source: branches/CloningRefactoring/HeuristicLab.Problems.DataAnalysis/3.3/SupportVectorMachine/SupportVectorMachineModelEvaluator.cs @ 4678

#region License Information
/* HeuristicLab
 * Copyright (C) 2002-2009 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 HeuristicLab.Core;
using HeuristicLab.Data;
using HeuristicLab.Operators;
using HeuristicLab.Parameters;
using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
using SVM;
using System.Collections.Generic;
using System.Linq;
using HeuristicLab.Common;

namespace HeuristicLab.Problems.DataAnalysis.SupportVectorMachine {
  [StorableClass]
  [Item("SupportVectorMachineModelEvaluator", "Represents a operator that evaluates a support vector machine model on a data set.")]
  public class SupportVectorMachineModelEvaluator : SingleSuccessorOperator {
    private const string DataAnalysisProblemDataParameterName = "DataAnalysisProblemData";
    private const string ModelParameterName = "SupportVectorMachineModel";
    private const string SamplesStartParameterName = "SamplesStart";
    private const string SamplesEndParameterName = "SamplesEnd";
    private const string ValuesParameterName = "Values";

    #region parameter properties
    public IValueLookupParameter<DataAnalysisProblemData> DataAnalysisProblemDataParameter {
      get { return (IValueLookupParameter<DataAnalysisProblemData>)Parameters[DataAnalysisProblemDataParameterName]; }
    }
    public IValueLookupParameter<IntValue> SamplesStartParameter {
      get { return (IValueLookupParameter<IntValue>)Parameters[SamplesStartParameterName]; }
    }
    public IValueLookupParameter<IntValue> SamplesEndParameter {
      get { return (IValueLookupParameter<IntValue>)Parameters[SamplesEndParameterName]; }
    }
    public ILookupParameter<SupportVectorMachineModel> SupportVectorMachineModelParameter {
      get { return (ILookupParameter<SupportVectorMachineModel>)Parameters[ModelParameterName]; }
    }
    public ILookupParameter<DoubleMatrix> ValuesParameter {
      get { return (ILookupParameter<DoubleMatrix>)Parameters[ValuesParameterName]; }
    }
    #endregion
    #region properties
    public DataAnalysisProblemData DataAnalysisProblemData {
      get { return DataAnalysisProblemDataParameter.ActualValue; }
    }
    public SupportVectorMachineModel SupportVectorMachineModel {
      get { return SupportVectorMachineModelParameter.ActualValue; }
    }
    public IntValue SamplesStart {
      get { return SamplesStartParameter.ActualValue; }
    }
    public IntValue SamplesEnd {
      get { return SamplesEndParameter.ActualValue; }
    }
    #endregion

    [StorableConstructor]
    protected SupportVectorMachineModelEvaluator(bool deserializing) : base(deserializing) { }
    protected SupportVectorMachineModelEvaluator(SupportVectorMachineModelEvaluator original, Cloner cloner) : base(original, cloner) { }
    public SupportVectorMachineModelEvaluator()
      : base() {
      Parameters.Add(new ValueLookupParameter<DataAnalysisProblemData>(DataAnalysisProblemDataParameterName, "The data analysis problem data to use for training."));
      Parameters.Add(new LookupParameter<SupportVectorMachineModel>(ModelParameterName, "The result model generated by the SVM."));
      Parameters.Add(new ValueLookupParameter<IntValue>(SamplesStartParameterName, "The first index of the data set partition on which the SVM model should be evaluated."));
      Parameters.Add(new ValueLookupParameter<IntValue>(SamplesEndParameterName, "The last index of the data set partition on which the SVM model should be evaluated."));
      Parameters.Add(new LookupParameter<DoubleMatrix>(ValuesParameterName, "A matrix of original values of the target variable and output values of the SVM model."));
    }

    public override IOperation Apply() {
      int start = SamplesStart.Value;
      int end = SamplesEnd.Value;
      IEnumerable<int> rows =
        Enumerable.Range(start, end - start)
        .Where(i => i < DataAnalysisProblemData.TestSamplesStart.Value || DataAnalysisProblemData.TestSamplesEnd.Value <= i);

      ValuesParameter.ActualValue = new DoubleMatrix(Evaluate(SupportVectorMachineModel, DataAnalysisProblemData, rows));
      return base.Apply();
    }

    public static double[,] Evaluate(SupportVectorMachineModel model, DataAnalysisProblemData problemData, IEnumerable<int> rowIndices) {
      SVM.Problem problem = SupportVectorMachineUtil.CreateSvmProblem(problemData, rowIndices);
      SVM.Problem scaledProblem = model.RangeTransform.Scale(problem);

      int targetVariableIndex = problemData.Dataset.GetVariableIndex(problemData.TargetVariable.Value);

      double[,] values = new double[scaledProblem.Count, 2];
      var rowEnumerator = rowIndices.GetEnumerator();
      for (int i = 0; i < scaledProblem.Count; i++) {
        rowEnumerator.MoveNext();
        values[i, 0] = problemData.Dataset[rowEnumerator.Current, targetVariableIndex];
        values[i, 1] = SVM.Prediction.Predict(model.Model, scaledProblem.X[i]);
      }

      return values;
    }
  }
}