source: branches/DataAnalysis Refactoring/HeuristicLab.Problems.DataAnalysis.Symbolic/3.4/SymbolicDataAnalysisProblem.cs @ 5722

#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.Drawing;
using System.Linq;
using HeuristicLab.Common;
using HeuristicLab.Common.Resources;
using HeuristicLab.Core;
using HeuristicLab.Data;
using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
using HeuristicLab.Optimization;
using HeuristicLab.Parameters;
using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
using HeuristicLab.PluginInfrastructure;

//TODO configure training start / end
//TODO configure analyzer validation

namespace HeuristicLab.Problems.DataAnalysis.Symbolic {
  [StorableClass]
  public abstract class SymbolicDataAnalysisProblem<T, U, V> : HeuristicOptimizationProblem<U, V>, ISymbolicDataAnalysisProblem, IStorableContent
    where T : class,IDataAnalysisProblemData
    where U : class, ISymbolicDataAnalysisEvaluator<T>
    where V : class, ISymbolicDataAnalysisSolutionCreator {
    #region parameter names & descriptions
    private const string ProblemDataParameterName = "ProblemData";
    private const string SymbolicExpressionTreeGrammarParameterName = "SymbolicExpressionTreeGrammar";
    private const string SymbolicExpressionTreeInterpreterParameterName = "SymbolicExpressionTreeInterpreter";
    private const string MaximumSymbolicExpressionTreeDepthParameterName = "MaximumSymbolicExpressionTreeDepth";
    private const string MaximumSymbolicExpressionTreeLengthParameterName = "MaximumSymbolicExpressionTreeLength";
    private const string MaximumFunctionDefinitionsParameterName = "MaximumFunctionDefinitions";
    private const string MaximumFunctionArgumentsParameterName = "MaximumFunctionArguments";

    private const string ProblemDataParameterDescription = "";
    private const string SymbolicExpressionTreeGrammarParameterDescription = "The grammar that should be used for symbolic expression tree.";
    private const string SymoblicExpressionTreeInterpreterParameterDescription = "The interpreter that should be used to evaluate the symbolic expression tree.";
    private const string MaximumSymbolicExpressionTreeDepthParameterDescription = "Maximal depth of the symbolic expression. The minimum depth needed for the algorithm is 3 because two levels are reserved for the ProgramRoot and the Start symbol.";
    private const string MaximumSymbolicExpressionTreeLengthParameterDescription = "Maximal length of the symbolic expression.";
    private const string MaximumFunctionDefinitionsParameterDescription = "Maximal number of automatically defined functions";
    private const string MaximumFunctionArgumentsParameterDescription = "Maximal number of arguments of automatically defined functions.";
    #endregion

    #region parameter properties
    IParameter IDataAnalysisProblem.ProblemDataParameter {
      get { return ProblemDataParameter; }
    }
    public IValueParameter<T> ProblemDataParameter {
      get { return (IValueParameter<T>)Parameters[ProblemDataParameterName]; }
    }
    public IValueParameter<ISymbolicDataAnalysisGrammar> SymbolicExpressionTreeGrammarParameter {
      get { return (IValueParameter<ISymbolicDataAnalysisGrammar>)Parameters[SymbolicExpressionTreeGrammarParameterName]; }
    }
    public IValueParameter<ISymbolicDataAnalysisExpressionTreeInterpreter> SymbolicExpressionTreeInterpreterParameter {
      get { return (IValueParameter<ISymbolicDataAnalysisExpressionTreeInterpreter>)Parameters[SymbolicExpressionTreeInterpreterParameterName]; }
    }
    public IFixedValueParameter<IntValue> MaximumSymbolicExpressionTreeDepthParameter {
      get { return (IFixedValueParameter<IntValue>)Parameters[MaximumSymbolicExpressionTreeDepthParameterName]; }
    }
    public IFixedValueParameter<IntValue> MaximumSymbolicExpressionTreeLengthParameter {
      get { return (IFixedValueParameter<IntValue>)Parameters[MaximumSymbolicExpressionTreeLengthParameterName]; }
    }
    public IFixedValueParameter<IntValue> MaximumFunctionDefinitionsParameter {
      get { return (IFixedValueParameter<IntValue>)Parameters[MaximumFunctionDefinitionsParameterName]; }
    }
    public IFixedValueParameter<IntValue> MaximumFunctionArgumentsParameter {
      get { return (IFixedValueParameter<IntValue>)Parameters[MaximumFunctionArgumentsParameterName]; }
    }
    #endregion

    #region properties
    public string Filename { get; set; }
    public override Image ItemImage { get { return VSImageLibrary.Type; } }

