source: branches/HeuristicLab.TimeSeries/HeuristicLab.Problems.DataAnalysis.Symbolic.TimeSeriesPrognosis/3.4/SymbolicTimeSeriesPrognosisModel.cs @ 7463

#region License Information
/* HeuristicLab
 * Copyright (C) 2002-2011 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.Drawing;
using System.Linq;
using HeuristicLab.Common;
using HeuristicLab.Core;
using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;

namespace HeuristicLab.Problems.DataAnalysis.Symbolic.TimeSeriesPrognosis {
  /// <summary>
  /// Represents a symbolic time-series prognosis model
  /// </summary>
  [StorableClass]
  [Item(Name = "Symbolic Time-Series Prognosis Model", Description = "Represents a symbolic time series prognosis model.")]
  public class SymbolicTimeSeriesPrognosisModel : NamedItem, ISymbolicTimeSeriesPrognosisModel {
    public override Image ItemImage {
      get { return HeuristicLab.Common.Resources.VSImageLibrary.Function; }
    }
    [Storable(DefaultValue = double.MinValue)]
    private double lowerEstimationLimit;
    [Storable(DefaultValue = double.MaxValue)]
    private double upperEstimationLimit;

    #region properties

    [Storable]
    private ISymbolicExpressionTree symbolicExpressionTree;
    public ISymbolicExpressionTree SymbolicExpressionTree {
      get { return symbolicExpressionTree; }
    }

    [Storable]
    private ISymbolicTimeSeriesPrognosisExpressionTreeInterpreter interpreter;
    public ISymbolicTimeSeriesPrognosisExpressionTreeInterpreter Interpreter {
      get { return interpreter; }
    }

    ISymbolicDataAnalysisExpressionTreeInterpreter ISymbolicDataAnalysisModel.Interpreter {
      get { return (ISymbolicDataAnalysisExpressionTreeInterpreter)interpreter; }
    }

    #endregion

    [Storable]
    private string[] targetVariables;


    [StorableConstructor]
    protected SymbolicTimeSeriesPrognosisModel(bool deserializing) : base(deserializing) { }
    protected SymbolicTimeSeriesPrognosisModel(SymbolicTimeSeriesPrognosisModel original, Cloner cloner)
      : base(original, cloner) {
      this.symbolicExpressionTree = cloner.Clone(original.symbolicExpressionTree);
      this.interpreter = cloner.Clone(original.interpreter);
      this.targetVariables = new string[original.targetVariables.Length];
      Array.Copy(original.targetVariables, this.targetVariables, this.targetVariables.Length);
      this.lowerEstimationLimit = original.lowerEstimationLimit;
      this.upperEstimationLimit = original.upperEstimationLimit;
    }
    public SymbolicTimeSeriesPrognosisModel(ISymbolicExpressionTree tree, ISymbolicTimeSeriesPrognosisExpressionTreeInterpreter interpreter, IEnumerable<string> targetVariables, double lowerLimit = double.MinValue, double upperLimit = double.MaxValue)
      : base() {
      this.name = ItemName;
      this.description = ItemDescription;
      this.symbolicExpressionTree = tree;
      this.interpreter = interpreter; this.targetVariables = targetVariables.ToArray();
      this.lowerEstimationLimit = lowerLimit;
      this.upperEstimationLimit = upperLimit;
    }

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

    public IEnumerable<IEnumerable<IEnumerable<double>>> GetPrognosedValues(Dataset dataset, IEnumerable<int> rows, int horizon) {
      var enumerator =
        Interpreter.GetSymbolicExpressionTreeValues(SymbolicExpressionTree, dataset, targetVariables, rows, horizon).
          GetEnumerator();
      foreach (var r in rows) {
        var l = new List<double[]>();
        for (int h = 0; h < horizon; h++) {
          double[] components = new double[targetVariables.Length];
          for (int c = 0; c < components.Length; c++) {
            enumerator.MoveNext();
            components[c] = Math.Min(upperEstimationLimit, Math.Max(lowerEstimationLimit, enumerator.Current));
          }
          l.Add(components);
        }
        yield return l;
      }
    }

    public ISymbolicTimeSeriesPrognosisSolution CreateTimeSeriesPrognosisSolution(ITimeSeriesPrognosisProblemData problemData) {
      return new SymbolicTimeSeriesPrognosisSolution(this, problemData);
    }
    ITimeSeriesPrognosisSolution ITimeSeriesPrognosisModel.CreateTimeSeriesPrognosisSolution(ITimeSeriesPrognosisProblemData problemData) {
      return CreateTimeSeriesPrognosisSolution(problemData);
    }

