private double CalculateClassificationError(BasicNeuralDataSet trainingSet)
{
int errorCount = 0;
foreach (var trainData in trainingSet)
{
IMLData output = _network.Compute(trainData.Input);
IMLData ideal = trainData.Ideal;
double maxValue = Double.MinValue;
int maxIndex = 0;
for (int i = 0; i < output.Count; ++i)
{
if (maxValue < output[i])
{
maxValue = output[i];
maxIndex = i;
}
}
if (Math.Abs(ideal[maxIndex] - 1) > 0.0001)
{
errorCount++;
}
}
return((double)errorCount / trainingSet.Count);
}
public void Predict(BasicNetwork network)
{
Console.WriteLine(@"Year Actual Predict Closed Loop Predict Denormalized Value Real Value");
for (var year = EvaluateStart; year < EvaluateEnd; year++)
{
// calculate based on actual data
var input = new BasicMLData(WindowSize);
for (var i = 0; i < input.Count; i++)
{
input[i] = _normalizedForexPair[(year - WindowSize) + i];
}
IMLData output = network.Compute(input);
var prediction = output[0];
_closedLoopForexPair[year] = prediction;
// calculate "closed loop", based on predicted data
for (var i = 0; i < input.Count; i++)
{
input[i] = _closedLoopForexPair[(year - WindowSize) + i];
}
output = network.Compute(input);
var closedLoopPrediction = output[0];
// display
Console.WriteLine("{0} {1} {2} {3} Accuracy:{4} Denormalized:{5} Real value:{6}",
(StartingYear + year),
Format.FormatDouble(_normalizedForexPair[year], 5),
Format.FormatDouble(prediction, 5),
Format.FormatDouble(closedLoopPrediction, 5),
Format.FormatDouble(_normalizedForexPair[year] - prediction, 5),
array.Stats.DeNormalize(prediction),
ForexPair[year]);
}
}
private static void ZrobKlasyfikacje()
{
DaneKlasyfikacja doNauki = new DaneKlasyfikacja();
doNauki.Wczytaj(sciezkaKlasyfikacjaTreningowe);
BasicNetwork siec = UtworzSiecDoKlasyfikacji();
IMLDataSet dataTrening = UczSiec(siec, doNauki);
// testuje siec na danych treningowych
for (int i = 0; i < dataTrening.Count; i++)
{
IMLData wynik = siec.Compute(dataTrening[i].Input);
doNauki.klasyWy.Add(wynik[0]);
}
doNauki.EksportujDoPliku(sciezkaKlasyfikacjaTreningoweWyniki);
// testuje siec na danych testowych
DaneKlasyfikacja doTestow = new DaneKlasyfikacja();
doTestow.Wczytaj(sciezkaKlasyfikacjaTestowe);
IMLDataSet dataTest = new BasicMLDataSet(doTestow.punkty.ToArray(), doTestow.klasyWej.ToArray());
for (int i = 0; i < dataTest.Count; i++)
{
IMLData wynik = siec.Compute(dataTest[i].Input);
doTestow.klasyWy.Add(wynik[0]);
}
doTestow.EksportujDoPliku(sciezkaKlasyfikacjaTestoweWyniki);
}
private static void ZrobRegresje()
{
DaneRegresja doNauki = new DaneRegresja();
doNauki.Wczytaj(sciezkaRegresjaTreningowe);
BasicNetwork siec = UtworzSiecDoRegresji();
IMLDataSet dataTrening = UczSiec(siec, doNauki);
// testuje siec na danych treningowych
for (int i = 0; i < dataTrening.Count; i++)
{
IMLData wynik = siec.Compute(dataTrening[i].Input);
doNauki.otrzymaneY.Add(wynik[0]);
}
doNauki.EksportujDoPliku(sciezkaRegresjaTreningoweWyniki);
// testuje siec na danych testowych
