source: branches/HeuristicLab.VariableInteractionNetworks/HeuristicLab.VariableInteractionNetworks/3.3/SymbolicDataAnalysisVariableImpactsAnalyzer.cs @ 12460

using System;
using System.Linq;
using HeuristicLab.Analysis;
using HeuristicLab.Common;
using HeuristicLab.Core;
using HeuristicLab.Data;
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.VariableInteractionNetworks
{
    [Item("SymbolicRegressionVariableImpactsAnalyzer", "An analyzer which calculates variable impacts based on the average node impacts from the tree")]
    [StorableClass]
    public class SymbolicRegressionVariableImpactsAnalyzer : SymbolicDataAnalysisAnalyzer
    {
        private const string UpdateCounterParameterName = "UpdateCounter";
        private const string UpdateIntervalParameterName = "UpdateInterval";
        public const string QualityParameterName = "Quality";
        private const string SymbolicDataAnalysisTreeInterpreterParameterName = "SymbolicExpressionTreeInterpreter";
        private const string ProblemDataParameterName = "ProblemData";
        private const string ApplyLinearScalingParameterName = "ApplyLinearScaling";
        private const string MaxCOIterationsParameterName = "MaxCOIterations";
        private const string EstimationLimitsParameterName = "EstimationLimits";
        private const string EvaluatorParameterName = "Evaluator";

        private const string VariableFrequenciesParameterName = "VariableFrequencies";
        private const string VariableImpactsParameterName = "AverageVariableImpacts";
        private const string PercentageBestParameterName = "PercentageBest";
        private const string LastGenerationsParameterName = "LastGenerations";
        private const string MaximumGenerationsParameterName = "MaximumGenerations";
        private const string OptimizedConstantsParameterName = "OptimizedConstants";
        
        private readonly SymbolicDataAnalysisExpressionTreeSimplifier simplifier;
        private readonly SymbolicRegressionSolutionImpactValuesCalculator impactsCalculator;

        #region parameters
        public ValueParameter<IntValue> UpdateCounterParameter
        {
            get { return (ValueParameter<IntValue>)Parameters[UpdateCounterParameterName]; }
        }
        public ValueParameter<IntValue> UpdateIntervalParameter
        {
            get { return (ValueParameter<IntValue>)Parameters[UpdateIntervalParameterName]; }
        }
        public IScopeTreeLookupParameter<DoubleValue> QualityParameter
        {
            get { return (IScopeTreeLookupParameter<DoubleValue>)Parameters[QualityParameterName]; }
        }
        public ILookupParameter<ISymbolicDataAnalysisExpressionTreeInterpreter> SymbolicDataAnalysisTreeInterpreterParameter
        {
            get { return (ILookupParameter<ISymbolicDataAnalysisExpressionTreeInterpreter>)Parameters[SymbolicDataAnalysisTreeInterpreterParameterName]; }
        }
        public ILookupParameter<IRegressionProblemData> ProblemDataParameter
        {
            get { return (ILookupParameter<IRegressionProblemData>)Parameters[ProblemDataParameterName]; }
        }
        public ILookupParameter<BoolValue> ApplyLinearScalingParameter
        {
            get { return (ILookupParameter<BoolValue>)Parameters[ApplyLinearScalingParameterName]; }
        }
        public IFixedValueParameter<IntValue> MaxCOIterationsParameter
        {
            get { return (IFixedValueParameter<IntValue>)Parameters[MaxCOIterationsParameterName]; }
        }
        public ILookupParameter<DoubleLimit> EstimationLimitsParameter
        {
            get { return (ILookupParameter<DoubleLimit>)Parameters[EstimationLimitsParameterName]; }
        }
        public ILookupParameter<ISymbolicRegressionSingleObjectiveEvaluator> EvaluatorParameter
        {
            get { return (ILookupParameter<ISymbolicRegressionSingleObjectiveEvaluator>)Parameters[EvaluatorParameterName]; }
        }
        public ILookupParameter<DataTable> VariableImpactsParameter
        {
            get { return (ILookupParameter<DataTable>)Parameters[VariableImpactsParameterName]; }
        }
        public IFixedValueParameter<PercentValue> PercentageBestParameter
        {
            get { return (IFixedValueParameter<PercentValue>)Parameters[PercentageBestParameterName]; }
        }
        public IFixedValueParameter<IntValue> LastGenerationsParameter
        {
            get { return (IFixedValueParameter<IntValue>)Parameters[LastGenerationsParameterName]; }
        }
        public IFixedValueParameter<BoolValue> OptimizedParameter
        {
            get { return (IFixedValueParameter<BoolValue>)Parameters[OptimizedConstantsParameterName]; }
        }
        private ILookupParameter<IntValue> MaximumGenerationsParameter
        {
            get { return (ILookupParameter<IntValue>)Parameters[MaximumGenerationsParameterName]; }
        }
        #endregion

