source: branches/GP-MoveOperators/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4/ReplaceBranchMultiMoveGenerator.cs @ 10235

#region License Information
/* HeuristicLab
 * Copyright (C) 2002-2012 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
 *
 * This file is part of HeuristicLab.
 *
 * HeuristicLab is free software: you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation, either version 3 of the License, or
 * (at your option) any later version.
 *
 * HeuristicLab is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with HeuristicLab. If not, see <http://www.gnu.org/licenses/>.
 */
#endregion

using System;
using System.Collections.Generic;
using System.Linq;
using HeuristicLab.Common;
using HeuristicLab.Core;
using HeuristicLab.Data;
using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
using HeuristicLab.Operators;
using HeuristicLab.Optimization;
using HeuristicLab.Parameters;
using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;

namespace HeuristicLab.Problems.DataAnalysis.Symbolic.Regression {
  [Item("ReplaceBranchMultiMoveGenerator", "")]
  [StorableClass]
  public class ReplaceBranchMultiMoveGenerator : SingleSuccessorOperator, IStochasticOperator, ISymbolicExpressionTreeMoveOperator, IMultiMoveGenerator,
    ISymbolicDataAnalysisInterpreterOperator, ISymbolicExpressionTreeGrammarBasedOperator, ISymbolicExpressionTreeSizeConstraintOperator {
    public ILookupParameter<IRandom> RandomParameter {
      get { return (ILookupParameter<IRandom>)Parameters["Random"]; }
    }
    public IValueLookupParameter<IntValue> SampleSizeParameter {
      get { return (IValueLookupParameter<IntValue>)Parameters["SampleSize"]; }
    }
    public ILookupParameter<ISymbolicDataAnalysisExpressionTreeInterpreter> SymbolicDataAnalysisTreeInterpreterParameter {
      get { return (ILookupParameter<ISymbolicDataAnalysisExpressionTreeInterpreter>)Parameters["Interpreter"]; }
    }

    public IValueLookupParameter<ISymbolicExpressionGrammar> SymbolicExpressionTreeGrammarParameter {
      get { return (IValueLookupParameter<ISymbolicExpressionGrammar>)Parameters["Grammar"]; }
    }
    public ILookupParameter<IRegressionProblemData> ProblemDataParameter {
      get { return (ILookupParameter<IRegressionProblemData>)Parameters["ProblemData"]; }
    }
    public IntValue SampleSize {
      get { return SampleSizeParameter.Value; }
      set { SampleSizeParameter.Value = value; }
    }
    public ILookupParameter<ISymbolicExpressionTree> SymbolicExpressionTreeParameter {
      get { return (ILookupParameter<ISymbolicExpressionTree>)Parameters["SymbolicExpressionTree"]; }
    }
    public ILookupParameter<ReplaceBranchMove> ReplaceBranchMoveParameter {
      get { return (LookupParameter<ReplaceBranchMove>)Parameters["ReplaceBranchMove"]; }
    }

    public IValueParameter<IntValue> ReplacementBranchesPoolSize {
      get { return (IValueParameter<IntValue>)Parameters["ReplacementBranchesPoolSize"]; }
    }

    public IValueParameter<IntValue> MaxReplacementBranchLength {
      get { return (IValueParameter<IntValue>)Parameters["MaxReplacementBranchLength"]; }
    }

    public IValueParameter<IntValue> MaxReplacementBranchDepth {
      get { return (IValueParameter<IntValue>)Parameters["MaxReplacementBranchDepth"]; }
    }

    protected ScopeParameter CurrentScopeParameter {
      get { return (ScopeParameter)Parameters["CurrentScope"]; }
    }

    public IValueLookupParameter<IntValue> MaximumSymbolicExpressionTreeDepthParameter {
      get { return (IValueLookupParameter<IntValue>)Parameters["MaximumSymbolicExpressionTreeDepth"]; }
    }

    public IValueLookupParameter<IntValue> MaximumSymbolicExpressionTreeLengthParameter {
      get { return (IValueLookupParameter<IntValue>)Parameters["MaximumSymbolicExpressionTreeLength"]; }
    }

    public IValueLookupParameter<IntValue> NeighbourhoodSizeParameter {
      get { return (IValueLookupParameter<IntValue>)Parameters["NeighbourhoodSize"]; }
    }
    public IValueLookupParameter<BoolValue> SemanticParameter {
      get { return (IValueLookupParameter<BoolValue>)Parameters["Semantic"]; }
    }
    public ILookupParameter<ItemList<ISymbolicExpressionTree>> FragmentsParameter {
      get { return (ILookupParameter<ItemList<ISymbolicExpressionTree>>)Parameters["Fragments"]; }
    }
    public ILookupParameter<ItemList<DoubleArray>> FragmentOutputsParameter {
      get { return (ILookupParameter<ItemList<DoubleArray>>)Parameters["FragmentOutputs"]; }
    }

