source: branches/HeuristicLab.Problems.GeneticProgramming.BloodGlucosePrediction/Solution.cs @ 16003

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

namespace HeuristicLab.Problems.GeneticProgramming.GlucosePrediction {
  [StorableClass]
  [Item("Solution", "")]
  // almost a complete copy of RegressionSolutionBase and RegressionSolution
  // only change: skipping missing values in the target
  public sealed class Solution : DataAnalysisSolution, IRegressionSolution {
    private const string TrainingMeanSquaredErrorResultName = "Mean squared error (training)";
    private const string TestMeanSquaredErrorResultName = "Mean squared error (test)";
    private const string TrainingMeanAbsoluteErrorResultName = "Mean absolute error (training)";
    private const string TestMeanAbsoluteErrorResultName = "Mean absolute error (test)";
    private const string TrainingSquaredCorrelationResultName = "Pearson's R² (training)";
    private const string TestSquaredCorrelationResultName = "Pearson's R² (test)";
    private const string TrainingRelativeErrorResultName = "Average relative error (training)";
    private const string TestRelativeErrorResultName = "Average relative error (test)";
    private const string TrainingNormalizedMeanSquaredErrorResultName = "Normalized mean squared error (training)";
    private const string TestNormalizedMeanSquaredErrorResultName = "Normalized mean squared error (test)";
    private const string TrainingRootMeanSquaredErrorResultName = "Root mean squared error (training)";
    private const string TestRootMeanSquaredErrorResultName = "Root mean squared error (test)";

    private const string TrainingMeanSquaredErrorResultDescription = "Mean of squared errors of the model on the training partition";
    private const string TestMeanSquaredErrorResultDescription = "Mean of squared errors of the model on the test partition";
    private const string TrainingMeanAbsoluteErrorResultDescription = "Mean of absolute errors of the model on the training partition";
    private const string TestMeanAbsoluteErrorResultDescription = "Mean of absolute errors of the model on the test partition";
    private const string TrainingSquaredCorrelationResultDescription = "Squared Pearson's correlation coefficient of the model output and the actual values on the training partition";
    private const string TestSquaredCorrelationResultDescription = "Squared Pearson's correlation coefficient of the model output and the actual values on the test partition";
    private const string TrainingRelativeErrorResultDescription = "Average of the relative errors of the model output and the actual values on the training partition";
    private const string TestRelativeErrorResultDescription = "Average of the relative errors of the model output and the actual values on the test partition";
    private const string TrainingNormalizedMeanSquaredErrorResultDescription = "Normalized mean of squared errors of the model on the training partition";
    private const string TestNormalizedMeanSquaredErrorResultDescription = "Normalized mean of squared errors of the model on the test partition";
    private const string TrainingRootMeanSquaredErrorResultDescription = "Root mean of squared errors of the model on the training partition";
    private const string TestRootMeanSquaredErrorResultDescription = "Root mean of squared errors of the model on the test partition";

    [StorableConstructor]
    public Solution(bool deserializing)
      : base(deserializing) {
    }

    public Solution(Solution original, Cloner cloner)
      : base(original, cloner) {
    }

    public Solution(IRegressionModel model, IRegressionProblemData problemData)
      : base(model, problemData) {
      Add(new Result(TrainingMeanSquaredErrorResultName, TrainingMeanSquaredErrorResultDescription, new DoubleValue()));
      Add(new Result(TestMeanSquaredErrorResultName, TestMeanSquaredErrorResultDescription, new DoubleValue()));
      Add(new Result(TrainingMeanAbsoluteErrorResultName, TrainingMeanAbsoluteErrorResultDescription, new DoubleValue()));
      Add(new Result(TestMeanAbsoluteErrorResultName, TestMeanAbsoluteErrorResultDescription, new DoubleValue()));
      Add(new Result(TrainingSquaredCorrelationResultName, TrainingSquaredCorrelationResultDescription, new DoubleValue()));
      Add(new Result(TestSquaredCorrelationResultName, TestSquaredCorrelationResultDescription, new DoubleValue()));
      Add(new Result(TrainingRelativeErrorResultName, TrainingRelativeErrorResultDescription, new PercentValue()));
      Add(new Result(TestRelativeErrorResultName, TestRelativeErrorResultDescription, new PercentValue()));
      Add(new Result(TrainingNormalizedMeanSquaredErrorResultName, TrainingNormalizedMeanSquaredErrorResultDescription, new DoubleValue()));
      Add(new Result(TestNormalizedMeanSquaredErrorResultName, TestNormalizedMeanSquaredErrorResultDescription, new DoubleValue()));
      Add(new Result(TrainingRootMeanSquaredErrorResultName, TrainingRootMeanSquaredErrorResultDescription, new DoubleValue()));
      Add(new Result(TestRootMeanSquaredErrorResultName, TestRootMeanSquaredErrorResultDescription, new DoubleValue()));
      CalculateRegressionResults();
    }