DaneRegresja doTestow = new DaneRegresja();
doTestow.Wczytaj(sciezkaRegresjaTestowe);
IMLDataSet dataTest = new BasicMLDataSet(doTestow.wejscioweX.ToArray(), doTestow.oczekiwaneY.ToArray());
for (int i = 0; i < dataTest.Count; i++)
{
IMLData wynik = siec.Compute(dataTest[i].Input);
doTestow.otrzymaneY.Add(wynik[0]);
}
doTestow.EksportujDoPliku(sciezkaRegresjaTestoweWyniki);
}
public void Predict(BasicNetwork network)
{
Console.WriteLine(@"Year Actual Predict Closed Loop Predict");
for (int year = EvaluateStart; year < EvaluateEnd; year++)
{
// calculate based on actual data
var input = new BasicMLData(WindowSize);
for (var i = 0; i < input.Count; i++)
{
input[i] = _normalizedSunspots[(year - WindowSize) + i];
}
IMLData output = network.Compute(input);
double prediction = output[0];
_closedLoopSunspots[year] = prediction;
// calculate "closed loop", based on predicted data
for (var i = 0; i < input.Count; i++)
{
input[i] = _closedLoopSunspots[(year - WindowSize) + i];
}
output = network.Compute(input);
double closedLoopPrediction = output[0];
// display
Console.WriteLine((StartingYear + year)
+ @" " + Format.FormatDouble(_normalizedSunspots[year], 2)
+ @" " + Format.FormatDouble(prediction, 2)
+ @" " + Format.FormatDouble(closedLoopPrediction, 2));
}
}
public void Predict(BasicNetwork network)
{
Console.WriteLine(@"Year Actual Predict Closed Loop Predict Denormalized Value Real Value");
for (int year = EvaluateStart; year < EvaluateEnd; year++)
{
// calculate based on actual data
IMLData input = new BasicMLData(WindowSize);
for (var i = 0; i < input.Count; i++)
{
input.Data[i] = _normalizedSunspots[(year - WindowSize) + i];
}
IMLData output = network.Compute(input);
double prediction = output.Data[0];
_closedLoopSunspots[year] = prediction;
// calculate "closed loop", based on predicted data
for (var i = 0; i < input.Count; i++)
{
input.Data[i] = _closedLoopSunspots[(year - WindowSize) + i];
}
output = network.Compute(input);
double closedLoopPrediction = output.Data[0];
// display
Console.WriteLine((StartingYear + year)
+ @" " + Format.FormatDouble(_normalizedSunspots[year], 5)
+ @" " + Format.FormatDouble(prediction, 5)
+ @" " + Format.FormatDouble(closedLoopPrediction, 5)
+ @" Accuracy:" +
Format.FormatDouble(_normalizedSunspots[year] - prediction, 5)
+ " Denormalized:" + array.Stats.DeNormalize(prediction)
+ " Real value:" + Sunspots[year]);
}
}
/// <summary>
/// Returns the prediction of the network for a given input.
/// </summary>
/// <param name="dataSource"></param>
/// <returns></returns>
public double[] getNetworkPrediction(NNDataSource dataSource)
{
double[] networkOutputs = new double[OUTPUT_NEURONS];
double[] networkInputs = new double[INPUT_NEURONS];
dataSource.returnInput(ref networkInputs);
network.Compute(networkInputs, networkOutputs);
if (networkOutputs.Length != OUTPUT_NEURONS)
throw new Exception("Unexpected number of network ouputs.");
return networkOutputs;
}
/// <summary>
/// Program entry point.
