source: branches/HeuristicLab.Crossovers/HeuristicLab.Tests/HeuristicLab.Problems.DataAnalysis.Symbolic-3.4/Util.cs @ 7489

#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.Collections.Generic;
using System.Diagnostics;
using System.Linq;
using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
using HeuristicLab.Problems.DataAnalysis.Symbolic;
using HeuristicLab.Random;
using Microsoft.VisualStudio.TestTools.UnitTesting;
using System;
namespace HeuristicLab.Problems.DataAnalysis.Symbolic.Tests {
  internal class Util {

    public static void InitTree(ISymbolicExpressionTree tree, MersenneTwister twister, List<string> varNames) {
      foreach (var node in tree.IterateNodesPostfix()) {
        if (node is VariableTreeNode) {
          var varNode = node as VariableTreeNode;
          varNode.Weight = twister.NextDouble() * 20.0 - 10.0;
          varNode.VariableName = varNames[twister.Next(varNames.Count)];
        } else if (node is ConstantTreeNode) {
          var constantNode = node as ConstantTreeNode;
          constantNode.Value = twister.NextDouble() * 20.0 - 10.0;
        }
      }
    }


    public static ISymbolicExpressionTree[] CreateRandomTrees(MersenneTwister twister, Dataset dataset, ISymbolicExpressionGrammar grammar, int popSize) {
      return CreateRandomTrees(twister, dataset, grammar, popSize, 1, 200, 3, 3);
    }

    public static ISymbolicExpressionTree[] CreateRandomTrees(MersenneTwister twister, Dataset dataset, ISymbolicExpressionGrammar grammar,
      int popSize, int minSize, int maxSize,
      int maxFunctionDefinitions, int maxFunctionArguments) {
      foreach (Variable variableSymbol in grammar.Symbols.OfType<Variable>()) {
        variableSymbol.VariableNames = dataset.VariableNames.Skip(1);
      }
      ISymbolicExpressionTree[] randomTrees = new ISymbolicExpressionTree[popSize];
      for (int i = 0; i < randomTrees.Length; i++) {
        randomTrees[i] = ProbabilisticTreeCreator.Create(twister, grammar, maxSize, 10);
      }
      return randomTrees;
    }


    public static Dataset CreateRandomDataset(MersenneTwister twister, int rows, int columns) {
      double[,] data = new double[rows, columns];
      for (int i = 0; i < rows; i++) {
        for (int j = 0; j < columns; j++) {
          data[i, j] = twister.NextDouble() * 2.0 - 1.0;
        }
      }
      IEnumerable<string> variableNames = new string[] { "y" }.Concat(Enumerable.Range(0, columns - 1).Select(x => "x" + x.ToString()));
      Dataset ds = new Dataset(variableNames, data);
      return ds;
    }

    public static double NodesPerSecond(long nNodes, Stopwatch watch) {
      return nNodes / (watch.ElapsedMilliseconds / 1000.0);
    }

    public static double CalculateEvaluatedNodesPerSec(ISymbolicExpressionTree[] trees, ISymbolicDataAnalysisExpressionTreeInterpreter interpreter, Dataset dataset, int repetitions) {
      // warm up
      IEnumerable<int> rows = Enumerable.Range(0, dataset.Rows);
      long nNodes = 0;
      double c = 0;
      for (int i = 0; i < trees.Length; i++) {
        nNodes += trees[i].Length * (dataset.Rows - 1);
        c = interpreter.GetSymbolicExpressionTreeValues(trees[i], dataset, rows).Count(); // count needs to evaluate all rows
      }

      Stopwatch watch = new Stopwatch();
      for (int rep = 0; rep < repetitions; rep++) {
        watch.Start();
        c = 0;
        for (int i = 0; i < trees.Length; i++) {
          interpreter.GetSymbolicExpressionTreeValues(trees[i], dataset, rows).Count(); // count needs to evaluate all rows
        }
        watch.Stop();
      }
      Console.WriteLine("Random tree evaluation performance of " + interpreter.GetType() + ": " +
        watch.ElapsedMilliseconds + "ms " +
        Util.NodesPerSecond(nNodes * repetitions, watch) + " nodes/sec");
      return Util.NodesPerSecond(nNodes * repetitions, watch);
    }

