Example #1
0
    /// <summary>
    /// Create and return a NeatEvolutionAlgorithm object ready for running the NEAT algorithm/search. Various sub-parts
    /// of the algorithm are also constructed and connected up.
    /// This overload accepts a pre-built genome population and their associated/parent genome factory.
    /// </summary>
    public NeatEvolutionAlgorithm <NeatGenome> CreateEvolutionAlgorithm(IGenomeFactory <NeatGenome> genomeFactory, List <NeatGenome> genomeList)
    {
        // Create distance metric. Mismatched genes have a fixed distance of 10; for matched genes the distance is their weigth difference.
        IDistanceMetric distanceMetric = new ManhattanDistanceMetric(1.0, 0.0, 10.0);
        ISpeciationStrategy <NeatGenome> speciationStrategy = new KMeansClusteringStrategy <NeatGenome>(distanceMetric);

        // Create complexity regulation strategy.
        IComplexityRegulationStrategy complexityRegulationStrategy = ExperimentUtils.CreateComplexityRegulationStrategy(_complexityRegulationStr, _complexityThreshold);

        // Create the evolution algorithm.
        NeatEvolutionAlgorithm <NeatGenome> ea = new NeatEvolutionAlgorithm <NeatGenome>(_eaParams, speciationStrategy, complexityRegulationStrategy);

        // Create IBlackBox evaluator.
        TestEvaluator evaluator = new TestEvaluator();

        // Create genome decoder.
        IGenomeDecoder <NeatGenome, IBlackBox> genomeDecoder = CreateGenomeDecoder();

        // Create a genome list evaluator. This packages up the genome decoder with the genome evaluator.
        IGenomeListEvaluator <NeatGenome> innerEvaluator = new SerialGenomeListEvaluator <NeatGenome, IBlackBox>(genomeDecoder, evaluator);

        // Wrap the list evaluator in a 'selective' evaulator that will only evaluate new genomes. That is, we skip re-evaluating any genomes
        // that were in the population in previous generations (elite genomes). This is determiend by examining each genome's evaluation info object.
        IGenomeListEvaluator <NeatGenome> selectiveEvaluator = new SelectiveGenomeListEvaluator <NeatGenome>(
            innerEvaluator,
            SelectiveGenomeListEvaluator <NeatGenome> .CreatePredicate_OnceOnly());

        // Initialize the evolution algorithm.
        ea.Initialize(selectiveEvaluator, genomeFactory, genomeList);

        // Finished. Return the evolution algorithm
        return(ea);
    }
Example #2
0
    private void evaluateChromosome(int index, TestEvaluator evaluator)
    {
        Chromosome chromosome = population.getChromosomes()[index];

        evaluator.startEvaluation(chromosome.getWeights(), index);
        ++chromosomesInEvaluation;
    }
Example #3
0
    void Start()
    {
        TestEvaluator simulator = Instantiate(simulatorPrefab);

        simulator.evolutionator = this;
        simulators.Add(simulator);

        population = new Population(null, CreateNeuralNet(simulators[0]), populationSize, .03, .5, .7);
        runEvaluation();
    }
Example #4
0
        private string BuildHeader(Subject subject)
        {
            TestEvaluator evaluation = new TestEvaluator();
            string        header     = $"<head><meta charset='UTF8'> " +
                                       "<style>table{font-family: arial, sans-serif;border-collapse: collapse;width:100%;}td,th{border: 1px solid #dddddd;text-align: left;padding: 8px;}tr:nth-child(even){background-color: #dddddd;}</style></head>" +
                                       "<h1 style=text-align:center;background-color:lightblue;font-size:xx-large;>Teszt eredmények</h1>" +
                                       "<p>tesztvezető neve:</p>" +
                                       $"<p>tesztalany neve: {subject.Nickname}</p>" +
                                       $"<p><b>életkor: {subject.Age}</b></p>" +
                                       $"<p><b>nem: {subject.Gender.ToString()}</b></p>" +
                                       $"<p><b>kitöltés időpontja: {subject.SessionStartDate.ToString("yyyy.MM.dd HH:mm:ss")}</b></p>" +
                                       $"<p><i>eredmény: {evaluation.Evaluate(subject).ToString()}</i><p >" +
                                       "<hr>";

            return(header);
        }
Example #5
0
        public void Test1()
        {
            TestEvaluator evaluator = new TestEvaluator();

            var expression = BindingExpression.ParseExpression("{eval path=Name}");

            Assert.AreEqual(expression.Name, "eval", "测试解析绑定表达式失败");

            object value;

