source: branches/LearningClassifierSystems/HeuristicLab.Encodings.ConditionActionEncoding/3.3/Ensemble/ConditionActionEnsembleSolution.cs @ 12214

#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;
using System.Collections.Generic;
using System.Drawing;
using System.Linq;
using HeuristicLab.Collections;
using HeuristicLab.Common;
using HeuristicLab.Core;
using HeuristicLab.Data;
using HeuristicLab.Optimization;
using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;

namespace HeuristicLab.Encodings.ConditionActionEncoding {
  [StorableClass]
  [Item("ConditionActionEnsembleSolution", "")]
  [Creatable("Data Analysis - Ensembles")]
  public class ConditionActionEnsembleSolution : ResultCollection, IConditionActionEnsembleSolution {
    private readonly Dictionary<int, IAction> trainingEvaluationCache = new Dictionary<int, IAction>();
    private readonly Dictionary<int, IAction> testEvaluationCache = new Dictionary<int, IAction>();
    private readonly Dictionary<int, IAction> evaluationCache = new Dictionary<int, IAction>();

    private const string ModelResultName = "Model";
    private const string ProblemDataResultName = "ProblemData";
    private const string TrainingAccuracyResultName = "Accuracy (training)";
    private const string TestAccuracyResultName = "Accuracy (test)";

    public string Filename { get; set; }

    public static new Image StaticItemImage {
      get { return HeuristicLab.Common.Resources.VSImageLibrary.Function; }
    }

    public double TrainingAccuracy {
      get { return ((PercentValue)this[TrainingAccuracyResultName].Value).Value; }
      private set { ((PercentValue)this[TrainingAccuracyResultName].Value).Value = value; }
    }
    public double TestAccuracy {
      get { return ((PercentValue)this[TestAccuracyResultName].Value).Value; }
      private set { ((PercentValue)this[TestAccuracyResultName].Value).Value = value; }
    }

    #region properties
    public IConditionActionEnsembleModel Model {
      get { return (IConditionActionEnsembleModel)this[ModelResultName].Value; }
      protected set {
        if (this[ModelResultName].Value != value) {
          if (value != null) {
            value.ClassifierComparer = ProblemData != null ? ProblemData.ClassifierComparer : null;
            this[ModelResultName].Value = value;
            OnModelChanged();
          }
        }
      }
    }

    public IConditionActionEnsembleProblemData ProblemData {
      get { return (IConditionActionEnsembleProblemData)this[ProblemDataResultName].Value; }
      set {
        if (this[ProblemDataResultName].Value != value) {
          if (value != null) {
            ProblemData.Changed -= new EventHandler(ProblemData_Changed);
            this[ProblemDataResultName].Value = value;
            ProblemData.Changed += new EventHandler(ProblemData_Changed);
            OnProblemDataChanged();
          }
        }
      }
    }

    private void ProblemData_Changed(object sender, EventArgs e) {
      OnProblemDataChanged();
    }
    #endregion

    private readonly ItemCollection<IConditionActionSolution> conditionActionSolutions;
    public IItemCollection<IConditionActionSolution> ConditionActionSolutions {
      get { return conditionActionSolutions; }
    }

    [Storable]
    private Dictionary<IConditionActionModel, IntRange> trainingPartitions;
    [Storable]
    private Dictionary<IConditionActionModel, IntRange> testPartitions;

    [StorableHook(HookType.AfterDeserialization)]
    private void AfterDeserialization() {
      Model.ClassifierComparer = ProblemData.ClassifierComparer;
      foreach (var model in Model.Models) {
        IConditionActionProblemData problemData = ProblemData.GetConditionActionProblemData();
        problemData.TrainingPartition.Start = trainingPartitions[model].Start;
        problemData.TrainingPartition.End = trainingPartitions[model].End;
        problemData.TestPartition.Start = testPartitions[model].Start;
        problemData.TestPartition.End = testPartitions[model].End;

        conditionActionSolutions.Add(model.CreateConditionActionSolution(problemData));
      }
      RegisterConditionActionSolutionsEventHandler();
    }

