Changeset 15830 for branches/M5Regression

Timestamp:

03/08/18 08:46:40 (6 years ago)

Author:

bwerth

Message:

#2847 adapted project to new rep structure; major changes to interfaces; restructures splitting and pruning

Location:

branches/M5Regression/HeuristicLab.Algorithms.DataAnalysis/3.4

Files:

• HeuristicLab.Algorithms.DataAnalysis-3.4.csproj (modified) (8 diffs)
• M5Regression/Interfaces/ILeafModel.cs (modified) (2 diffs)
• M5Regression/Interfaces/IM5Model.cs (modified) (1 diff)
• M5Regression/Interfaces/IPruning.cs (modified) (2 diffs)
• M5Regression/Interfaces/ISplitter.cs (added)
• M5Regression/LeafModels (added)
• M5Regression/LeafModels/ComponentReducedLinearModel.cs (added)
• M5Regression/LeafModels/DampenedLinearModel.cs (added)
• M5Regression/LeafModels/PreconstructedLinearModel.cs (added)
• M5Regression/LeafTypes/ComplexLeaf.cs (modified) (2 diffs)
• M5Regression/LeafTypes/ComponentReductionLinearLeaf.cs (modified) (4 diffs)
• M5Regression/LeafTypes/ConstantLeaf.cs (modified) (3 diffs)
• M5Regression/LeafTypes/GaussianProcessLeaf.cs (modified) (5 diffs)
• M5Regression/LeafTypes/LeafBase.cs (added)
• M5Regression/LeafTypes/LinearLeaf.cs (modified) (2 diffs)
• M5Regression/LeafTypes/LogisticLeaf.cs (modified) (2 diffs)
• M5Regression/LeafTypes/M5Leaf.cs (added)
• M5Regression/LeafTypes/M5regLeaf.cs (added)
• M5Regression/M5Regression.cs (modified) (7 diffs)
• M5Regression/M5Utilities/RegressionTreeAnalyzer.cs (added)
• M5Regression/M5Utilities/RegressionTreeParameters.cs (added)
• M5Regression/M5Utilities/RegressionTreeUtilities.cs (added)
• M5Regression/MetaModels/RegressionNodeModel.cs (added)
• M5Regression/MetaModels/RegressionNodeTreeModel.cs (added)
• M5Regression/MetaModels/RegressionRuleModel.cs (added)
• M5Regression/MetaModels/RegressionRuleSetModel.cs (added)
• M5Regression/Pruning/ComplexityPruning.cs (added)
• M5Regression/Pruning/NoPruning.cs (modified) (2 diffs)
• M5Regression/Spliting/CorrelationImpuritiyCalculator.cs (added)
• M5Regression/Spliting/CorrelationSplitter.cs (added)
• M5Regression/Spliting/M5Splitter.cs (added)
• M5Regression/Spliting/NeumaierSum.cs (added)
• M5Regression/Spliting/OrderImpurityCalculator.cs (modified) (3 diffs)
• M5Regression/Spliting/SplitterBase.cs (added)
• M5Regression/Spliting/UnivariateOnlineLR.cs (added)
• M5Regression/m5.patch (added)

branches/M5Regression/HeuristicLab.Algorithms.DataAnalysis/3.4/HeuristicLab.Algorithms.DataAnalysis-3.4.csproj