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

    protected override void RecalculateResults() {
      CalculateRegressionResults();
    }

    private void CalculateRegressionResults() {
      IEnumerable<double> estimatedTrainingValues = EstimatedTrainingValues; // cache values
      IEnumerable<double> originalTrainingValues = ProblemData.Dataset.GetDoubleValues(ProblemData.TargetVariable, ProblemData.TrainingIndices);
      IEnumerable<double> estimatedTestValues = EstimatedTestValues; // cache values
      IEnumerable<double> originalTestValues = ProblemData.Dataset.GetDoubleValues(ProblemData.TargetVariable, ProblemData.TestIndices);

      // only take predictions for which the target is not NaN
      var selectedTrainingTuples = originalTrainingValues.Zip(estimatedTrainingValues, Tuple.Create).Where(t => !double.IsNaN(t.Item1)).ToArray();
      originalTrainingValues = selectedTrainingTuples.Select(t => t.Item1);
      estimatedTrainingValues = selectedTrainingTuples.Select(t => t.Item2);

      var selectedTestTuples = originalTestValues.Zip(estimatedTestValues, Tuple.Create).Where(t => !double.IsNaN(t.Item1)).ToArray();
      originalTestValues = selectedTestTuples.Select(t => t.Item1);
      estimatedTestValues = selectedTestTuples.Select(t => t.Item2);

      OnlineCalculatorError errorState;
      double trainingMSE = OnlineMeanSquaredErrorCalculator.Calculate(originalTrainingValues, estimatedTrainingValues, out errorState);
      TrainingMeanSquaredError = errorState == OnlineCalculatorError.None ? trainingMSE : double.NaN;
      double testMSE = OnlineMeanSquaredErrorCalculator.Calculate(originalTestValues, estimatedTestValues, out errorState);
      TestMeanSquaredError = errorState == OnlineCalculatorError.None ? testMSE : double.NaN;

      double trainingMAE = OnlineMeanAbsoluteErrorCalculator.Calculate(originalTrainingValues, estimatedTrainingValues, out errorState);
      TrainingMeanAbsoluteError = errorState == OnlineCalculatorError.None ? trainingMAE : double.NaN;
      double testMAE = OnlineMeanAbsoluteErrorCalculator.Calculate(originalTestValues, estimatedTestValues, out errorState);
      TestMeanAbsoluteError = errorState == OnlineCalculatorError.None ? testMAE : double.NaN;

      double trainingR = OnlinePearsonsRCalculator.Calculate(originalTrainingValues, estimatedTrainingValues, out errorState);
      TrainingRSquared = errorState == OnlineCalculatorError.None ? trainingR * trainingR : double.NaN;
      double testR = OnlinePearsonsRCalculator.Calculate(originalTestValues, estimatedTestValues, out errorState);
      TestRSquared = errorState == OnlineCalculatorError.None ? testR * testR : double.NaN;

      double trainingRelError = OnlineMeanAbsolutePercentageErrorCalculator.Calculate(originalTrainingValues, estimatedTrainingValues, out errorState);
      TrainingRelativeError = errorState == OnlineCalculatorError.None ? trainingRelError : double.NaN;
      double testRelError = OnlineMeanAbsolutePercentageErrorCalculator.Calculate(originalTestValues, estimatedTestValues, out errorState);
      TestRelativeError = errorState == OnlineCalculatorError.None ? testRelError : double.NaN;

      double trainingNMSE = OnlineNormalizedMeanSquaredErrorCalculator.Calculate(originalTrainingValues, estimatedTrainingValues, out errorState);
      TrainingNormalizedMeanSquaredError = errorState == OnlineCalculatorError.None ? trainingNMSE : double.NaN;
      double testNMSE = OnlineNormalizedMeanSquaredErrorCalculator.Calculate(originalTestValues, estimatedTestValues, out errorState);
      TestNormalizedMeanSquaredError = errorState == OnlineCalculatorError.None ? testNMSE : double.NaN;