    [StorableConstructor]
    protected ConditionActionEnsembleSolution(bool deserializing)
      : base(deserializing) {
      conditionActionSolutions = new ItemCollection<IConditionActionSolution>();
    }
    protected ConditionActionEnsembleSolution(ConditionActionEnsembleSolution original, Cloner cloner)
      : base(original, cloner) {
      trainingPartitions = new Dictionary<IConditionActionModel, IntRange>();
      testPartitions = new Dictionary<IConditionActionModel, IntRange>();
      foreach (var pair in original.trainingPartitions) {
        trainingPartitions[cloner.Clone(pair.Key)] = cloner.Clone(pair.Value);
      }
      foreach (var pair in original.testPartitions) {
        testPartitions[cloner.Clone(pair.Key)] = cloner.Clone(pair.Value);
      }

      trainingEvaluationCache = new Dictionary<int, IAction>(original.ProblemData.TrainingIndices.Count());
      testEvaluationCache = new Dictionary<int, IAction>(original.ProblemData.TestIndices.Count());

      conditionActionSolutions = cloner.Clone(original.conditionActionSolutions);
      RegisterConditionActionSolutionsEventHandler();
    }

    public ConditionActionEnsembleSolution(IEnumerable<IConditionActionModel> models, IConditionActionProblemData problemData)
      : this(models, problemData,
             models.Select(m => (IntRange)problemData.TrainingPartition.Clone()),
             models.Select(m => (IntRange)problemData.TestPartition.Clone())
      ) { }

    public ConditionActionEnsembleSolution()
      : base() {
      trainingPartitions = new Dictionary<IConditionActionModel, IntRange>();
      testPartitions = new Dictionary<IConditionActionModel, IntRange>();
      conditionActionSolutions = new ItemCollection<IConditionActionSolution>();

      RegisterConditionActionSolutionsEventHandler();
    }

    public ConditionActionEnsembleSolution(IConditionActionProblemData problemData)
      : this(Enumerable.Empty<IConditionActionModel>(), problemData) {
    }

    public ConditionActionEnsembleSolution(IEnumerable<IConditionActionModel> models, IConditionActionProblemData problemData, IEnumerable<IntRange> trainingPartitions, IEnumerable<IntRange> testPartitions)
      : base() {
      Add(new Result(ModelResultName, "The data analysis model.", new ConditionActionEnsembleModel(Enumerable.Empty<IConditionActionModel>())));
      Add(new Result(ProblemDataResultName, "The data analysis problem data.", new ConditionActionEnsembleProblemData((IConditionActionProblemData)problemData.Clone())));
      Add(new Result(TrainingAccuracyResultName, "Accuracy of the model on the training partition (percentage of correctly classified instances).", new PercentValue()));
      Add(new Result(TestAccuracyResultName, "Accuracy of the model on the test partition (percentage of correctly classified instances).", new PercentValue()));

      Model.ClassifierComparer = ProblemData.ClassifierComparer;

      this.trainingPartitions = new Dictionary<IConditionActionModel, IntRange>();
      this.testPartitions = new Dictionary<IConditionActionModel, IntRange>();
      this.conditionActionSolutions = new ItemCollection<IConditionActionSolution>();