/// </summary>
/// <param name="app">Holds arguments and other info.</param>
public void Execute(IExampleInterface app)
{
// create a neural network, without using a factory
var network = new BasicNetwork();
network.AddLayer(new BasicLayer(null, true, 2));
network.AddLayer(new BasicLayer(new ActivationSigmoid(), true, 3));
network.AddLayer(new BasicLayer(new ActivationSigmoid(), false, 1));
network.Structure.FinalizeStructure();
network.Reset();
// create training data
IMLDataSet trainingSet = new BasicMLDataSet(XORInput, XORIdeal);
// train the neural network
IMLTrain train = new ResilientPropagation(network, trainingSet);
int epoch = 1;
do
{
train.Iteration();
Console.WriteLine(@"Epoch #" + epoch + @" Error:" + train.Error);
epoch++;
} while (train.Error > 0.01);
// test the neural network
Console.WriteLine(@"Neural Network Results:");
foreach (IMLDataPair pair in trainingSet)
{
IMLData output = network.Compute(pair.Input);
Console.WriteLine(pair.Input[0] + @"," + pair.Input[1]
+ @", actual=" + output[0] + @",ideal=" + pair.Ideal[0]);
}
}
/// <summary>
/// Process one training set element.
/// </summary>
/// <param name="errorCalc">The error calculation to use.</param>
/// <param name="input">The network input.</param>
/// <param name="ideal">The ideal values.</param>
public void Process(IErrorCalculation errorCalc, double[] input, double[] ideal)
{
_network.Compute(input, _actual);
errorCalc.UpdateError(_actual, ideal, 1.0);
// Calculate error for the output layer.
var outputLayerIndex = _network.Layers.Count - 1;
var outputActivation = _network.Layers[outputLayerIndex].Activation;
errorFunction.CalculateError(
outputActivation, _layerSums, _layerOutput,
ideal, _actual, _layerDelta, 0, 1.0);
// Apply regularization, if requested.
if (_owner.L1 > AIFH.DefaultPrecision ||
_owner.L1 > AIFH.DefaultPrecision)
{
var lp = new double[2];
CalculateRegularizationPenalty(lp);
for (var i = 0; i < _actual.Length; i++)
{
var p = lp[0] * _owner.L1 + lp[1] * _owner.L2;
_layerDelta[i] += p;
}
}
// Propagate backwards (chain rule from calculus).
for (var i = _network.Layers.Count - 1; i > 0; i--)
{
var layer = _network.Layers[i];
layer.ComputeGradient(this);
}
}
static void Main(string[] args)
{
INeuralDataSet trainingSet = new BasicNeuralDataSet(AndInput, AndIdeal);
var network = new BasicNetwork();
network.AddLayer(new BasicLayer(new ActivationSigmoid(), true, 2));
network.AddLayer(new BasicLayer(new ActivationSigmoid(), true, 2));
network.AddLayer(new BasicLayer(new ActivationSigmoid(), true, 1));
network.Structure.FinalizeStructure();
network.Reset();
ITrain train = new ResilientPropagation(network, trainingSet);
int epoch = 1;
do
{
train.Iteration();
Console.WriteLine($"Epoch no {epoch}. Error: {train.Error}");
epoch++;
} while ((epoch < MaxEpoch) && (train.Error > AcceptableError));
Console.WriteLine("\nAnd function Results:");
foreach (IMLDataPair pair in trainingSet)
{
IMLData output = network.Compute(pair.Input);
Console.WriteLine($"{pair.Input[0]} AND {pair.Input[1]} should be: {pair.Ideal[0]} actual value is: {output[0]}");
}
Console.ReadKey();
}
static void Main(string[] args)
{
var network = new BasicNetwork();
network.AddLayer(new BasicLayer(null, true, 4));
network.AddLayer(new BasicLayer(new ActivationSigmoid(), true, 4));