@@ -43 +43 @@
     <DebugType>full</DebugType>
     <Optimize>false</Optimize>
-    <OutputPath>..\..\..\..\trunk\sources\bin\</OutputPath>
+    <OutputPath>..\..\..\..\trunk\bin\</OutputPath>
     <DefineConstants>DEBUG;TRACE</DefineConstants>
     <ErrorReport>prompt</ErrorReport>
@@ -54 +54 @@
     <DebugType>pdbonly</DebugType>
     <Optimize>true</Optimize>
-    <OutputPath>..\..\..\..\trunk\sources\bin\</OutputPath>
+    <OutputPath>..\..\..\..\trunk\bin\</OutputPath>
     <DefineConstants>TRACE</DefineConstants>
     <ErrorReport>prompt</ErrorReport>
@@ -65 +65 @@
   <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Debug|x86' ">
     <DebugSymbols>true</DebugSymbols>
-    <OutputPath>..\..\..\..\trunk\sources\bin\</OutputPath>
+    <OutputPath>..\..\..\..\trunk\bin\</OutputPath>
     <DefineConstants>DEBUG;TRACE</DefineConstants>
     <DebugType>full</DebugType>
@@ -74 +74 @@
   </PropertyGroup>
   <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Release|x86' ">
-    <OutputPath>..\..\..\..\trunk\sources\bin\</OutputPath>
+    <OutputPath>..\..\..\..\trunk\bin\</OutputPath>
     <DefineConstants>TRACE</DefineConstants>
     <DocumentationFile>
@@ -87 +87 @@
   <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Debug|x64' ">
     <DebugSymbols>true</DebugSymbols>
-    <OutputPath>..\..\..\..\trunk\sources\bin\</OutputPath>
+    <OutputPath>..\..\..\..\trunk\bin\</OutputPath>
     <DefineConstants>DEBUG;TRACE</DefineConstants>
     <DebugType>full</DebugType>
@@ -96 +96 @@
   </PropertyGroup>
   <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Release|x64' ">
-    <OutputPath>..\..\..\..\trunk\sources\bin\</OutputPath>
+    <OutputPath>..\..\..\..\trunk\bin\</OutputPath>
     <DefineConstants>TRACE</DefineConstants>
     <DocumentationFile>
@@ -108 +108 @@
   </PropertyGroup>
   <ItemGroup>
-    <Reference Include="ALGLIB-3.7.0, Version=3.7.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
-      <HintPath>..\..\bin\ALGLIB-3.7.0.dll</HintPath>
-      <Private>False</Private>
-    </Reference>
-    <Reference Include="HeuristicLab.Algorithms.GradientDescent-3.3, Version=3.3.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
-      <SpecificVersion>False</SpecificVersion>
-      <HintPath>..\..\..\..\trunk\sources\bin\HeuristicLab.Algorithms.GradientDescent-3.3.dll</HintPath>
+    <Reference Include="ALGLIB-3.7.0">
+      <HintPath>..\..\..\..\trunk\bin\ALGLIB-3.7.0.dll</HintPath>
+    </Reference>
+    <Reference Include="HeuristicLab.Algorithms.DataAnalysis.Glmnet-3.4, Version=3.4.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
+      <SpecificVersion>False</SpecificVersion>
+      <HintPath>..\..\..\..\trunk\bin\HeuristicLab.Algorithms.DataAnalysis.Glmnet-3.4.dll</HintPath>
+    </Reference>
+    <Reference Include="HeuristicLab.Algorithms.GradientDescent-3.3">
+      <HintPath>..\..\..\..\trunk\bin\HeuristicLab.Algorithms.GradientDescent-3.3.dll</HintPath>
     </Reference>
     <Reference Include="HeuristicLab.Algorithms.OffspringSelectionGeneticAlgorithm-3.3, Version=3.3.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
       <SpecificVersion>False</SpecificVersion>
-      <HintPath>..\..\..\..\trunk\sources\bin\HeuristicLab.Algorithms.OffspringSelectionGeneticAlgorithm-3.3.dll</HintPath>
+      <HintPath>..\..\..\..\trunk\bin\HeuristicLab.Algorithms.OffspringSelectionGeneticAlgorithm-3.3.dll</HintPath>
     </Reference>
     <Reference Include="HeuristicLab.Analysis-3.3, Version=3.3.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
       <SpecificVersion>False</SpecificVersion>
-      <HintPath>..\..\..\..\trunk\sources\bin\HeuristicLab.Analysis-3.3.dll</HintPath>
+      <HintPath>..\..\..\..\trunk\bin\HeuristicLab.Analysis-3.3.dll</HintPath>
     </Reference>
     <Reference Include="HeuristicLab.Collections-3.3, Version=3.3.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
       <SpecificVersion>False</SpecificVersion>
-      <HintPath>..\..\..\..\trunk\sources\bin\HeuristicLab.Collections-3.3.dll</HintPath>
+      <HintPath>..\..\..\..\trunk\bin\HeuristicLab.Collections-3.3.dll</HintPath>
     </Reference>
     <Reference Include="HeuristicLab.Common-3.3, Version=3.3.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
       <SpecificVersion>False</SpecificVersion>
-      <HintPath>..\..\..\..\trunk\sources\bin\HeuristicLab.Common-3.3.dll</HintPath>
+      <HintPath>..\..\..\..\trunk\bin\HeuristicLab.Common-3.3.dll</HintPath>
     </Reference>
     <Reference Include="HeuristicLab.Common.Resources-3.3, Version=3.3.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
       <SpecificVersion>False</SpecificVersion>
-      <HintPath>..\..\..\..\trunk\sources\bin\HeuristicLab.Common.Resources-3.3.dll</HintPath>
+      <HintPath>..\..\..\..\trunk\bin\HeuristicLab.Common.Resources-3.3.dll</HintPath>
     </Reference>
     <Reference Include="HeuristicLab.Core-3.3, Version=3.3.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
       <SpecificVersion>False</SpecificVersion>
-      <HintPath>..\..\..\..\trunk\sources\bin\HeuristicLab.Core-3.3.dll</HintPath>
+      <HintPath>..\..\..\..\trunk\bin\HeuristicLab.Core-3.3.dll</HintPath>
     </Reference>
     <Reference Include="HeuristicLab.Data-3.3, Version=3.3.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
       <SpecificVersion>False</SpecificVersion>
-      <HintPath>..\..\..\..\trunk\sources\bin\HeuristicLab.Data-3.3.dll</HintPath>
+      <HintPath>..\..\..\..\trunk\bin\HeuristicLab.Data-3.3.dll</HintPath>
     </Reference>
     <Reference Include="HeuristicLab.Encodings.PermutationEncoding-3.3, Version=3.3.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
       <SpecificVersion>False</SpecificVersion>
-      <HintPath>..\..\..\..\trunk\sources\bin\HeuristicLab.Encodings.PermutationEncoding-3.3.dll</HintPath>
+      <HintPath>..\..\..\..\trunk\bin\HeuristicLab.Encodings.PermutationEncoding-3.3.dll</HintPath>
     </Reference>
     <Reference Include="HeuristicLab.Encodings.RealVectorEncoding-3.3, Version=3.3.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
       <SpecificVersion>False</SpecificVersion>
-      <HintPath>..\..\..\..\trunk\sources\bin\HeuristicLab.Encodings.RealVectorEncoding-3.3.dll</HintPath>
+      <HintPath>..\..\..\..\trunk\bin\HeuristicLab.Encodings.RealVectorEncoding-3.3.dll</HintPath>
     </Reference>
     <Reference Include="HeuristicLab.Encodings.SymbolicExpressionTreeEncoding-3.4, Version=3.4.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
       <SpecificVersion>False</SpecificVersion>
-      <HintPath>..\..\..\..\trunk\sources\bin\HeuristicLab.Encodings.SymbolicExpressionTreeEncoding-3.4.dll</HintPath>
+      <HintPath>..\..\..\..\trunk\bin\HeuristicLab.Encodings.SymbolicExpressionTreeEncoding-3.4.dll</HintPath>
     </Reference>
     <Reference Include="HeuristicLab.LibSVM-3.12, Version=3.12.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
       <SpecificVersion>False</SpecificVersion>
-      <HintPath>..\..\..\..\trunk\sources\bin\HeuristicLab.LibSVM-3.12.dll</HintPath>
+      <HintPath>..\..\..\..\trunk\bin\HeuristicLab.LibSVM-3.12.dll</HintPath>
     </Reference>
     <Reference Include="HeuristicLab.Operators-3.3, Version=3.3.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
       <SpecificVersion>False</SpecificVersion>
-      <HintPath>..\..\..\..\trunk\sources\bin\HeuristicLab.Operators-3.3.dll</HintPath>
+      <HintPath>..\..\..\..\trunk\bin\HeuristicLab.Operators-3.3.dll</HintPath>
     </Reference>
     <Reference Include="HeuristicLab.Optimization-3.3, Version=3.3.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
       <SpecificVersion>False</SpecificVersion>
-      <HintPath>..\..\..\..\trunk\sources\bin\HeuristicLab.Optimization-3.3.dll</HintPath>
+      <HintPath>..\..\..\..\trunk\bin\HeuristicLab.Optimization-3.3.dll</HintPath>
     </Reference>
     <Reference Include="HeuristicLab.Parameters-3.3, Version=3.3.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
       <SpecificVersion>False</SpecificVersion>