      List<IConditionActionSolution> solutions = new List<IConditionActionSolution>();
      var modelEnumerator = models.GetEnumerator();
      var trainingPartitionEnumerator = trainingPartitions.GetEnumerator();
      var testPartitionEnumerator = testPartitions.GetEnumerator();

      while (modelEnumerator.MoveNext() & trainingPartitionEnumerator.MoveNext() & testPartitionEnumerator.MoveNext()) {
        var p = (IConditionActionProblemData)problemData.Clone();
        p.TrainingPartition.Start = trainingPartitionEnumerator.Current.Start;
        p.TrainingPartition.End = trainingPartitionEnumerator.Current.End;
        p.TestPartition.Start = testPartitionEnumerator.Current.Start;
        p.TestPartition.End = testPartitionEnumerator.Current.End;

        solutions.Add(modelEnumerator.Current.CreateConditionActionSolution(p));
      }
      if (modelEnumerator.MoveNext() | trainingPartitionEnumerator.MoveNext() | testPartitionEnumerator.MoveNext()) {
        throw new ArgumentException();
      }

      trainingEvaluationCache = new Dictionary<int, IAction>(problemData.TrainingIndices.Count());
      testEvaluationCache = new Dictionary<int, IAction>(problemData.TestIndices.Count());

      RegisterConditionActionSolutionsEventHandler();
      conditionActionSolutions.AddRange(solutions);
    }

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

    private void RegisterConditionActionSolutionsEventHandler() {
      conditionActionSolutions.ItemsAdded += new CollectionItemsChangedEventHandler<IConditionActionSolution>(conditionActionSolutions_ItemsAdded);
      conditionActionSolutions.ItemsRemoved += new CollectionItemsChangedEventHandler<IConditionActionSolution>(conditionActionSolutions_ItemsRemoved);
      conditionActionSolutions.CollectionReset += new CollectionItemsChangedEventHandler<IConditionActionSolution>(conditionActionSolutions_CollectionReset);
    }

    #region Evaluation
    public IEnumerable<IAction> EstimatedAction {
      get { return GetEstimatedNiches(Enumerable.Range(0, ProblemData.Dataset.Rows)); }
    }

    public IEnumerable<IAction> EstimatedTrainingAction {
      get {
        var rows = ProblemData.TrainingIndices;
        var rowsToEvaluate = rows.Except(trainingEvaluationCache.Keys);
        var rowsEnumerator = rowsToEvaluate.GetEnumerator();
        var valuesEnumerator = GetEstimatedValues(rowsToEvaluate, (r, m) => RowIsTrainingForModel(r, m) && !RowIsTestForModel(r, m)).GetEnumerator();

        while (rowsEnumerator.MoveNext() & valuesEnumerator.MoveNext()) {
          trainingEvaluationCache.Add(rowsEnumerator.Current, valuesEnumerator.Current);
        }

        return rows.Select(row => trainingEvaluationCache[row]);
      }
    }

    public IEnumerable<IAction> EstimatedTestAction {
      get {
        var rows = ProblemData.TestIndices;
        var rowsToEvaluate = rows.Except(testEvaluationCache.Keys);
        var rowsEnumerator = rowsToEvaluate.GetEnumerator();
        var valuesEnumerator = GetEstimatedValues(rowsToEvaluate, RowIsTestForModel).GetEnumerator();

        while (rowsEnumerator.MoveNext() & valuesEnumerator.MoveNext()) {
          testEvaluationCache.Add(rowsEnumerator.Current, valuesEnumerator.Current);
        }

        return rows.Select(row => testEvaluationCache[row]);
      }
    }

    public IEnumerable<IAction> GetEstimatedNiches(IEnumerable<int> rows) {
      var rowsToEvaluate = rows.Except(evaluationCache.Keys);
      var rowsEnumerator = rowsToEvaluate.GetEnumerator();

      var valuesEnumerator = (from xs in GetEstimatedNicheVectors(ProblemData.FetchInput(rows))
                              select AggregateEstimatedClassValues(xs))
                              .GetEnumerator();

      while (rowsEnumerator.MoveNext() & valuesEnumerator.MoveNext()) {
        evaluationCache.Add(rowsEnumerator.Current, valuesEnumerator.Current);
      }