network.AddLayer(new BasicLayer(new ActivationSigmoid(), true, 5));
network.Structure.FinalizeStructure();
network.Reset();
IMLDataSet trainingSet = new BasicMLDataSet(SensoriInput, AttuatoriOutput);
IMLTrain train = new ResilientPropagation(network, trainingSet);
int epoch = 1;
do
{
/* Avvia la redistribuzione dei pesi */
train.Iteration();
Console.WriteLine(@"Epoch #" + epoch + @" Error:" + train.Error);
epoch++;
} while (train.Error > 0.001); /* Itera finche' non viene raggiunto un errore tollerabile */
/* Test la MLP */
Console.WriteLine("\r\n+------------------------------------+");
Console.WriteLine("|Neural Network Results: |");
Console.WriteLine("+------------------------------------+");
foreach (IMLDataPair pair in trainingSet)
{
IMLData output = network.Compute(pair.Input);
Console.WriteLine("Input:" + pair.Input[0] + " - " + pair.Input[1] + " - " + pair.Input[2] + " - " + pair.Input[3]
+ "\tactual=" + Math.Round(output[0], 2) + " - " + Math.Round(output[1], 2) + " - " + Math.Round(output[2], 2) + " - " + Math.Round(output[3], 2) + " - " + Math.Round(output[4], 2)
+ "\tideal=" + pair.Ideal[0] + " - " + pair.Ideal[1] + " - " + pair.Ideal[2] + " - " + pair.Ideal[3] + " - " + pair.Ideal[4]);
}
Console.Read();
}
public LasPoint.ClassificationType[] Classify(LasFile file)
{
Stopwatch sw = Stopwatch.StartNew();
LasPointDataRecords points = file.LasPointDataRecords;
LasPoint.ClassificationType[] output = new LasPoint.ClassificationType[points.Count];
Statistics stats = new Statistics();
stats.Count = points.Count;
for (int i = 0; i < points.Count; i++)
{
LasPoint3Short point = (LasPoint3Short)points[i];
double green = point.Green - (point.Red + point.Blue) / 2;
IMLData classed = Network.Compute(
new BasicMLData(new double[] { file.LasHeader.ScaleZ(point.Z), point.Intensity, green }));
output[i] = Utills.QuickClassess[classed.IndexOfMax()];
if (output[i] != points[i].Classification)
{
stats.ClassErrors[(int)points[i].Classification]++;
}
stats.PredictionMatrix[(int)points[i].Classification, (int)output[i]]++;
stats.ClassCount[(int)output[i]]++;
stats.ClassRealCount[(int)points[i].Classification]++;
if (i % 1000 == 0)
{
Console.WriteLine(i);
}
}
Console.Write(stats.ToString());
sw.Stop();
Console.WriteLine("Czas trwania [" + sw.Elapsed.TotalSeconds.ToString() + "s]");
stats.SaveMatrixAsCSV();
return(output);
}
public void Run()
{
//Se crea la red neuronal con sus respectivas capas
var network = new BasicNetwork();
network.AddLayer(new BasicLayer(null, true, 2));
network.AddLayer(new BasicLayer(new ActivationSigmoid(), true, 3));
network.AddLayer(new BasicLayer(new ActivationSigmoid(), false, 1));
network.Structure.FinalizeStructure();
network.Reset();
//Crear el conjunto de entrenamiento
IMLDataSet conjuntoEntrenamiento = new BasicMLDataSet(entradas, salidas);
//Entrenar
IMLTrain train = new ResilientPropagation(network, conjuntoEntrenamiento);
int epoch = 1;
do
{
train.Iteration();
Console.WriteLine("Epoca #" + epoch + " Error:" + train.Error);
epoch++;
} while (train.Error > 0.01);
// test the neural network
Console.WriteLine("Resultados:");
foreach (IMLDataPair pair in conjuntoEntrenamiento)
{
IMLData output = network.Compute(pair.Input);
Console.WriteLine(pair.Input[0] + @"," + pair.Input[1]
