source: branches/symbreg-factors-2650/HeuristicLab.Problems.DataAnalysis.Symbolic/3.4/Symbols/FactorVariable.cs @ 14233

#region License Information
/* HeuristicLab
 * Copyright (C) 2002-2016 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.Encodings.SymbolicExpressionTreeEncoding;
using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
namespace HeuristicLab.Problems.DataAnalysis.Symbolic {
  // TODO: handle correctly in all interpreters and formatters
  // TODO: view for factor variables (configuration of actually allowed factors)
  // TODO: handle correctly in variable impacts view
  // TODO: handle correctly in Non-linear regression (infix parser and infix formatter)
  // TODO: support in all analyzers which handle variable symbols specifically
  // TODO: handle correctly in gradient views
  // TODO: handle correctly in ERC view (create linear regression model)
  // TODO: handle correctly in classification - solution comparison
  // TODO: allow factor variables in decision trees (and therefore GBT)?
  // TODO: support in more algs?
  // TODO: support in more views?
  [StorableClass]
  [Item("FactorVariable", "Represents a categorical variable (comparable to factors as in R).")]
  public class FactorVariable : Symbol {
    #region Properties
    private List<string> variableNames;
    [Storable]
    public IEnumerable<string> VariableNames {
      get { return variableNames; }
      set {
        if (value == null) throw new ArgumentNullException();
        variableNames.Clear();
        variableNames.AddRange(value);
        OnChanged(EventArgs.Empty);
      }
    }

    private List<string> allVariableNames;
    [Storable]
    public IEnumerable<string> AllVariableNames {
      get { return allVariableNames; }
      set {
        if (value == null) throw new ArgumentNullException();
        allVariableNames.Clear();
        allVariableNames.AddRange(value);
      }
    }

    private Dictionary<string, List<string>> variableValues;

    [Storable]
    public IEnumerable<KeyValuePair<string, List<string>>> VariableValues {
      get { return variableValues; }
      set {
        if (value == null) throw new ArgumentNullException();
        variableValues.Clear();
        foreach (var kvp in value) {
          variableValues.Add(kvp.Key, new List<string>(kvp.Value));
        }
      }
    }


    public override bool Enabled {
      get {
        if (variableNames.Count == 0) return false;
        return base.Enabled;
      }
      set {
        if (variableNames.Count == 0) base.Enabled = false;
        else base.Enabled = value;
      }
    }

    private const int minimumArity = 0;
    private const int maximumArity = 0;

    public override int MinimumArity {
      get { return minimumArity; }
    }
    public override int MaximumArity {
      get { return maximumArity; }
    }
    #endregion

    [StorableConstructor]
    protected FactorVariable(bool deserializing)
      : base(deserializing) {
      variableNames = new List<string>();
      allVariableNames = new List<string>();
      variableValues = new Dictionary<string, List<string>>();
    }
    protected FactorVariable(FactorVariable original, Cloner cloner)
      : base(original, cloner) {
      variableNames = new List<string>(original.variableNames);
      allVariableNames = new List<string>(original.allVariableNames);
      variableValues =
        original.variableValues.ToDictionary(kvp => kvp.Key, kvp => new List<string>(kvp.Value));
    }
    public FactorVariable() : this("FactorVariable", "Represents a categorical variable (comparable to factors as in R).") { }
    public FactorVariable(string name, string description)
      : base(name, description) {
      variableNames = new List<string>();
      allVariableNames = new List<string>();
      variableValues = new Dictionary<string, List<string>>();
    }

    [StorableHook(HookType.AfterDeserialization)]
    private void AfterDeserialization() {
      if (allVariableNames == null || (allVariableNames.Count == 0 && variableNames.Count > 0)) {
        allVariableNames = variableNames;
      }
    }
    public override ISymbolicExpressionTreeNode CreateTreeNode() {
      return new FactorVariableTreeNode(this);
    }

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

    public IEnumerable<string> GetVariableValues(string variableName) {
      return variableValues[variableName];
    }
  }
}