#region License Information
/* HeuristicLab
 * Copyright (C) 2002-2019 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 HeuristicLab.Common;
using HeuristicLab.Core;
using HeuristicLab.Data;
using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
using HeuristicLab.Optimization;
using HeuristicLab.Parameters;
using HEAL.Attic;

namespace HeuristicLab.Problems.DataAnalysis.Symbolic.Regression {
  [Item("Constant Optimization Evaluator (new)", "Calculates Pearson R² of a symbolic regression solution and optimizes the constant used.")]
  [StorableType("1D5361E9-EF73-47D2-9211-FDD39BBC1018")]
  public class SymbolicRegressionNewConstantOptimizationEvaluator : SymbolicRegressionSingleObjectiveEvaluator {
    private const string ConstantOptimizationIterationsParameterName = "ConstantOptimizationIterations";
    private const string ConstantOptimizationImprovementParameterName = "ConstantOptimizationImprovement";
    private const string ConstantOptimizationProbabilityParameterName = "ConstantOptimizationProbability";
    private const string ConstantOptimizationRowsPercentageParameterName = "ConstantOptimizationRowsPercentage";
    private const string UpdateConstantsInTreeParameterName = "UpdateConstantsInSymbolicExpressionTree";
    private const string UpdateVariableWeightsParameterName = "Update Variable Weights";

    private const string FunctionEvaluationsResultParameterName = "Constants Optimization Function Evaluations";
    private const string GradientEvaluationsResultParameterName = "Constants Optimization Gradient Evaluations";
    private const string CountEvaluationsParameterName = "Count Function and Gradient Evaluations";

    public IFixedValueParameter<IntValue> ConstantOptimizationIterationsParameter {
      get { return (IFixedValueParameter<IntValue>)Parameters[ConstantOptimizationIterationsParameterName]; }
    }
    public IFixedValueParameter<DoubleValue> ConstantOptimizationImprovementParameter {
      get { return (IFixedValueParameter<DoubleValue>)Parameters[ConstantOptimizationImprovementParameterName]; }
    }
    public IFixedValueParameter<PercentValue> ConstantOptimizationProbabilityParameter {
      get { return (IFixedValueParameter<PercentValue>)Parameters[ConstantOptimizationProbabilityParameterName]; }
    }
    public IFixedValueParameter<PercentValue> ConstantOptimizationRowsPercentageParameter {
      get { return (IFixedValueParameter<PercentValue>)Parameters[ConstantOptimizationRowsPercentageParameterName]; }
    }
    public IFixedValueParameter<BoolValue> UpdateConstantsInTreeParameter {
      get { return (IFixedValueParameter<BoolValue>)Parameters[UpdateConstantsInTreeParameterName]; }
    }
    public IFixedValueParameter<BoolValue> UpdateVariableWeightsParameter {
      get { return (IFixedValueParameter<BoolValue>)Parameters[UpdateVariableWeightsParameterName]; }
    }

    public IResultParameter<IntValue> FunctionEvaluationsResultParameter {
      get { return (IResultParameter<IntValue>)Parameters[FunctionEvaluationsResultParameterName]; }
    }
    public IResultParameter<IntValue> GradientEvaluationsResultParameter {
      get { return (IResultParameter<IntValue>)Parameters[GradientEvaluationsResultParameterName]; }
    }
    public IFixedValueParameter<BoolValue> CountEvaluationsParameter {
      get { return (IFixedValueParameter<BoolValue>)Parameters[CountEvaluationsParameterName]; }
    }


    public IntValue ConstantOptimizationIterations {
      get { return ConstantOptimizationIterationsParameter.Value; }
    }
    public DoubleValue ConstantOptimizationImprovement {
      get { return ConstantOptimizationImprovementParameter.Value; }
    }
    public PercentValue ConstantOptimizationProbability {
      get { return ConstantOptimizationProbabilityParameter.Value; }
    }
    public PercentValue ConstantOptimizationRowsPercentage {
      get { return ConstantOptimizationRowsPercentageParameter.Value; }
    }
    public bool UpdateConstantsInTree {
      get { return UpdateConstantsInTreeParameter.Value.Value; }
      set { UpdateConstantsInTreeParameter.Value.Value = value; }
    }

    public bool UpdateVariableWeights {
      get { return UpdateVariableWeightsParameter.Value.Value; }
      set { UpdateVariableWeightsParameter.Value.Value = value; }
    }

    public bool CountEvaluations {
      get { return CountEvaluationsParameter.Value.Value; }
      set { CountEvaluationsParameter.Value.Value = value; }
    }

