public void Deveria_retornar_excecao_quando_treinar_sem_dados()
{
Action action = () => _naiveBayes.Fit();
action.Should().ThrowExactly <InvalidOperationException>()
.And.Message.Should().Be("Não há dados para treinar o algoritmo");
}
private static void TestNaiveBayes(FeatureVector training, FeatureVector test)
{
NaiveBayes nb = new NaiveBayes();
NaiveBayesModel nbModel = (NaiveBayesModel)nb.Fit(training);
FeatureVector predictions = nbModel.transform(test);
PrintPredictionsAndEvaluate(predictions);
}
private void buttonForDataSplitNext_Click(object sender, EventArgs e)
{
trainingSetPercentage = (double)numericUpDownForTrainingSetPercent.Value / 100.0;
numFolds = (int)numericUpDownForNumFolds.Value;
double[] smaOut = null;
double[] wmaOut = null;
double[] emaOut = null;
double[] macdOut = null;
double[] stochasticsOut = null;
double[] williamsROut = null;
double[] rsiOut = null;
double[] closesOut = null;
var data = IndicatorService.GetData(code, targetDate, new string[] { "Tarih", "Kapanis" }, numberOfData + 1);
if (isSMAChecked)
{
smaOut = IndicatorDataPreprocessor.GetSMAOut(MovingAverage.Simple(code, targetDate, smaPeriod, numberOfData));
}
if (isWMAChecked)
{
wmaOut = IndicatorDataPreprocessor.GetWMAOut(MovingAverage.Weighted(code, targetDate, wmaPeriod, numberOfData));
}
if (isEMAChecked)
{
emaOut = IndicatorDataPreprocessor.GetEMAOut(MovingAverage.Exponential(code, targetDate, emaPeriod, numberOfData));
}
if (isMACDChecked)
{
macdOut = IndicatorDataPreprocessor.GetMACDOut(new MovingAverageConvergenceDivergence(code, targetDate, firstPeriod, secondPeriod, triggerPeriod, numberOfData));
}
if (isStochasticsChecked)
{
stochasticsOut = IndicatorDataPreprocessor.GetStochasticsOut(new Stochastics(code, targetDate, fastKPeriod, fastDPeriod, slowDPeriod, numberOfData));
}
if (isWilliamsRChecked)
{
williamsROut = IndicatorDataPreprocessor.GetWilliamsROut(WilliamsR.Wsr(code, targetDate, williamsRPeriod, numberOfData));
}
if (isRSIChecked)
{
rsiOut = IndicatorDataPreprocessor.GetRSIOut(RelativeStrengthIndex.Rsi(code, targetDate, rsiPeriod, numberOfData));
}
closesOut = IndicatorDataPreprocessor.GetClosesOut(numberOfData, data);
int minRowCount = 1000000;
if (smaOut != null)
{
minRowCount = smaOut.Length;
}
if (wmaOut != null)
{
minRowCount = minRowCount < wmaOut.Length ? minRowCount : wmaOut.Length;
}
if (emaOut != null)
{
minRowCount = minRowCount < emaOut.Length ? minRowCount : emaOut.Length;
}
if (macdOut != null)
{
minRowCount = minRowCount < macdOut.Length ? minRowCount : macdOut.Length;
}
if (rsiOut != null)
{
minRowCount = minRowCount < rsiOut.Length ? minRowCount : rsiOut.Length;
}
if (williamsROut != null)
{
minRowCount = minRowCount < williamsROut.Length ? minRowCount : williamsROut.Length;
}
if (stochasticsOut != null)
{
minRowCount = minRowCount < stochasticsOut.Length ? minRowCount : stochasticsOut.Length;
}
if (closesOut != null)
{
minRowCount = minRowCount < closesOut.Length ? minRowCount : closesOut.Length;
}
var fv = new FeatureVector();
if (isSMAChecked)
{
fv.AddColumn("SMA", smaOut.Select(p => (object)p.ToString(CultureInfo.InvariantCulture)).Take(minRowCount).ToArray());
}
if (isWMAChecked)
{
fv.AddColumn("WMA", wmaOut.Select(p => (object)p.ToString(CultureInfo.InvariantCulture)).Take(minRowCount).ToArray());
}
if (isEMAChecked)
{
fv.AddColumn("EMA", emaOut.Select(p => (object)p.ToString(CultureInfo.InvariantCulture)).Take(minRowCount).ToArray());
}
if (isMACDChecked)
{
fv.AddColumn("MACD", macdOut.Select(p => (object)p.ToString(CultureInfo.InvariantCulture)).Take(minRowCount).ToArray());
}
if (isRSIChecked)
{
fv.AddColumn("RSI", rsiOut.Select(p => (object)p.ToString(CultureInfo.InvariantCulture)).Take(minRowCount).ToArray());
}
if (isWilliamsRChecked)
{
fv.AddColumn("WilliamsR", williamsROut.Select(p => (object)p.ToString(CultureInfo.InvariantCulture)).Take(minRowCount).ToArray());
}
if (isStochasticsChecked)
{
fv.AddColumn("Stochastics", stochasticsOut.Select(p => (object)p.ToString(CultureInfo.InvariantCulture)).Take(minRowCount).ToArray());
}
fv.AddColumn("label", closesOut.Select(p => (object)string.Format("{0:0.0}", p).ToString(CultureInfo.InvariantCulture)).Take(minRowCount).ToArray());
var training = new FeatureVector();
var test = new FeatureVector();
int count = fv.Values[0].Length;
for (int i = 0; i < fv.ColumnName.Count; i++)
{
training.AddColumn(fv.ColumnName[i], fv.Values[i].Take((int)(count * trainingSetPercentage)).ToArray());
}
for (int i = 0; i < fv.ColumnName.Count; i++)
{
test.AddColumn(fv.ColumnName[i], fv.Values[i].Skip((int)(count * trainingSetPercentage)).Take(count).ToArray()); // Take(count) means take the rest of all elements, number of the rest of the elements is smaller than count.