      return rows.Select(row => evaluationCache[row]);
    }

    public IEnumerable<IEnumerable<IAction>> GetEstimatedNicheVectors(IEnumerable<IInput> input) {
      if (!Model.Models.Any()) yield break;
      var estimatedValuesEnumerators = (from model in Model.Models
                                        select model.GetAction(input).GetEnumerator())
                                       .ToList();

      while (estimatedValuesEnumerators.All(en => en.MoveNext())) {
        yield return from enumerator in estimatedValuesEnumerators
                     select enumerator.Current;
      }
    }

    private IEnumerable<IAction> GetEstimatedValues(IEnumerable<int> rows, Func<int, IConditionActionModel, bool> modelSelectionPredicate) {
      var input = ProblemData.FetchInput(rows);
      var estimatedValuesEnumerators = (from model in Model.Models
                                        select new { Model = model, EstimatedValuesEnumerator = model.GetAction(input).GetEnumerator() })
                                       .ToList();
      var rowsEnumerator = rows.GetEnumerator();
      // aggregate to make sure that MoveNext is called for all enumerators 
      while (rowsEnumerator.MoveNext() & estimatedValuesEnumerators.Select(en => en.EstimatedValuesEnumerator.MoveNext()).Aggregate(true, (acc, b) => acc & b)) {
        int currentRow = rowsEnumerator.Current;

        var selectedEnumerators = from pair in estimatedValuesEnumerators
                                  where modelSelectionPredicate(currentRow, pair.Model)
                                  select pair.EstimatedValuesEnumerator;

        yield return AggregateEstimatedClassValues(selectedEnumerators.Select(x => x.Current));
      }
    }

    private IAction AggregateEstimatedClassValues(IEnumerable<IAction> estimatedNiches) {
      return estimatedNiches
      .GroupBy(x => x, ProblemData.ClassifierComparer)
      .OrderByDescending(g => g.Count())
      .Select(g => g.Key)
      .FirstOrDefault();
    }

    private void RecalculateResults() {
      var originalTrainingCondition = ProblemData.FetchInput(ProblemData.TrainingIndices);
      var originalTestCondition = ProblemData.FetchInput(ProblemData.TestIndices);
      var estimatedTraining = EstimatedTrainingAction;
      var estimatedTest = EstimatedTestAction;

      var originalTrainingAction = ProblemData.FetchAction(ProblemData.TrainingIndices);
      var originalTestAction = ProblemData.FetchAction(ProblemData.TestIndices);

      TrainingAccuracy = CalculateAccuracy(originalTrainingAction, estimatedTraining);
      TestAccuracy = CalculateAccuracy(originalTestAction, estimatedTest);
    }

    public static double CalculateAccuracy(IEnumerable<IAction> original, IEnumerable<IAction> estimated) {
      double correctClassified = 0;

      double rows = original.Count();
      var originalEnumerator = original.GetEnumerator();
      var estimatedActionEnumerator = estimated.GetEnumerator();

      while (originalEnumerator.MoveNext() && estimatedActionEnumerator.MoveNext()) {
        if (originalEnumerator.Current.Match(estimatedActionEnumerator.Current)) {
          correctClassified++;
        }
      }

      return correctClassified / rows;
    }

    private bool RowIsTrainingForModel(int currentRow, IConditionActionModel model) {
      return trainingPartitions == null || !trainingPartitions.ContainsKey(model) ||
              (trainingPartitions[model].Start <= currentRow && currentRow < trainingPartitions[model].End);
    }

    private bool RowIsTestForModel(int currentRow, IConditionActionModel model) {
      return testPartitions == null || !testPartitions.ContainsKey(model) ||
              (testPartitions[model].Start <= currentRow && currentRow < testPartitions[model].End);
    }
    #endregion

    public event EventHandler ProblemDataChanged;
    protected void OnProblemDataChanged() {
      trainingEvaluationCache.Clear();
      testEvaluationCache.Clear();
      evaluationCache.Clear();