    public override bool Maximization {
      get { return true; }
    }

    [StorableConstructor]
    protected SymbolicRegressionNewConstantOptimizationEvaluator(StorableConstructorFlag _) : base(_) { }
    protected SymbolicRegressionNewConstantOptimizationEvaluator(SymbolicRegressionNewConstantOptimizationEvaluator original, Cloner cloner)
      : base(original, cloner) {
    }
    public SymbolicRegressionNewConstantOptimizationEvaluator()
      : base() {
      Parameters.Add(new FixedValueParameter<IntValue>(ConstantOptimizationIterationsParameterName, "Determines how many iterations should be calculated while optimizing the constant of a symbolic expression tree (0 indicates other or default stopping criterion).", new IntValue(10)));
      Parameters.Add(new FixedValueParameter<DoubleValue>(ConstantOptimizationImprovementParameterName, "Determines the relative improvement which must be achieved in the constant optimization to continue with it (0 indicates other or default stopping criterion).", new DoubleValue(0)) { Hidden = true });
      Parameters.Add(new FixedValueParameter<PercentValue>(ConstantOptimizationProbabilityParameterName, "Determines the probability that the constants are optimized", new PercentValue(1)));
      Parameters.Add(new FixedValueParameter<PercentValue>(ConstantOptimizationRowsPercentageParameterName, "Determines the percentage of the rows which should be used for constant optimization", new PercentValue(1)));
      Parameters.Add(new FixedValueParameter<BoolValue>(UpdateConstantsInTreeParameterName, "Determines if the constants in the tree should be overwritten by the optimized constants.", new BoolValue(true)) { Hidden = true });
      Parameters.Add(new FixedValueParameter<BoolValue>(UpdateVariableWeightsParameterName, "Determines if the variable weights in the tree should be  optimized.", new BoolValue(true)) { Hidden = true });

      Parameters.Add(new FixedValueParameter<BoolValue>(CountEvaluationsParameterName, "Determines if function and gradient evaluation should be counted.", new BoolValue(false)));
      Parameters.Add(new ResultParameter<IntValue>(FunctionEvaluationsResultParameterName, "The number of function evaluations performed by the constants optimization evaluator", "Results", new IntValue()));
      Parameters.Add(new ResultParameter<IntValue>(GradientEvaluationsResultParameterName, "The number of gradient evaluations performed by the constants optimization evaluator", "Results", new IntValue()));
    }

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

    [StorableHook(HookType.AfterDeserialization)]
    private void AfterDeserialization() { }

    private static readonly object locker = new object();

    public override IOperation InstrumentedApply() {
      var solution = SymbolicExpressionTreeParameter.ActualValue;
      double quality;
      if (RandomParameter.ActualValue.NextDouble() < ConstantOptimizationProbability.Value) {
        IEnumerable<int> constantOptimizationRows = GenerateRowsToEvaluate(ConstantOptimizationRowsPercentage.Value);
        var counter = new EvaluationsCounter();
        quality = OptimizeConstants(SymbolicDataAnalysisTreeInterpreterParameter.ActualValue, solution, ProblemDataParameter.ActualValue,
           constantOptimizationRows, ApplyLinearScalingParameter.ActualValue.Value, ConstantOptimizationIterations.Value, updateVariableWeights: UpdateVariableWeights, lowerEstimationLimit: EstimationLimitsParameter.ActualValue.Lower, upperEstimationLimit: EstimationLimitsParameter.ActualValue.Upper, updateConstantsInTree: UpdateConstantsInTree, counter: counter);

        if (ConstantOptimizationRowsPercentage.Value != RelativeNumberOfEvaluatedSamplesParameter.ActualValue.Value) {
          var evaluationRows = GenerateRowsToEvaluate();
          quality = SymbolicRegressionSingleObjectivePearsonRSquaredEvaluator.Calculate(SymbolicDataAnalysisTreeInterpreterParameter.ActualValue, solution, EstimationLimitsParameter.ActualValue.Lower, EstimationLimitsParameter.ActualValue.Upper, ProblemDataParameter.ActualValue, evaluationRows, ApplyLinearScalingParameter.ActualValue.Value);
        }

        if (CountEvaluations) {
          lock (locker) {
            FunctionEvaluationsResultParameter.ActualValue.Value += counter.FunctionEvaluations;
            GradientEvaluationsResultParameter.ActualValue.Value += counter.GradientEvaluations;
          }
        }

