source: branches/3040_VectorBasedGP/HeuristicLab.Problems.Instances.DataAnalysis/3.3/Regression/VectorData/VectorDataTestOne.cs @ 17365

#region License Information
/* HeuristicLab
 * Copyright (C) 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;
using System.Collections.Generic;
using System.Linq;
using HeuristicLab.Core;
using HeuristicLab.Problems.DataAnalysis;
using HeuristicLab.Random;

namespace HeuristicLab.Problems.Instances.DataAnalysis {
  public class VectorDataTestOne : ArtificialRegressionDataDescriptor {

    public override string Name { get { return "Vector Data Test - I (Y = X1 * sum(V1) + X2 * avg(V2)"; } }
    public override string Description { get { return ""; } }

    protected override string TargetVariable { get { return "Y"; } }
    protected override string[] VariableNames { get { return new string[] { "X1", "X2", "X3", "V1", "V2", "Y" }; } }
    protected override string[] AllowedInputVariables { get { return new string[] { "X1", "X2", "X3", "V1", "V2" }; } }
    protected override int TrainingPartitionStart { get { return 0; } }
    protected override int TrainingPartitionEnd { get { return 80; } }
    protected override int TestPartitionStart { get { return 80; } }
    protected override int TestPartitionEnd { get { return 100; } }

    public int Seed { get; private set; }

    public VectorDataTestOne()
      : this((int)DateTime.Now.Ticks) { }
    public VectorDataTestOne(int seed)
      : base() {
      Seed = seed;
    }


    protected override List<List<double>> GenerateValues() { return null; }
    protected override List<IList> GenerateValuesExtended() {
      var rand = new MersenneTwister((uint)Seed);

      double x1, x2, x3;
      DoubleVector v1, v2;
      double y;

      var x1Column = new List<double>(100);
      var x2Column = new List<double>(100);
      var x3Column = new List<double>(100);
      var v1Column = new List<DoubleVector>(100);
      var v2Column = new List<DoubleVector>(100);
      var yColumn = new List<double>(100);

      for (int i = 0; i < 100; i++) {
        x1 = GetRandomDouble(-2, 2, rand);
        x2 = GetRandomDouble(2, 6, rand);
        x3 = GetRandomDouble(0, 1, rand);
        int length = rand.Next(3, 6);
        v1 = GetRandomDoubleVector(-2, 2, length, rand);
        v2 = GetRandomDoubleVector(3, 5, length, rand);
        y = x1 * v1.Sum() + x2 * v2.Average();

        x1Column.Add(x1);
        x2Column.Add(x2);
        x3Column.Add(x3);
        v1Column.Add(v1);
        v2Column.Add(v2);
        yColumn.Add(y);
      }

      return new List<IList> { x1Column, x2Column, x3Column, v1Column, v2Column, yColumn };
    }


    private static double GetRandomDouble(double min, double max, IRandom rand) {
      return (max - min) * rand.NextDouble() + min;
    }
    private static DoubleVector GetRandomDoubleVector(double min, double max, int length, IRandom rand) {
      var values = new double[length];
      for (int i = 0; i < values.Length; i++) {
        values[i] = GetRandomDouble(min, max, rand);
      }
      return new DoubleVector(values);
    }
  }
}