}
if (numFolds > 0)
{
BinaryClassificationEvaluator bce1 = new BinaryClassificationEvaluator();
LinearRegression linearRegression = new LinearRegression();
CrossValidator cvLinReg = new CrossValidator(linearRegression, bce1, numFolds);
CrossValidatorModel cvLinRegModel = (CrossValidatorModel)cvLinReg.Fit(training);
FeatureVector linRegPredictions = cvLinRegModel.transform(test);
bce1.evaluate(linRegPredictions);
linRegAcc = bce1.Accuracy;
BinaryClassificationEvaluator bce2 = new BinaryClassificationEvaluator();
LogisticRegression logisticRegression = new LogisticRegression();
CrossValidator cvLogReg = new CrossValidator(logisticRegression, bce2, numFolds);
CrossValidatorModel cvLogRegModel = (CrossValidatorModel)cvLogReg.Fit(training);
FeatureVector logRegPredictions = cvLogRegModel.transform(test);
bce2.evaluate(logRegPredictions);
logRegAcc = bce2.Accuracy;
BinaryClassificationEvaluator bce3 = new BinaryClassificationEvaluator();
NaiveBayes naiveBayes = new NaiveBayes();
CrossValidator cvNaiBay = new CrossValidator(naiveBayes, bce3, numFolds);
CrossValidatorModel cvNaiBayModel = (CrossValidatorModel)cvNaiBay.Fit(training);
FeatureVector naiBayPredictions = cvNaiBayModel.transform(test);
bce3.evaluate(naiBayPredictions);
naiBayAcc = bce3.Accuracy;
}
else
{
BinaryClassificationEvaluator bce1 = new BinaryClassificationEvaluator();
LinearRegression linearRegression = new LinearRegression();
LinearRegressionModel linearRegressionModel = (LinearRegressionModel)linearRegression.Fit(training);
FeatureVector linRegPredictions = linearRegressionModel.transform(test);
bce1.evaluate(linRegPredictions);
linRegAcc = bce1.Accuracy;
BinaryClassificationEvaluator bce2 = new BinaryClassificationEvaluator();
LogisticRegression logicticRegression = new LogisticRegression();
LogisticRegressionModel logisticRegressionModel = (LogisticRegressionModel)logicticRegression.Fit(training);
FeatureVector logRegPredictions = logisticRegressionModel.transform(test);
bce2.evaluate(logRegPredictions);
logRegAcc = bce2.Accuracy;
BinaryClassificationEvaluator bce3 = new BinaryClassificationEvaluator();
NaiveBayes naiveBayes = new NaiveBayes();
NaiveBayesModel naiveBayesModel = (NaiveBayesModel)naiveBayes.Fit(training);
FeatureVector naiBayPredictions = naiveBayesModel.transform(test);
bce3.evaluate(naiBayPredictions);
naiBayAcc = bce3.Accuracy;
}
labelForLinRegAcc.Text = linRegAcc.ToString();
labelForLogRegAcc.Text = logRegAcc.ToString();
labelForNaiBayAcc.Text = naiBayAcc.ToString();
panelForResults.BringToFront();
}
private static double CalculateAccuracy(List <int> indicators, int mlAlgorithm, bool isCrossValidationEnabled, int minRowCount, double trainingSetPercentage, double[] smaOut, double[] wmaOut, double[] emaOut, double[] macdOut, double[] rsiOut, double[] williamsROut, double[] stochasticsOut, double[] closesOut)
{
FeatureVector vector = new FeatureVector();
if (indicators.Contains(IndicatorService.SMA))
{
vector.AddColumn("SMA", smaOut.Select(p => (object)p.ToString(CultureInfo.InvariantCulture)).Take(minRowCount).ToArray());
}
if (indicators.Contains(IndicatorService.WMA))
{
vector.AddColumn("WMA", wmaOut.Select(p => (object)p.ToString(CultureInfo.InvariantCulture)).Take(minRowCount).ToArray());