-      <HintPath>..\..\..\..\trunk\sources\bin\HeuristicLab.Parameters-3.3.dll</HintPath>
+      <HintPath>..\..\..\..\trunk\bin\HeuristicLab.Parameters-3.3.dll</HintPath>
     </Reference>
     <Reference Include="HeuristicLab.Persistence-3.3, Version=3.3.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
       <SpecificVersion>False</SpecificVersion>
-      <HintPath>..\..\..\..\trunk\sources\bin\HeuristicLab.Persistence-3.3.dll</HintPath>
+      <HintPath>..\..\..\..\trunk\bin\HeuristicLab.Persistence-3.3.dll</HintPath>
     </Reference>
     <Reference Include="HeuristicLab.PluginInfrastructure-3.3, Version=3.3.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
       <SpecificVersion>False</SpecificVersion>
-      <HintPath>..\..\..\..\trunk\sources\bin\HeuristicLab.PluginInfrastructure-3.3.dll</HintPath>
+      <HintPath>..\..\..\..\trunk\bin\HeuristicLab.PluginInfrastructure-3.3.dll</HintPath>
     </Reference>
     <Reference Include="HeuristicLab.Problems.DataAnalysis-3.4, Version=3.4.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
       <SpecificVersion>False</SpecificVersion>
-      <HintPath>..\..\..\..\trunk\sources\bin\HeuristicLab.Problems.DataAnalysis-3.4.dll</HintPath>
+      <HintPath>..\..\..\..\trunk\bin\HeuristicLab.Problems.DataAnalysis-3.4.dll</HintPath>
     </Reference>
     <Reference Include="HeuristicLab.Problems.DataAnalysis.Symbolic-3.4, Version=3.4.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
       <SpecificVersion>False</SpecificVersion>
-      <HintPath>..\..\..\..\trunk\sources\bin\HeuristicLab.Problems.DataAnalysis.Symbolic-3.4.dll</HintPath>
+      <HintPath>..\..\..\..\trunk\bin\HeuristicLab.Problems.DataAnalysis.Symbolic-3.4.dll</HintPath>
     </Reference>
     <Reference Include="HeuristicLab.Problems.DataAnalysis.Symbolic.Classification-3.4, Version=3.4.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
       <SpecificVersion>False</SpecificVersion>
-      <HintPath>..\..\..\..\trunk\sources\bin\HeuristicLab.Problems.DataAnalysis.Symbolic.Classification-3.4.dll</HintPath>
+      <HintPath>..\..\..\..\trunk\bin\HeuristicLab.Problems.DataAnalysis.Symbolic.Classification-3.4.dll</HintPath>
     </Reference>
     <Reference Include="HeuristicLab.Problems.DataAnalysis.Symbolic.Regression-3.4, Version=3.4.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
       <SpecificVersion>False</SpecificVersion>
-      <HintPath>..\..\..\..\trunk\sources\bin\HeuristicLab.Problems.DataAnalysis.Symbolic.Regression-3.4.dll</HintPath>
+      <HintPath>..\..\..\..\trunk\bin\HeuristicLab.Problems.DataAnalysis.Symbolic.Regression-3.4.dll</HintPath>
     </Reference>
     <Reference Include="HeuristicLab.Problems.DataAnalysis.Symbolic.TimeSeriesPrognosis-3.4, Version=3.4.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
       <SpecificVersion>False</SpecificVersion>
-      <HintPath>..\..\..\..\trunk\sources\bin\HeuristicLab.Problems.DataAnalysis.Symbolic.TimeSeriesPrognosis-3.4.dll</HintPath>
+      <HintPath>..\..\..\..\trunk\bin\HeuristicLab.Problems.DataAnalysis.Symbolic.TimeSeriesPrognosis-3.4.dll</HintPath>
     </Reference>
     <Reference Include="HeuristicLab.Problems.Instances-3.3, Version=3.3.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
       <SpecificVersion>False</SpecificVersion>
-      <HintPath>..\..\..\..\trunk\sources\bin\HeuristicLab.Problems.Instances-3.3.dll</HintPath>
+      <HintPath>..\..\..\..\trunk\bin\HeuristicLab.Problems.Instances-3.3.dll</HintPath>
     </Reference>
     <Reference Include="HeuristicLab.Random-3.3, Version=3.3.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
       <SpecificVersion>False</SpecificVersion>
-      <HintPath>..\..\..\..\trunk\sources\bin\HeuristicLab.Random-3.3.dll</HintPath>
+      <HintPath>..\..\..\..\trunk\bin\HeuristicLab.Random-3.3.dll</HintPath>
     </Reference>
     <Reference Include="HeuristicLab.Selection-3.3, Version=3.3.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
       <SpecificVersion>False</SpecificVersion>
-      <HintPath>..\..\..\..\trunk\sources\bin\HeuristicLab.Selection-3.3.dll</HintPath>
+      <HintPath>..\..\..\..\trunk\bin\HeuristicLab.Selection-3.3.dll</HintPath>
     </Reference>
     <Reference Include="LibSVM-3.12, Version=3.12.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
@@ -365 +367 @@
     <Compile Include="Linear\MultinomialLogitModel.cs" />
     <Compile Include="Linear\Scaling.cs" />
-    <Compile Include="M5Regression\Interfaces\ISpliter.cs" />
     <Compile Include="M5Regression\Interfaces\IM5Model.cs" />
     <Compile Include="M5Regression\Interfaces\ILeafModel.cs" />
     <Compile Include="M5Regression\Interfaces\IPruning.cs" />
+    <Compile Include="M5Regression\Interfaces\ISplitter.cs" />
+    <Compile Include="M5Regression\LeafModels\ComponentReducedLinearModel.cs" />
+    <Compile Include="M5Regression\LeafModels\DampenedLinearModel.cs" />
+    <Compile Include="M5Regression\LeafModels\PreconstructedLinearModel.cs" />
     <Compile Include="M5Regression\LeafTypes\ComplexLeaf.cs" />
     <Compile Include="M5Regression\LeafTypes\ComponentReductionLinearLeaf.cs" />
+    <Compile Include="M5Regression\LeafTypes\LeafBase.cs" />
     <Compile Include="M5Regression\LeafTypes\ConstantLeaf.cs" />
     <Compile Include="M5Regression\LeafTypes\GaussianProcessLeaf.cs" />
     <Compile Include="M5Regression\LeafTypes\LinearLeaf.cs" />
     <Compile Include="M5Regression\LeafTypes\LogisticLeaf.cs" />
+    <Compile Include="M5Regression\LeafTypes\M5Leaf.cs" />
+    <Compile Include="M5Regression\LeafTypes\M5regLeaf.cs" />
     <Compile Include="M5Regression\M5Regression.cs" />
-    <Compile Include="M5Regression\M5Utilities\M5StaticUtilities.cs" />
-    <Compile Include="M5Regression\M5Utilities\M5Analyzer.cs" />
-    <Compile Include="M5Regression\M5Utilities\M5Parameters.cs" />
-    <Compile Include="M5Regression\MetaModels\ComponentReducedLinearModel.cs" />
-    <Compile Include="M5Regression\MetaModels\M5NodeModel.cs" />
-    <Compile Include="M5Regression\MetaModels\M5RuleModel.cs" />
-    <Compile Include="M5Regression\MetaModels\M5RuleSetModel.cs" />
-    <Compile Include="M5Regression\MetaModels\M5TreeModel.cs" />
-    <Compile Include="M5Regression\MetaModels\DampenedLinearModel.cs" />
-    <Compile Include="M5Regression\MetaModels\PreconstructedLinearModel.cs" />
-    <Compile Include="M5Regression\Pruning\M5LinearBottomUpPruning.cs" />
-    <Compile Include="M5Regression\Pruning\BottomUpPruningBase.cs" />
+    <Compile Include="M5Regression\M5Utilities\RegressionTreeUtilities.cs" />
+    <Compile Include="M5Regression\M5Utilities\RegressionTreeAnalyzer.cs" />
+    <Compile Include="M5Regression\M5Utilities\RegressionTreeParameters.cs" />
+    <Compile Include="M5Regression\MetaModels\RegressionNodeModel.cs" />
+    <Compile Include="M5Regression\MetaModels\RegressionRuleModel.cs" />
+    <Compile Include="M5Regression\MetaModels\RegressionRuleSetModel.cs" />
+    <Compile Include="M5Regression\MetaModels\RegressionNodeTreeModel.cs" />
+    <Compile Include="M5Regression\Pruning\ComplexityPruning.cs" />
     <Compile Include="M5Regression\Pruning\NoPruning.cs" />
-    <Compile Include="M5Regression\Pruning\M5LeafBottomUpPruning.cs" />
+    <Compile Include="M5Regression\Spliting\CorrelationImpuritiyCalculator.cs" />
+    <Compile Include="M5Regression\Spliting\CorrelationSplitter.cs" />
+    <Compile Include="M5Regression\Spliting\SplitterBase.cs" />
+    <Compile Include="M5Regression\Spliting\M5Splitter.cs" />
+    <Compile Include="M5Regression\Spliting\NeumaierSum.cs" />
     <Compile Include="M5Regression\Spliting\OrderImpurityCalculator.cs" />
-    <Compile Include="M5Regression\Spliting\OptimumSearchingSpliter.cs" />
-    <Compile Include="M5Regression\Spliting\M5Spliter.cs" />
+    <Compile Include="M5Regression\Spliting\UnivariateOnlineLR.cs" />
     <Compile Include="Nca\Initialization\INcaInitializer.cs" />
     <Compile Include="Nca\Initialization\LdaInitializer.cs" />