        #region parameter properties
        public int UpdateCounter
        {
            get { return UpdateCounterParameter.Value.Value; }
            set { UpdateCounterParameter.Value.Value = value; }
        }
        public int UpdateInterval
        {
            get { return UpdateIntervalParameter.Value.Value; }
            set { UpdateIntervalParameter.Value.Value = value; }
        }
        #endregion

        public SymbolicRegressionVariableImpactsAnalyzer()
        {
            Parameters.Add(new ValueParameter<IntValue>(UpdateCounterParameterName, new IntValue(0)));
            Parameters.Add(new ValueParameter<IntValue>(UpdateIntervalParameterName, new IntValue(1)));
            Parameters.Add(new LookupParameter<IRegressionProblemData>(ProblemDataParameterName));
            Parameters.Add(new LookupParameter<ISymbolicDataAnalysisExpressionTreeInterpreter>(SymbolicDataAnalysisTreeInterpreterParameterName));
            Parameters.Add(new ScopeTreeLookupParameter<DoubleValue>(QualityParameterName, "The individual qualities."));
            Parameters.Add(new LookupParameter<BoolValue>(ApplyLinearScalingParameterName));
            Parameters.Add(new LookupParameter<DoubleLimit>(EstimationLimitsParameterName));
            Parameters.Add(new FixedValueParameter<IntValue>(MaxCOIterationsParameterName));         
            Parameters.Add(new LookupParameter<DataTable>(VariableImpactsParameterName, "The relative variable relevance calculated as the average relative variable frequency over the whole run."));
            Parameters.Add(new FixedValueParameter<PercentValue>(PercentageBestParameterName));
            Parameters.Add(new FixedValueParameter<IntValue>(LastGenerationsParameterName));
            Parameters.Add(new FixedValueParameter<BoolValue>(OptimizedConstantsParameterName));
            Parameters.Add(new LookupParameter<IntValue>(MaximumGenerationsParameterName, "The maximum number of generations which should be processed."));

            simplifier = new SymbolicDataAnalysisExpressionTreeSimplifier();
            impactsCalculator = new SymbolicRegressionSolutionImpactValuesCalculator();
        }

        [StorableConstructor]
        protected SymbolicRegressionVariableImpactsAnalyzer(bool deserializing) : base(deserializing) { }

        protected SymbolicRegressionVariableImpactsAnalyzer(SymbolicRegressionVariableImpactsAnalyzer original, Cloner cloner)
            : base(original, cloner)
        {
        }

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

        public override IOperation Apply()
        {
            #region Update counter & update interval
            UpdateCounter++;
            if (UpdateCounter != UpdateInterval)
            {
                return base.Apply();
            }
            UpdateCounter = 0;
            #endregion
            var results = ResultCollectionParameter.ActualValue;
            int maxGen = MaximumGenerationsParameter.ActualValue.Value;
            int gen = ((IntValue)results["Generations"].Value).Value;
            int lastGen = LastGenerationsParameter.Value.Value;

            if (lastGen > maxGen)
                lastGen = maxGen;
            if (maxGen - gen < lastGen)
                return base.Apply();

            var trees = SymbolicExpressionTree.ToArray();
            var qualities = QualityParameter.ActualValue.ToArray();