    IDataAnalysisProblemData IDataAnalysisProblem.ProblemData {
      get { return ProblemData; }
    }
    public T ProblemData {
      get { return ProblemDataParameter.Value; }
      set { ProblemDataParameter.Value = value; }
    }

    public ISymbolicDataAnalysisGrammar SymbolicExpressionTreeGrammar {
      get { return SymbolicExpressionTreeGrammarParameter.Value; }
      set { SymbolicExpressionTreeGrammarParameter.Value = value; }
    }
    public ISymbolicDataAnalysisExpressionTreeInterpreter SymbolicExpressionTreeInterpreter {
      get { return SymbolicExpressionTreeInterpreterParameter.Value; }
      set { SymbolicExpressionTreeInterpreterParameter.Value = value; }
    }

    public IntValue MaximumSymbolicExpressionTreeDepth {
      get { return MaximumSymbolicExpressionTreeDepthParameter.Value; }
    }
    public IntValue MaximumSymbolicExpressionTreeLength {
      get { return MaximumSymbolicExpressionTreeLengthParameter.Value; }
    }
    public IntValue MaximumFunctionDefinitions {
      get { return MaximumFunctionDefinitionsParameter.Value; }
    }
    public IntValue MaximumFunctionArguments {
      get { return MaximumFunctionArgumentsParameter.Value; }
    }
    #endregion

    [StorableConstructor]
    protected SymbolicDataAnalysisProblem(bool deserializing) : base(deserializing) { }
    [StorableHook(HookType.AfterDeserialization)]
    private void AfterDeserialization() {
      RegisterEventHandlers();
    }
    protected SymbolicDataAnalysisProblem(SymbolicDataAnalysisProblem<T, U, V> original, Cloner cloner)
      : base(original, cloner) {
      RegisterEventHandlers();
    }

    protected SymbolicDataAnalysisProblem(T problemData, U evaluator, V solutionCreator)
      : base(evaluator, solutionCreator) {
      Parameters.Add(new ValueParameter<T>(ProblemDataParameterName, ProblemDataParameterDescription, problemData));
      Parameters.Add(new ValueParameter<ISymbolicDataAnalysisGrammar>(SymbolicExpressionTreeGrammarParameterName, SymbolicExpressionTreeGrammarParameterDescription));
      Parameters.Add(new ValueParameter<ISymbolicDataAnalysisExpressionTreeInterpreter>(SymbolicExpressionTreeInterpreterParameterName, SymoblicExpressionTreeInterpreterParameterDescription));
      Parameters.Add(new FixedValueParameter<IntValue>(MaximumSymbolicExpressionTreeDepthParameterName, MaximumSymbolicExpressionTreeDepthParameterDescription, new IntValue()));
      Parameters.Add(new FixedValueParameter<IntValue>(MaximumSymbolicExpressionTreeLengthParameterName, MaximumSymbolicExpressionTreeLengthParameterDescription, new IntValue()));
      Parameters.Add(new FixedValueParameter<IntValue>(MaximumFunctionDefinitionsParameterName, MaximumFunctionDefinitionsParameterDescription, new IntValue()));
      Parameters.Add(new FixedValueParameter<IntValue>(MaximumFunctionArgumentsParameterName, MaximumFunctionArgumentsParameterDescription, new IntValue()));

      SymbolicExpressionTreeGrammar = new TypeCoherentExpressionGrammar();
      SymbolicExpressionTreeInterpreter = new SymbolicDataAnalysisExpressionTreeInterpreter();

      InitializeOperators();

      UpdateGrammar();
      UpdateDatasetPartitions();
      RegisterEventHandlers();
    }

    protected virtual void UpdateDatasetPartitions() {
      Evaluator.SamplesStartParameter.Value.Value = ProblemData.TrainingPartitionStart.Value;
      Evaluator.SamplesEndParameter.Value.Value = ProblemData.TrainingPartitionEnd.Value;

      foreach (var analyzer in Operators.OfType<ISymbolicDataAnalysisValidationAnalyzer<U, T>>()) {
        analyzer.ValidationSamplesStartParameter.Value = new IntValue(ProblemData.TrainingPartitionStart.Value);
        analyzer.ValidationSamplesEndParameter.Value = new IntValue(ProblemData.TrainingPartitionEnd.Value);
      }
    }

    protected virtual void UpdateGrammar() {
      foreach (var varSymbol in SymbolicExpressionTreeGrammar.Symbols.OfType<HeuristicLab.Problems.DataAnalysis.Symbolic.Variable>()) {
        varSymbol.VariableNames = ProblemData.AllowedInputVariables;
      }
      foreach (var varSymbol in SymbolicExpressionTreeGrammar.Symbols.OfType<HeuristicLab.Problems.DataAnalysis.Symbolic.VariableCondition>()) {
        varSymbol.VariableNames = ProblemData.AllowedInputVariables;
      }
    }

    private void InitializeOperators() {
      Operators.AddRange(ApplicationManager.Manager.GetInstances<ISymbolicExpressionTreeOperator>());
      Operators.Add(new SymbolicExpressionSymbolFrequencyAnalyzer());
      Operators.Add(new SymbolicDataAnalysisVariableFrequencyAnalyzer());
      Operators.Add(new MinAverageMaxSymbolicExpressionTreeLengthAnalyzer());
      ParameterizeOperators();
    }

    #region events
    private void RegisterEventHandlers() {
      ProblemDataParameter.ValueChanged += new EventHandler(ProblemDataParameter_ValueChanged);
      ProblemDataParameter.Value.Changed += (object sender, EventArgs e) => OnProblemDataChanged();