branches/M5Regression/HeuristicLab.Algorithms.DataAnalysis/3.4/M5Regression/Interfaces/ILeafModel.cs

@@ -20 +20 @@
 #endregion
 
+using System.Collections.Generic;
 using System.Threading;
 using HeuristicLab.Core;
@@ -27 +28 @@
   public interface ILeafModel : IParameterizedNamedItem {
     bool ProvidesConfidence { get; }
-    IRegressionModel Build(IRegressionProblemData pd, IRandom random, CancellationToken cancellationToken, out int noParameters);
+    // IRegressionModel Build(IRegressionProblemData pd, IRandom random, CancellationToken cancellationToken, out int noParameters);
     int MinLeafSize(IRegressionProblemData pd);
+
+    void Initialize(IScope states);
+    void Build(RegressionNodeTreeModel tree, IReadOnlyList<int> trainingRows, IScope stateScope, CancellationToken cancellationToken);
+    IRegressionModel BuildModel(IReadOnlyList<int> rows, RegressionTreeParameters parameters, CancellationToken cancellation, out int numParams);
   }
 }

branches/M5Regression/HeuristicLab.Algorithms.DataAnalysis/3.4/M5Regression/Interfaces/IM5Model.cs

@@ -22 +22 @@
 using System.Collections.Generic;
 using System.Threading;
+using HeuristicLab.Core;
+using HeuristicLab.Optimization;
 using HeuristicLab.Problems.DataAnalysis;
 
 namespace HeuristicLab.Algorithms.DataAnalysis {
-  internal interface IM5Model : IRegressionModel {
-    void Build(IReadOnlyList<int> trainingRows, IReadOnlyList<int> pruningRows, M5Parameters m5Params, CancellationToken cancellationToken);
-    void Update(IReadOnlyList<int> rows, M5Parameters m5Parameters, CancellationToken cancellationToken);
+  public interface IM5Model : IRegressionModel {
+    void Build(IReadOnlyList<int> trainingRows, IReadOnlyList<int> pruningRows, IScope stateScope, ResultCollection results, CancellationToken cancellationToken);
+    void Update(IReadOnlyList<int> rows, IScope stateScope, CancellationToken cancellationToken);
   }
 }

branches/M5Regression/HeuristicLab.Algorithms.DataAnalysis/3.4/M5Regression/Interfaces/IPruning.cs

@@ -20 +20 @@
 #endregion
 using System.Collections.Generic;
+using System.Threading;
 using HeuristicLab.Core;
 using HeuristicLab.Problems.DataAnalysis;
@@ -26 +27 @@
   public interface IPruning : IParameterizedNamedItem {
     int MinLeafSize(IRegressionProblemData pd, ILeafModel leafModel);
+
+    void Initialize(IScope states);
+    void Prune(RegressionNodeTreeModel treeModel, IReadOnlyList<int> trainingRows, IReadOnlyList<int> pruningRows, IScope scope, CancellationToken cancellationToken);
   }
 }

branches/M5Regression/HeuristicLab.Algorithms.DataAnalysis/3.4/M5Regression/LeafTypes/ComplexLeaf.cs

@@ -32 +32 @@
   [StorableClass]
   [Item("ComplexLeaf", "A leaf type that uses an arbitriary RegressionAlgorithm to create leaf models")]
-  public class ComplexLeaf : ParameterizedNamedItem, ILeafModel {
+  public class ComplexLeaf : LeafBase {
     public const string RegressionParameterName = "Regression";
     public IValueParameter<IDataAnalysisAlgorithm<IRegressionProblem>> RegressionParameter {
@@ -55 +55 @@
 
     #region IModelType
-    public bool ProvidesConfidence {
+    public override bool ProvidesConfidence {
       get { return false; }
     }
-    public IRegressionModel Build(IRegressionProblemData pd, IRandom random, CancellationToken cancellationToken, out int noParameters) {
+    public override IRegressionModel Build(IRegressionProblemData pd, IRandom random, CancellationToken cancellationToken, out int noParameters) {
       if (pd.Dataset.Rows < MinLeafSize(pd)) throw new ArgumentException("The number of training instances is too small to create a linear model");
       noParameters = pd.Dataset.Rows + 1;
       Regression.Problem = new RegressionProblem {ProblemData = pd};
-      var res = M5StaticUtilities.RunSubAlgorithm(Regression, random.Next(), cancellationToken);
+      var res = RegressionTreeUtilities.RunSubAlgorithm(Regression, random.Next(), cancellationToken);
       var t = res.Select(x => x.Value).OfType<IRegressionSolution>().FirstOrDefault();
       if (t == null) throw new ArgumentException("No RegressionSolution was provided by the algorithm");
       return t.Model;
     }
-
-    public int MinLeafSize(IRegressionProblemData pd) {
+    public override int MinLeafSize(IRegressionProblemData pd) {
       return 3;
     }

branches/M5Regression/HeuristicLab.Algorithms.DataAnalysis/3.4/M5Regression/LeafTypes/ComponentReductionLinearLeaf.cs

@@ -34 +34 @@
   [StorableClass]
   [Item("ComponentReductionLinearLeaf", "A leaf type that uses principle component analysis to create smaller linear models as leaf models")]
-  public class ComponentReductionLinearLeaf : ParameterizedNamedItem, ILeafModel {
+  public class ComponentReductionLinearLeaf : LeafBase {
     public const string NoComponentsParameterName = "NoComponents";
     public IFixedValueParameter<IntValue> NoComponentsParameter {
@@ -45 +45 @@
     #region Constructors & Cloning
     [StorableConstructor]
-    private ComponentReductionLinearLeaf(bool deserializing) : base(deserializing) { }
-    private ComponentReductionLinearLeaf(ComponentReductionLinearLeaf original, Cloner cloner) : base(original, cloner) { }
+    protected ComponentReductionLinearLeaf(bool deserializing) : base(deserializing) { }
+    protected ComponentReductionLinearLeaf(ComponentReductionLinearLeaf original, Cloner cloner) : base(original, cloner) { }
     public ComponentReductionLinearLeaf() {
       Parameters.Add(new FixedValueParameter<IntValue>(NoComponentsParameterName, "The maximum number of principle components used", new IntValue(10)));
@@ -56 +56 @@
 
