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

Show more of this group Show more artifacts with this name
Show all versions of weka-dev Show documentation
The Waikato Environment for Knowledge Analysis (WEKA), a machine learning workbench. This version represents the developer version, the "bleeding edge" of development, you could say. New functionality gets added to this version.
There is a newer version: 3.9.6
Show newest version
/*
 *   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 .
 */

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

package weka.classifiers.evaluation.output.prediction;

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

/**
 
 * Outputs the predictions in HTML.
 * 
 
 *
 
 * 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)
 * 
 
 *
 * @author  fracpete (fracpete at waikato dot ac dot nz)
 * @version $Revision: 8937 $
 */
public class HTML
  extends AbstractOutput {
  
  /** for serialization. */
  private static final long serialVersionUID = 7241252244954353300L;

  /**
   * Returns a string describing the output generator.
   * 
   * @return 		a description suitable for
   * 			displaying in the GUI
   */
  public String globalInfo() {
    return "Outputs the predictions in HTML.";
  }
  
  /**
   * Returns a short display text, to be used in comboboxes.
   * 
   * @return 		a short display text
   */
  public String getDisplay() {
    return "HTML";
  }

  /**
   * Replaces certain characters with their HTML entities.
   * 
   * @param s		the string to process
   * @return		the processed string
   */
  protected String sanitize(String s) {
    String 	result;
    
    result = s;
    result = result.replaceAll("&", "&");
    result = result.replaceAll("<", "<");
    result = result.replaceAll(">", ">");
    result = result.replaceAll("\"", """);
    
    return result;
  }
  
  /**
   * Performs the actual printing of the header.
   */
  protected void doPrintHeader() {
    append("\n");
    append("\n");
    append("Predictions for dataset " + sanitize(m_Header.relationName()) + "\n");
    append("\n");
    append("\n");
    append("\n");
    append("Predictions for dataset " + sanitize(m_Header.relationName()) + "\n");
    append("\n");
    append("\n");
    if (m_Header.classAttribute().isNominal())
      if (m_OutputDistribution)
	append("");
      else
	append("");
    else
      append("");
    
    if (m_Attributes != null) {
      append("");
    }
    
    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) {
      boolean firstOutput = true;
      m_Attributes.setUpper(instance.numAttributes() - 1);
      for (int i=0; i");
	  if (m_Header.attribute(i).isNumeric())
	    text.append("");
    }
    return text.toString();
  }
  
  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("");
    append("");

    if (inst.dataset().classAttribute().isNumeric()) {
      // actual
      if (inst.classIsMissing())
        append("");
      else
        append("");
      // predicted
      if (Utils.isMissingValue(predValue))
        append("");
      else
        append("");
      // error
      if (Utils.isMissingValue(predValue) || inst.classIsMissing())
        append("");
      else
        append("");
    } else {
      // actual
      append("");
      // predicted
      if (Utils.isMissingValue(predValue))
        append("");
      else
        append("");
      // error?
      if (!Utils.isMissingValue(predValue) && !inst.classIsMissing() && ((int) predValue+1 != (int) inst.classValue()+1))
        append("");
      else
        append("");
      // prediction/distribution
      if (m_OutputDistribution) {
        if (Utils.isMissingValue(predValue)) {
          append("");
        }
        else {
          append("");
        }
      }
      else {
        if (Utils.isMissingValue(predValue))
          append("");
        else
          append("");
      }
    }

    // attributes
    append(attributeValuesString(withMissing) + "\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
   */
  protected void doPrintClassification(Classifier classifier, Instance inst, int index) throws Exception {
    
    double[] d = classifier.distributionForInstance(inst);
    doPrintClassification(d, inst, index);    
  }
  
  /**
   * Does nothing.
   */
  protected void doPrintFooter() {
    append("inst# actual predicted error distribution inst# actual predicted error prediction inst# actual predicted error ");
      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(" ");
          append(sanitize(m_Header.attribute(i).name()));
          first = false;
        }
      }
      append("
");
	  else
	    text.append(" ");
	  text.append(sanitize(instance.toString(i)));
	  firstOutput = false;
	}
      if (!firstOutput)
	text.append("
" + (index+1) + " " + "?" + " " + Utils.doubleToString(inst.classValue(), prec) + " " + "?" + " " + Utils.doubleToString(predValue, prec) + " " + "?" + " " + Utils.doubleToString(predValue - inst.classValue(), prec) + " " + ((int) inst.classValue()+1) + ":" + sanitize(inst.toString(inst.classIndex())) + " " + "?" + " " + ((int) predValue+1) + ":" + sanitize(inst.dataset().classAttribute().value((int)predValue)) + " " + "+" + " " + " " + " " + "?" + " ");
          for (int n = 0; n < dist.length; n++) {
            if (n > 0)
              append(" ");
            if (n == (int) predValue)
              append("*");
            append(Utils.doubleToString(dist[n], prec));
          }
          append(" " + "?" + " " + Utils.doubleToString(dist[(int)predValue], prec) + "\n");
    append("\n");
    append("\n");
    append("\n");
  }
}