#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.Linq;
using HeuristicLab.Algorithms.DataAnalysis;
using HeuristicLab.Common;
using HeuristicLab.Core;
using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
using HeuristicLab.Problems.DataAnalysis;

namespace HeuristicLab.Algorithms.NCA {
  [Item("NCAModel", "")]
  [StorableClass]
  public class NCAModel : NamedItem, INCAModel {

    [Storable]
    private Scaling scaling;
    [Storable]
    private double[,] transformationMatrix;
    public double[,] TransformationMatrix {
      get { return (double[,])transformationMatrix.Clone(); }
    }
    [Storable]
    private string[] allowedInputVariables;
    [Storable]
    private string targetVariable;
    [Storable]
    private INearestNeighbourModel nnModel;
    [Storable]
    private Dictionary<double, double> nn2ncaClassMapping;
    [Storable]
    private Dictionary<double, double> nca2nnClassMapping;

    [StorableConstructor]
    protected NCAModel(bool deserializing) : base(deserializing) { }
    protected NCAModel(NCAModel original, Cloner cloner)
      : base(original, cloner) {
      this.scaling = cloner.Clone(original.scaling);
      this.transformationMatrix = (double[,])original.transformationMatrix.Clone();
      this.allowedInputVariables = (string[])original.allowedInputVariables.Clone();
      this.targetVariable = original.targetVariable;
      this.nnModel = cloner.Clone(original.nnModel);
      this.nn2ncaClassMapping = original.nn2ncaClassMapping.ToDictionary(x => x.Key, y => y.Value);
      this.nca2nnClassMapping = original.nca2nnClassMapping.ToDictionary(x => x.Key, y => y.Value);
    }
    public NCAModel(int k, double[,] scaledData, Scaling scaling, double[,] transformationMatrix, string targetVariable, IEnumerable<double> targetVector, IEnumerable<string> allowedInputVariables) {
      Name = ItemName;
      Description = ItemDescription;
      this.scaling = scaling;
      this.transformationMatrix = transformationMatrix;
      this.allowedInputVariables = allowedInputVariables.ToArray();
      this.targetVariable = targetVariable;

      nca2nnClassMapping = targetVector.Distinct().OrderBy(x => x).Select((v, i) => new { Index = (double)i, Class = v }).ToDictionary(x => x.Class, y => y.Index);
      nn2ncaClassMapping = nca2nnClassMapping.ToDictionary(x => x.Value, y => y.Key);

      var transformedData = ReduceWithTarget(scaledData, targetVector.Select(x => nca2nnClassMapping[x]));

      var kdtree = new alglib.nearestneighbor.kdtree();
      alglib.nearestneighbor.kdtreebuild(transformedData, transformedData.GetLength(0), transformedData.GetLength(1) - 1, 1, 2, kdtree);

      nnModel = new NearestNeighbourModel(kdtree, k, targetVariable,
        Enumerable.Range(0, transformationMatrix.GetLength(1)).Select(x => x.ToString()),
        nn2ncaClassMapping.Keys.ToArray());
    }

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

    public IEnumerable<double> GetEstimatedClassValues(Dataset dataset, IEnumerable<int> rows) {
      var unknownClasses = dataset.GetDoubleValues(targetVariable, rows).Where(x => !nca2nnClassMapping.ContainsKey(x));
      if (unknownClasses.Any())
        foreach (var uc in unknownClasses) {
          nca2nnClassMapping[uc] = nca2nnClassMapping.Count;
          nn2ncaClassMapping[nca2nnClassMapping[uc]] = uc;
        }
      var transformedData = ReduceWithTarget(dataset, rows, dataset.GetDoubleValues(targetVariable, rows).Select(x => nca2nnClassMapping[x]));
      var ds = new Dataset(Enumerable.Range(0, transformationMatrix.GetLength(1)).Select(x => x.ToString()).Concat(targetVariable.ToEnumerable()), transformedData);
      return nnModel.GetEstimatedClassValues(ds, Enumerable.Range(0, ds.Rows)).Select(x => nn2ncaClassMapping[x]);
    }

    public NCAClassificationSolution CreateClassificationSolution(IClassificationProblemData problemData) {
      return new NCAClassificationSolution(problemData, this);
    }

    IClassificationSolution IClassificationModel.CreateClassificationSolution(IClassificationProblemData problemData) {
      return CreateClassificationSolution(problemData);
    }

    public double[,] Reduce(Dataset dataset, IEnumerable<int> rows) {
      var scaledData = AlglibUtil.PrepareAndScaleInputMatrix(dataset, allowedInputVariables, rows, scaling);
      return Reduce(scaledData);
    }

    private double[,] Reduce(double[,] scaledData) {
      var result = new double[scaledData.GetLength(0), transformationMatrix.GetLength(1)];
      for (int i = 0; i < scaledData.GetLength(0); i++)
        for (int j = 0; j < scaledData.GetLength(1); j++)
          for (int x = 0; x < transformationMatrix.GetLength(1); x++) {
            result[i, x] += scaledData[i, j] * transformationMatrix[j, x];
          }
      return result;
    }

    private double[,] ReduceWithTarget(Dataset dataset, IEnumerable<int> rows, IEnumerable<double> targetValues) {
      var scaledData = AlglibUtil.PrepareAndScaleInputMatrix(dataset, allowedInputVariables, rows, scaling);
      return ReduceWithTarget(scaledData, targetValues);
    }

    private double[,] ReduceWithTarget(double[,] scaledData, IEnumerable<double> targetValues) {
      var result = new double[scaledData.GetLength(0), transformationMatrix.GetLength(1) + 1];
      for (int i = 0; i < scaledData.GetLength(0); i++)
        for (int j = 0; j < scaledData.GetLength(1); j++)
          for (int x = 0; x < transformationMatrix.GetLength(1); x++) {
            result[i, x] += scaledData[i, j] * transformationMatrix[j, x];
          }

      int r = 0;
      foreach (var d in targetValues) result[r++, transformationMatrix.GetLength(1)] = d;

      return result;
    }
  }
}