+ @", actual=" + output[0] + @",ideal=" + pair.Ideal[0]);
}
}
static void Main(string[] args)
{
Console.Write("Enter network ID: ");
int networkID = int.Parse(Console.ReadLine());
FileInfo trainFile = new FileInfo("dataset.egb");
FileInfo networkFile = new FileInfo($"network{networkID}.nn");
IMLDataSet trainingSet = LoadDataSet(trainFile);
BasicNetwork network = LoadNetwork(networkFile);
using (var p = Process.GetCurrentProcess())
Console.WriteLine($"RAM usage: {p.WorkingSet64 / 1024 / 1024} MB.");
foreach (var sample in trainingSet)
{
Console.WriteLine("------------");
for (int i = 0; i < sample.Ideal.Count; i++)
{
Console.Write(fmt, sample.Ideal[i]);
}
Console.WriteLine();
//Console.WriteLine(sample.Ideal.ToString());
IMLData res = network.Compute(sample.Input);
for (int i = 0; i < sample.Ideal.Count; i++)
{
Console.Write(fmt, res[i]);
}
Console.WriteLine();
//Console.WriteLine(res.ToString());
Console.ReadKey();
}
}
protected override TimeSeries _BuildOutput(TimeSeries simulatedData, object userState = null)
{
if (mModel == null)
{
mModel = BuildModel(simulatedData, out mScaleFactor);
}
TimeSeries preds = new TimeSeries();
for (int i = 0; i < simulatedData.Count; ++i)
{
double[] input = new double[mWindowSize];
for (int j = 0; j < mWindowSize; ++j)
{
int index = i - (mWindowSize - j);
if (index >= 0)
{
input[j] = simulatedData[index] / mScaleFactor;
}
}
double[] output = new double[1];
mModel.Compute(input, output);
preds.Add(simulatedData.TimeStamp(i), output[0] * mScaleFactor, false);
}
return(preds);
}
public TimeSeries Predict(BasicNetwork network, NormalizeArray norm, TimeSeries simulatedData)
{
double[] data = GenerateData(simulatedData);
int data_count = simulatedData.Count;
TimeSeries ts = new TimeSeries();
double input_val = 0;
for (int idx = 0; idx < data_count; ++idx)
{
var input = new BasicMLData(WindowSize);
for (var i = 0; i < WindowSize; i++)
{
int idx2 = (idx - WindowSize) + i;
if (idx2 < 0)
{
input_val = 0;
}
else
{
input_val = norm.Stats.Normalize(data[idx2]);
}
input[i] = input_val;
}
IMLData output = network.Compute(input);
double prediction = norm.Stats.DeNormalize(output[0]);
ts.Add(simulatedData.TimeStamp(idx), prediction, false);
}
return(ts);
}
double Evaluate(double[] input)
{
var output = new double[1];
_network.Compute(input, output);
return(output[0]);
}
public static void Main()
{
BasicNetwork network = new BasicNetwork();
network.AddLayer(new BasicLayer(new ActivationSigmoid(), true, 2));
network.AddLayer(new BasicLayer(new ActivationSigmoid(), true, 6));
network.AddLayer(new BasicLayer(new ActivationSigmoid(), true, 1));
network.Structure.FinalizeStructure();
network.Reset();
INeuralDataSet trainingSet = new BasicNeuralDataSet(XorInput, XorIdeal);
ITrain train = new ResilientPropagation(network, trainingSet);
int epoch = 1;
var timer = Stopwatch.StartNew();
do
{
train.Iteration();
epoch++;
} while ((epoch < 50000) && (train.Error > 0.0001));
timer.Stop();
Console.WriteLine("Neural Network Results:");
foreach (var pair in trainingSet)
{
var output = network.Compute(pair.Input);
Console.WriteLine(pair.Input[0] + "," + pair.Input[1]
+ ", actual=" + output[0] + ", ideal=" + pair.Ideal[0]);
}
Console.WriteLine($"Completed {epoch} epochs in {timer.Elapsed} ({(float)timer.ElapsedMilliseconds / epoch} ms per epoch)");