}
if (indicators.Contains(IndicatorService.EMA))
{
vector.AddColumn("EMA", emaOut.Select(p => (object)p.ToString(CultureInfo.InvariantCulture)).Take(minRowCount).ToArray());
}
if (indicators.Contains(IndicatorService.MACD))
{
vector.AddColumn("MACD", macdOut.Select(p => (object)p.ToString(CultureInfo.InvariantCulture)).Take(minRowCount).ToArray());
}
if (indicators.Contains(IndicatorService.RSI))
{
vector.AddColumn("RSI", rsiOut.Select(p => (object)p.ToString(CultureInfo.InvariantCulture)).Take(minRowCount).ToArray());
}
if (indicators.Contains(IndicatorService.WilliamsR))
{
vector.AddColumn("WilliamsR", williamsROut.Select(p => (object)p.ToString(CultureInfo.InvariantCulture)).Take(minRowCount).ToArray());
}
if (indicators.Contains(IndicatorService.Stochastics))
{
vector.AddColumn("Stochastics", stochasticsOut.Select(p => (object)p.ToString(CultureInfo.InvariantCulture)).Take(minRowCount).ToArray());
}
vector.AddColumn("label", closesOut.Select(p => (object)string.Format("{0:0.0}", p).ToString(CultureInfo.InvariantCulture)).Take(minRowCount).ToArray());
new CSVExporter(vector).Export("c:\\users\\yasin\\indicatorOutput.csv");
int count = vector.Values[0].Length;
FeatureVector training = new FeatureVector();
for (int i = 0; i < vector.ColumnName.Count; i++)
{
training.AddColumn(vector.ColumnName[i], vector.Values[i].Take((int)(count * trainingSetPercentage)).ToArray());
}
FeatureVector test = new FeatureVector();
for (int i = 0; i < vector.ColumnName.Count; i++)
{
test.AddColumn(vector.ColumnName[i], vector.Values[i].Skip((int)(count * trainingSetPercentage)).Take(count).ToArray());
}
double accuracy = 0;
if (mlAlgorithm == MLAService.LIN_REG)
{
var linReg = new LinearRegression();
var bce = new BinaryClassificationEvaluator();
if (isCrossValidationEnabled)
{
var cv = new CrossValidator(linReg, bce, 10);
var cvModel = (CrossValidatorModel)cv.Fit(training);
var predictions = cvModel.transform(test);
bce.evaluate(predictions);
accuracy = bce.Accuracy;
}
else
{
var linRegModel = (LinearRegressionModel)linReg.Fit(training);
var predictions = linRegModel.transform(test);
bce.evaluate(predictions);
accuracy = bce.Accuracy;
}
}
else if (mlAlgorithm == MLAService.LOG_REG)
{
var logReg = new LogisticRegression();
var bce = new BinaryClassificationEvaluator();
if (isCrossValidationEnabled)
{
var cv = new CrossValidator(logReg, bce, 10);
var cvModel = (CrossValidatorModel)cv.Fit(training);
var predictions = cvModel.transform(test);
bce.evaluate(predictions);
accuracy = bce.Accuracy;
}
else
{
var logRegModel = (LogisticRegressionModel)logReg.Fit(training);
var predictions = logRegModel.transform(test);
bce.evaluate(predictions);
accuracy = bce.Accuracy;
}
}
else if (mlAlgorithm == MLAService.NAI_BAY)
{
var naiBay = new NaiveBayes();
var bce = new BinaryClassificationEvaluator();
if (isCrossValidationEnabled)
{
var cv = new CrossValidator(naiBay, bce, 10);
var cvModel = (CrossValidatorModel)cv.Fit(training);
var predictions = cvModel.transform(test);
bce.evaluate(predictions);
accuracy = bce.Accuracy;
}
else
{
var naiBayModel = (NaiveBayesModel)naiBay.Fit(training);
var predictions = naiBayModel.transform(test);
bce.evaluate(predictions);
accuracy = bce.Accuracy;
}
}
return(accuracy);
}