[5540] | 1 | #region License Information
|
---|
| 2 | /* HeuristicLab
|
---|
[15583] | 3 | * Copyright (C) 2002-2018 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
|
---|
[5540] | 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 System.Collections.Generic;
|
---|
| 24 | using System.Linq;
|
---|
[10540] | 25 | using System.Text;
|
---|
[5586] | 26 | using HeuristicLab.Collections;
|
---|
[5540] | 27 | using HeuristicLab.Common;
|
---|
| 28 | using HeuristicLab.Core;
|
---|
[5586] | 29 | using HeuristicLab.Data;
|
---|
| 30 | using HeuristicLab.Parameters;
|
---|
[5540] | 31 | using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
|
---|
| 32 |
|
---|
| 33 | namespace HeuristicLab.Problems.DataAnalysis {
|
---|
| 34 | [StorableClass]
|
---|
[5586] | 35 | public abstract class DataAnalysisProblemData : ParameterizedNamedItem, IDataAnalysisProblemData {
|
---|
[6666] | 36 | protected const string DatasetParameterName = "Dataset";
|
---|
| 37 | protected const string InputVariablesParameterName = "InputVariables";
|
---|
| 38 | protected const string TrainingPartitionParameterName = "TrainingPartition";
|
---|
| 39 | protected const string TestPartitionParameterName = "TestPartition";
|
---|
[11114] | 40 | protected const string TransformationsParameterName = "Transformations";
|
---|
[5586] | 41 |
|
---|
| 42 | #region parameter properites
|
---|
[14507] | 43 | //mkommend: inserted parameter caching due to performance reasons
|
---|
| 44 | private IFixedValueParameter<Dataset> datasetParameter;
|
---|
[5601] | 45 | public IFixedValueParameter<Dataset> DatasetParameter {
|
---|
[14507] | 46 | get {
|
---|
| 47 | if (datasetParameter == null) datasetParameter = (IFixedValueParameter<Dataset>)Parameters[DatasetParameterName];
|
---|
| 48 | return datasetParameter;
|
---|
| 49 | }
|
---|
[5586] | 50 | }
|
---|
[14507] | 51 |
|
---|
| 52 | private IFixedValueParameter<ReadOnlyCheckedItemList<StringValue>> inputVariablesParameter;
|
---|
[5847] | 53 | public IFixedValueParameter<ReadOnlyCheckedItemList<StringValue>> InputVariablesParameter {
|
---|
[14507] | 54 | get {
|
---|
| 55 | if (inputVariablesParameter == null) inputVariablesParameter = (IFixedValueParameter<ReadOnlyCheckedItemList<StringValue>>)Parameters[InputVariablesParameterName];
|
---|
| 56 | return inputVariablesParameter;
|
---|
| 57 | }
|
---|
[5586] | 58 | }
|
---|
[14507] | 59 |
|
---|
| 60 | private IFixedValueParameter<IntRange> trainingPartitionParameter;
|
---|
[5759] | 61 | public IFixedValueParameter<IntRange> TrainingPartitionParameter {
|
---|
[14507] | 62 | get {
|
---|
| 63 | if (trainingPartitionParameter == null) trainingPartitionParameter = (IFixedValueParameter<IntRange>)Parameters[TrainingPartitionParameterName];
|
---|
| 64 | return trainingPartitionParameter;
|
---|
| 65 | }
|
---|
[5586] | 66 | }
|
---|
[14507] | 67 |
|
---|
| 68 | private IFixedValueParameter<IntRange> testPartitionParameter;
|
---|
[5759] | 69 | public IFixedValueParameter<IntRange> TestPartitionParameter {
|
---|
[14507] | 70 | get {
|
---|
| 71 | if (testPartitionParameter == null) testPartitionParameter = (IFixedValueParameter<IntRange>)Parameters[TestPartitionParameterName];
|
---|
| 72 | return testPartitionParameter;
|
---|
| 73 | }
|
---|
[5586] | 74 | }
|
---|
[14507] | 75 |
|
---|