Console.ReadLine();
}
public static void Main(string[] args)
{
var data = LoadData();
var label = LoadLabel();
var network = new BasicNetwork();
network.AddLayer(new BasicLayer(null, true, 4));
network.AddLayer(new BasicLayer(new ActivationReLU(), true, 8));
network.AddLayer(new BasicLayer(new ActivationSigmoid(), false, 3));
network.Structure.FinalizeStructure();
network.Reset();
var trainingSet = new BasicMLDataSet(data, label);
network.Flat.Weights = LoadNetwork();
//Train(network, trainingSet);
//SaveNetwork(network);
var sum = 0;
foreach (var pair in trainingSet)
{
var output = network.Compute(pair.Input);
Console.WriteLine($"Input: {pair.Input} Actual: {output.ToOneHot()} Ideal: {pair.Ideal}");
if (CompareMLData(output.ToOneHot(), pair.Ideal))
{
sum++;
}
}
Console.WriteLine($"Result = {((float)sum / trainingSet.Count) * 100}");
}
public void Run()
{
var network = new BasicNetwork();
network.AddLayer(new BasicLayer(null, true, 2));
network.AddLayer(new BasicLayer(new ActivationSigmoid(), true, 3));
network.AddLayer(new BasicLayer(new ActivationSigmoid(), false, 1));
network.Structure.FinalizeStructure();
network.Reset();
IMLDataSet trainingSet = new BasicMLDataSet(XORInput, XORIdeal);
IMLTrain train = new ResilientPropagation(network, trainingSet);
int epoch = 1;
do
{
train.Iteration();
Console.WriteLine(@"Epoch # " + epoch + @" Error: " + train.Error);
epoch++;
} while (train.Error > 0.01);
train.FinishTraining();
Console.WriteLine(@"Neural Network Results: ");
foreach (IMLDataPair pair in trainingSet)
{
IMLData output = network.Compute(pair.Input);
Console.WriteLine(pair.Input[0] + @" , " + pair.Input[1] + @" , actual = " + output[0] + @" , ideal = " + pair.Ideal[0]);
}
EncogFramework.Instance.Shutdown();
}
public int IdentifyMagic(double[] raw_input)
{
List <double> input;
double max = 0;
double[] op = new double[4];
int index = 0;
for (int i = 0; i < magics.Count; i++)
{
input = raw_input.ToList();
input.AddRange(magics[i].baseline);
IMLData inputData = new BasicMLData(input.ToArray());
IMLData output;
output = network.Compute(inputData);
op[i] = output[0];
if (max < output[0])
{
max = output[0];
index = i;
}
}
foreach (double o in op)
{
Debug.Log(o);
}
return((max > tolerance) ? index : -1);
}
public static double EvaluateNetworks(BasicNetwork network, BasicMLDataSet set)
{
int count = 0;
int correct = 0;
foreach (IMLDataPair pair in set)
{
IMLData input = pair.Input;
IMLData actualData = pair.Ideal;
IMLData predictData = network.Compute(input);
double actual = actualData[0];
double predict = predictData[0];
double diff = Math.Abs(predict - actual);
Direction actualDirection = DetermineDirection(actual);
Direction predictDirection = DetermineDirection(predict);
if (actualDirection == predictDirection)
{
correct++;
}
count++;
Console.WriteLine(@"Number" + @"count" + @": actual=" + Format.FormatDouble(actual, 4) + @"(" + actualDirection + @")"
+ @",predict=" + Format.FormatDouble(predict, 4) + @"(" + predictDirection + @")" + @",diff=" + diff);
}
double percent = correct / (double)count;
Console.WriteLine(@"Direction correct:" + correct + @"/" + count);
Console.WriteLine(@"Directional Accuracy:"
+ Format.FormatPercent(percent));
return(percent);
}
