utils.isMissingValue(predValue) && !inst.classIsMissing()
        && ((int) predValue + 1 != (int) inst.classValue() + 1)) {
        append(m_Delimiter + "+");
      } else {
        append(m_Delimiter + "");
      }
      // prediction/distribution
      if (m_OutputDistribution) {
        if (Utils.isMissingValue(predValue)) {
          append(m_Delimiter + "?");
        } else {
          append(m_Delimiter);
          for (int n = 0; n < dist.length; n++) {
            if (n > 0) {
              append(m_Delimiter);
            }
            if (n == (int) predValue) {
              append("*");
            }
            append(Utils.doubleToString(dist[n], prec));
          }
        }
      } else {
        if (Utils.isMissingValue(predValue)) {
          append(m_Delimiter + "?");
        } else {
          append(m_Delimiter
            + Utils.doubleToString(dist[(int) predValue], prec));
        }
      }
    }

    // attributes
    if (m_Attributes != null) {
      append(m_Delimiter + attributeValuesString(withMissing));
    }
    append("\n");
  }

  /**
   * Store the prediction made by the classifier as a string.
   * 
   * @param classifier the classifier to use
   * @param inst the instance to generate text from
   * @param index the index in the dataset
   * @throws Exception if something goes wrong
   */
  @Override
  protected void doPrintClassification(Classifier classifier, Instance inst,
    int index) throws Exception {

    double[] d = classifier.distributionForInstance(inst);
    doPrintClassification(d, inst, index);
  }

  /**
   * Does nothing.
   */
  @Override
  protected void doPrintFooter() {
  }
}