[11114] | 76 | public IFixedValueParameter<ReadOnlyItemList<ITransformation>> TransformationsParameter {
|
---|
| 77 | get { return (IFixedValueParameter<ReadOnlyItemList<ITransformation>>)Parameters[TransformationsParameterName]; }
|
---|
| 78 | }
|
---|
[5586] | 79 | #endregion
|
---|
| 80 |
|
---|
[6666] | 81 | #region properties
|
---|
| 82 | protected bool isEmpty = false;
|
---|
| 83 | public bool IsEmpty {
|
---|
| 84 | get { return isEmpty; }
|
---|
| 85 | }
|
---|
[12509] | 86 | public IDataset Dataset {
|
---|
[5586] | 87 | get { return DatasetParameter.Value; }
|
---|
[5540] | 88 | }
|
---|
[5649] | 89 | public ICheckedItemList<StringValue> InputVariables {
|
---|
[5586] | 90 | get { return InputVariablesParameter.Value; }
|
---|
| 91 | }
|
---|
[5554] | 92 | public IEnumerable<string> AllowedInputVariables {
|
---|
[5649] | 93 | get { return InputVariables.CheckedItems.Select(x => x.Value.Value); }
|
---|
[5540] | 94 | }
|
---|
| 95 |
|
---|
[14843] | 96 | public double[,] AllowedInputsTrainingValues {
|
---|
| 97 | get { return Dataset.ToArray(AllowedInputVariables, TrainingIndices); }
|
---|
| 98 | }
|
---|
| 99 |
|
---|
| 100 | public double[,] AllowedInputsTestValues { get { return Dataset.ToArray(AllowedInputVariables, TestIndices); } }
|
---|
[5759] | 101 | public IntRange TrainingPartition {
|
---|
| 102 | get { return TrainingPartitionParameter.Value; }
|
---|
[5540] | 103 | }
|
---|
[5759] | 104 | public IntRange TestPartition {
|
---|
| 105 | get { return TestPartitionParameter.Value; }
|
---|
[5540] | 106 | }
|
---|
[5554] | 107 |
|
---|
[13766] | 108 | public virtual IEnumerable<int> AllIndices {
|
---|
| 109 | get { return Enumerable.Range(0, Dataset.Rows); }
|
---|
| 110 | }
|
---|
[8139] | 111 | public virtual IEnumerable<int> TrainingIndices {
|
---|
[5554] | 112 | get {
|
---|
[7265] | 113 | return Enumerable.Range(TrainingPartition.Start, Math.Max(0, TrainingPartition.End - TrainingPartition.Start))
|
---|
[6672] | 114 | .Where(IsTrainingSample);
|
---|
[5540] | 115 | }
|
---|
| 116 | }
|
---|
[8139] | 117 | public virtual IEnumerable<int> TestIndices {
|
---|
[5554] | 118 | get {
|
---|
[7265] | 119 | return Enumerable.Range(TestPartition.Start, Math.Max(0, TestPartition.End - TestPartition.Start))
|
---|
[6672] | 120 | .Where(IsTestSample);
|
---|
[5554] | 121 | }
|
---|
| 122 | }
|
---|
[6672] | 123 |
|
---|
[11114] | 124 | public IEnumerable<ITransformation> Transformations {
|
---|
| 125 | get { return TransformationsParameter.Value; }
|
---|
| 126 | }
|
---|
| 127 |
|
---|
[6672] | 128 | public virtual bool IsTrainingSample(int index) {
|
---|
| 129 | return index >= 0 && index < Dataset.Rows &&
|
---|
[14507] | 130 | TrainingPartition.Start <= index && index < TrainingPartition.End &&
|
---|
| 131 | (index < TestPartition.Start || TestPartition.End <= index);
|
---|
[6672] | 132 | }
|
---|
| 133 |
|
---|
| 134 | public virtual bool IsTestSample(int index) {
|
---|
| 135 | return index >= 0 && index < Dataset.Rows &&
|
---|
| 136 | TestPartition.Start <= index && index < TestPartition.End;
|
---|
| 137 | }
|
---|
[5540] | 138 | #endregion
|
---|
| 139 |
|
---|
[6236] | 140 | protected DataAnalysisProblemData(DataAnalysisProblemData original, Cloner cloner)
|
---|
| 141 | : base(original, cloner) {
|
---|
[6666] | 142 | isEmpty = original.isEmpty;
|
---|
