1 | #region License Information
|
---|
2 | /* HeuristicLab
|
---|
3 | * Copyright (C) 2002-2010 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.Linq;
|
---|
25 | using HeuristicLab.Core;
|
---|
26 | using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
|
---|
27 | using HeuristicLab.Parameters;
|
---|
28 | using HeuristicLab.Data;
|
---|
29 | using HeuristicLab.Optimization;
|
---|
30 | using HeuristicLab.Problems.DataAnalysis;
|
---|
31 | using System.Drawing;
|
---|
32 | using System.IO;
|
---|
33 |
|
---|
34 | namespace HeuristicLab.Problems.DataAnalysis.Regression {
|
---|
35 | [Item("RegressionProblem", "Represents a regression problem.")]
|
---|
36 | [Creatable("Problems")]
|
---|
37 | [StorableClass]
|
---|
38 | public class RegressionProblem : ParameterizedNamedItem {
|
---|
39 | public override Image ItemImage {
|
---|
40 | get { return HeuristicLab.Common.Resources.VS2008ImageLibrary.Type; }
|
---|
41 | }
|
---|
42 |
|
---|
43 | #region Parameter Properties
|
---|
44 | public ValueParameter<Dataset> DatasetParameter {
|
---|
45 | get { return (ValueParameter<Dataset>)Parameters["Dataset"]; }
|
---|
46 | }
|
---|
47 | public ValueParameter<StringValue> TargetVariableParameter {
|
---|
48 | get { return (ValueParameter<StringValue>)Parameters["TargetVariable"]; }
|
---|
49 | }
|
---|
50 | public ValueParameter<ItemList<StringValue>> InputVariablesParameter {
|
---|
51 | get { return (ValueParameter<ItemList<StringValue>>)Parameters["InputVariables"]; }
|
---|
52 | }
|
---|
53 | public ValueParameter<IntValue> TrainingSamplesStartParameter {
|
---|
54 | get { return (ValueParameter<IntValue>)Parameters["TrainingSamplesStart"]; }
|
---|
55 | }
|
---|
56 | public ValueParameter<IntValue> TrainingSamplesEndParameter {
|
---|
57 | get { return (ValueParameter<IntValue>)Parameters["TrainingSamplesEnd"]; }
|
---|
58 | }
|
---|
59 | public OptionalValueParameter<IntValue> ValidationSamplesStartParameter {
|
---|
60 | get { return (OptionalValueParameter<IntValue>)Parameters["ValidationSamplesStart"]; }
|
---|
61 | }
|
---|
62 | public OptionalValueParameter<IntValue> ValidationSamplesEndParameter {
|
---|
63 | get { return (OptionalValueParameter<IntValue>)Parameters["ValidationSamplesEnd"]; }
|
---|
64 | }
|
---|
65 | public ValueParameter<IntValue> TestSamplesStartParameter {
|
---|
66 | get { return (ValueParameter<IntValue>)Parameters["TestSamplesStart"]; }
|
---|
67 | }
|
---|
68 | public ValueParameter<IntValue> TestSamplesEndParameter {
|
---|
69 | get { return (ValueParameter<IntValue>)Parameters["TestSamplesEnd"]; }
|
---|
70 | }
|
---|
71 | #endregion
|
---|
72 | #region properties
|
---|
73 | public Dataset Dataset {
|
---|
74 | get { return DatasetParameter.Value; }
|
---|
75 | set { DatasetParameter.Value = value; }
|
---|
76 | }
|
---|
77 | public StringValue TargetVariable {
|
---|
78 | get { return TargetVariableParameter.Value; }
|
---|
79 | set { TargetVariableParameter.Value = value; }
|
---|
80 | }
|
---|
81 | public ItemList<StringValue> InputVariables {
|
---|
82 | get { return InputVariablesParameter.Value; }
|
---|
83 | set { InputVariablesParameter.Value = value; }
|
---|
84 | }
|
---|
85 | public IntValue TrainingSamplesStart {
|
---|
86 | get { return TrainingSamplesStartParameter.Value; }
|
---|
87 | set { TrainingSamplesStartParameter.Value = value; }
|
---|
88 | }
|
---|
89 | public IntValue TrainingSamplesEnd {
|
---|
90 | get { return TrainingSamplesEndParameter.Value; }
|
---|
