source: branches/2988_ModelsOfModels2/HeuristicLab.Algorithms.EMM/EMMMapTreeModel.cs @ 16824

#region License Information
/* HeuristicLab
 * Copyright (C) 2002-2019 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 HEAL.Attic;
using HeuristicLab.Common;
using HeuristicLab.Core;
using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
using HeuristicLab.Problems.DataAnalysis.Symbolic;
using System.Collections.Generic;
using System.IO;
using System.Linq;

namespace HeuristicLab.Algorithms.EvolvmentModelsOfModels {
  [Item("TreeModelMap", "A map of models of models of models")]
  [StorableType("E4AB04B9-FD5D-47EE-949D-243660754F3A")]
  public class EMMMapTreeModel : EMMMapBase<ISymbolicExpressionTree> {
    #region conctructors
    [StorableConstructor]
    protected EMMMapTreeModel(StorableConstructorFlag _) : base(_) { }
    public EMMMapTreeModel() : this(1) { }
    public EMMMapTreeModel(int k) {
      K = k;
      ModelSet = new List<ISymbolicExpressionTree>();
      ClusterNumber = new List<int>();
      Map = new List<List<int>>();
    }
    public EMMMapTreeModel(EMMMapTreeModel original, Cloner cloner) {
      //original.ModelSet.ForEach(x => ModelSet.Add((ISymbolicExpressionTree)x.Clone(cloner)));
      //original.ClusterNumber.ForEach(x => ClusterNumber.Add(x));
      //original.Map.ForEach(x => Map.Add(x));
      if (original.ModelSet != null) {
        ModelSet = original.ModelSet.Select(cloner.Clone).ToList();
      }
      if (original.ClusterNumber != null) {
        ClusterNumber = original.ClusterNumber.ToList();
      }
      if (original.Map != null) {
        Map = original.Map.Select(x => x.ToList()).ToList();
      }
      K = original.K;
    }
    public EMMMapTreeModel(IRandom random, IEnumerable<ISymbolicExpressionTree> trees, int k, int neghboorNumber) : this(k) {
      ModelSet = trees.ToList();
      CalculateDistances();
      if (k < ModelSet.Count)
        CreateIslandMap(random, k);
      else if (k == ModelSet.Count) {
        CreateFullConnectedMap(random, k, neghboorNumber);
      } else {
        k -= ModelSet.Count;
        CreateIslandMap(random, k);
      }
    }
    public EMMMapTreeModel(IRandom random, IEnumerable<ISymbolicExpressionTree> trees) : this(1) {
      ModelSet = trees.ToList();
      string input = File.ReadAllText("Map.txt");

      int i = 0;
      foreach (var row in input.Split('\n')) {
        Map.Add(new List<int>());
        foreach (var col in row.Trim().Split(' ')) {
          Map[i].Add(int.Parse(col.Trim()));
        }
        i++;
      }
      K = Map.Count;
      MapPreparation();
    }
    public override IDeepCloneable Clone(Cloner cloner) {
      return new EMMMapTreeModel(this, cloner);
    }
    #endregion
    #region MapTransformation
    override protected void CalculateDistances() {
      Distances = SymbolicExpressionTreeHash.ComputeSimilarityMatrix(ModelSet, simplify: false, strict: true);
      for (int i = 0; i < ModelSet.Count - 1; i++) {
        for (int j = i + 1; j < ModelSet.Count; j++) {
          Distances[j, i] = Distances[i, j] = 1 - Distances[i, j];
        }
      }
    }
    protected void CreateFullConnectedMap(IRandom random, int k, int neghboorNumber) {
      EMModelsClusterizationAlgorithm.ApplyFullConectedMapCreationAlgorithm(random, Distances, Map, k, neghboorNumber);
      K = k;
      for (int i = 0; i < Map.Count; i++) {
        ClusterNumber.Add(i);
      }
    }
    override protected void CreateIslandMap(IRandom random, int k) {
      //Clusterization
      K = EMModelsClusterizationAlgorithm.ApplyClusteringAlgorithm(random, Distances, ClusterNumber, k);
      // Cheking a Map size
      if (Map != null) Map.Clear();
      else Map = new List<List<int>>();
      if (Map.Count != K) {
        if (Map.Count != 0) {
          Map.Clear();
        }
        for (int i = 0; i < K; i++) {
          Map.Add(new List<int>());
        }
      }
      // Map fulfilment
      for (int i = 0; i < ModelSet.Count; i++) {
        Map[ClusterNumber[i]].Add(i);
      }
    }
    protected void MapPreparation() {
      for (int i = 0; i < Map.Count; i++) {
        for (int j = 0; j < Map[i].Count; j++) {
          ClusterNumber.Add(0);
        }
      }
      for (int i = 0; i < Map.Count; i++) {
        for (int j = 0; j < Map[i].Count; j++) {
          ClusterNumber[Map[i][j]] = i;
        }
      }
    }
    #endregion
    #region Dialog with surroudings
    override public ISymbolicExpressionTree NewModelForInizializtion(IRandom random, out int cluster, out int treeNumber) {
      treeNumber = random.Next(ModelSet.Count);
      cluster = ClusterNumber[treeNumber];
      return (ISymbolicExpressionTree)ModelSet[treeNumber].Clone();
    }
    public string[] MapToString() {
      string[] s;
      s = new string[K];
      for (int i = 0; i < K; i++) {
        s[i] = "";
        for (int j = 0; j < Map[i].Count; j++) {
          s[i] += Map[i][j].ToString();
          s[i] += " ";
        }
      }
      return s;
    }
    public string[] MapToSee() {
      var fmt = new InfixExpressionFormatter();
      string[] s;
      s = new string[(ModelSet.Count) + 1];
      s[0] = "ClusterNumber" + "," + "Modfelnumber" + "," + "Model";
      for (int i = 1; i < ((ModelSet.Count) + 1); i++) {
        s[i] = ClusterNumber[i - 1].ToString() + "," + (i - 1).ToString() + "," + fmt.Format(ModelSet[i - 1]);
      }
      return s;
    }

    #endregion
  }
}