[6236] | 143 | RegisterEventHandlers();
|
---|
| 144 | }
|
---|
[5540] | 145 | [StorableConstructor]
|
---|
| 146 | protected DataAnalysisProblemData(bool deserializing) : base(deserializing) { }
|
---|
[8542] | 147 |
|
---|
[6581] | 148 | [StorableHook(HookType.AfterDeserialization)]
|
---|
| 149 | private void AfterDeserialization() {
|
---|
[11114] | 150 | if (!Parameters.ContainsKey(TransformationsParameterName)) {
|
---|
| 151 | Parameters.Add(new FixedValueParameter<ReadOnlyItemList<ITransformation>>(TransformationsParameterName, "", new ItemList<ITransformation>().AsReadOnly()));
|
---|
| 152 | TransformationsParameter.Hidden = true;
|
---|
| 153 | }
|
---|
[6581] | 154 | RegisterEventHandlers();
|
---|
| 155 | }
|
---|
[5559] | 156 |
|
---|
[12509] | 157 | protected DataAnalysisProblemData(IDataset dataset, IEnumerable<string> allowedInputVariables, IEnumerable<ITransformation> transformations = null) {
|
---|
[5559] | 158 | if (dataset == null) throw new ArgumentNullException("The dataset must not be null.");
|
---|
[14826] | 159 | if (allowedInputVariables == null) throw new ArgumentNullException("The allowed input variables must not be null.");
|
---|
[5559] | 160 |
|
---|
[14826] | 161 | if (allowedInputVariables.Except(dataset.DoubleVariables).Except(dataset.StringVariables).Any())
|
---|
| 162 | throw new ArgumentException("All allowed input variables must be present in the dataset and of type double or string.");
|
---|
[5554] | 163 |
|
---|
[14826] | 164 | var variables = dataset.VariableNames.Where(variable => dataset.VariableHasType<double>(variable) || dataset.VariableHasType<string>(variable));
|
---|
[16059] | 165 | var inputVariables = new CheckedItemList<StringValue>(variables.Select(x => new StringValue(x).AsReadOnly()));
|
---|
[5586] | 166 | foreach (StringValue x in inputVariables)
|
---|
| 167 | inputVariables.SetItemCheckedState(x, allowedInputVariables.Contains(x.Value));
|
---|
[5540] | 168 |
|
---|
[5586] | 169 | int trainingPartitionStart = 0;
|
---|
| 170 | int trainingPartitionEnd = dataset.Rows / 2;
|
---|
| 171 | int testPartitionStart = dataset.Rows / 2;
|
---|
| 172 | int testPartitionEnd = dataset.Rows;
|
---|
[5540] | 173 |
|
---|
[11156] | 174 | var transformationsList = new ItemList<ITransformation>(transformations ?? Enumerable.Empty<ITransformation>());
|
---|
[11114] | 175 |
|
---|
[12509] | 176 | Parameters.Add(new FixedValueParameter<Dataset>(DatasetParameterName, "", (Dataset)dataset));
|
---|
[5847] | 177 | Parameters.Add(new FixedValueParameter<ReadOnlyCheckedItemList<StringValue>>(InputVariablesParameterName, "", inputVariables.AsReadOnly()));
|
---|
[5759] | 178 | Parameters.Add(new FixedValueParameter<IntRange>(TrainingPartitionParameterName, "", new IntRange(trainingPartitionStart, trainingPartitionEnd)));
|
---|
| 179 | Parameters.Add(new FixedValueParameter<IntRange>(TestPartitionParameterName, "", new IntRange(testPartitionStart, testPartitionEnd)));
|
---|
[11114] | 180 | Parameters.Add(new FixedValueParameter<ReadOnlyItemList<ITransformation>>(TransformationsParameterName, "", transformationsList.AsReadOnly()));
|
---|
[5586] | 181 |
|
---|
[11114] | 182 | TransformationsParameter.Hidden = true;
|
---|
| 183 |
|
---|
[5601] | 184 | ((ValueParameter<Dataset>)DatasetParameter).ReactOnValueToStringChangedAndValueItemImageChanged = false;
|
---|
