package de.lmu.ifi.dbs.elki.math.linearalgebra.pca;

/*
 This file is part of ELKI:
 Environment for Developing KDD-Applications Supported by Index-Structures

 Copyright (C) 2015
 Ludwig-Maximilians-Universität München
 Lehr- und Forschungseinheit für Datenbanksysteme
 ELKI Development Team

 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU Affero 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 Affero General Public License for more details.

 You should have received a copy of the GNU Affero General Public License
 along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */

import java.util.ArrayList;
import java.util.List;

import de.lmu.ifi.dbs.elki.logging.Logging;
import de.lmu.ifi.dbs.elki.math.linearalgebra.EigenPair;
import de.lmu.ifi.dbs.elki.math.linearalgebra.SortedEigenPairs;
import de.lmu.ifi.dbs.elki.utilities.documentation.Description;
import de.lmu.ifi.dbs.elki.utilities.documentation.Title;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.AbstractParameterizer;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.OptionID;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.constraints.CommonConstraints;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameterization.Parameterization;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameters.DoubleParameter;

/**
 * The PercentageEigenPairFilter sorts the eigenpairs in descending order of
 * their eigenvalues and marks the first eigenpairs, whose sum of eigenvalues is
 * higher than the given percentage of the sum of all eigenvalues as strong
 * eigenpairs.
 * 
 * @author Elke Achtert
 * @since 0.2
 */
@Title("Percentage based Eigenpair filter")
@Description("Sorts the eigenpairs in decending order of their eigenvalues and returns the first eigenpairs, whose sum of eigenvalues is higher than the given percentage of the sum of all eigenvalues.")
public class PercentageEigenPairFilter implements EigenPairFilter {
  /**
   * The logger for this class.
   */
  private static final Logging LOG = Logging.getLogger(PercentageEigenPairFilter.class);

  /**
   * The default value for alpha.
   */
  public static final double DEFAULT_ALPHA = 0.85;

  /**
   * The threshold for strong eigenvectors: the strong eigenvectors explain a
   * portion of at least alpha of the total variance.
   */
  private double alpha;

  /**
   * Constructor.
   * 
   * @param alpha
   */
  public PercentageEigenPairFilter(double alpha) {
    super();
    this.alpha = alpha;
  }

  @Override
  public FilteredEigenPairs filter(SortedEigenPairs eigenPairs) {
    StringBuilder msg = new StringBuilder();
    if(LOG.isDebugging()) {
      msg.append("alpha = ").append(alpha);
      msg.append("\nsortedEigenPairs = ").append(eigenPairs);
    }

    // init strong and weak eigenpairs
    List<EigenPair> strongEigenPairs = new ArrayList<>();
    List<EigenPair> weakEigenPairs = new ArrayList<>();

    // determine sum of eigenvalues
    double totalSum = 0;
    for(int i = 0; i < eigenPairs.size(); i++) {
      EigenPair eigenPair = eigenPairs.getEigenPair(i);
      totalSum += eigenPair.getEigenvalue();
    }
    if(LOG.isDebugging()) {
      msg.append("\ntotalSum = ").append(totalSum);
    }

    // determine strong and weak eigenpairs
    double currSum = 0;
    boolean found = false;
    for(int i = 0; i < eigenPairs.size(); i++) {
      EigenPair eigenPair = eigenPairs.getEigenPair(i);
      currSum += eigenPair.getEigenvalue();
      if(currSum / totalSum >= alpha) {
        if(!found) {
          found = true;
          strongEigenPairs.add(eigenPair);
        }
        else {
          weakEigenPairs.add(eigenPair);
        }
      }
      else {
        strongEigenPairs.add(eigenPair);
      }
    }
    if(LOG.isDebugging()) {
      msg.append("\nstrong EigenPairs = ").append(strongEigenPairs);
      msg.append("\nweak EigenPairs = ").append(weakEigenPairs);
      LOG.debugFine(msg.toString());
    }

    return new FilteredEigenPairs(weakEigenPairs, strongEigenPairs);
  }

  /**
   * Parameterization class.
   * 
   * @author Erich Schubert
   * 
   * @apiviz.exclude
   */
  public static class Parameterizer extends AbstractParameterizer {
    /**
     * The threshold for 'strong' eigenvectors: the 'strong' eigenvectors explain
     * a portion of at least alpha of the total variance.
     * <p>
     * Default value: {@link #DEFAULT_ALPHA}
     * </p>
     * <p>
     * Key: {@code -pca.filter.alpha}
     * </p>
     */
    public static final OptionID ALPHA_ID = new OptionID("pca.filter.alpha", "The share (0.0 to 1.0) of variance that needs to be explained by the 'strong' eigenvectors." + "The filter class will choose the number of strong eigenvectors by this share.");
    /**
     * The threshold for strong eigenvectors: the strong eigenvectors explain a
     * portion of at least alpha of the total variance.
     */
    private double alpha;

    @Override
    protected void makeOptions(Parameterization config) {
      super.makeOptions(config);
      DoubleParameter alphaP = new DoubleParameter(ALPHA_ID, DEFAULT_ALPHA);
      alphaP.addConstraint(CommonConstraints.GREATER_THAN_ZERO_DOUBLE);
      alphaP.addConstraint(CommonConstraints.LESS_THAN_ONE_DOUBLE);
      if(config.grab(alphaP)) {
        alpha = alphaP.doubleValue();
      }
    }

    @Override
    protected PercentageEigenPairFilter makeInstance() {
      return new PercentageEigenPairFilter(alpha);
    }
  }
}