[645] | 1 | #region License Information
|
---|
| 2 | /* HeuristicLab
|
---|
| 3 | * Copyright (C) 2002-2008 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
|
---|
| 4 | *
|
---|
| 5 | * This file is part of HeuristicLab.
|
---|
| 6 | *
|
---|
| 7 | * HeuristicLab is free software: you can redistribute it and/or modify
|
---|
| 8 | * it under the terms of the GNU General Public License as published by
|
---|
| 9 | * the Free Software Foundation, either version 3 of the License, or
|
---|
| 10 | * (at your option) any later version.
|
---|
| 11 | *
|
---|
| 12 | * HeuristicLab is distributed in the hope that it will be useful,
|
---|
| 13 | * but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
| 14 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
| 15 | * GNU General Public License for more details.
|
---|
| 16 | *
|
---|
| 17 | * You should have received a copy of the GNU General Public License
|
---|
| 18 | * along with HeuristicLab. If not, see <http://www.gnu.org/licenses/>.
|
---|
| 19 | */
|
---|
| 20 | #endregion
|
---|
| 21 |
|
---|
| 22 | using System;
|
---|
| 23 | using HeuristicLab.Core;
|
---|
| 24 | using HeuristicLab.Data;
|
---|
[702] | 25 | using HeuristicLab.DataAnalysis;
|
---|
[2351] | 26 | using System.Linq;
|
---|
| 27 | using HeuristicLab.Common;
|
---|
[645] | 28 |
|
---|
[2351] | 29 | namespace HeuristicLab.Modeling {
|
---|
| 30 | public class SimpleAccuracyEvaluator : SimpleEvaluatorBase {
|
---|
| 31 | public override string OutputVariableName {
|
---|
| 32 | get {
|
---|
| 33 | return "Accuracy";
|
---|
| 34 | }
|
---|
| 35 | }
|
---|
[645] | 36 | public override string Description {
|
---|
| 37 | get {
|
---|
| 38 | return @"Calculates the total accuracy of the model (ratio of correctly classified instances to total number of instances) given a model and the list of possible target class values.";
|
---|
| 39 | }
|
---|
| 40 | }
|
---|
| 41 |
|
---|
[2351] | 42 | public override double Evaluate(double[,] values) {
|
---|
| 43 | return Calculate(values);
|
---|
[645] | 44 | }
|
---|
| 45 |
|
---|
[2351] | 46 | public static double Calculate(double[,] values) {
|
---|
| 47 | int nSamples = values.GetLength(0);
|
---|
| 48 | int nCorrect = 0;
|
---|
| 49 | double[] classes = CalculateTargetClasses(values);
|
---|
| 50 | double[] thresholds = CalculateThresholds(classes);
|
---|
[645] | 51 |
|
---|
[2351] | 52 | for (int sample = 0; sample < nSamples; sample++) {
|
---|
[2357] | 53 | double est = values[sample, ESTIMATION_INDEX];
|
---|
| 54 | double origClass = values[sample, ORIGINAL_INDEX];
|
---|
[645] | 55 | double estClass = double.NaN;
|
---|
| 56 | // if estimation is lower than the smallest threshold value -> estimated class is the lower class
|
---|
[712] | 57 | if (est < thresholds[0]) estClass = classes[0];
|
---|
[645] | 58 | // if estimation is larger (or equal) than the largest threshold value -> estimated class is the upper class
|
---|
[712] | 59 | else if (est >= thresholds[thresholds.Length - 1]) estClass = classes[classes.Length - 1];
|
---|
[645] | 60 | else {
|
---|
| 61 | // otherwise the estimated class is the class which upper threshold is larger than the estimated value
|
---|
[712] | 62 | for (int k = 0; k < thresholds.Length; k++) {
|
---|
| 63 | if (thresholds[k] > est) {
|
---|
[702] | 64 | estClass = classes[k];
|
---|
[645] | 65 | break;
|
---|
| 66 | }
|
---|
| 67 | }
|
---|
| 68 | }
|
---|
[2351] | 69 | if (estClass.IsAlmost(origClass)) nCorrect++;
|
---|
[645] | 70 | }
|
---|
[2351] | 71 | return nCorrect / (double)nSamples;
|
---|
[645] | 72 | }
|
---|
[2351] | 73 |
|
---|
| 74 | public static double[] CalculateTargetClasses(double[,] values) {
|
---|
| 75 | int n = values.GetLength(0);
|
---|
| 76 | double[] original = new double[n];
|
---|
[2357] | 77 | for (int i = 0; i < n; i++) original[i] = values[i, ORIGINAL_INDEX];
|
---|
[2351] | 78 | return original.OrderBy(x => x).Distinct().ToArray();
|
---|
| 79 | }
|
---|
| 80 |
|
---|
| 81 | public static double[] CalculateThresholds(double[] targetClasses) {
|
---|
| 82 | double[] thresholds = new double[targetClasses.Length - 1];
|
---|
| 83 | for (int i = 1; i < targetClasses.Length; i++) {
|
---|
| 84 | thresholds[i - 1] = (targetClasses[i - 1] + targetClasses[i]) / 2.0;
|
---|
| 85 | }
|
---|
| 86 | return thresholds;
|
---|
| 87 | }
|
---|
[645] | 88 | }
|
---|
| 89 | }
|
---|