source: branches/RegressionBenchmarks/HeuristicLab.Problems.DataAnalysis.Benchmarks/3.4/ClassificationBenchmark/RealWorldProblems/Mammography.cs @ 7127

#region License Information
/* HeuristicLab
 * Copyright (C) 2002-2011 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;
using System.Collections.Generic;
using System.Linq;
using HeuristicLab.Data;

namespace HeuristicLab.Problems.DataAnalysis.Benchmarks {
  public class Mammography : ClassificationRealWorldBenchmark {

    private const string fileName = "mammography.csv";

    public Mammography() {
      Name = "RealWorldProblem Mammography";
      //Description = "Paper: Improving Symbolic Regression with Interval Arithmetic and Linear Scaling" + Environment.NewLine
      //  + "Authors: Maarten Keijzer" + Environment.NewLine
      //  + "Function: f(x) = log(x)" + Environment.NewLine
      //  + "range(train): x = [0:1:100]" + Environment.NewLine
      //  + "range(test): x = [0:0.1:100]" + Environment.NewLine
      //  + "Function Set: x + y, x * y, 1/x, -x, sqrt(x)";
    }

    protected override List<IList> GetData() {
      csvFileParser = Benchmark.getParserForFile(fileName);

      targetVariable = csvFileParser.VariableNames.Last();
      inputVariables = new List<string>(csvFileParser.VariableNames.Take(csvFileParser.Columns - 1));
      int trainingPartEnd = csvFileParser.Rows * 2 / 3;
      trainingPartition = new IntRange(0, trainingPartEnd);
      testPartition = new IntRange(trainingPartEnd, csvFileParser.Rows);

      return csvFileParser.Values.Skip(csvFileParser.Columns - 1).Union(csvFileParser.Values.Take(csvFileParser.Columns - 1)).ToList();
    }
  }
}