     #region IModelType
-    public bool ProvidesConfidence {
+    public override bool ProvidesConfidence {
       get { return true; }
     }
-    public IRegressionModel Build(IRegressionProblemData pd, IRandom random,
+    public override IRegressionModel Build(IRegressionProblemData pd, IRandom random,
       CancellationToken cancellationToken, out int noParameters) {
       var pca = PrincipleComponentTransformation.CreateProjection(pd.Dataset, pd.TrainingIndices, pd.AllowedInputVariables, true);
@@ -82 +82 @@
     }
 
-    public int MinLeafSize(IRegressionProblemData pd) {
+    public override int MinLeafSize(IRegressionProblemData pd) {
       return NoComponents + 2;
     }

branches/M5Regression/HeuristicLab.Algorithms.DataAnalysis/3.4/M5Regression/LeafTypes/ConstantLeaf.cs

@@ -31 +31 @@
   [StorableClass]
   [Item("ConstantLeaf", "A leaf type that uses constant models as leaf models")]
-  public class ConstantLeaf : ParameterizedNamedItem, ILeafModel {
+  public class ConstantLeaf : LeafBase {
     #region Constructors & Cloning
     [StorableConstructor]
-    private ConstantLeaf(bool deserializing) : base(deserializing) { }
-    private ConstantLeaf(ConstantLeaf original, Cloner cloner) : base(original, cloner) { }
+    protected ConstantLeaf(bool deserializing) : base(deserializing) { }
+    protected ConstantLeaf(ConstantLeaf original, Cloner cloner) : base(original, cloner) { }
     public ConstantLeaf() { }
     public override IDeepCloneable Clone(Cloner cloner) {
@@ -43 +43 @@
 
     #region IModelType
-    public bool ProvidesConfidence {
+    public override bool ProvidesConfidence {
       get { return false; }
     }
-    public IRegressionModel Build(IRegressionProblemData pd, IRandom random, CancellationToken cancellationToken, out int noParameters) {
+    public override IRegressionModel Build(IRegressionProblemData pd, IRandom random, CancellationToken cancellationToken, out int noParameters) {
       if (pd.Dataset.Rows < MinLeafSize(pd)) throw new ArgumentException("The number of training instances is too small to create a linear model");
       noParameters = 1;
@@ -52 +52 @@
     }
 
-    public int MinLeafSize(IRegressionProblemData pd) {
+    public override int MinLeafSize(IRegressionProblemData pd) {
       return 0;
     }

branches/M5Regression/HeuristicLab.Algorithms.DataAnalysis/3.4/M5Regression/LeafTypes/GaussianProcessLeaf.cs

@@ -33 +33 @@
   [StorableClass]
   [Item("GaussianProcessLeaf", "A leaf type that uses gaussian process models as leaf models.")]
-  public class GaussianProcessLeaf : ParameterizedNamedItem, ILeafModel {
+  public class GaussianProcessLeaf : LeafBase {
     #region ParameterNames
     public const string TriesParameterName = "Tries";
@@ -59 +59 @@
     #region Constructors & Cloning
     [StorableConstructor]
-    private GaussianProcessLeaf(bool deserializing) : base(deserializing) { }
-    private GaussianProcessLeaf(GaussianProcessLeaf original, Cloner cloner) : base(original, cloner) { }
+    protected GaussianProcessLeaf(bool deserializing) : base(deserializing) { }
+    protected GaussianProcessLeaf(GaussianProcessLeaf original, Cloner cloner) : base(original, cloner) { }
     public GaussianProcessLeaf() {
       var gp = new GaussianProcessRegression();
@@ -75 +75 @@
 
     #region IModelType
-    public bool ProvidesConfidence {
+    public override bool ProvidesConfidence {
       get { return true; }
     }
-    public IRegressionModel Build(IRegressionProblemData pd, IRandom random, CancellationToken cancellationToken, out int noParameters) {
+    public override IRegressionModel Build(IRegressionProblemData pd, IRandom random, CancellationToken cancellationToken, out int noParameters) {
       if (pd.Dataset.Rows < MinLeafSize(pd)) throw new ArgumentException("The number of training instances is too small to create a gaussian process model");
       Regression.Problem = new RegressionProblem {ProblemData = pd};
@@ -85 +85 @@
 
       for (var i = 0; i < Tries; i++) {
-        var res = M5StaticUtilities.RunSubAlgorithm(Regression, random.Next(), cancellationToken);
+        var res = RegressionTreeUtilities.RunSubAlgorithm(Regression, random.Next(), cancellationToken);
         var t = res.Select(x => x.Value).OfType<GaussianProcessRegressionSolution>().FirstOrDefault();
         var score = ((DoubleValue)res["Negative log pseudo-likelihood (LOO-CV)"].Value).Value;
@@ -101 +101 @@
     }
 
-    public int MinLeafSize(IRegressionProblemData pd) {
+    public override int MinLeafSize(IRegressionProblemData pd) {
       return 3;
     }

branches/M5Regression/HeuristicLab.Algorithms.DataAnalysis/3.4/M5Regression/LeafTypes/LinearLeaf.cs

@@ -31 +31 @@
   [StorableClass]
   [Item("LinearLeaf", "A leaf type that uses linear models as leaf models. This is the standard for M5' regression")]
-  public class LinearLeaf : ParameterizedNamedItem, ILeafModel {
+  public class LinearLeaf : LeafBase {
     #region Constructors & Cloning
     [StorableConstructor]
-    private LinearLeaf(bool deserializing) : base(deserializing) { }
-    private LinearLeaf(LinearLeaf original, Cloner cloner) : base(original, cloner) { }
+    protected LinearLeaf(bool deserializing) : base(deserializing) { }
+    protected LinearLeaf(LinearLeaf original, Cloner cloner) : base(original, cloner) { }
     public LinearLeaf() { }
     public override IDeepCloneable Clone(Cloner cloner) {
@@ -43 +43 @@
 
     #region IModelType
-    public bool ProvidesConfidence {
+    public override bool ProvidesConfidence {
       get { return true; }
     }
-    public IRegressionModel Build(IRegressionProblemData pd, IRandom random, CancellationToken cancellationToken, out int noParameters) {
+    public override IRegressionModel Build(IRegressionProblemData pd, IRandom random, CancellationToken cancellationToken, out int noParameters) {
       if (pd.Dataset.Rows < MinLeafSize(pd)) throw new ArgumentException("The number of training instances is too small to create a linear model");
       double rmse, cvRmse;
       noParameters = pd.AllowedInputVariables.Count() + 1;
-      return PreconstructedLinearModel.CreateConfidenceLinearModel(pd, out rmse, out cvRmse);
+      var res = PreconstructedLinearModel.CreateConfidenceLinearModel(pd, out rmse, out cvRmse);
+      return res;
     }
 
