source: branches/2974_Constants_Optimization/HeuristicLab.Problems.DataAnalysis.Symbolic/3.4/Constants Optimization/Util.cs @ 16475

#region License Information
/* HeuristicLab
 * Copyright (C) 2002-2018 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.Encodings.SymbolicExpressionTreeEncoding;
using static HeuristicLab.Problems.DataAnalysis.Symbolic.TreeToAutoDiffTermConverter;

namespace HeuristicLab.Problems.DataAnalysis.Symbolic.ConstantsOptimization {
  public static class Util {

    public static double[,] ExtractData(IDataset dataset, IEnumerable<DataForVariable> variables, IEnumerable<int> rows) {
      var x = new double[rows.Count(), variables.Count()];

      int row = 0;
      foreach (var r in rows) {
        int col = 0;
        foreach (var variable in variables) {
          if (dataset.VariableHasType<double>(variable.variableName)) {
            x[row, col] = dataset.GetDoubleValue(variable.variableName, r + variable.lag);
          } else if (dataset.VariableHasType<string>(variable.variableName)) {
            x[row, col] = dataset.GetStringValue(variable.variableName, r) == variable.variableValue ? 1 : 0;
          } else throw new InvalidProgramException("found a variable of unknown type");
          col++;
        }
        row++;
      }
      return x;
    }

    public static Dictionary<DataForVariable, AutoDiff.Variable> ExtractParameters(IDataset dataset) {
      var parameters = new Dictionary<DataForVariable, AutoDiff.Variable>();
      foreach (var doubleVariable in dataset.DoubleVariables) {
        var data = new DataForVariable(doubleVariable, string.Empty, 0);
        var param = new AutoDiff.Variable();
        parameters.Add(data, param);
      }

      foreach (var stringVariable in dataset.StringVariables) {
        foreach (var stringValue in dataset.GetStringValues(stringVariable).Distinct()) {
          var data = new DataForVariable(stringVariable, stringValue, 0);
          var param = new AutoDiff.Variable();
          parameters.Add(data, param);
        }
      }
      return parameters;
    }

    public static double[] ExtractConstants(ISymbolicExpressionTree tree) {
      var constants = new List<double>();
      foreach (var node in tree.IterateNodesPrefix().OfType<SymbolicExpressionTreeTerminalNode>()) {
        ConstantTreeNode constantTreeNode = node as ConstantTreeNode;
        VariableTreeNodeBase variableTreeNodeBase = node as VariableTreeNodeBase;
        FactorVariableTreeNode factorVarTreeNode = node as FactorVariableTreeNode;
        if (constantTreeNode != null)
          constants.Add(constantTreeNode.Value);
        else if (variableTreeNodeBase != null)
          constants.Add(variableTreeNodeBase.Weight);
        else if (factorVarTreeNode != null) {
          for (int j = 0; j < factorVarTreeNode.Weights.Length; j++)
            constants.Add(factorVarTreeNode.Weights[j]);
        }        
      }
      return constants.ToArray();
    }

    public static void UpdateConstants(ISymbolicExpressionTree tree, double[] constants) {
      int i = 0;
      foreach (var node in tree.Root.IterateNodesPrefix().OfType<SymbolicExpressionTreeTerminalNode>()) {
        ConstantTreeNode constantTreeNode = node as ConstantTreeNode;
        VariableTreeNodeBase variableTreeNodeBase = node as VariableTreeNodeBase;
        FactorVariableTreeNode factorVarTreeNode = node as FactorVariableTreeNode;
        if (constantTreeNode != null)
          constantTreeNode.Value = constants[i++];
        else if (variableTreeNodeBase != null)
          variableTreeNodeBase.Weight = constants[i++];
        else if (factorVarTreeNode != null) {
          for (int j = 0; j < factorVarTreeNode.Weights.Length; j++)
            factorVarTreeNode.Weights[j] = constants[i++];
        }
      }
    }
  }
}