    [StorableConstructor]
    protected ReplaceBranchMultiMoveGenerator(bool deserializing) : base(deserializing) { }
    protected ReplaceBranchMultiMoveGenerator(ReplaceBranchMultiMoveGenerator original, Cloner cloner) : base(original, cloner) { }
    public ReplaceBranchMultiMoveGenerator()
      : base() {
      Parameters.Add(new LookupParameter<IRandom>("Random", "The random number generator."));
      Parameters.Add(new ValueLookupParameter<IntValue>("SampleSize", "The number of moves to generate."));

      Parameters.Add(new LookupParameter<ISymbolicExpressionTree>("SymbolicExpressionTree", "The symbolic expression tree for which moves should be generated."));
      Parameters.Add(new LookupParameter<ReplaceBranchMove>("ReplaceBranchMove", "The moves that should be generated in subscopes."));
      Parameters.Add(new ScopeParameter("CurrentScope", "The current scope where the moves should be added as subscopes."));
      Parameters.Add(new ValueLookupParameter<ISymbolicExpressionGrammar>("Grammar"));
      Parameters.Add(new LookupParameter<ISymbolicDataAnalysisExpressionTreeInterpreter>("Interpreter"));
      Parameters.Add(new LookupParameter<IRegressionProblemData>("ProblemData"));
      Parameters.Add(new ValueParameter<IntValue>("ReplacementBranchesPoolSize", new IntValue(10000)));
      Parameters.Add(new ValueParameter<IntValue>("MaxReplacementBranchLength", new IntValue(8)));
      Parameters.Add(new ValueParameter<IntValue>("MaxReplacementBranchDepth", new IntValue(4)));
      Parameters.Add(new ValueLookupParameter<IntValue>("MaximumSymbolicExpressionTreeDepth"));
      Parameters.Add(new ValueLookupParameter<IntValue>("MaximumSymbolicExpressionTreeLength"));
      Parameters.Add(new ValueLookupParameter<IntValue>("NeighbourhoodSize", new IntValue(5)));
      Parameters.Add(new ValueLookupParameter<BoolValue>("Semantic", new BoolValue()));
      Parameters.Add(new LookupParameter<ItemList<ISymbolicExpressionTree>>("Fragments"));
      Parameters.Add(new LookupParameter<ItemList<DoubleArray>>("FragmentOutputs"));
    }


    [StorableHook(HookType.AfterDeserialization)]
    private void AfterDeserialization() {
      if (!Parameters.ContainsKey("MaximumSymbolicExpressionTreeDepth")) {
        Parameters.Add(new ValueLookupParameter<IntValue>("MaximumSymbolicExpressionTreeDepth"));
        Parameters.Add(new ValueLookupParameter<IntValue>("MaximumSymbolicExpressionTreeLength"));
      }
      if (!Parameters.ContainsKey("NeighbourhoodSize")) {
        Parameters.Add(new ValueLookupParameter<IntValue>("NeighbourhoodSize", new IntValue(5)));
      }

    }


    public override IDeepCloneable Clone(Cloner cloner) {
      return new ReplaceBranchMultiMoveGenerator(this, cloner);
    }

    public override IOperation Apply() {
      var random = RandomParameter.ActualValue;
      if (FragmentsParameter.ActualValue == null || FragmentOutputsParameter.ActualValue == null) {
        InitializeOperator();
      }

      var tree = SymbolicExpressionTreeParameter.ActualValue;

      string moveParameterName = ReplaceBranchMoveParameter.ActualName;
      var moveScopes = new List<Scope>();
      int n = SampleSizeParameter.ActualValue.Value;

      var moves = GenerateMoves(tree, random, n);

      foreach (var m in moves) {
        var moveScope = new Scope(moveScopes.Count.ToString());
        moveScope.Variables.Add(new HeuristicLab.Core.Variable(moveParameterName, m));
        moveScopes.Add(moveScope);
      }
      CurrentScopeParameter.ActualValue.SubScopes.AddRange(moveScopes);
      return base.Apply();
    }