-    public int MinLeafSize(IRegressionProblemData pd) {
-      return pd.AllowedInputVariables.Count() + 2;
+    public override int MinLeafSize(IRegressionProblemData pd) {
+      return pd.AllowedInputVariables.Count() == 1 ? 2 : pd.AllowedInputVariables.Count() + 2;
     }
     #endregion

branches/M5Regression/HeuristicLab.Algorithms.DataAnalysis/3.4/M5Regression/LeafTypes/LogisticLeaf.cs

@@ -33 +33 @@
   [StorableClass]
   [Item("LogisticLeaf", "A leaf type that uses linear models with a logistic dampening as leaf models. Dampening reduces prediction values far outside the observed target values.")]
-  public class LogisticLeaf : ParameterizedNamedItem, ILeafModel {
+  public class LogisticLeaf : LeafBase {
     private const string DampeningParameterName = "Dampening";
     public IFixedValueParameter<DoubleValue> DampeningParameter {
@@ -55 +55 @@
 
     #region IModelType
-    public bool ProvidesConfidence {
+    public override bool ProvidesConfidence {
       get { return true; }
     }
-    public IRegressionModel Build(IRegressionProblemData pd, IRandom random, CancellationToken cancellationToken, out int noParameters) {
-      if (pd.Dataset.Rows < MinLeafSize(pd)) throw new ArgumentException("The number of training instances is too small to create a linear model");
-      double rmse, cvRmse;
-      noParameters = pd.AllowedInputVariables.Count() + 1;
-      return new DampenedLinearModel(PreconstructedLinearModel.CreateConfidenceLinearModel(pd, out rmse, out cvRmse), pd, Dampening);
+    public override IRegressionModel Build(IRegressionProblemData pd, IRandom random, CancellationToken cancellationToken, out int noParameters) {
+      var res = (IConfidenceRegressionModel)new LinearLeaf().Build(pd, random, cancellationToken, out noParameters);
+      return new DampenedLinearModel(res, pd, Dampening);
     }
 
-    public int MinLeafSize(IRegressionProblemData pd) {
+    public override int MinLeafSize(IRegressionProblemData pd) {
       return pd.AllowedInputVariables.Count() + 2;
     }

branches/M5Regression/HeuristicLab.Algorithms.DataAnalysis/3.4/M5Regression/M5Regression.cs

@@ -19 +19 @@
   [Item("M5RegressionTree", "A M5 regression tree / rule set")]
   public sealed class M5Regression : FixedDataAnalysisAlgorithm<IRegressionProblem> {
+    public override bool SupportsPause {
+      get { return true; }
+    }
+
+    public const string RegressionTreeParameterVariableName = "RegressionTreeParameters";
+    public const string ModelVariableName = "Model";
+    public const string PruningSetVariableName = "PruningSet";
+    public const string TrainingSetVariableName = "TrainingSet";
+
     #region Parametername
     private const string GenerateRulesParameterName = "GenerateRules";
     private const string HoldoutSizeParameterName = "HoldoutSize";
-    private const string SpliterParameterName = "Spliter";
+    private const string SpliterParameterName = "Splitter";
     private const string MinimalNodeSizeParameterName = "MinimalNodeSize";
     private const string LeafModelParameterName = "LeafModel";
@@ -38 +47 @@
       get { return (IFixedValueParameter<PercentValue>)Parameters[HoldoutSizeParameterName]; }
     }
-    public IConstrainedValueParameter<ISpliter> ImpurityParameter {
-      get { return (IConstrainedValueParameter<ISpliter>)Parameters[SpliterParameterName]; }
+    public IConstrainedValueParameter<ISplitter> ImpurityParameter {
+      get { return (IConstrainedValueParameter<ISplitter>)Parameters[SpliterParameterName]; }
     }
     public IFixedValueParameter<IntValue> MinimalNodeSizeParameter {
@@ -68 +77 @@
       get { return HoldoutSizeParameter.Value.Value; }
     }
-    public ISpliter Split {
+    public ISplitter Splitter {
       get { return ImpurityParameter.Value; }
     }
@@ -89 +98 @@
       get { return UseHoldoutParameter.Value.Value; }
     }
+    #endregion
+
+    #region State
+    [Storable]
+    private IScope stateScope;
     #endregion
 
@@ -94 +108 @@
     [StorableConstructor]
     private M5Regression(bool deserializing) : base(deserializing) { }
-    private M5Regression(M5Regression original, Cloner cloner) : base(original, cloner) { }
+    private M5Regression(M5Regression original, Cloner cloner) : base(original, cloner) {
+      stateScope = cloner.Clone(stateScope);
+    }
     public M5Regression() {
       var modelSet = new ItemSet<ILeafModel>(ApplicationManager.Manager.GetInstances<ILeafModel>());
       var pruningSet = new ItemSet<IPruning>(ApplicationManager.Manager.GetInstances<IPruning>());
-      var impuritySet = new ItemSet<ISpliter>(ApplicationManager.Manager.GetInstances<ISpliter>());
+      var impuritySet = new ItemSet<ISplitter>(ApplicationManager.Manager.GetInstances<ISplitter>());
       Parameters.Add(new FixedValueParameter<BoolValue>(GenerateRulesParameterName, "Whether a set of rules or a decision tree shall be created", new BoolValue(false)));
       Parameters.Add(new FixedValueParameter<PercentValue>(HoldoutSizeParameterName, "How much of the training set shall be reserved for pruning", new PercentValue(0.2)));
-      Parameters.Add(new ConstrainedValueParameter<ISpliter>(SpliterParameterName, "The type of split function used to create node splits", impuritySet, impuritySet.OfType<M5Spliter>().First()));
+      Parameters.Add(new ConstrainedValueParameter<ISplitter>(SpliterParameterName, "The type of split function used to create node splits", impuritySet, impuritySet.OfType<M5Splitter>().First()));
       Parameters.Add(new FixedValueParameter<IntValue>(MinimalNodeSizeParameterName, "The minimal number of samples in a leaf node", new IntValue(1)));
       Parameters.Add(new ConstrainedValueParameter<ILeafModel>(LeafModelParameterName, "The type of model used for the nodes", modelSet, modelSet.OfType<LinearLeaf>().First()));
-      Parameters.Add(new ConstrainedValueParameter<IPruning>(PruningTypeParameterName, "The type of pruning used", pruningSet, pruningSet.OfType<M5LinearBottomUpPruning>().First()));
+      Parameters.Add(new ConstrainedValueParameter<IPruning>(PruningTypeParameterName, "The type of pruning used", pruningSet, pruningSet.OfType<ComplexityPruning>().First()));
       Parameters.Add(new FixedValueParameter<IntValue>(SeedParameterName, "The random seed used to initialize the new pseudo random number generator.", new IntValue(0)));
       Parameters.Add(new FixedValueParameter<BoolValue>(SetSeedRandomlyParameterName, "True if the random seed should be set to a random value, otherwise false.", new BoolValue(true)));
@@ -115 +131 @@
     #endregion
 