            Assert.IsTrue(expression.TryGetValue(evaluator, "path", out value), "测试解析绑定表达式失败");
            Assert.AreEqual(value, "Name", "测试解析绑定表达式失败");


            expression = BindingExpression.ParseExpression("{eval path=Name , key==@#$}");
            Assert.AreEqual(expression.Name, "eval", "测试解析绑定表达式失败");
            Assert.IsTrue(expression.TryGetValue(evaluator, "path", out value), "测试解析绑定表达式失败");
            Assert.AreEqual(value, "Name ", "测试解析绑定表达式失败");
            Assert.IsTrue(expression.TryGetValue(evaluator, "key", out value), "测试解析绑定表达式失败");
            Assert.AreEqual(value, "=@#$", "测试解析绑定表达式失败");

            expression = BindingExpression.ParseExpression("{eval path={{abc,,}},key=abc}");
            Assert.AreEqual(expression.Name, "eval", "测试解析绑定表达式失败");
            Assert.IsTrue(expression.TryGetValue(evaluator, "path", out value), "测试解析绑定表达式失败");
            Assert.AreEqual(value, "{abc,}", "测试解析绑定表达式失败");
            Assert.IsTrue(expression.TryGetValue(evaluator, "key", out value), "测试解析绑定表达式失败");
            Assert.AreEqual(value, "abc", "测试解析绑定表达式失败");

            expression = BindingExpression.ParseExpression("{eval path={},,key=abc}");
            Assert.IsNull(expression, "错误的解析了错误的表达式");

            expression = BindingExpression.ParseExpression("{eval path={eval a=b, c=d},key=abc}");
            Assert.AreEqual(expression.Name, "eval", "测试解析绑定表达式失败");
            Assert.IsTrue(expression.TryGetValue(evaluator, "path", out value), "测试解析绑定表达式失败");
            Assert.AreEqual(value, "a:b,c:d", "测试解析绑定表达式失败");
            Assert.IsTrue(expression.TryGetValue(evaluator, "key", out value), "测试解析绑定表达式失败");
            Assert.AreEqual(value, "abc", "测试解析绑定表达式失败");


            expression = BindingExpression.ParseExpression("{eval a, b=}");
            Assert.AreEqual(expression.Name, "eval", "测试解析绑定表达式失败");
            Assert.IsTrue(expression.TryGetValue(evaluator, "a", out value), "测试解析绑定表达式失败");
            Assert.IsNull(value, "测试解析绑定表达式失败");
            Assert.IsTrue(expression.TryGetValue(evaluator, "b", out value), "测试解析绑定表达式失败");
            Assert.AreEqual(value, "", "测试解析绑定表达式失败");
        }
Example #6
0
        public void Test_SynchronizerConstruct_Steps()
        {
            Model model = new Model("SFC Test 1");
            ProcedureFunctionChart pfc = new ProcedureFunctionChart(model, "SFC 1", "", Guid.NewGuid());

            IPfcStepNode t0 = pfc.CreateStep("S_Alice", "", Guid.Empty);
            IPfcStepNode t1 = pfc.CreateStep("S_Bob", "", Guid.Empty);
            IPfcStepNode t2 = pfc.CreateStep("S_Charley", "", Guid.Empty);
            IPfcStepNode t3 = pfc.CreateStep("S_David", "", Guid.Empty);
            IPfcStepNode t4 = pfc.CreateStep("S_Edna", "", Guid.Empty);
            IPfcStepNode t5 = pfc.CreateStep("S_Frank", "", Guid.Empty);
            IPfcStepNode t6 = pfc.CreateStep("S_Gary", "", Guid.Empty);
            IPfcStepNode t7 = pfc.CreateStep("S_Hailey", "", Guid.Empty);

            pfc.Synchronize(new IPfcStepNode[] { t0, t1, t2, t3 }, new IPfcStepNode[] { t4, t5, t6, t7 });

            string structureString = PfcDiagnostics.GetStructure(pfc);

            structureString = structureString.Replace("SFC 1.Root", "SFC 1.Root");
            string shouldBe = "{S_Alice-->[L_000(SFC 1.Root)]-->T_000}\r\n{S_Bob-->[L_001(SFC 1.Root)]-->T_000}\r\n{S_Charley-->[L_002(SFC 1.Root)]-->T_000}\r\n{S_David-->[L_003(SFC 1.Root)]-->T_000}\r\n{T_000-->[L_004(SFC 1.Root)]-->S_Edna}\r\n{T_000-->[L_005(SFC 1.Root)]-->S_Frank}\r\n{T_000-->[L_006(SFC 1.Root)]-->S_Gary}\r\n{T_000-->[L_007(SFC 1.Root)]-->S_Hailey}\r\n";