      IConditionActionProblemData problemData = ProblemData.GetConditionActionProblemData();

      problemData.TrainingPartition.Start = ProblemData.TrainingPartition.Start;
      problemData.TrainingPartition.End = ProblemData.TrainingPartition.End;
      problemData.TestPartition.Start = ProblemData.TestPartition.Start;
      problemData.TestPartition.End = ProblemData.TestPartition.End;

      foreach (var solution in conditionActionSolutions) {
        if (solution is ConditionActionEnsembleSolution)
          solution.ProblemData = ProblemData;
        else
          solution.ProblemData = problemData;
      }
      foreach (var trainingPartition in trainingPartitions.Values) {
        trainingPartition.Start = ProblemData.TrainingPartition.Start;
        trainingPartition.End = ProblemData.TrainingPartition.End;
      }
      foreach (var testPartition in testPartitions.Values) {
        testPartition.Start = ProblemData.TestPartition.Start;
        testPartition.End = ProblemData.TestPartition.End;
      }

      RecalculateResults();
      var listeners = ProblemDataChanged;
      if (listeners != null) listeners(this, EventArgs.Empty);
    }

    public event EventHandler ModelChanged;
    protected virtual void OnModelChanged() {
      RecalculateResults();
      var listeners = ModelChanged;
      if (listeners != null) listeners(this, EventArgs.Empty);
    }

    public void AddConditionActionSolutions(IEnumerable<IConditionActionSolution> solutions) {
      conditionActionSolutions.AddRange(solutions);

      trainingEvaluationCache.Clear();
      testEvaluationCache.Clear();
      evaluationCache.Clear();
    }
    public void RemoveConditionActionSolutions(IEnumerable<IConditionActionSolution> solutions) {
      conditionActionSolutions.RemoveRange(solutions);

      trainingEvaluationCache.Clear();
      testEvaluationCache.Clear();
      evaluationCache.Clear();
    }

    private void conditionActionSolutions_ItemsAdded(object sender, CollectionItemsChangedEventArgs<IConditionActionSolution> e) {
      foreach (var solution in e.Items) AddConditionActionSolution(solution);
      RecalculateResults();
    }
    private void conditionActionSolutions_ItemsRemoved(object sender, CollectionItemsChangedEventArgs<IConditionActionSolution> e) {
      foreach (var solution in e.Items) RemoveConditionActionSolution(solution);
      RecalculateResults();
    }
    private void conditionActionSolutions_CollectionReset(object sender, CollectionItemsChangedEventArgs<IConditionActionSolution> e) {
      foreach (var solution in e.OldItems) RemoveConditionActionSolution(solution);
      foreach (var solution in e.Items) AddConditionActionSolution(solution);
      RecalculateResults();
    }

    private void AddConditionActionSolution(IConditionActionSolution solution) {
      if (Model.Models.Contains(solution.Model)) throw new ArgumentException();
      Model.Add(solution.Model);
      trainingPartitions[solution.Model] = solution.ProblemData.TrainingPartition;
      testPartitions[solution.Model] = solution.ProblemData.TestPartition;

      trainingEvaluationCache.Clear();
      testEvaluationCache.Clear();
      evaluationCache.Clear();
    }

    private void RemoveConditionActionSolution(IConditionActionSolution solution) {
      if (!Model.Models.Contains(solution.Model)) throw new ArgumentException();
      Model.Remove(solution.Model);
      trainingPartitions.Remove(solution.Model);
      testPartitions.Remove(solution.Model);

      trainingEvaluationCache.Clear();
      testEvaluationCache.Clear();
      evaluationCache.Clear();
    }

    #region IConditionActionSolution Members
    IConditionActionModel IConditionActionSolution.Model {
      get { return Model; }
    }
    IConditionActionProblemData IConditionActionSolution.ProblemData {
      get { return ProblemData; }
      set { ProblemData = new ConditionActionEnsembleProblemData(value); }
    }
    #endregion
  }
}