-    protected override void Run(CancellationToken cancellationToken) {
+    protected override void Initialize(CancellationToken cancellationToken) {
+      base.Initialize(cancellationToken);
       var random = new MersenneTwister();
       if (SetSeedRandomly) SeedParameter.Value.Value = new System.Random().Next();
       random.Reset(Seed);
-      var solution = CreateM5RegressionSolution(Problem.ProblemData, random, LeafModel, Split, Pruning, UseHoldout, HoldoutSize, MinimalNodeSize, GenerateRules, Results, cancellationToken);
-      AnalyzeSolution(solution);
+      stateScope = InitializeScope(random, Problem.ProblemData, Pruning, MinimalNodeSize, LeafModel, Splitter, GenerateRules, UseHoldout, HoldoutSize);
+      stateScope.Variables.Add(new Variable("Algorithm", this));
+      Results.AddOrUpdateResult("StateScope", stateScope);
+    }
+
+    protected override void Run(CancellationToken cancellationToken) {
+      var model = Build(stateScope, Results, cancellationToken);
+      AnalyzeSolution(model.CreateRegressionSolution(Problem.ProblemData), Results, Problem.ProblemData);
     }
 
     #region Static Interface
-    public static IRegressionSolution CreateM5RegressionSolution(IRegressionProblemData problemData, IRandom random,
-      ILeafModel leafModel = null, ISpliter spliter = null, IPruning pruning = null,
-      bool useHoldout = false, double holdoutSize = 0.2, int minNumInstances = 4, bool generateRules = false, ResultCollection results = null, CancellationToken? cancellationToken = null) {
-      //set default values
+    public static IRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData, IRandom random, ILeafModel leafModel = null, ISplitter splitter = null, IPruning pruning = null,
+      bool useHoldout = false, double holdoutSize = 0.2, int minimumLeafSize = 4, bool generateRules = false, ResultCollection results = null, CancellationToken? cancellationToken = null) {
       if (leafModel == null) leafModel = new LinearLeaf();
-      if (spliter == null) spliter = new M5Spliter();
+      if (splitter == null) splitter = new M5Splitter();
       if (cancellationToken == null) cancellationToken = CancellationToken.None;
-      if (pruning == null) pruning = new M5LeafBottomUpPruning();
-
+      if (pruning == null) pruning = new ComplexityPruning();
+
+      var stateScope = InitializeScope(random, problemData, pruning, minimumLeafSize, leafModel, splitter, generateRules, useHoldout, holdoutSize);
+      var model = Build(stateScope, results, cancellationToken.Value);
+      return model.CreateRegressionSolution(problemData);
+    }
+
+    public static void UpdateModel(IM5Model model, IRegressionProblemData problemData, IRandom random, ILeafModel leafModel, CancellationToken? cancellationToken = null) {
+      if (cancellationToken == null) cancellationToken = CancellationToken.None;
+      var regressionTreeParameters = new RegressionTreeParameters(leafModel, problemData, random);
+      var scope = new Scope();
+      scope.Variables.Add(new Variable(RegressionTreeParameterVariableName, regressionTreeParameters));
+      leafModel.Initialize(scope);
+      model.Update(problemData.TrainingIndices.ToList(), scope, cancellationToken.Value);
+    }
+    #endregion
+
+    #region Helpers
+    private static IScope InitializeScope(IRandom random, IRegressionProblemData problemData, IPruning pruning, int minLeafSize, ILeafModel leafModel, ISplitter splitter, bool GenerateRules, bool useHoldout, double holdoutSize) {
+      var stateScope = new Scope("RegressionTreeStateScope");
+
+      //reduce RegressionProblemData to AllowedInput & Target column wise and to TrainingSet row wise
       var doubleVars = new HashSet<string>(problemData.Dataset.DoubleVariables);
       var vars = problemData.AllowedInputVariables.Concat(new[] {problemData.TargetVariable}).ToArray();
       if (vars.Any(v => !doubleVars.Contains(v))) throw new NotSupportedException("M5 regression supports only double valued input or output features.");
-
-      var values = vars.Select(v => problemData.Dataset.GetDoubleValues(v, problemData.TrainingIndices).ToArray()).ToArray();
-      if (values.Any(v => v.Any(x => double.IsNaN(x) || double.IsInfinity(x))))
+      var doubles = vars.Select(v => problemData.Dataset.GetDoubleValues(v, problemData.TrainingIndices).ToArray()).ToArray();
+      if (doubles.Any(v => v.Any(x => double.IsNaN(x) || double.IsInfinity(x))))
         throw new NotSupportedException("M5 regression does not support NaN or infinity values in the input dataset.");
-
-      var trainingData = new Dataset(vars, values);
+      var trainingData = new Dataset(vars, doubles);
       var pd = new RegressionProblemData(trainingData, problemData.AllowedInputVariables, problemData.TargetVariable);
       pd.TrainingPartition.End = pd.TestPartition.Start = pd.TestPartition.End = pd.Dataset.Rows;
       pd.TrainingPartition.Start = 0;
 
-      //create & build Model
-      var m5Params = new M5Parameters(pruning, minNumInstances, leafModel, pd, random, spliter, results);
-
-      IReadOnlyList<int> trainingRows, pruningRows;
-      GeneratePruningSet(problemData.TrainingIndices.ToArray(), random, useHoldout, holdoutSize, out trainingRows, out pruningRows);
-
-      IM5Model model;
-      if (generateRules)
-        model = M5RuleSetModel.CreateRuleModel(problemData.TargetVariable, m5Params);
-      else
-        model = M5TreeModel.CreateTreeModel(problemData.TargetVariable, m5Params);
-
-      model.Build(trainingRows, pruningRows, m5Params, cancellationToken.Value);
-      return model.CreateRegressionSolution(problemData);
-    }
-
-    public static void UpdateM5Model(IRegressionModel model, IRegressionProblemData problemData, IRandom random,
-      ILeafModel leafModel, CancellationToken? cancellationToken = null) {
-      var m5Model = model as IM5Model;
-      if (m5Model == null) throw new ArgumentException("This type of model can not be updated");
-      UpdateM5Model(m5Model, problemData, random, leafModel, cancellationToken);
-    }
-
-    private static void UpdateM5Model(IM5Model model, IRegressionProblemData problemData, IRandom random,
-      ILeafModel leafModel = null, CancellationToken? cancellationToken = null) {
-      if (cancellationToken == null) cancellationToken = CancellationToken.None;
-      var m5Params = new M5Parameters(leafModel, problemData, random);
-      model.Update(problemData.TrainingIndices.ToList(), m5Params, cancellationToken.Value);
-    }
-    #endregion
-
-    #region Helpers
+      //store regression tree parameters
+      var regressionTreeParams = new RegressionTreeParameters(pruning, minLeafSize, leafModel, pd, random, splitter);
+      stateScope.Variables.Add(new Variable(RegressionTreeParameterVariableName, regressionTreeParams));
+
+      //initialize tree operators
+      pruning.Initialize(stateScope);
+      splitter.Initialize(stateScope);
+      leafModel.Initialize(stateScope);
+
+      //store unbuilt model
+      IItem model;
+      if (GenerateRules) {
+        model = RegressionRuleSetModel.CreateRuleModel(problemData.TargetVariable, regressionTreeParams);
+        RegressionRuleSetModel.Initialize(stateScope);
+      }
+      else {
+        model = RegressionNodeTreeModel.CreateTreeModel(problemData.TargetVariable, regressionTreeParams);
+      }
+      stateScope.Variables.Add(new Variable(ModelVariableName, model));
+
+      //store training & pruning indices
+      IReadOnlyList<int> trainingSet, pruningSet;
+      GeneratePruningSet(pd.TrainingIndices.ToArray(), random, useHoldout, holdoutSize, out trainingSet, out pruningSet);
+      stateScope.Variables.Add(new Variable(TrainingSetVariableName, new IntArray(trainingSet.ToArray())));
+      stateScope.Variables.Add(new Variable(PruningSetVariableName, new IntArray(pruningSet.ToArray())));
+
+      return stateScope;
+    }
+
+    private static IRegressionModel Build(IScope stateScope, ResultCollection results, CancellationToken cancellationToken) {
+      var model = (IM5Model)stateScope.Variables[ModelVariableName].Value;
+      var trainingRows = (IntArray)stateScope.Variables[TrainingSetVariableName].Value;
+      var pruningRows = (IntArray)stateScope.Variables[PruningSetVariableName].Value;
+      model.Build(trainingRows.ToArray(), pruningRows.ToArray(), stateScope, results, cancellationToken);
+      return model;
+    }
+
     private static void GeneratePruningSet(IReadOnlyList<int> allrows, IRandom random, bool useHoldout, double holdoutSize, out IReadOnlyList<int> training, out IReadOnlyList<int> pruning) {
       if (!useHoldout) {
@@ -190 +234 @@
     }
 
