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 System.Collections.Generic;
|
---|
24 | using System.Text;
|
---|
25 | using System.Xml;
|
---|
26 | using HeuristicLab.Core;
|
---|
27 | using HeuristicLab.Data;
|
---|
28 | using HeuristicLab.DataAnalysis;
|
---|
29 | using System.Linq;
|
---|
30 |
|
---|
31 | namespace HeuristicLab.Modeling {
|
---|
32 | public class VariableQualityImpactCalculator : OperatorBase {
|
---|
33 | public override string Description {
|
---|
34 | get { return @"Calculates the impact of all allowed input variables on the quality of the model using evaluator supplied as suboperator."; }
|
---|
35 | }
|
---|
36 |
|
---|
37 | public VariableQualityImpactCalculator()
|
---|
38 | : base() {
|
---|
39 | AddVariableInfo(new VariableInfo("Dataset", "Dataset", typeof(Dataset), VariableKind.In));
|
---|
40 | AddVariableInfo(new VariableInfo("TargetVariable", "TargetVariable", typeof(IntData), VariableKind.In));
|
---|
41 | AddVariableInfo(new VariableInfo("AllowedFeatures", "Indexes of allowed input variables", typeof(ItemList<IntData>), VariableKind.In));
|
---|
42 | AddVariableInfo(new VariableInfo("TrainingSamplesStart", "TrainingSamplesStart", typeof(IntData), VariableKind.In));
|
---|
43 | AddVariableInfo(new VariableInfo("TrainingSamplesEnd", "TrainingSamplesEnd", typeof(IntData), VariableKind.In));
|
---|
44 | AddVariableInfo(new VariableInfo("VariableQualityImpacts", "Effect on quality of model (percentage of original quality) if variable is replaced by its mean.", typeof(ItemList), VariableKind.New));
|
---|
45 | }
|
---|
46 |
|
---|
47 | public override IOperation Apply(IScope scope) {
|
---|
48 | ItemList<IntData> allowedFeatures = GetVariableValue<ItemList<IntData>>("AllowedFeatures", scope, true);
|
---|
49 | int targetVariable = GetVariableValue<IntData>("TargetVariable", scope, true).Data;
|
---|
50 | Dataset dataset = GetVariableValue<Dataset>("Dataset", scope, true);
|
---|
51 | Dataset dirtyDataset = (Dataset)dataset.Clone();
|
---|
52 | int start = GetVariableValue<IntData>("TrainingSamplesStart", scope, true).Data;
|
---|
53 | int end = GetVariableValue<IntData>("TrainingSamplesEnd", scope, true).Data;
|
---|
54 |
|
---|
55 | if (SubOperators.Count < 1) throw new InvalidOperationException("VariableQualityImpactCalculator needs a suboperator to evaluate the model");
|
---|
56 | IOperator evaluationOperator = this.SubOperators[0];
|
---|
57 | ItemList variableQualityImpacts = new ItemList();
|
---|
58 |
|
---|
59 | // calculateReferenceQuality
|
---|
60 | double referenceQuality = CalculateQuality(scope, dataset, evaluationOperator);
|
---|
61 |
|
---|
62 | for (int i = 0; i < allowedFeatures.Count; i++) {
|
---|
63 | int currentVariable = allowedFeatures[i].Data;
|
---|
64 | var oldValues = ReplaceVariableValues(dirtyDataset, currentVariable , CalculateNewValues(dirtyDataset, currentVariable, start, end), start, end);
|
---|
65 | double newQuality = CalculateQuality(scope, dirtyDataset, evaluationOperator);
|
---|
66 | double ratio = newQuality / referenceQuality;
|
---|
67 | ItemList row = new ItemList();
|
---|
68 | row.Add(new StringData(dataset.GetVariableName(currentVariable)));
|
---|
69 | row.Add(new DoubleData(ratio));
|
---|
70 | variableQualityImpacts.Add(row);
|
---|
71 | ReplaceVariableValues(dirtyDataset, currentVariable, oldValues, start, end);
|
---|
72 | }
|
---|
73 | scope.AddVariable(new Variable(scope.TranslateName("VariableQualityImpacts"), variableQualityImpacts));
|
---|
74 | return null;
|
---|
75 | }
|
---|
76 |
|
---|
77 | private double CalculateQuality(IScope scope, Dataset dataset, IOperator evaluationOperator) {
|
---|
78 | Scope s = new Scope();
|
---|
79 | s.AddVariable(new Variable("Dataset", dataset));
|
---|
80 | scope.AddSubScope(s);
|
---|
81 | evaluationOperator.Execute(s);
|
---|
82 | double quality = s.GetVariableValue<DoubleData>("Quality", false).Data;
|
---|
83 | scope.RemoveSubScope(s);
|
---|
84 | return quality;
|
---|
85 | }
|
---|
86 |
|
---|
87 | private IEnumerable<double> ReplaceVariableValues(Dataset ds, int variableIndex, IEnumerable<double> newValues, int start, int end) {
|
---|
88 | double[] oldValues = new double[end - start];
|
---|
89 | for (int i = 0; i < end - start; i++) oldValues[i] = ds.GetValue(i + start, variableIndex);
|
---|
90 | if (newValues.Count() != end - start) throw new ArgumentException("The length of the new values sequence doesn't match the required length (number of replaced values)");
|
---|
91 |
|
---|
92 | int index = start;
|
---|
93 | ds.FireChangeEvents = false;
|
---|
94 | foreach(double v in newValues) {
|
---|
95 | ds.SetValue(index++, variableIndex, v);
|
---|
96 | }
|
---|
97 | ds.FireChangeEvents = true;
|
---|
98 | ds.FireChanged();
|
---|
99 | return oldValues;
|
---|
100 | }
|
---|
101 |
|
---|
102 | private IEnumerable<double> CalculateNewValues(Dataset ds, int variableIndex, int start, int end) {
|
---|
103 | double mean = ds.GetMean(variableIndex, start, end);
|
---|
104 | return Enumerable.Repeat(mean, end - start);
|
---|
105 | }
|
---|
106 | }
|
---|
107 | }
|
---|