      } else {
        var evaluationRows = GenerateRowsToEvaluate();
        quality = SymbolicRegressionSingleObjectivePearsonRSquaredEvaluator.Calculate(SymbolicDataAnalysisTreeInterpreterParameter.ActualValue, solution, EstimationLimitsParameter.ActualValue.Lower, EstimationLimitsParameter.ActualValue.Upper, ProblemDataParameter.ActualValue, evaluationRows, ApplyLinearScalingParameter.ActualValue.Value);
      }
      QualityParameter.ActualValue = new DoubleValue(quality);

      return base.InstrumentedApply();
    }

    public override double Evaluate(IExecutionContext context, ISymbolicExpressionTree tree, IRegressionProblemData problemData, IEnumerable<int> rows) {
      SymbolicDataAnalysisTreeInterpreterParameter.ExecutionContext = context;
      EstimationLimitsParameter.ExecutionContext = context;
      ApplyLinearScalingParameter.ExecutionContext = context;
      FunctionEvaluationsResultParameter.ExecutionContext = context;
      GradientEvaluationsResultParameter.ExecutionContext = context;

      // Pearson R² evaluator is used on purpose instead of the const-opt evaluator, 
      // because Evaluate() is used to get the quality of evolved models on 
      // different partitions of the dataset (e.g., best validation model)
      double r2 = SymbolicRegressionSingleObjectivePearsonRSquaredEvaluator.Calculate(SymbolicDataAnalysisTreeInterpreterParameter.ActualValue, tree, EstimationLimitsParameter.ActualValue.Lower, EstimationLimitsParameter.ActualValue.Upper, problemData, rows, ApplyLinearScalingParameter.ActualValue.Value);

      SymbolicDataAnalysisTreeInterpreterParameter.ExecutionContext = null;
      EstimationLimitsParameter.ExecutionContext = null;
      ApplyLinearScalingParameter.ExecutionContext = null;
      FunctionEvaluationsResultParameter.ExecutionContext = null;
      GradientEvaluationsResultParameter.ExecutionContext = null;

      return r2;
    }

    public class EvaluationsCounter {
      public int FunctionEvaluations = 0;
      public int GradientEvaluations = 0;
    }

    private static void GetParameterNodes(ISymbolicExpressionTree tree, out List<ISymbolicExpressionTreeNode> thetaNodes, out List<double> thetaValues) {
      thetaNodes = new List<ISymbolicExpressionTreeNode>();
      thetaValues = new List<double>();

      var nodes = tree.IterateNodesPrefix().ToArray();
      for (int i = 0; i < nodes.Length; ++i) {
        var node = nodes[i];
        if (node is VariableTreeNode variableTreeNode) {
          thetaValues.Add(variableTreeNode.Weight);
          thetaNodes.Add(node);
        } else if (node is ConstantTreeNode constantTreeNode) {
          thetaNodes.Add(node);
          thetaValues.Add(constantTreeNode.Value);
        }
      }
    }

    public static double OptimizeConstants(ISymbolicDataAnalysisExpressionTreeInterpreter interpreter,
      ISymbolicExpressionTree tree, IRegressionProblemData problemData, IEnumerable<int> rows, bool applyLinearScaling,
      int maxIterations, bool updateVariableWeights = true,
      double lowerEstimationLimit = double.MinValue, double upperEstimationLimit = double.MaxValue,
      bool updateConstantsInTree = true, Action<double[], double, object> iterationCallback = null, EvaluationsCounter counter = null) {

      if (!updateVariableWeights) throw new NotSupportedException();

      // // numeric constants in the tree become variables for constant opt
      // // variables in the tree become parameters (fixed values) for constant opt
      // // for each parameter (variable in the original tree) we store the 
      // // variable name, variable value (for factor vars) and lag as a DataForVariable object.
      // // A dictionary is used to find parameters
      // double[] initialConstants;
      // var parameters = new List<TreeToAutoDiffTermConverter.DataForVariable>();
      // 
      // TreeToAutoDiffTermConverter.ParametricFunction func;
      // TreeToAutoDiffTermConverter.ParametricFunctionGradient func_grad;
      // if (!TreeToAutoDiffTermConverter.TryConvertToAutoDiff(tree, updateVariableWeights, applyLinearScaling, out parameters, out initialConstants, out func, out func_grad))
      //   throw new NotSupportedException("Could not optimize constants of symbolic expression tree due to not supported symbols used in the tree.");
      // if (parameters.Count == 0) return 0.0; // gkronber: constant expressions always have a R² of 0.0 
      // var parameterEntries = parameters.ToArray(); // order of entries must be the same for x


      GetParameterNodes(tree, out List<ISymbolicExpressionTreeNode> thetaNodes, out List<double> thetaValues);
      var initialConstants = thetaValues.ToArray();

      //extract inital constants
      double[] c;
      if (applyLinearScaling) {
        c = new double[initialConstants.Length + 2];
        c[0] = 0.0;
        c[1] = 1.0;
        Array.Copy(initialConstants, 0, c, 2, initialConstants.Length);
      } else {
        c = (double[])initialConstants.Clone();
      }

      double originalQuality = SymbolicRegressionSingleObjectivePearsonRSquaredEvaluator.Calculate(interpreter, tree, lowerEstimationLimit, upperEstimationLimit, problemData, rows, applyLinearScaling);

      if (counter == null) counter = new EvaluationsCounter();
      var rowEvaluationsCounter = new EvaluationsCounter();

      alglib.minlmstate state;
      alglib.minlmreport rep;