-    private void AnalyzeSolution(IRegressionSolution solution) {
-      Results.Add(new Result("RegressionSolution", (IItem)solution.Clone()));
-
-      Dictionary<string, int> frequencies;
-      if (!GenerateRules) {
-        Results.Add(M5Analyzer.CreateLeafDepthHistogram((M5TreeModel)solution.Model));
-        frequencies = M5Analyzer.GetTreeVariableFrequences((M5TreeModel)solution.Model);
-      }
-      else {
-        Results.Add(M5Analyzer.CreateRulesResult((M5RuleSetModel)solution.Model, Problem.ProblemData, "M5TreeResult", true));
-        frequencies = M5Analyzer.GetRuleVariableFrequences((M5RuleSetModel)solution.Model);
-        Results.Add(M5Analyzer.CreateCoverageDiagram((M5RuleSetModel)solution.Model, Problem.ProblemData));
+    private void AnalyzeSolution(IRegressionSolution solution, ResultCollection results, IRegressionProblemData problemData) {
+      results.Add(new Result("RegressionSolution", (IItem)solution.Clone()));
+
+      Dictionary<string, int> frequencies = null;
+
+      var tree = solution.Model as RegressionNodeTreeModel;
+      if (tree != null) {
+        results.Add(RegressionTreeAnalyzer.CreateLeafDepthHistogram(tree));
+        frequencies = RegressionTreeAnalyzer.GetTreeVariableFrequences(tree);
+        RegressionTreeAnalyzer.AnalyzeNodes(tree, results, problemData);
+      }
+
+      var ruleSet = solution.Model as RegressionRuleSetModel;
+      if (ruleSet != null) {
+        results.Add(RegressionTreeAnalyzer.CreateRulesResult(ruleSet, problemData, "M5Rules", true));
+        frequencies = RegressionTreeAnalyzer.GetRuleVariableFrequences(ruleSet);
+        results.Add(RegressionTreeAnalyzer.CreateCoverageDiagram(ruleSet, problemData));
       }
 
       //Variable frequencies
-      var sum = frequencies.Values.Sum();
-      sum = sum == 0 ? 1 : sum;
-      var impactArray = new DoubleArray(frequencies.Select(i => (double)i.Value / sum).ToArray()) {
-        ElementNames = frequencies.Select(i => i.Key)
-      };
-      Results.Add(new Result("Variable Frequences", "relative frequencies of variables in rules and tree nodes", impactArray));
+      if (frequencies != null) {
+        var sum = frequencies.Values.Sum();
+        sum = sum == 0 ? 1 : sum;
+        var impactArray = new DoubleArray(frequencies.Select(i => (double)i.Value / sum).ToArray()) {
+          ElementNames = frequencies.Select(i => i.Key)
+        };
+        results.Add(new Result("Variable Frequences", "relative frequencies of variables in rules and tree nodes", impactArray));
+      }
+
+      var pruning = Pruning as ComplexityPruning;
+      if (pruning != null && tree != null)
+        RegressionTreeAnalyzer.PruningChart(tree, pruning, results);
     }
     #endregion

branches/M5Regression/HeuristicLab.Algorithms.DataAnalysis/3.4/M5Regression/Pruning/NoPruning.cs

@@ -21 +21 @@
 
 using System.Collections.Generic;
+using System.Threading;
 using HeuristicLab.Common;
 using HeuristicLab.Core;
@@ -38 +39 @@
       return new NoPruning(this, cloner);
     }
+    #endregion
+
+
     public int MinLeafSize(IRegressionProblemData pd, ILeafModel leafModel) {
       return 0;
     }
-    #endregion
+    public void Initialize(IScope states) { }
+
+    public void Prune(RegressionNodeTreeModel treeModel, IReadOnlyList<int> trainingRows, IReadOnlyList<int> pruningRows, IScope scope, CancellationToken cancellationToken) { }
   }
 }

branches/M5Regression/HeuristicLab.Algorithms.DataAnalysis/3.4/M5Regression/Spliting/OrderImpurityCalculator.cs

@@ -28 +28 @@
   /// <summary>
   /// Helper class for incremental split calculation.
-  /// Used while moving a potential Spliter along the ordered training Instances
+  /// Used while moving a potential Splitter along the ordered training Instances
   /// </summary>
   internal class OrderImpurityCalculator {
@@ -105 +105 @@
       VarRight = NoRight <= 0 ? 0 : Math.Abs(NoRight * SqSumRight - SumRight * SumRight) / (NoRight * NoRight);
 
-      if (Order <= 0) throw new ArgumentException("Spliter order must be larger than 0");
+      if (Order <= 0) throw new ArgumentException("Splitter order must be larger than 0");
       if (Order.IsAlmost(1)) {
         y = VarTotal;
@@ -116 +116 @@
         yr = Math.Pow(VarRight, 1.0 / Order);
       }
-      var t = NoRight + NoLeft;
-      if (NoLeft <= 0.0 || NoRight <= 0.0) Impurity = double.MinValue; //Spliter = 0;
-      else Impurity = y - NoLeft / t * yl - NoRight / t * yr; //  Spliter = y - NoLeft / NoRight * yl - NoRight / NoLeft * yr
+      if (NoLeft <= 0.0 || NoRight <= 0.0) Impurity = double.MinValue; //Splitter = 0;
+      else Impurity = y - (NoLeft * yl + NoRight * yr) / (NoRight + NoLeft);
     }
     #endregion