public List <PredictionResults> Predict(DateTime predictFrom, DateTime predictTo)
{
List <PredictionResults> results = new List <PredictionResults>();
double[] present = new double[InputTuples * IndexesToConsider];
double[] actualOutput = new double[OutputSize];
int index = 0;
foreach (var sample in _manager.Samples)
{
if (sample.Date.CompareTo(predictFrom) > 0 && sample.Date.CompareTo(predictTo) < 0)
{
var result = new PredictionResults();
_manager.GetInputData(index - InputTuples, present);
_manager.GetOutputData(index - InputTuples, actualOutput);
var data = new BasicNeuralData(present);
var predict = _network.Compute(data);
result.ActualLotos = actualOutput[0] * (_manager.MaxLotos - _manager.MinLotos) + _manager.MinLotos;
result.PredictedLotos = predict[0] * (_manager.MaxLotos - _manager.MinLotos) + _manager.MinLotos;
result.ActualPir = actualOutput[1] * (_manager.MaxPrimeRate - _manager.MinPrimeRate) + _manager.MinPrimeRate;
result.PredictedPir = predict[1] * (_manager.MaxPrimeRate - _manager.MinPrimeRate) + _manager.MinPrimeRate;
result.ActualOrlen = actualOutput[2] * (_manager.MaxOrlen - _manager.MinOrlen) + _manager.MinOrlen;
result.PredictedOrlen = predict[2] * (_manager.MaxOrlen - _manager.MinOrlen) + _manager.MinOrlen;
result.Date = sample.Date;
var error = new ErrorCalculation();
error.UpdateError(actualOutput, predict.Data);
result.Error = error.CalculateRMS();
results.Add(result);
}
index++;
}
return(results);
}
public void GetResults()
{
foreach (Texture2D texture in OpenFile.Open())
{
IMLDataPair pair = new BasicMLDataPair(new BasicMLData(Texture2List(texture).ToArray()));
IMLData output = basicNetwork.Compute(pair.Input);
string result = "";
float ideal = 0;
if (output[0] < 0.25f)
{
result = "Normal";
}
else if (output[0] > 0.25f && output[0] < 0.75f)
{
result = "Esquemico";
ideal = 0.5f;
}
else
{
result = "Hemorragico";
ideal = 1.0f;
}
Debug.Log("Isso parece ser: " + result + "\nEquivalência{ Imagem Testada: " + output[0] + " Imagem Original: " + ideal + " }");
debugText.text = ("Isso parece ser: " + result + "\nEquivalência{ Imagem Testada: " + output[0] + " Imagem Original: " + ideal + " }");
}
}
private static void CalculateProfit(IMLDataSet trainingSet, BasicNetwork network, Results res)
{
foreach (var article in trainingSet)
{
bool tradeMade = false;
var computed = network.Compute(article.Input);
for (int i = 0; i < trainingSet.IdealSize; i++)
{
if (computed[i] > 0.2)
{
tradeMade = true;
double reward = article.Ideal[i] * moneyPerTrade;
if (reward > transactionFee)
{
res.win[i]++;
}
else
{
res.loss[i]++;
}
if (reward > 0)
{
res.goodDir[i]++;
}
else
{
res.badDir[i]++;
}
res.profit[i] += reward - transactionFee;
}
if (computed[i] < -0.2)
{
tradeMade = true;
double reward = -article.Ideal[i] * moneyPerTrade;
if (reward > transactionFee)
{
res.win[i]++;
}
else
{
res.loss[i]++;
}
if (reward > 0)
{
res.goodDir[i]++;
}
else
{
res.badDir[i]++;
}
res.profit[i] += reward - transactionFee;
}
}
if (tradeMade)
{
res.articlesTraded++;
}
}
}
public static double[] Compute(this BasicNetwork network, double[] input)
{
double[] retVal = new double[network.OutputCount];
network.Compute(input, retVal);
return(retVal);
}
/// <summary>
/// Takes a state of the board and returns probability of
/// first player win.
