source: branches/2789_MathNetNumerics-Exploration/HeuristicLab.Algorithms.DataAnalysis.Experimental/RBF.cs @ 16123

#region License Information
/* HeuristicLab
 * Copyright (C) 2002-2016 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.Concurrent;
using System.Collections.Generic;
using System.Linq;
using System.Threading;
using System.Threading.Tasks;
using HeuristicLab.Common;
using HeuristicLab.Core;
using HeuristicLab.Data;
using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
using HeuristicLab.Optimization;
using HeuristicLab.Parameters;
using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
using HeuristicLab.Problems.DataAnalysis;
using HeuristicLab.Problems.DataAnalysis.Symbolic;
using HeuristicLab.Problems.DataAnalysis.Symbolic.Regression;

namespace HeuristicLab.Algorithms.DataAnalysis.Experimental {
  [Item("RBF (alglib)", "")]
  [Creatable(CreatableAttribute.Categories.DataAnalysisRegression, Priority = 102)]
  [StorableClass]
  public sealed class RBF : FixedDataAnalysisAlgorithm<IRegressionProblem> {
    [StorableConstructor]
    private RBF(bool deserializing) : base(deserializing) { }
    [StorableHook(HookType.AfterDeserialization)]
    private void AfterDeserialization() {
    }

    private RBF(RBF original, Cloner cloner)
      : base(original, cloner) {
    }
    public override IDeepCloneable Clone(Cloner cloner) {
      return new RBF(this, cloner);
    }

    public RBF()
      : base() {
      Problem = new RegressionProblem();
      Parameters.Add(new ValueParameter<DoubleValue>("RBase", new DoubleValue(1.0)));
      Parameters.Add(new ValueParameter<IntValue>("NLayers", new IntValue(3)));
      Parameters.Add(new ValueParameter<DoubleValue>("LambdaNS", new DoubleValue(1.0)));
    }


    protected override void Run(CancellationToken cancellationToken) {
      var scaling = CreateScaling(Problem.ProblemData.Dataset, Problem.ProblemData.TrainingIndices.ToArray(), Problem.ProblemData.AllowedInputVariables.ToArray());

      double[,] inputMatrix = ExtractData(Problem.ProblemData.Dataset, Problem.ProblemData.TrainingIndices, Problem.ProblemData.AllowedInputVariables.ToArray(), scaling);

      double[,] target = ExtractData(Problem.ProblemData.Dataset, Problem.ProblemData.TrainingIndices, new string[] { Problem.ProblemData.TargetVariable });
      inputMatrix = inputMatrix.HorzCat(target);

      if (inputMatrix.Cast<double>().Any(x => double.IsNaN(x) || double.IsInfinity(x)))
        throw new NotSupportedException("Splines does not support NaN or infinity values in the input dataset.");


      var inputVars = Problem.ProblemData.AllowedInputVariables.ToArray();
      if (inputVars.Length > 3) throw new NotSupportedException();

      alglib.rbfmodel model;
      alglib.rbfreport rep;

      alglib.rbfcreate(inputVars.Length, 1, out model);

      alglib.rbfsetzeroterm(model);
      var rbase = ((DoubleValue)Parameters["RBase"].ActualValue).Value;
      var nlayers = ((IntValue)Parameters["NLayers"].ActualValue).Value;
      var lambdans = ((DoubleValue)Parameters["LambdaNS"].ActualValue).Value;
      alglib.rbfsetalgohierarchical(model, rbase, nlayers, lambdans);
      alglib.rbfsetpoints(model, inputMatrix);
      alglib.rbfbuildmodel(model, out rep);

      Results.Add(new Result("TerminationType", new DoubleValue(rep.terminationtype)));
      Results.Add(new Result("RMSE", new DoubleValue(rep.rmserror)));

      Results.Add(new Result("Solution", new RegressionSolution(new RBFModel(model, Problem.ProblemData.TargetVariable, inputVars, scaling),
        (IRegressionProblemData)Problem.ProblemData.Clone())));
    }


    private static ITransformation<double>[] CreateScaling(IDataset dataset, int[] rows, IReadOnlyCollection<string> allowedInputVariables) {
      var trans = new ITransformation<double>[allowedInputVariables.Count];
      int i = 0;
      foreach (var variable in allowedInputVariables) {
        var lin = new LinearTransformation(allowedInputVariables);
        var max = dataset.GetDoubleValues(variable, rows).Max();
        var min = dataset.GetDoubleValues(variable, rows).Min();
        lin.Multiplier = 1.0 / (max - min);
        lin.Addend = -min / (max - min);
        trans[i] = lin;
        i++;
      }
      return trans;
    }

    private static double[,] ExtractData(IDataset dataset, IEnumerable<int> rows, IReadOnlyCollection<string> allowedInputVariables, ITransformation<double>[] scaling = null) {
      double[][] variables;
      if (scaling != null) {
        variables =
          allowedInputVariables.Select((var, i) => scaling[i].Apply(dataset.GetDoubleValues(var, rows)).ToArray())
            .ToArray();
      } else {
        variables =
        allowedInputVariables.Select(var => dataset.GetDoubleValues(var, rows).ToArray()).ToArray();
      }
      int n = variables.First().Length;
      var res = new double[n, variables.Length];
      for (int r = 0; r < n; r++)
        for (int c = 0; c < variables.Length; c++) {
          res[r, c] = variables[c][r];
        }
      return res;
    }
  }

}


// UNFINISHED
public class RBFModel : NamedItem, IRegressionModel {
  private alglib.rbfmodel model;

  public string TargetVariable { get; set; }

  public IEnumerable<string> VariablesUsedForPrediction { get; private set; }
  private ITransformation<double>[] scaling;

  public event EventHandler TargetVariableChanged;

  public RBFModel(RBFModel orig, Cloner cloner) : base(orig, cloner) {
    this.TargetVariable = orig.TargetVariable;
    this.VariablesUsedForPrediction = orig.VariablesUsedForPrediction.ToArray();
    this.model = (alglib.rbfmodel)orig.model.make_copy();
    this.scaling = orig.scaling.Select(s => cloner.Clone(s)).ToArray();
  }
  public RBFModel(alglib.rbfmodel model, string targetVar, string[] inputs, IEnumerable<ITransformation<double>> scaling) : base("RBFModel", "RBFModel") {
    this.model = model;
    this.TargetVariable = targetVar;
    this.VariablesUsedForPrediction = inputs;
    this.scaling = scaling.ToArray();
  }

  public override IDeepCloneable Clone(Cloner cloner) {
    return new RBFModel(this, cloner);
  }

  public IRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData) {
    return new RegressionSolution(this, (IRegressionProblemData)problemData.Clone());
  }

  public IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows) {
    double[] x = new double[VariablesUsedForPrediction.Count()];
    double[] y;
    foreach (var r in rows) {
      int c = 0;
      foreach (var v in VariablesUsedForPrediction) {
        x[c] = scaling[c].Apply(dataset.GetDoubleValue(v, r).ToEnumerable()).First(); // OUCH!
        c++;
      }
      alglib.rbfcalc(model, x, out y);
      yield return y[0];
    }
  }
}