            Array.Sort(qualities, trees);
            Array.Reverse(qualities);
            Array.Reverse(trees);

            var interpreter = SymbolicDataAnalysisTreeInterpreterParameter.ActualValue;
            var problemData = ProblemDataParameter.ActualValue;
            var applyLinearScaling = ApplyLinearScalingParameter.ActualValue.Value;
            var maxCOIterations = MaxCOIterationsParameter.Value.Value; // fixed value parameter => Value
            var estimationLimits = EstimationLimitsParameter.ActualValue; // lookup parameter => ActualValue
            var percentageBest = PercentageBestParameter.Value.Value;
            var optimizedConstants = OptimizedParameter.Value.Value;

            var allowedInputVariables = problemData.AllowedInputVariables.ToList();
            var variableImpacts = allowedInputVariables.ToDictionary(x => x, x => 0.0);
            DataTable datatable;
            if (VariableImpactsParameter.ActualValue == null)
            {
                datatable = new DataTable("Variable impacts", "Average impact of variables over the population");
                datatable.VisualProperties.XAxisTitle = "Generation";
                datatable.VisualProperties.YAxisTitle = "Average variable impact";
                VariableImpactsParameter.ActualValue = datatable;
                results.Add(new Result("Average variable impacts", "The relative variable relevance calculated as the average relative variable frequency over the whole run.", new DataTable()));
                
                foreach (var v in allowedInputVariables)
                {
                    datatable.Rows.Add(new DataRow(v) { VisualProperties = { StartIndexZero = true } });
                }
                VariableImpactsParameter.ActualValue = datatable;
            }
            datatable = VariableImpactsParameter.ActualValue;
            int nTrees = (int)Math.Round(trees.Length * percentageBest);

            // simplify trees
            var simplifiedTrees = trees.Take(nTrees).Select(x => simplifier.Simplify(x));
            var variableCounts = problemData.AllowedInputVariables.ToDictionary(x => x, x => simplifiedTrees.Count(t => t.IterateNodesPrefix().Any(n => n is VariableTreeNode && ((VariableTreeNode)n).VariableName == x)));
            foreach (var simplifiedTree in simplifiedTrees)
            {
                if (optimizedConstants == true)
                {
                    SymbolicRegressionConstantOptimizationEvaluator.OptimizeConstants(interpreter, simplifiedTree, problemData, problemData.TrainingIndices, applyLinearScaling, maxCOIterations, estimationLimits.Upper, estimationLimits.Lower);
                }

                var quality = SymbolicRegressionSingleObjectivePearsonRSquaredEvaluator.Calculate(interpreter, simplifiedTree, estimationLimits.Lower, estimationLimits.Upper, problemData, problemData.TrainingIndices, applyLinearScaling);

                var model = new SymbolicRegressionModel(simplifiedTree, interpreter, estimationLimits.Lower, estimationLimits.Upper);
                var variables = simplifiedTree.IterateNodesPrefix().Where(x => x is VariableTreeNode).GroupBy(x => ((VariableTreeNode)x).VariableName);

                foreach (var g in variables)
                {
                    var avgImpact = g.Average(x => impactsCalculator.CalculateImpactValue(model, x, problemData, problemData.TrainingIndices, quality));
                    variableImpacts[g.Key] += avgImpact;
                }
            }

            foreach (var pair in variableImpacts)
            {
                datatable.Rows[pair.Key].Values.Add(pair.Value / variableCounts[pair.Key]);
            }
            results["Average variable impacts"].Value = datatable;
            return base.Apply();
        }
    }
}