    public IEnumerable<ReplaceBranchMove> GenerateMoves(ISymbolicExpressionTree tree, IRandom random, int n) {
      int maxDepth = MaximumSymbolicExpressionTreeDepthParameter.ActualValue.Value;
      int maxLength = MaximumSymbolicExpressionTreeLengthParameter.ActualValue.Value;
      var possibleInternalChildren = (from parent in tree.Root.GetSubtree(0).IterateNodesPrefix()
                                      from i in Enumerable.Range(0, parent.SubtreeCount)
                                      let currentChild = parent.GetSubtree(i)
                                      where currentChild.SubtreeCount > 0
                                      where tree.Root.GetBranchLevel(currentChild) < maxDepth + 2
                                      where tree.Length - currentChild.GetLength() < maxLength
                                      select new CutPoint(parent, i)).ToArray();

      var possibleLeaveChildren = (from parent in tree.Root.GetSubtree(0).IterateNodesPrefix()
                                   from i in Enumerable.Range(0, parent.SubtreeCount)
                                   let currentChild = parent.GetSubtree(i)
                                   where currentChild.SubtreeCount == 0
                                   where tree.Root.GetBranchLevel(currentChild) < maxDepth + 2
                                   where tree.Length - 1 < maxLength
                                   select new CutPoint(parent, i)).ToArray();
      if (possibleInternalChildren.Length == 0) possibleInternalChildren = possibleLeaveChildren;
      if (possibleLeaveChildren.Length == 0) possibleLeaveChildren = possibleInternalChildren;

      var root = (new ProgramRootSymbol()).CreateTreeNode();
      var start = (new StartSymbol()).CreateTreeNode();
      root.AddSubtree(start);
      var t = new SymbolicExpressionTree(root);
      var interpreter = SymbolicDataAnalysisTreeInterpreterParameter.ActualValue;
      var ds = ProblemDataParameter.ActualValue.Dataset;
      var rows = ProblemDataParameter.ActualValue.TrainingIndices;

      bool semantic = SemanticParameter.ActualValue.Value;
      int maxNeighbours = NeighbourhoodSizeParameter.ActualValue.Value;
      var count = 0;
      while (count < n) {
        // select a random replacement point
        CutPoint[] possibleChildren;
        if (random.NextDouble() < 0.9)
          possibleChildren = possibleInternalChildren;
        else possibleChildren = possibleLeaveChildren;
        var selected = possibleChildren[random.Next(possibleChildren.Length)];
        // evaluate 
        start.AddSubtree(selected.Parent.GetSubtree(selected.ChildIndex));
        var output = interpreter.GetSymbolicExpressionTreeValues(t, ds, rows).ToArray();
        start.RemoveSubtree(0);

        if (semantic) {
          foreach (var m in FindMostSimilarFragments(tree, maxLength, maxDepth, selected, random, maxNeighbours, output)) {
            yield return m;
            count++;
          }
        } else {
          foreach (var m in FindRandomFragments(tree, maxLength, maxDepth, selected, random, maxNeighbours, output)) {
            yield return m;
            count++;
          }
        }
      }
    }

    private IEnumerable<ReplaceBranchMove> FindRandomFragments(ISymbolicExpressionTree tree, int maxLength, int maxDepth, CutPoint selected,
  IRandom random, int maxNeighbours, double[] output) {
      var selectedFragments = new List<int>(maxNeighbours);
      int treeLength = tree.Length;
      int removedFragementLength = selected.Parent.GetSubtree(selected.ChildIndex).GetLength();
      int parentBranchLevel = tree.Root.GetBranchLevel(selected.Parent);
      int iterations = 0;
      int maxIterations = maxNeighbours + 100;
      var fragments = FragmentsParameter.ActualValue;
      var fragmentOutput = FragmentOutputsParameter.ActualValue;
      // select random fragments
      while (selectedFragments.Count < maxNeighbours && iterations++ < maxIterations) {
        int r = random.Next(fragments.Count);
        var selectedFragment = fragments[r];
        var selectedFragmentOutput = fragmentOutput[r];
        // if the branch is allowed in the selected point
        if (treeLength - removedFragementLength + selectedFragment.Length <= maxLength + 4 &&
          parentBranchLevel + selectedFragment.Depth - 2 <= maxDepth + 2 &&
          tree.Root.Grammar.IsAllowedChildSymbol(selected.Parent.Symbol, selectedFragment.Root.GetSubtree(0).GetSubtree(0).Symbol, selected.ChildIndex)) {
          selectedFragments.Add(r);
        }
      }
      // yield moves (we need to add linear scaling parameters for the inserted tree)
      return selectedFragments
        .Select(i => new ReplaceBranchMove(tree, selected.Parent, selected.ChildIndex, fragments[i].Root.GetSubtree(0).GetSubtree(0), output, fragmentOutput[i].ToArray(), i));
    }