    public static void IsValid(ISymbolicExpressionTree tree) {
      int reportedSize = tree.Length;
      int actualSize = tree.IterateNodesPostfix().Count();
      Assert.AreEqual(actualSize, reportedSize);

      foreach (var defunTreeNode in tree.Root.Subtrees.OfType<DefunTreeNode>()) {
        int arity = defunTreeNode.NumberOfArguments;

        foreach (var argTreenode in defunTreeNode.IterateNodesPrefix().OfType<ArgumentTreeNode>()) {
          Assert.IsTrue(argTreenode.SubtreeCount == 0);
          Assert.IsTrue(((Argument)argTreenode.Symbol).ArgumentIndex < arity);
        }

        foreach (var argSymbol in Enumerable.Range(0, defunTreeNode.NumberOfArguments).Select(x => new Argument(x))) {
          Assert.IsTrue(defunTreeNode.Grammar.ContainsSymbol(argSymbol));
          Assert.IsTrue(defunTreeNode.Grammar.GetMaximumSubtreeCount(argSymbol) == 0);
          Assert.IsTrue(defunTreeNode.Grammar.GetMinimumSubtreeCount(argSymbol) == 0);
        }

        var invoke = new InvokeFunction(defunTreeNode.FunctionName);
        foreach (var otherRootNode in tree.Root.Subtrees) {
          if (otherRootNode.Grammar.ContainsSymbol(invoke)) {
            Assert.IsTrue(otherRootNode.Grammar.GetMinimumSubtreeCount(invoke) == arity);
            Assert.IsTrue(otherRootNode.Grammar.GetMaximumSubtreeCount(invoke) == arity);
            Assert.IsFalse(otherRootNode.Grammar.IsAllowedChildSymbol(invoke, invoke));
            for (int i = 0; i < arity; i++) {
              Assert.IsFalse(otherRootNode.Grammar.IsAllowedChildSymbol(invoke, invoke, i));
            }
          }
        }

      }

      foreach (var subtree in tree.Root.Subtrees) {
        Assert.AreNotSame(subtree.Grammar, tree.Root.Grammar);
        IsValid(subtree.Grammar);
      }

      IsValid(tree.Root.Grammar);
      IsValid(tree.Root);
    }

    public static void IsValid(ISymbolicExpressionTreeGrammar grammar) {
      Assert.IsTrue(grammar.Symbols.Count() == grammar.Symbols.Distinct().Count());
      foreach (ISymbol symbol in grammar.AllowedSymbols) {
        Assert.IsTrue(grammar.GetAllowedChildSymbols(symbol).Count() == grammar.GetAllowedChildSymbols(symbol).Distinct().Count());
        for (int i = 0; i < grammar.GetMaximumSubtreeCount(symbol); i++) {
          Assert.IsTrue(grammar.GetAllowedChildSymbols(symbol, i).Count() == grammar.GetAllowedChildSymbols(symbol, i).Distinct().Count());
        }
      }

      foreach (var symbol in grammar.ModifyableSymbols) {
        //check if ever symbol has at least one allowed child
        for (int i = 0; i < grammar.GetMaximumSubtreeCount(symbol); i++)
          Assert.IsTrue(grammar.GetAllowedChildSymbols(symbol, i).Any());
      }
    }

    public static void IsValid(ISymbolicExpressionTreeNode treeNode) {
      var matchingSymbol = (from symb in treeNode.Grammar.Symbols
                            where symb.Name == treeNode.Symbol.Name
                            select symb).SingleOrDefault();
      Assert.IsTrue(treeNode.Subtrees.Count() >= treeNode.Grammar.GetMinimumSubtreeCount(matchingSymbol));
      Assert.IsTrue(treeNode.Subtrees.Count() <= treeNode.Grammar.GetMaximumSubtreeCount(matchingSymbol));
      Assert.AreNotEqual(0.0, matchingSymbol.InitialFrequency); // check that no deactivated symbols occur in the tree
      for (int i = 0; i < treeNode.Subtrees.Count(); i++) {
        Assert.IsTrue(treeNode.Grammar.GetAllowedChildSymbols(treeNode.Symbol, i).Select(x => x.Name).Contains(treeNode.GetSubtree(i).Symbol.Name));
        IsValid(treeNode.GetSubtree(i));
      }
    }
  }
}