public static Tuple <double, ConfusionMatrix, double, double> LearnNetwork(INeuralDataSet learningSet, INeuralDataSet testingSet, int inputSize, InputClass inputData, int testingSize)
{
int iteracje = inputData.iterations;
List <double> errors = new List <double>();
Console.WriteLine("Tworze siec...");
ITrain Network = NetworkHelper.CreateNeuronNetwork(learningSet, inputSize, inputData);
Stopwatch stopwatch = new Stopwatch();
stopwatch.Start();
int iteracja = 0;
do
{
Network.Iteration();
Console.WriteLine("Epoch #" + iteracja + " Error:" + Network.Error);
errors.Add(Network.Error);
iteracja++;
} while ((iteracja < iteracje) && (Network.Error > 0.0001) && (Network.Error < 10000));
stopwatch.Stop();
/// TUTAJ SIEC SIE TEORETYCZNIE NAUCZYLA
double[] neuralAnswer = new double[testingSize];
int i = 0;
foreach (INeuralDataPair pair in testingSet)
{
INeuralData output = Network.Network.Compute(pair.Input);
double small = 0.0;
for (int r = 0; r < 4; r++)
{
if ((double)(output[r]) >= small)
{
neuralAnswer[i] = (double)r;
small = (double)(output[r]);
}
}
i++;
}
int[] answers = NetworkHelper.DenormaliseAnswers(neuralAnswer);
double calculateError = NetworkHelper.CalculateFinalError(answers, testingSet);
if ((errors[errors.Count - 1] * 100).ToString().Length > 4)
{
inputData.learningError = (errors[errors.Count - 1] * 100).ToString().Substring(0, 4) + " %";
}
else
{
inputData.learningError = (errors[errors.Count - 1] * 100).ToString() + " %";
}
if (calculateError.ToString().Length > 4)
{
inputData.testingError = calculateError.ToString().Substring(0, 4) + " %";
}
else
{
inputData.testingError = calculateError.ToString() + " %";
}
inputData.timeElapsed = stopwatch.Elapsed.Hours + "h " + stopwatch.Elapsed.Minutes + "min " + stopwatch.Elapsed.Seconds + "sec";
ConfusionMatrix confusionMatrix = new ConfusionMatrix(4);
CalculateConfusionMatrix(confusionMatrix, answers, testingSet);
double precission = CalculatePrecission(confusionMatrix);
double recall = CalculateRecall(confusionMatrix);
return(new Tuple <double, ConfusionMatrix, double, double>(calculateError, confusionMatrix, precission, recall));
}
