[15846] | 1 | #region License Information
|
---|
| 2 | /* HeuristicLab
|
---|
| 3 | * Copyright (C) 2002-2018 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.Collections.Generic;
|
---|
| 23 | using System.Linq;
|
---|
| 24 | using HeuristicLab.Common;
|
---|
| 25 | using HeuristicLab.Core;
|
---|
| 26 | using HeuristicLab.Data;
|
---|
| 27 | using HeuristicLab.Parameters;
|
---|
| 28 | using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
|
---|
| 29 |
|
---|
| 30 | namespace HeuristicLab.Problems.DataAnalysis {
|
---|
| 31 | [Item("Z-Score Normalization", "Z-Score normalization transformation to standardize (target_mu = 0, target_sigma = 1) the values")]
|
---|
| 32 | [StorableClass]
|
---|
| 33 | public class ZNormalizationTransformation : Transformation<double> {
|
---|
| 34 | #region Parameters
|
---|
| 35 | private IFixedValueParameter<DoubleValue> TargetMeanParameter {
|
---|
| 36 | get { return (IFixedValueParameter<DoubleValue>)Parameters["Target Mean"]; }
|
---|
| 37 | }
|
---|
| 38 | private IFixedValueParameter<DoubleValue> TargetStandardDeviationParameter {
|
---|
| 39 | get { return (IFixedValueParameter<DoubleValue>)Parameters["Target Standard Deviation"]; }
|
---|
| 40 | }
|
---|
| 41 | private IFixedValueParameter<DoubleValue> OriginalMeanParameter {
|
---|
| 42 | get { return (IFixedValueParameter<DoubleValue>)Parameters["Original Mean"]; }
|
---|
| 43 | }
|
---|
| 44 | private IFixedValueParameter<DoubleValue> OriginalStandardDeviationParameter {
|
---|
| 45 | get { return (IFixedValueParameter<DoubleValue>)Parameters["Original Standard Deviation"]; }
|
---|
| 46 | }
|
---|
| 47 | #endregion
|
---|
| 48 |
|
---|
| 49 | #region Properties
|
---|
| 50 | public double TargetMean {
|
---|
| 51 | get { return TargetMeanParameter.Value.Value; }
|
---|
| 52 | set { TargetMeanParameter.Value.Value = value; }
|
---|
| 53 | }
|
---|
| 54 | public double TargetStandardDeviation {
|
---|
| 55 | get { return TargetStandardDeviationParameter.Value.Value; }
|
---|
| 56 | set { TargetStandardDeviationParameter.Value.Value = value; }
|
---|
| 57 | }
|
---|
| 58 | public double OriginalMean {
|
---|
| 59 | get { return OriginalMeanParameter.Value.Value; }
|
---|
| 60 | set { OriginalMeanParameter.Value.Value = value; }
|
---|
| 61 | }
|
---|
| 62 | public double OriginalStandardDeviation {
|
---|
| 63 | get { return OriginalStandardDeviationParameter.Value.Value; }
|
---|
| 64 | set { OriginalStandardDeviationParameter.Value.Value = value; }
|
---|
| 65 | }
|
---|
| 66 | #endregion
|
---|
| 67 |
|
---|
| 68 | #region Constructor, Cloning & Persistence
|
---|
| 69 | public ZNormalizationTransformation()
|
---|
| 70 | : base() {
|
---|
| 71 | Parameters.Add(new FixedValueParameter<DoubleValue>("Target Mean", new DoubleValue(0)));
|
---|
| 72 | Parameters.Add(new FixedValueParameter<DoubleValue>("Target Standard Deviation", new DoubleValue(1)));
|
---|
| 73 | Parameters.Add(new FixedValueParameter<DoubleValue>("Original Mean", new DoubleValue(double.NaN)) { Hidden = true });
|
---|
| 74 | Parameters.Add(new FixedValueParameter<DoubleValue>("Original Standard Deviation", new DoubleValue(double.NaN)) { Hidden = true });
|
---|
| 75 | }
|
---|
| 76 |
|
---|
| 77 | protected ZNormalizationTransformation(ZNormalizationTransformation original, Cloner cloner)
|
---|
| 78 | : base(original, cloner) {
|
---|
| 79 | }
|
---|
| 80 | public override IDeepCloneable Clone(Cloner cloner) {
|
---|
| 81 | return new ZNormalizationTransformation(this, cloner);
|
---|
| 82 | }
|
---|
| 83 |
|
---|
| 84 | [StorableConstructor]
|
---|
| 85 | protected ZNormalizationTransformation(bool deserializing)
|
---|
| 86 | : base(deserializing) {
|
---|
| 87 | }
|
---|
| 88 | #endregion
|
---|
| 89 |
|
---|
| 90 | public override bool Check(IEnumerable<double> data, out string errorMessage) {
|
---|
| 91 | if (data.StandardDeviationPop().IsAlmost(0.0)) {
|
---|
| 92 | errorMessage = "Z-Score Normalization cannot be applied for data with a standard deviation of zero.";
|
---|
| 93 | return false;
|
---|
| 94 | }
|
---|
| 95 | return base.Check(data, out errorMessage);
|
---|
| 96 | }
|
---|
| 97 |
|
---|
| 98 | public override void Configure(IEnumerable<double> data) {
|
---|
| 99 | OriginalMean = data.Average();
|
---|
| 100 | OriginalStandardDeviation = data.StandardDeviationPop();
|
---|
| 101 | base.Configure(data);
|
---|
| 102 | }
|
---|
| 103 |
|
---|
| 104 | public override IEnumerable<double> Apply(IEnumerable<double> data) {
|
---|
| 105 | if (double.IsNaN(OriginalMean) || double.IsNaN(OriginalStandardDeviation))
|
---|
| 106 | Configure(data);
|
---|
| 107 |
|
---|
| 108 | return Apply(data, TargetMean, TargetStandardDeviation, OriginalMean, OriginalStandardDeviation);
|
---|
| 109 | }
|
---|
| 110 |
|
---|
| 111 | public override IEnumerable<double> InverseApply(IEnumerable<double> data) {
|
---|
| 112 | return InverseApply(data, TargetMean, TargetStandardDeviation, OriginalMean, OriginalStandardDeviation);
|
---|
| 113 | }
|
---|
| 114 |
|
---|
| 115 | public static IEnumerable<double> Apply(IEnumerable<double> data, double targetMean, double targetStandardDeviation, double originalMean = double.NaN, double originalStandardDeviation = double.NaN) {
|
---|
| 116 | if (double.IsNaN(originalMean)) originalMean = data.Average();
|
---|
| 117 | if (double.IsNaN(originalStandardDeviation)) originalStandardDeviation = data.StandardDeviationPop();
|
---|
| 118 |
|
---|
| 119 | return data
|
---|
| 120 | .Select(x => (x - originalMean) / originalStandardDeviation) // standardize (0, 1)
|
---|
| 121 | .Select(x => x * targetStandardDeviation + targetMean);
|
---|
| 122 | }
|
---|
| 123 |
|
---|
| 124 | public static IEnumerable<double> InverseApply(IEnumerable<double> data, double targetMean, double targetStandardDeviation, double originalMean, double originalStandardDeviation) {
|
---|
| 125 | return Apply(data, originalMean, originalStandardDeviation, targetMean, targetStandardDeviation);
|
---|
| 126 | }
|
---|
| 127 | }
|
---|
| 128 | } |
---|