      TrainingRootMeanSquaredError = Math.Sqrt(TrainingMeanSquaredError);
      TestRootMeanSquaredError = Math.Sqrt(TestMeanSquaredError);
    }

    public new IRegressionModel Model {
      get { return (IRegressionModel)base.Model; }
      private set {
        base.Model = value;
      }
    }
    public new IRegressionProblemData ProblemData {
      get { return (IRegressionProblemData)base.ProblemData; }
      set {
        base.ProblemData = value;
      }
    }

    public IEnumerable<double> EstimatedValues {
      get { return GetEstimatedValues(Enumerable.Range(0, ProblemData.Dataset.Rows)); }
    }
    public IEnumerable<double> EstimatedTrainingValues {
      get {
        var all = EstimatedValues.ToArray();
        return ProblemData.TrainingIndices.Select(r => all[r]);
      }
    }
    public IEnumerable<double> EstimatedTestValues {
      get {
        var all = EstimatedValues.ToArray();
        return ProblemData.TestIndices.Select(r => all[r]);
      }
    }

    public IEnumerable<double> GetEstimatedValues(IEnumerable<int> rows) {
      var all = Model.GetEstimatedValues(ProblemData.Dataset, ProblemData.AllIndices).ToArray();
      return rows.Select(r => all[r]);
    }


    #region Results
    public double TrainingMeanSquaredError {
      get { return ((DoubleValue)this[TrainingMeanSquaredErrorResultName].Value).Value; }
      private set { ((DoubleValue)this[TrainingMeanSquaredErrorResultName].Value).Value = value; }
    }
    public double TestMeanSquaredError {
      get { return ((DoubleValue)this[TestMeanSquaredErrorResultName].Value).Value; }
      private set { ((DoubleValue)this[TestMeanSquaredErrorResultName].Value).Value = value; }
    }
    public double TrainingMeanAbsoluteError {
      get { return ((DoubleValue)this[TrainingMeanAbsoluteErrorResultName].Value).Value; }
      private set { ((DoubleValue)this[TrainingMeanAbsoluteErrorResultName].Value).Value = value; }
    }
    public double TestMeanAbsoluteError {
      get { return ((DoubleValue)this[TestMeanAbsoluteErrorResultName].Value).Value; }
      private set { ((DoubleValue)this[TestMeanAbsoluteErrorResultName].Value).Value = value; }
    }
    public double TrainingRSquared {
      get { return ((DoubleValue)this[TrainingSquaredCorrelationResultName].Value).Value; }
      private set { ((DoubleValue)this[TrainingSquaredCorrelationResultName].Value).Value = value; }
    }
    public double TestRSquared {
      get { return ((DoubleValue)this[TestSquaredCorrelationResultName].Value).Value; }
      private set { ((DoubleValue)this[TestSquaredCorrelationResultName].Value).Value = value; }
    }
    public double TrainingRelativeError {
      get { return ((DoubleValue)this[TrainingRelativeErrorResultName].Value).Value; }
      private set { ((DoubleValue)this[TrainingRelativeErrorResultName].Value).Value = value; }
    }
    public double TestRelativeError {
      get { return ((DoubleValue)this[TestRelativeErrorResultName].Value).Value; }
      private set { ((DoubleValue)this[TestRelativeErrorResultName].Value).Value = value; }
    }
    public double TrainingNormalizedMeanSquaredError {
      get { return ((DoubleValue)this[TrainingNormalizedMeanSquaredErrorResultName].Value).Value; }
      private set { ((DoubleValue)this[TrainingNormalizedMeanSquaredErrorResultName].Value).Value = value; }
    }
    public double TestNormalizedMeanSquaredError {
      get { return ((DoubleValue)this[TestNormalizedMeanSquaredErrorResultName].Value).Value; }
      private set { ((DoubleValue)this[TestNormalizedMeanSquaredErrorResultName].Value).Value = value; }
    }
    public double TrainingRootMeanSquaredError {
      get { return ((DoubleValue)this[TrainingRootMeanSquaredErrorResultName].Value).Value; }
      private set { ((DoubleValue)this[TrainingRootMeanSquaredErrorResultName].Value).Value = value; }
    }
    public double TestRootMeanSquaredError {
      get { return ((DoubleValue)this[TestRootMeanSquaredErrorResultName].Value).Value; }
      private set { ((DoubleValue)this[TestRootMeanSquaredErrorResultName].Value).Value = value; }
    }


    #endregion

  }
}