    public static void Scale(SymbolicTimeSeriesPrognosisModel model, ITimeSeriesPrognosisProblemData problemData) {
      var dataset = problemData.Dataset;
      var targetVariables = problemData.TargetVariables.ToArray();
      var rows = problemData.TrainingIndizes;
      var estimatedValuesEnumerator = model.Interpreter.GetSymbolicExpressionTreeValues(model.SymbolicExpressionTree, dataset,
                                                                              targetVariables,
                                                                              rows).GetEnumerator();
      var scalingParameterCalculators =
        problemData.TargetVariables.Select(v => new OnlineLinearScalingParameterCalculator()).ToArray();
      var targetValuesEnumerator = problemData.Dataset.GetVectorEnumerable(targetVariables, rows).GetEnumerator();

      var more = targetValuesEnumerator.MoveNext() & estimatedValuesEnumerator.MoveNext();
      // foreach row
      while (more) {
        // foreach component
        for (int i = 0; i < targetVariables.Length; i++) {
          scalingParameterCalculators[i].Add(estimatedValuesEnumerator.Current, targetValuesEnumerator.Current);
          more = estimatedValuesEnumerator.MoveNext() & targetValuesEnumerator.MoveNext();
        }
      }

      for (int i = 0; i < targetVariables.Count(); i++) {
        if (scalingParameterCalculators[i].ErrorState != OnlineCalculatorError.None) continue;
        double alpha = scalingParameterCalculators[i].Alpha;
        double beta = scalingParameterCalculators[i].Beta;
        ConstantTreeNode alphaTreeNode = null;
        ConstantTreeNode betaTreeNode = null;
        // check if model has been scaled previously by analyzing the structure of the tree
        var startNode = model.SymbolicExpressionTree.Root.GetSubtree(0);
        if (startNode.GetSubtree(i).Symbol is Addition) {
          var addNode = startNode.GetSubtree(i);
          if (addNode.SubtreeCount == 2 && addNode.GetSubtree(0).Symbol is Multiplication &&
              addNode.GetSubtree(1).Symbol is Constant) {
            alphaTreeNode = addNode.GetSubtree(1) as ConstantTreeNode;
            var mulNode = addNode.GetSubtree(0);
            if (mulNode.SubtreeCount == 2 && mulNode.GetSubtree(1).Symbol is Constant) {
              betaTreeNode = mulNode.GetSubtree(1) as ConstantTreeNode;
            }
          }
        }
        // if tree structure matches the structure necessary for linear scaling then reuse the existing tree nodes
        if (alphaTreeNode != null && betaTreeNode != null) {
          betaTreeNode.Value *= beta;
          alphaTreeNode.Value *= beta;
          alphaTreeNode.Value += alpha;
        } else {
          var mainBranch = startNode.GetSubtree(i);
          startNode.RemoveSubtree(i);
          var scaledMainBranch = MakeSum(MakeProduct(mainBranch, beta), alpha);
          startNode.InsertSubtree(i, scaledMainBranch);
        }
      } // foreach
    }

    private static ISymbolicExpressionTreeNode MakeSum(ISymbolicExpressionTreeNode treeNode, double alpha) {
      if (alpha.IsAlmost(0.0)) {
        return treeNode;
      } else {
        var addition = new Addition();
        var node = addition.CreateTreeNode();
        var alphaConst = MakeConstant(alpha);
        node.AddSubtree(treeNode);
        node.AddSubtree(alphaConst);
        return node;
      }
    }

    private static ISymbolicExpressionTreeNode MakeProduct(ISymbolicExpressionTreeNode treeNode, double beta) {
      if (beta.IsAlmost(1.0)) {
        return treeNode;
      } else {
        var multipliciation = new Multiplication();
        var node = multipliciation.CreateTreeNode();
        var betaConst = MakeConstant(beta);
        node.AddSubtree(treeNode);
        node.AddSubtree(betaConst);
        return node;
      }
    }

    private static ISymbolicExpressionTreeNode MakeConstant(double c) {
      var node = (ConstantTreeNode)(new Constant()).CreateTreeNode();
      node.Value = c;
      return node;
    }
  }
}