91 | set { TrainingSamplesEndParameter.Value = value; }
|
---|
92 | }
|
---|
93 | public IntValue ValidationSamplesStart {
|
---|
94 | get { return ValidationSamplesStartParameter.Value; }
|
---|
95 | set { ValidationSamplesStartParameter.Value = value; }
|
---|
96 | }
|
---|
97 | public IntValue ValidationSamplesEnd {
|
---|
98 | get { return ValidationSamplesEndParameter.Value; }
|
---|
99 | set { ValidationSamplesEndParameter.Value = value; }
|
---|
100 | }
|
---|
101 | public IntValue TestSamplesStart {
|
---|
102 | get { return TestSamplesStartParameter.Value; }
|
---|
103 | set { TestSamplesStartParameter.Value = value; }
|
---|
104 | }
|
---|
105 | public IntValue TestSamplesEnd {
|
---|
106 | get { return TestSamplesEndParameter.Value; }
|
---|
107 | set { TestSamplesEndParameter.Value = value; }
|
---|
108 | }
|
---|
109 | #endregion
|
---|
110 |
|
---|
111 | public RegressionProblem()
|
---|
112 | : base() {
|
---|
113 | var dataset = new Dataset();
|
---|
114 | // TODO: wiring for sanity checks of parameter values based on dataset (target & input variables available?, training and test partition correct?...)
|
---|
115 | Parameters.Add(new ValueParameter<Dataset>("Dataset", "The data set containing data to be analyzer.", dataset));
|
---|
116 | Parameters.Add(new ValueParameter<StringValue>("TargetVariable", "The target variable for which a regression model should be created.", new StringValue()));
|
---|
117 | Parameters.Add(new ValueParameter<ItemList<StringValue>>("InputVariables", "The input variables (regressors) that are available for the regression model.", new ItemList<StringValue>()));
|
---|
118 | Parameters.Add(new ValueParameter<IntValue>("TrainingSamplesStart", "The start index of the training partition.", new IntValue()));
|
---|
119 | Parameters.Add(new ValueParameter<IntValue>("TrainingSamplesEnd", "The end index of the training partition.", new IntValue()));
|
---|
120 | Parameters.Add(new OptionalValueParameter<IntValue>("ValidationSamplesStart", "The start index of the validation partition."));
|
---|
121 | Parameters.Add(new OptionalValueParameter<IntValue>("ValidationSamplesEnd", "The end index of the validation partition."));
|
---|
122 | Parameters.Add(new ValueParameter<IntValue>("TestSamplesStart", "The start index of the test partition.", new IntValue()));
|
---|
123 | Parameters.Add(new ValueParameter<IntValue>("TestSamplesEnd", "The end index of the test partition.", new IntValue()));
|
---|
124 | }
|
---|
125 |
|
---|
126 | [StorableConstructor]
|
---|
127 | private RegressionProblem(bool deserializing) : base() { }
|
---|
128 |
|
---|
129 | public virtual void ImportFromFile(string fileName) {
|
---|
130 | var csvFileParser = new CsvFileParser();
|
---|
131 | csvFileParser.Parse(fileName);
|
---|
132 | Name = "Regression Problem (imported from " + Path.GetFileName(fileName);
|
---|
133 | Dataset = new Dataset(csvFileParser.VariableNames, csvFileParser.Values);
|
---|
134 | Dataset.Name = Path.GetFileName(fileName);
|
---|
135 | TargetVariable = new StringValue(Dataset.VariableNames.First());
|
---|
136 | InputVariables = new ItemList<StringValue>(Dataset.VariableNames.Skip(1).Select(s => new StringValue(s)));
|
---|
137 | TrainingSamplesStart = new IntValue(0);
|
---|
138 | TrainingSamplesEnd = new IntValue(csvFileParser.Rows);
|
---|
139 | TestSamplesStart = new IntValue(0);
|
---|
140 | TestSamplesEnd = new IntValue(csvFileParser.Rows);
|
---|
141 | }
|
---|
142 | }
|
---|
143 | }
|
---|