[5586] | 185 | RegisterEventHandlers();
|
---|
[5540] | 186 | }
|
---|
[5542] | 187 |
|
---|
[5586] | 188 | private void RegisterEventHandlers() {
|
---|
| 189 | DatasetParameter.ValueChanged += new EventHandler(Parameter_ValueChanged);
|
---|
[5649] | 190 | InputVariables.CheckedItemsChanged += new CollectionItemsChangedEventHandler<IndexedItem<StringValue>>(InputVariables_CheckedItemsChanged);
|
---|
[5759] | 191 | TrainingPartition.ValueChanged += new EventHandler(Parameter_ValueChanged);
|
---|
| 192 | TestPartition.ValueChanged += new EventHandler(Parameter_ValueChanged);
|
---|
[11114] | 193 | TransformationsParameter.ValueChanged += new EventHandler(Parameter_ValueChanged);
|
---|
[5540] | 194 | }
|
---|
| 195 |
|
---|
[5649] | 196 | private void InputVariables_CheckedItemsChanged(object sender, CollectionItemsChangedEventArgs<IndexedItem<StringValue>> e) {
|
---|
[5586] | 197 | OnChanged();
|
---|
| 198 | }
|
---|
[5649] | 199 |
|
---|
[5586] | 200 | private void Parameter_ValueChanged(object sender, EventArgs e) {
|
---|
| 201 | OnChanged();
|
---|
| 202 | }
|
---|
| 203 |
|
---|
[5554] | 204 | public event EventHandler Changed;
|
---|
| 205 | protected virtual void OnChanged() {
|
---|
[5540] | 206 | var listeners = Changed;
|
---|
| 207 | if (listeners != null) listeners(this, EventArgs.Empty);
|
---|
| 208 | }
|
---|
[10540] | 209 |
|
---|
| 210 | protected virtual bool IsProblemDataCompatible(IDataAnalysisProblemData problemData, out string errorMessage) {
|
---|
| 211 | errorMessage = string.Empty;
|
---|
| 212 | if (problemData == null) throw new ArgumentNullException("problemData", "The provided problemData is null.");
|
---|
| 213 |
|
---|
| 214 | //check allowed input variables
|
---|
| 215 | StringBuilder message = new StringBuilder();
|
---|
| 216 | var variables = new HashSet<string>(problemData.InputVariables.Select(x => x.Value));
|
---|
| 217 | foreach (var item in AllowedInputVariables) {
|
---|
| 218 | if (!variables.Contains(item))
|
---|
| 219 | message.AppendLine("Input variable '" + item + "' is not present in the new problem data.");
|
---|
| 220 | }
|
---|
| 221 |
|
---|
| 222 | if (message.Length != 0) {
|
---|
| 223 | errorMessage = message.ToString();
|
---|
| 224 | return false;
|
---|
| 225 | }
|
---|
| 226 | return true;
|
---|
| 227 |
|
---|
| 228 | }
|
---|
| 229 |
|
---|
| 230 | public virtual void AdjustProblemDataProperties(IDataAnalysisProblemData problemData) {
|
---|
| 231 | DataAnalysisProblemData data = problemData as DataAnalysisProblemData;
|
---|
| 232 | if (data == null) throw new ArgumentException("The problem data is not a data analysis problem data. Instead a " + problemData.GetType().GetPrettyName() + " was provided.", "problemData");
|
---|
| 233 |
|
---|
| 234 | string errorMessage;
|
---|
| 235 | if (!data.IsProblemDataCompatible(this, out errorMessage)) {
|
---|
| 236 | throw new InvalidOperationException(errorMessage);
|
---|
| 237 | }
|
---|
| 238 |
|
---|
| 239 | foreach (var inputVariable in InputVariables) {
|
---|
| 240 | var variable = data.InputVariables.FirstOrDefault(i => i.Value == inputVariable.Value);
|
---|
| 241 | InputVariables.SetItemCheckedState(inputVariable, variable != null && data.InputVariables.ItemChecked(variable));
|
---|
| 242 | }
|
---|
| 243 | }
|
---|
[5540] | 244 | }
|
---|
| 245 | }
|
---|