      IDataset ds = problemData.Dataset;
      double[] y = ds.GetDoubleValues(problemData.TargetVariable, rows).ToArray();
      int n = y.Length;
      int k = c.Length;

      var trainRows = problemData.TrainingIndices.ToArray();
      var parameterNodes = thetaNodes.ToArray();
      alglib.ndimensional_fvec function_cx_1_func = CreateFunc(tree, new VectorEvaluator(), parameterNodes, ds, problemData.TargetVariable, trainRows);
      alglib.ndimensional_jac function_cx_1_jac = CreateJac(tree, new VectorAutoDiffEvaluator(), parameterNodes, ds, problemData.TargetVariable, trainRows);
      alglib.ndimensional_rep xrep = (p, f, obj) => iterationCallback(p, f, obj);

      try {
        alglib.minlmcreatevj(n, c, out state);
        alglib.minlmsetcond(state, 0.0, maxIterations);
        alglib.minlmsetxrep(state, iterationCallback != null);
        // alglib.minlmsetgradientcheck(state, 0.001);
        alglib.minlmoptimize(state, function_cx_1_func, function_cx_1_jac, xrep, rowEvaluationsCounter);
        alglib.minlmresults(state, out c, out rep);
      } catch (ArithmeticException) {
        return originalQuality;
      } catch (alglib.alglibexception) {
        return originalQuality;
      }

      counter.FunctionEvaluations += rowEvaluationsCounter.FunctionEvaluations / n;
      counter.GradientEvaluations += rowEvaluationsCounter.GradientEvaluations / n;

      //retVal == -7  => constant optimization failed due to wrong gradient
      if (rep.terminationtype != -7) {
        if (applyLinearScaling) {
          var tmp = new double[c.Length - 2];
          Array.Copy(c, 2, tmp, 0, tmp.Length);
          UpdateConstants(parameterNodes, tmp);
        } else UpdateConstants(parameterNodes, c);
      }
      var quality = SymbolicRegressionSingleObjectivePearsonRSquaredEvaluator.Calculate(interpreter, tree, lowerEstimationLimit, upperEstimationLimit, problemData, rows, applyLinearScaling);

      if (!updateConstantsInTree) UpdateConstants(parameterNodes, initialConstants);

      if (originalQuality - quality > 0.001 || double.IsNaN(quality)) {
        UpdateConstants(parameterNodes, initialConstants);
        return originalQuality;
      }
      return quality;
    }

    private static void UpdateConstants(ISymbolicExpressionTreeNode[] nodes, double[] constants) {
      if (nodes.Length != constants.Length) throw new InvalidOperationException();
      for(int i = 0;i<nodes.Length;i++) {
        if (nodes[i] is VariableTreeNode varNode) varNode.Weight = constants[i];
        else if (nodes[i] is ConstantTreeNode constNode) constNode.Value = constants[i];
      }
    }

    private static alglib.ndimensional_fvec CreateFunc(ISymbolicExpressionTree tree, VectorEvaluator eval, ISymbolicExpressionTreeNode[] parameterNodes, IDataset ds, string targetVar, int[] rows) {
      var y = ds.GetDoubleValues(targetVar, rows).ToArray();
      return (double[] c, double[] fi, object o) => {
        UpdateConstants(parameterNodes, c);
        var pred = eval.Evaluate(tree, ds, rows);
        for (int i = 0; i < fi.Length; i++)
          fi[i] = pred[i] - y[i];

        var counter = (EvaluationsCounter)o;
        counter.FunctionEvaluations++;
      };
    }

    private static alglib.ndimensional_jac CreateJac(ISymbolicExpressionTree tree, VectorAutoDiffEvaluator eval, ISymbolicExpressionTreeNode[] parameterNodes, IDataset ds, string targetVar, int[] rows) {
      var y = ds.GetDoubleValues(targetVar, rows).ToArray();
      return (double[] c, double[] fi, double[,] jac, object o) => {
        UpdateConstants(parameterNodes, c);
        eval.Evaluate(tree, ds, rows, parameterNodes, fi, jac);

        for (int i = 0; i < fi.Length; i++)
          fi[i] -= y[i];

        var counter = (EvaluationsCounter)o;
        counter.GradientEvaluations++;
      };
    }
    public static bool CanOptimizeConstants(ISymbolicExpressionTree tree) {
      return TreeToAutoDiffTermConverter.IsCompatible(tree);
    }
  }
}