#region License Information
/* HeuristicLab
* Copyright (C) 2002-2012 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
*
* This file is part of HeuristicLab.
*
* HeuristicLab 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.
*
* HeuristicLab 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 HeuristicLab. If not, see .
*/
#endregion
using System.Collections;
using System.Collections.Generic;
using System.Linq;
using HeuristicLab.Common;
using HeuristicLab.Core;
using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
namespace HeuristicLab.Problems.DataAnalysis {
[StorableClass]
[Item("MedianThresholdCalculator", "")]
public class MedianThresholdCalculator : DiscriminantClassificationWeightCalculator {
public MedianThresholdCalculator()
: base() {
}
[StorableConstructor]
protected MedianThresholdCalculator(bool deserializing) : base(deserializing) { }
protected MedianThresholdCalculator(MedianThresholdCalculator original, Cloner cloner)
: base(original, cloner) {
}
public override IDeepCloneable Clone(Cloner cloner) {
return new MedianThresholdCalculator(this, cloner);
}
protected double[] threshold;
protected double[] classValues;
///
///
///
///
/// median instead of weights, because it doesn't use any weights
protected override IEnumerable DiscriminantCalculateWeights(IEnumerable discriminantSolutions) {
List> estimatedValues = new List>();
List> estimatedClassValues = new List>();
List solutionProblemData = discriminantSolutions.Select(sol => sol.ProblemData).ToList();
Dataset dataSet = solutionProblemData[0].Dataset;
IEnumerable rows = Enumerable.Range(0, dataSet.Rows);
foreach (var solution in discriminantSolutions) {
estimatedValues.Add(solution.Model.GetEstimatedValues(dataSet, rows).ToList());
estimatedClassValues.Add(solution.Model.GetEstimatedValues(dataSet, rows).ToList());
}
List median = new List();
List targetValues = dataSet.GetDoubleValues(solutionProblemData[0].TargetVariable).ToList();
IList curTrainingpoints = new List();
int removed = 0;
int count = targetValues.Count;
for (int point = 0; point < count; point++) {
curTrainingpoints.Clear();
for (int solutionPos = 0; solutionPos < solutionProblemData.Count; solutionPos++) {
if (PointInTraining(solutionProblemData[solutionPos], point)) {
curTrainingpoints.Add(estimatedValues[solutionPos][point]);
}
}
if (curTrainingpoints.Count > 0)
median.Add(GetMedian(curTrainingpoints.OrderBy(p => p).ToList()));
else {
//remove not used points
targetValues.RemoveAt(point - removed);
removed++;
}
}
AccuracyMaximizationThresholdCalculator.CalculateThresholds(solutionProblemData[0], median, targetValues, out classValues, out threshold);
return Enumerable.Repeat(1, discriminantSolutions.Count());
}
protected override double DiscriminantAggregateEstimatedClassValues(IDictionary estimatedClassValues, IDictionary estimatedValues) {
IList values = estimatedValues.Select(x => x.Value).ToList();
if (values.Count <= 0)
return double.NaN;
double median = GetMedian(values);
return GetClassValueToMedian(median);
}
private double GetClassValueToMedian(double median) {
double classValue = classValues.First();
for (int i = 0; i < classValues.Count(); i++) {
if (median > threshold[i])
classValue = classValues[i];
else
break;
}
return classValue;
}
protected override double GetDiscriminantConfidence(IEnumerable solutions, int index, double estimatedClassValue) {
// only works with binary classification
if (!classValues.Count().Equals(2))
return double.NaN;
Dataset dataset = solutions.First().ProblemData.Dataset;
IList values = solutions.Select(s => s.Model.GetEstimatedValues(dataset, Enumerable.Repeat(index, 1)).First()).ToList();
if (values.Count <= 0)
return double.NaN;
double median = GetMedian(values);
if (estimatedClassValue.Equals(classValues[0])) {
if (median < estimatedClassValue)
return 1;
else if (median >= threshold[1])
return 0;
else {
double distance = threshold[1] - classValues[0];
return (1 / distance) * (median - classValues[0]);
}
} else if (estimatedClassValue.Equals(classValues[1])) {
if (median > estimatedClassValue)
return 1;
else if (median <= threshold[1])
return 0;
else {
double distance = classValues[1] - threshold[1];
return (1 / distance) * (classValues[1] - median);
}
} else
return double.NaN;
}
private double GetMedian(IList estimatedValues) {
int count = estimatedValues.Count;
if (count % 2 == 0)
return 0.5 * (estimatedValues[count / 2 - 1] + estimatedValues[count / 2]);
else
return estimatedValues[count / 2];
}
}
}