/// </summary>
/// <param name="vector"></param>
/// <returns></returns>
public double EvaluateState(Board board)
{
//IMLData input = ANNAdapter.Adapt(board);
IMLData input = ANNAdapter.Adapt192(board);
IMLData output = network.Compute(input);
return(output[0]);
}
//public double Travel(ref int timeout, out int movesCnt)
public double Travel(int timerTimeout, out int movesCnt)
{
MazeGame game = new MazeGame();
game.InitGame(maze);
game.traveler = this;
game.traveler.location.X = maze.StartingPosition.X;
game.traveler.location.Y = maze.StartingPosition.Y;
var recentOutcome = new MazeCycleOutcome();
tmr.Interval = timerTimeout;
tmr.Start();
timeout = 0;
movesCnt = 0;
while (!recentOutcome.GameOver && timeout == 0)
{
movesCnt++;
var input = new BasicMLData(2);
input[0] = xInput.Normalize(Convert.ToDouble(game.traveler.location.X));
input[1] = yInput.Normalize(Convert.ToDouble(game.traveler.location.Y));
IMLData output = network.Compute(input);
double maxVal = double.MinValue;
int direction = 0;
for (int i = 0; i < output.Count; i++)
{
if (output[i] > maxVal)
{
direction = i;
maxVal = output[i];
}
}
recentOutcome = game.CycleMaze(direction);
MazeCycleComplete?.Invoke(game.traveler.location.X, game.traveler.location.Y, recentOutcome.BumpedIntoWall);
}
tmr.Stop();
var score = game.CalculateFinalScore(movesCnt);
return(score);
}
private void button2_Click(object sender, EventArgs e)
{
FeatureExtract Inputs = new FeatureExtract();
Inputs.dataMagnitude = dataMagnitude;
Inputs.Feature();
feature = new double[7];
feature[0] = (Inputs.MAV - 18.231) * 2 / (131.22 - 18.231) - 1;
feature[1] = (Inputs.RMS - 24.78176668) * 2 / (180.9976057 - 24.78176668) - 1;
feature[2] = (Inputs.VAR - 575.07346) * 2 / (32723.06952 - 575.07346) - 1;
feature[3] = (Inputs.SD - 23.98068931) * 2 / (180.8951893 - 23.98068931) - 1;
feature[4] = (Inputs.WL - 411.76) * 2 / (1664.26 - 411.76) - 1;
feature[5] = (Inputs.ZC - 1) * 2 / (12 - 1) - 1;
feature[6] = (Inputs.SSC - 3) * 2 / (15 - 3) - 1;
IMLData q = new BasicMLData(feature);
BasicNetwork JST = new BasicNetwork();
openFileDialog1.Title = "Open Network File...";
openFileDialog1.FileName = "";
openFileDialog1.Filter = "EG (Encog Network)|*.eg|All Files|*.*";
if (openFileDialog1.ShowDialog() == DialogResult.Cancel)
{
MessageBox.Show("Choice Cancelled");
}
else
{
JST = (BasicNetwork)EncogDirectoryPersistence.LoadObject(new FileInfo(openFileDialog1.FileName));
IMLData output = JST.Compute(q);
if (output[0] > output[1] && output[0] > output[2] && output[0] > output[3])
{
label2.Text = "Atas";
}
else if (output[1] > output[0] && output[1] > output[2] && output[1] > output[3])
{
label2.Text = "Bawah";
}
else if (output[2] > output[1] && output[2] > output[0] && output[2] > output[3])
{
label2.Text = "Kanan";
}
else if (output[3] > output[1] && output[3] > output[2] && output[3] > output[0])
{
label2.Text = "Kiri";
}
else
{
label2.Text = "Tidak Terdefinisikan";
}
label3.Text = "output" + "= " + output[0] + " " + output[1] + " " + output[2] + " " + output[3];
}
}
public double TestSingle(double[] input)
{
double[] outPut = new double[1];
BasicNetwork network = (BasicNetwork)SerializeObject.Load(networkFile);
network.Compute(input, outPut);
//Console.Write("The chance of winning is: " + Math.Round(output[0]*100,2) + "% | ");
return(outPut[0]);
}