            Console.WriteLine("After a synchronization of steps, structure is \r\n" + structureString);
            Assert.AreEqual(structureString, shouldBe, "Structure should have been\r\n" + shouldBe + "\r\nbut it was\r\n" + structureString + "\r\ninstead.");

            if (m_runSFCs)
            {
                TestEvaluator testEvaluator = new TestEvaluator(new IPfcStepNode[] { t0, t1, t2, t3, t4, t5, t6, t7 });
                pfc.Synchronize(new IPfcStepNode[] { t0, t1, t2, t3 }, new IPfcStepNode[] { t4, t5, t6, t7 });

                testEvaluator.NextExpectedActivations = new IPfcStepNode[] { t0, t1, t2, t3, t4, t5, t6, t7 };

                foreach (IPfcNode ilinkable in new IPfcStepNode[] { t0, t1, t2, t3 })
                {
                    Console.WriteLine("Incrementing " + ilinkable.Name + ".");
                    //ilinkable.Increment();
                    throw new ApplicationException("PFCs are not currently executable.");
                }

                testEvaluator.NextExpectedActivations = new IPfcTransitionNode[] { }; // Ensure it's empty and all have fired.
            }
        }
Example #7
0
    public void reportFitness(TestEvaluator evaluator, double fitness, int index)
    {
        totalFitness += fitness;
        --chromosomesInEvaluation;
        Chromosome chromosome = population.getChromosomes()[index];

        chromosome.setFitness(fitness);

        print("current index: " + currentChromosomeIndex);
        if (currentChromosomeIndex < populationSize - 1)
        {
            if (currentChromosomeIndex + chromosomesInEvaluation < populationSize - 1)
            {
                evaluateChromosome(currentChromosomeIndex + chromosomesInEvaluation + 1, evaluator);
            }
            ++currentChromosomeIndex;
        }
        else
        {
            print("restart generation");
            startNextGeneration();
        }
    }
Example #8
0
 public static NeuralNet CreateNeuralNet(TestEvaluator evaluator)
 {
     return(new NeuralNet(NeuronMode.NEURON, true, 2, evaluator.getOutputsRequired(), 7, 2));
 }
    /// <summary>
    /// Create and return a NeatEvolutionAlgorithm object ready for running the NEAT algorithm/search. Various sub-parts
    /// of the algorithm are also constructed and connected up.
    /// This overload accepts a pre-built genome population and their associated/parent genome factory.
    /// </summary>
    public NeatEvolutionAlgorithm<NeatGenome> CreateEvolutionAlgorithm(IGenomeFactory<NeatGenome> genomeFactory, List<NeatGenome> genomeList)
    {
        // Create distance metric. Mismatched genes have a fixed distance of 10; for matched genes the distance is their weigth difference.
            IDistanceMetric distanceMetric = new ManhattanDistanceMetric(1.0, 0.0, 10.0);
            ISpeciationStrategy<NeatGenome> speciationStrategy = new KMeansClusteringStrategy<NeatGenome>(distanceMetric);

            // Create complexity regulation strategy.
            IComplexityRegulationStrategy complexityRegulationStrategy = ExperimentUtils.CreateComplexityRegulationStrategy(_complexityRegulationStr, _complexityThreshold);

            // Create the evolution algorithm.
            NeatEvolutionAlgorithm<NeatGenome> ea = new NeatEvolutionAlgorithm<NeatGenome>(_eaParams, speciationStrategy, complexityRegulationStrategy);

            // Create IBlackBox evaluator.
            TestEvaluator evaluator = new TestEvaluator();

            // Create genome decoder.
            IGenomeDecoder<NeatGenome, IBlackBox> genomeDecoder = CreateGenomeDecoder();

            // Create a genome list evaluator. This packages up the genome decoder with the genome evaluator.
            IGenomeListEvaluator<NeatGenome> innerEvaluator = new SerialGenomeListEvaluator<NeatGenome, IBlackBox>(genomeDecoder, evaluator);

            // Wrap the list evaluator in a 'selective' evaulator that will only evaluate new genomes. That is, we skip re-evaluating any genomes
            // that were in the population in previous generations (elite genomes). This is determiend by examining each genome's evaluation info object.
            IGenomeListEvaluator<NeatGenome> selectiveEvaluator = new SelectiveGenomeListEvaluator<NeatGenome>(
                                                                                    innerEvaluator,
                                                                                    SelectiveGenomeListEvaluator<NeatGenome>.CreatePredicate_OnceOnly());
            // Initialize the evolution algorithm.
            ea.Initialize(selectiveEvaluator, genomeFactory, genomeList);

            // Finished. Return the evolution algorithm
            return ea;
    }