source: branches/LearningClassifierSystems/HeuristicLab.Problems.VariableVectorClassification/3.3/VariableVectorClassificationProblemData.cs @ 9411

#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.ConditionActionEncoding;
using HeuristicLab.Encodings.VariableVector;
using HeuristicLab.Parameters;
using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
using HeuristicLab.Problems.ConditionActionClassification;
using HeuristicLab.Problems.DataAnalysis;

namespace HeuristicLab.Problems.VariableVectorClassification {
  [StorableClass]
  [Item("CombinedIntegerVectorClassificationProblemData", "A problem data for LCS.")]
  public class VariableVectorClassificationProblemData : ConditionActionClassificationProblemData, IVariableVectorClassificationProblemData {

    #region parameter properites
    public IValueParameter<VariableVector> SampleVariableVectorParameter {
      get { return (IValueParameter<VariableVector>)Parameters["SampleVariableVector"]; }
    }
    public IFixedValueParameter<PercentValue> SpreadPercentageParameter {
      get { return (IFixedValueParameter<PercentValue>)Parameters["SpreadPercentage"]; }
    }
    #endregion

    #region properties
    public VariableVector SampleVariableVector {
      get { return SampleVariableVectorParameter.Value; }
    }
    public PercentValue SpreadPercentage {
      get { return SpreadPercentageParameter.Value; }
    }

    public VariableVectorActionComparer ConcreteClassifierComparer {
      get { return new VariableVectorActionComparer(); }
    }
    public override IClassifierComparer ClassifierComparer {
      get { return ConcreteClassifierComparer; }
    }
    #endregion

    [StorableConstructor]
    protected VariableVectorClassificationProblemData(bool deserializing) : base(deserializing) { }
    protected VariableVectorClassificationProblemData(VariableVectorClassificationProblemData original, Cloner cloner)
      : base(original, cloner) {
    }
    public override IDeepCloneable Clone(Cloner cloner) {
      return new VariableVectorClassificationProblemData(this, cloner);
    }

    public VariableVectorClassificationProblemData(Dataset dataset, IEnumerable<string> allowedConditionVariables, IEnumerable<string> allowedActionVariables) :
      base(dataset, allowedConditionVariables, allowedActionVariables) {
      Parameters.Add(new ValueParameter<VariableVector>("SampleVariableVector", "", GenerateSampleVariableVector(dataset, allowedConditionVariables, allowedActionVariables)));
      Parameters.Add(new FixedValueParameter<PercentValue>("SpreadPercentage", "", new PercentValue(0.5)));
    }

    private VariableVector GenerateSampleVariableVector(Dataset dataset, IEnumerable<string> allowedConditionVariables, IEnumerable<string> allowedActionVariables) {
      var conditionVariables = GetVariablesOfDataSet(dataset, allowedConditionVariables);
      var actionVariables = GetVariablesOfDataSet(dataset, allowedActionVariables);
      if (actionVariables.Count() == 0 || !actionVariables.All(x => x is IActionVariable)) {
        throw new ArgumentException("Action variable can not be empty and all action variables have to be of type int or string.");
      }
      return new VariableVector(conditionVariables, actionVariables);
    }

    private IEnumerable<Encodings.VariableVector.IVariable> GetVariablesOfDataSet(DataAnalysis.Dataset dataset, IEnumerable<string> allowedVariables) {
      var variables = new List<HeuristicLab.Encodings.VariableVector.IVariable>();
      foreach (var variableName in allowedVariables) {
        var variableValues = dataset.GetValues(variableName);
        HeuristicLab.Encodings.VariableVector.IVariable variable;
        if (variableValues is List<string>) {
          variable = new StringVariable(variableName, (variableValues as List<string>).Distinct());
        } else if (variableValues is List<double>) {
          var doubleValues = (variableValues as List<double>).Distinct();
          if (doubleValues.All(x => x % 1 == 0 || Double.IsNaN(x))) {
            // ToList call is necessary, because otherwise it wouldn't be possible to serialize it
            variable = new IntVariable(variableName, doubleValues.Select(x => Convert.ToInt32(x)).ToList());
          } else {
            variable = new DoubleVariable(variableName, doubleValues);
          }
        } else {
          throw new ArgumentException("There is no matching variable type for the values in the dataset");
        }
        variables.Add(variable);
      }
      return variables;
    }

    public override IInput FetchInput(int rowNumber) {
      if (!fetchInputCache.ContainsKey(rowNumber)) {
        VariableVectorInput input = new VariableVectorInput();
        IEnumerable<string> variableNames = SampleVariableVector.Condition.VariableDictionary.Keys.Union(SampleVariableVector.Action.VariableDictionary.Keys);
        foreach (var variableName in variableNames) {
          input.InputDictionary.Add(variableName, Dataset.GetValue(rowNumber, variableName));
        }
        fetchInputCache.Add(rowNumber, input);
      }
      return fetchInputCache[rowNumber];
    }

    protected IDictionary<int, IAction> fetchActionCache = new Dictionary<int, IAction>();
    public override IAction FetchAction(int rowNumber) {
      if (!fetchActionCache.ContainsKey(rowNumber)) {
        var action = SampleVariableVector.Action.GetEmptyCopy();
        foreach (var variableName in action.VariableDictionary.Keys) {
          action.VariableDictionary[variableName].SetTo(Dataset.GetValue(rowNumber, variableName));
        }
        fetchActionCache.Add(rowNumber, action);
      }
      return fetchActionCache[rowNumber];
    }

    protected override void ActionConditionVariablesChanged() {
      SampleVariableVectorParameter.Value = GenerateSampleVariableVector(Dataset, AllowedConditionVariables, AllowedActionVariables);
    }
  }
}