#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.Generic;
using System.Linq;
using System.Threading;
using HeuristicLab.Algorithms.DataAnalysis;
using HeuristicLab.Common;
using HeuristicLab.Core;
using HeuristicLab.Data;
using HeuristicLab.Encodings.RealVectorEncoding;
using HeuristicLab.Optimization;
using HeuristicLab.Problems.DataAnalysis;

namespace HeuristicLab.Algorithms.SAPBA {
  internal static class EgoUtilities {
    //Extention methods for convenience
    public static int ArgMax<T>(this IEnumerable<T> values, Func<T, double> func) {
      var max = double.MinValue;
      var maxIdx = 0;
      var idx = 0;
      foreach (var v in values) {
        var d = func.Invoke(v);
        if (d > max) {
          max = d;
          maxIdx = idx;
        }
        idx++;
      }
      return maxIdx;
    }
    public static int ArgMin<T>(this IEnumerable<T> values, Func<T, double> func) {
      return ArgMax(values, x => -func.Invoke(x));
    }
    public static double GetEstimation(this IRegressionModel model, RealVector r) {
      var dataset = GetDataSet(new[] { new Tuple<RealVector, double>(r, 0.0) }, false);
      return model.GetEstimatedValues(dataset, new[] { 0 }).First();
    }
    public static double GetVariance(this IConfidenceRegressionModel model, RealVector r) {
      var dataset = GetDataSet(new[] { new Tuple<RealVector, double>(r, 0.0) }, false);
      return model.GetEstimatedVariances(dataset, new[] { 0 }).First();
    }
    public static double GetDoubleValue(this IDataset dataset, int i, int j) {
      return dataset.GetDoubleValue("input" + j, i);
    }

    //Sub-Algorithms
    public static ResultCollection SyncRunSubAlgorithm(IAlgorithm alg, int random) {

      if (alg.Parameters.ContainsKey("SetSeedRandomly") && alg.Parameters.ContainsKey("Seed")) {
        var setSeed = alg.Parameters["SetSeedRandomly"].ActualValue as BoolValue;
        var seed = alg.Parameters["Seed"].ActualValue as IntValue;
        if (seed == null || setSeed == null) throw new ArgumentException("wrong SeedParametertypes");
        setSeed.Value = false;
        seed.Value = random;

      }


      EventWaitHandle trigger = new AutoResetEvent(false);
      Exception ex = null;
      EventHandler<EventArgs<Exception>> exhandler = (sender, e) => ex = e.Value;
      EventHandler stoppedHandler = (sender, e) => trigger.Set();
      alg.ExceptionOccurred += exhandler;
      alg.Stopped += stoppedHandler;
      alg.Prepare();
      alg.Start();
      trigger.WaitOne();
      alg.ExceptionOccurred -= exhandler;
      alg.Stopped -= stoppedHandler;
      if (ex != null) throw ex;
      return alg.Results;
    }

    public static IRegressionSolution BuildModel(CancellationToken cancellationToken, IEnumerable<Tuple<RealVector, double>> samples, IDataAnalysisAlgorithm<IRegressionProblem> regressionAlgorithm, IRandom random, bool removeDuplicates = true, IRegressionSolution oldSolution = null) {
      var dataset = GetDataSet(samples.ToList(), removeDuplicates);
      var problemdata = new RegressionProblemData(dataset, dataset.VariableNames.Where(x => !x.Equals("output")), "output");
      problemdata.TrainingPartition.Start = 0;
      problemdata.TrainingPartition.End = dataset.Rows;
      problemdata.TestPartition.Start = dataset.Rows;
      problemdata.TestPartition.End = dataset.Rows;


      if (regressionAlgorithm.Problem == null) regressionAlgorithm.Problem = new RegressionProblem();
      var problem = regressionAlgorithm.Problem;
      problem.ProblemDataParameter.Value = problemdata;
      var i = 0;
      IRegressionSolution solution = null;

      while (solution == null && i++ < 100) {
        var results = EgoUtilities.SyncRunSubAlgorithm(regressionAlgorithm, random.Next(int.MaxValue));
        solution = results.Select(x => x.Value).OfType<IRegressionSolution>().SingleOrDefault();
        cancellationToken.ThrowIfCancellationRequested();
      }

      //special treatement for GaussianProcessRegression
      var gp = regressionAlgorithm;
      var oldGaussian = oldSolution as GaussianProcessRegressionSolution;
      if (gp != null && oldGaussian != null) {
        const double noise = 0.0;
        var n = samples.First().Item1.Length;
        var mean = (IMeanFunction)oldGaussian.Model.MeanFunction.Clone();
        var cov = (ICovarianceFunction)oldGaussian.Model.CovarianceFunction.Clone();
        if (mean.GetNumberOfParameters(n) != 0 || cov.GetNumberOfParameters(n) != 0) throw new ArgumentException("DEBUG: assumption about fixed paramters wrong");
        double[] hyp = { noise };
        try {
          var model = new GaussianProcessModel(problemdata.Dataset, problemdata.TargetVariable, problemdata.AllowedInputVariables, problemdata.TrainingIndices, hyp, mean, cov);
          model.FixParameters();
          var sol = new GaussianProcessRegressionSolution(model, problemdata);
          if (solution == null || solution.TrainingMeanSquaredError > sol.TrainingMeanSquaredError) {
            solution = sol;
          }
        }
        catch (ArgumentException) { }
      }

      if (solution == null) throw new ArgumentException("The algorithm didn't return a model");
      regressionAlgorithm.Runs.Clear();
      return solution;
    }
    //RegressionModel extensions
    public const double DuplicateResolution = 0.0001;
    public static Dataset GetDataSet(IReadOnlyList<Tuple<RealVector, double>> samples, bool removeDuplicates) {
      if (removeDuplicates) samples = RemoveDuplicates(samples); //TODO duplicate removal leads to incorrect uncertainty values in models
      var dimensions = samples[0].Item1.Length + 1;
      var data = new double[samples.Count, dimensions];
      var names = new string[dimensions - 1];
      for (var i = 0; i < names.Length; i++) names[i] = "input" + i;
      for (var j = 0; j < samples.Count; j++) {
        for (var i = 0; i < names.Length; i++) data[j, i] = samples[j].Item1[i];
        data[j, dimensions - 1] = samples[j].Item2;
      }
      return new Dataset(names.Concat(new[] { "output" }).ToArray(), data);
    }
    private static IReadOnlyList<Tuple<RealVector, double>> RemoveDuplicates(IReadOnlyList<Tuple<RealVector, double>> samples) {
      var res = new List<Tuple<RealVector, double, int>>();
      foreach (var sample in samples) {
        if (res.Count == 0) {
          res.Add(new Tuple<RealVector, double, int>(sample.Item1, sample.Item2, 1));
          continue;
        }
        var index = res.ArgMin(x => Euclidian(sample.Item1, x.Item1));
        var d = Euclidian(res[index].Item1, sample.Item1);
        if (d > DuplicateResolution)
          res.Add(new Tuple<RealVector, double, int>(sample.Item1, sample.Item2, 1));
        else {
          var t = res[index];
          res.RemoveAt(index);
          res.Add(new Tuple<RealVector, double, int>(t.Item1, t.Item2 + sample.Item2, t.Item3 + 1));
        }
      }
      return res.Select(x => new Tuple<RealVector, double>(x.Item1, x.Item2 / x.Item3)).ToArray();
    }
    private static double Euclidian(IEnumerable<double> a, IEnumerable<double> b) {
      return Math.Sqrt(a.Zip(b, (d, d1) => d - d1).Sum(d => d * d));
    }
  }
}