    private IEnumerable<ReplaceBranchMove> FindMostSimilarFragments(ISymbolicExpressionTree tree, int maxLength, int maxDepth, CutPoint selected,
      IRandom random, int maxNeighbours, double[] output) {
      var fragments = FragmentsParameter.ActualValue;
      var fragmentOutput = FragmentOutputsParameter.ActualValue;
      var bestTrees = new SortedList<double, List<int>>(fragments.Count);
      int treeLength = tree.Length;
      int removedFragementLength = selected.Parent.GetSubtree(selected.ChildIndex).GetLength();
      int parentBranchLevel = tree.Root.GetBranchLevel(selected.Parent);
      // iterate over the whole pool of branches for replacement
      for (int i = 0; i < fragments.Count; i++) {
        // if the branch is allowed in the selected point
        if (treeLength - removedFragementLength + fragments[i].Length <= maxLength + 4 &&
          parentBranchLevel + fragments[i].Depth - 2 <= maxDepth + 2 &&
          tree.Root.Grammar.IsAllowedChildSymbol(selected.Parent.Symbol, fragments[i].Root.GetSubtree(0).GetSubtree(0).Symbol, selected.ChildIndex)) {
          OnlineCalculatorError error;
          // calculate the similarity
          double similarity = OnlinePearsonsRSquaredCalculator.Calculate(output, fragmentOutput[i], out error);
          similarity = Math.Round(similarity, 5);
          if (error != OnlineCalculatorError.None) similarity = 0.0;
          // if we found a new bestSimilarity then keep the replacement branch in a sorted list (keep maximally the n best for this replacement point)
          if (similarity < 1 && ((bestTrees.Count < maxNeighbours) || similarity > bestTrees.ElementAt(0).Key)) {
            if (!bestTrees.ContainsKey(similarity)) {
              var l = new List<int>();
              bestTrees.Add(similarity, l);
            }
            bestTrees[similarity].Add(i);
            if (bestTrees.Count > maxNeighbours) bestTrees.RemoveAt(0);
          }
        }
      }
      int c = 0;
      // yield moves (we need to add linear scaling parameters for the inserted tree)
      while (c < maxNeighbours) {
        var l = bestTrees.ElementAt(c % bestTrees.Count).Value;
        var index = l[random.Next(l.Count)];
        yield return
          new ReplaceBranchMove(tree, selected.Parent, selected.ChildIndex, fragments[index].Root.GetSubtree(0).GetSubtree(0),
                                output, fragmentOutput[index].ToArray(), index);
        c++;
      }
    }

    private void InitializeOperator() {
      // init locally and set only at the end in case of exceptions
      var trees = new List<ISymbolicExpressionTree>();
      var treeOutput = new List<double[]>();
      var random = RandomParameter.ActualValue;
      var g = SymbolicExpressionTreeGrammarParameter.ActualValue;
      var constSym = g.Symbols.Single(s => s is Constant);
      // temporarily disable constants
      double oldConstFreq = constSym.InitialFrequency;
      constSym.InitialFrequency = 0.0;
      var interpreter = SymbolicDataAnalysisTreeInterpreterParameter.ActualValue;
      var ds = ProblemDataParameter.ActualValue.Dataset;
      var rows = ProblemDataParameter.ActualValue.TrainingIndices;
      // create pool of random branches for replacement (no constants)
      // and evaluate the output
      // only keep fragments if the output does not contain invalid values
      var n = ReplacementBranchesPoolSize.Value.Value;
      while (trees.Count < n) {
        var t = ProbabilisticTreeCreator.Create(random, g, MaxReplacementBranchLength.Value.Value, MaxReplacementBranchDepth.Value.Value);
        var output = interpreter.GetSymbolicExpressionTreeValues(t, ds, rows);
        if (!output.Any(x => double.IsInfinity(x) || double.IsNaN(x))) {
          trees.Add(t);
          treeOutput.Add(output.ToArray());
        }
      }
      // enable constants again
      constSym.InitialFrequency = oldConstFreq;
      // set parameters
      FragmentsParameter.ActualValue = new ItemList<ISymbolicExpressionTree>(trees);
      FragmentOutputsParameter.ActualValue = new ItemList<DoubleArray>(treeOutput.Select(a => new DoubleArray(a)));
    }
  }
}