Changeset 15614 for branches/M5Regression/HeuristicLab.Algorithms.DataAnalysis/3.4/M5Regression/M5Utilities/M5StaticUtilities.cs

Timestamp:

01/15/18 08:21:48 (6 years ago)

Author:

bwerth

Message:

#2847 made changes to M5 according to review comments

Location:

branches/M5Regression/HeuristicLab.Algorithms.DataAnalysis

Files:

• . (modified) (1 prop)
• 3.4 (modified) (1 prop)
• 3.4/M5Regression/M5Utilities/M5StaticUtilities.cs (modified) (2 diffs)

branches/M5Regression/HeuristicLab.Algorithms.DataAnalysis/3.4/M5Regression/M5Utilities/M5StaticUtilities.cs

@@ -21 +21 @@
 
 using System;
+using System.Collections.Generic;
+using System.Linq;
 using System.Threading;
+using HeuristicLab.Common;
 using HeuristicLab.Core;
 using HeuristicLab.Data;
 using HeuristicLab.Optimization;
+using HeuristicLab.Problems.DataAnalysis;
 
 namespace HeuristicLab.Algorithms.DataAnalysis {
   internal static class M5StaticUtilities {
-    public static ResultCollection RunSubAlgorithm(IAlgorithm alg, int random, CancellationToken cancellation) {
+    public static ResultCollection RunSubAlgorithm(IAlgorithm alg, int random, CancellationToken cancellationToken) {
       if (alg.Parameters.ContainsKey("SetSeedRandomly") && alg.Parameters.ContainsKey("Seed")) {
         var seed = alg.Parameters["Seed"].ActualValue as IntValue;
@@ -38 +42 @@
       }
       if (alg.ExecutionState != ExecutionState.Paused) alg.Prepare();
-      alg.Start(cancellation);
+      alg.Start(cancellationToken);
       return alg.Results;
+    }
+
+    public static void SplitRows(IReadOnlyList<int> rows, IDataset data, string splitAttr, double splitValue, out IReadOnlyList<int> leftRows, out IReadOnlyList<int> rightRows) {
+      //TODO check and revert points at borders are now used multipe times
+      var assignment = data.GetDoubleValues(splitAttr, rows).Select(x => x.IsAlmost(splitValue) ? 2 : x < splitValue ? 0 : 1).ToArray();
+      leftRows = rows.Zip(assignment, (i, b) => new {i, b}).Where(x => x.b == 0 || x.b == 2).Select(x => x.i).ToList();
+      rightRows = rows.Zip(assignment, (i, b) => new {i, b}).Where(x => x.b > 0).Select(x => x.i).ToList();
+    }
+
+    public static IRegressionModel BuildModel(IReadOnlyList<int> rows, M5Parameters parameters, ILeafModel leafModel, CancellationToken cancellation, out int numParams) {
+      var reducedData = ReduceDataset(parameters.Data, rows, parameters.AllowedInputVariables.ToArray(), parameters.TargetVariable);
+      var pd = new RegressionProblemData(reducedData, parameters.AllowedInputVariables.ToArray(), parameters.TargetVariable);
+      pd.TrainingPartition.Start = 0;
+      pd.TrainingPartition.End = pd.TestPartition.Start = pd.TestPartition.End = reducedData.Rows;
+
+      int numP;
+      var model = leafModel.Build(pd, parameters.Random, cancellation, out numP);
+      numParams = numP;
+      cancellation.ThrowIfCancellationRequested();
+      return model;
+    }
+
+    public static IDataset ReduceDataset(IDataset data, IReadOnlyList<int> rows, IReadOnlyList<string> inputVariables, string target) {
+      return new Dataset(inputVariables.Concat(new[] {target}), inputVariables.Concat(new[] {target}).Select(x => data.GetDoubleValues(x, rows).ToList()));
     }
   }