weka.classifiers.functions.SimpleLinearRegression Maven / Gradle / Ivy

Go to download
/*
 *   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 .
 */

/*
 *    SimpleLinearRegression.java
 *    Copyright (C) 2002-2012 University of Waikato, Hamilton, New Zealand
 *
 */

package weka.classifiers.functions;

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

import weka.classifiers.AbstractClassifier;
import weka.classifiers.evaluation.RegressionAnalysis;
import weka.core.Attribute;
import weka.core.Capabilities;
import weka.core.Capabilities.Capability;
import weka.core.Instance;
import weka.core.Instances;
import weka.core.Option;
import weka.core.RevisionUtils;
import weka.core.Utils;
import weka.core.WeightedInstancesHandler;

/**
  
 * Learns a simple linear regression model. Picks the
 * attribute that results in the lowest squared error. Can only deal with
 * numeric attributes.
 * 
 
 * 
  
 * Valid options are:
 * 

 * 
 * 
 * -additional-stats
 *  Output additional statistics.
 * 
 * 
 *  * -output-debug-info
 *  If set, classifier is run in debug mode and
 *  may output additional info to the console
 * 
 * 
 *  * -do-not-check-capabilities
 *  If set, classifier capabilities are not checked before classifier is built
 *  (use with caution).
 * 
 * 
 
 * 
 * @author Eibe Frank ([email protected])
 * @version $Revision: 11130 $
 */
public class SimpleLinearRegression extends AbstractClassifier implements
  WeightedInstancesHandler {

  /** for serialization */
  static final long serialVersionUID = 1679336022895414137L;

  /** The chosen attribute */
  private Attribute m_attribute;

  /** The index of the chosen attribute */
  private int m_attributeIndex;

  /** The slope */
  private double m_slope;

  /** The intercept */
  private double m_intercept;

  /** The class mean for missing values */
  private double m_classMeanForMissing;

  /**
   * Whether to output additional statistics such as std. dev. of coefficients
   * and t-stats
   */
  protected boolean m_outputAdditionalStats;

  /** Degrees of freedom, used in statistical calculations */
  private int m_df;

  /** standard error of the slope */
  private double m_seSlope = Double.NaN;

  /** standard error of the intercept */
  private double m_seIntercept = Double.NaN;

  /** t-statistic of the slope */
  private double m_tstatSlope = Double.NaN;

  /** t-statistic of the intercept */
  private double m_tstatIntercept = Double.NaN;

  /** R^2 value for the regression */
  private double m_rsquared = Double.NaN;

  /** Adjusted R^2 value for the regression */
  private double m_rsquaredAdj = Double.NaN;

  /** F-statistic for the regression */
  private double m_fstat = Double.NaN;

  /** If true, suppress error message if no useful attribute was found */
  private boolean m_suppressErrorMessage = false;

  /**
   * Returns a string describing this classifier
   * 
   * @return a description of the classifier suitable for displaying in the
   *         explorer/experimenter gui
   */
  public String globalInfo() {
    return "Learns a simple linear regression model. "
      + "Picks the attribute that results in the lowest squared error. "
      + "Can only deal with numeric attributes.";
  }

  /**
   * Returns an enumeration describing the available options.
   * 
   * @return an enumeration of all the available options.
   */
  @Override
  public Enumeration