      MaximumFunctionArguments.ValueChanged += new EventHandler(ArchitectureParameterValue_ValueChanged);
      MaximumFunctionDefinitions.ValueChanged += new EventHandler(ArchitectureParameterValue_ValueChanged);
      MaximumSymbolicExpressionTreeDepth.ValueChanged += new EventHandler(MaximumSymbolicExpressionTreeDepth_ValueChanged);
    }

    private void ProblemDataParameter_ValueChanged(object sender, EventArgs e) {
      ProblemDataParameter.Value.Changed += (object s, EventArgs args) => OnProblemDataChanged();
      OnProblemDataChanged();
    }

    private void ArchitectureParameterValue_ValueChanged(object sender, EventArgs e) {
      UpdateGrammar();
    }

    private void MaximumSymbolicExpressionTreeDepth_ValueChanged(object sender, EventArgs e) {
      if (MaximumSymbolicExpressionTreeDepth != null && MaximumSymbolicExpressionTreeDepth.Value < 3)
        MaximumSymbolicExpressionTreeDepth.Value = 3;
    }

    protected override void OnSolutionCreatorChanged() {
      base.OnSolutionCreatorChanged();
      SolutionCreator.SymbolicExpressionTreeParameter.ActualNameChanged += new EventHandler(SolutionCreator_SymbolicExpressionTreeParameter_ActualNameChanged);
      ParameterizeOperators();
    }

    private void SolutionCreator_SymbolicExpressionTreeParameter_ActualNameChanged(object sender, EventArgs e) {
      ParameterizeOperators();
    }

    protected override void OnEvaluatorChanged() {
      base.OnEvaluatorChanged();
      ParameterizeOperators();
    }

    public event EventHandler ProblemDataChanged;
    protected virtual void OnProblemDataChanged() {
      UpdateGrammar();
      UpdateDatasetPartitions();
      ParameterizeOperators();

      var handler = ProblemDataChanged;
      if (handler != null) handler(this, EventArgs.Empty);

      OnReset();
    }
    #endregion

    protected virtual void ParameterizeOperators() {
      var operators = Parameters.OfType<IValueParameter>().Select(p => p.Value).OfType<IOperator>().Union(Operators);

      foreach (var op in operators.OfType<ISymbolicExpressionTreeGrammarBasedOperator>()) {
        op.SymbolicExpressionTreeGrammarParameter.ActualName = SymbolicExpressionTreeGrammarParameterName;
      }
      foreach (var op in operators.OfType<ISymbolicExpressionTreeSizeConstraintOperator>()) {
        op.MaximumSymbolicExpressionTreeDepthParameter.ActualName = MaximumSymbolicExpressionTreeDepthParameterName;
        op.MaximumSymbolicExpressionTreeLengthParameter.ActualName = MaximumSymbolicExpressionTreeLengthParameterName;
      }
      foreach (var op in operators.OfType<ISymbolicExpressionTreeArchitectureAlteringOperator>()) {
        op.MaximumFunctionArgumentsParameter.ActualName = MaximumFunctionArgumentsParameterName;
        op.MaximumFunctionDefinitionsParameter.ActualName = MaximumFunctionDefinitionsParameterName;
      }
      foreach (var op in operators.OfType<ISymbolicDataAnalysisEvaluator<T>>()) {
        op.ProblemDataParameter.ActualName = ProblemDataParameterName;
        op.SymbolicExpressionTreeParameter.ActualName = SolutionCreator.SymbolicExpressionTreeParameter.ActualName;
        op.SamplesStartParameter.Value.Value = ProblemData.TrainingPartitionStart.Value;
        op.SamplesEndParameter.Value.Value = ProblemData.TrainingPartitionEnd.Value;
      }
      foreach (var op in operators.OfType<ISymbolicExpressionTreeCrossover>()) {
        op.ParentsParameter.ActualName = SolutionCreator.SymbolicExpressionTreeParameter.ActualName;
        op.ChildParameter.ActualName = SolutionCreator.SymbolicExpressionTreeParameter.ActualName;
      }
      foreach (var op in operators.OfType<ISymbolicExpressionTreeManipulator>()) {
        op.SymbolicExpressionTreeParameter.ActualName = SolutionCreator.SymbolicExpressionTreeParameter.ActualName;
      }
      foreach (var op in operators.OfType<ISymbolicExpressionTreeAnalyzer>()) {
        op.SymbolicExpressionTreeParameter.ActualName = SolutionCreator.SymbolicExpressionTreeParameter.ActualName;
      }
      foreach (var op in operators.OfType<ISymbolicDataAnalysisInterpreterOperator>()) {
        op.SymbolicDataAnalysisTreeInterpreterParameter.ActualName = SymbolicExpressionTreeInterpreterParameterName;
      }
      foreach (var op in operators.OfType<ISymbolicDataAnalysisAnalyzer>()) {
        op.SymbolicExpressionTreeParameter.ActualName = SolutionCreator.SymbolicExpressionTreeParameter.ActualName;
      }
    }

    public abstract void ImportProblemDataFromFile(string fileName);
  }
}