public static double TrainNetworks(SupportVectorMachine network, MarketMLDataSet training)
{
// train the neural network
SVMTrain trainMain = new SVMTrain(network, training);
StopTrainingStrategy stop = new StopTrainingStrategy(0.0001, 200);
trainMain.AddStrategy(stop);
var sw = new Stopwatch();
sw.Start();
while (!stop.ShouldStop())
{
trainMain.PreIteration();
trainMain.Iteration();
trainMain.PostIteration();
Console.WriteLine(@"Iteration #:" + trainMain.IterationNumber + @" Error:" + trainMain.Error);
}
sw.Stop();
Console.WriteLine("SVM Trained in :" + sw.ElapsedMilliseconds + "For error:" + trainMain.Error + " Iterated:" + trainMain.IterationNumber);
return(trainMain.Error);
}
public static MarketMLDataSet GrabData(string newfileLoad)
{
IMarketLoader loader = new CSVFileLoader();//CSVLoader();
loader.GetFile(newfileLoad);
var result = new MarketMLDataSet(loader,
Config.INPUT_WINDOW, Config.PREDICT_WINDOW);
// var desc = new MarketDataDescription(Config.TICKER,
// MarketDataType.Close, true, true);
var desc = new MarketDataDescription(Config.TICKER,
MarketDataType.Close, TemporalDataDescription.Type.PercentChange, true, true);
result.AddDescription(desc);
var begin = DateTime.ParseExact("29.05.2005", "dd.MM.yyyy", CultureInfo.CurrentCulture); // begin 30 days ago
var end = DateTime.ParseExact("22.07.2005", "dd.MM.yyyy", CultureInfo.CurrentCulture); // begin 30 days ago
begin = begin.AddDays(Config.DAYS_OFFSET).AddDays(Config.TEST_OFFSET);
end = end.AddDays(Config.DAYS_OFFSET).AddDays(Config.TEST_OFFSET).AddDays(Config.TEST_STRATCH);
result.Load(begin, end);
result.Generate();
return(result);
}
public static MarketMLDataSet GrabData(string newfileLoad)
{
IMarketLoader loader = new CSVFinal();
loader.GetFile(newfileLoad);
var result = new MarketMLDataSet(loader,
CONFIG.INPUT_WINDOW, CONFIG.PREDICT_WINDOW);
// var desc = new MarketDataDescription(Config.TICKER,
// MarketDataType.Close, true, true);
var desc = new MarketDataDescription(CONFIG.TICKER,
MarketDataType.Close, true, true);
result.AddDescription(desc);
var end = DateTime.Now; // end today
var begin = new DateTime(end.Ticks); // begin 30 days ago
begin = begin.AddDays(-950);
result.Load(begin, end);
result.Generate();
return(result);
}
public static void Generate(FileInfo dataDir)
{
IMarketLoader loader = new YahooFinanceLoader();
var market = new MarketMLDataSet(loader,
Config.INPUT_WINDOW, Config.PREDICT_WINDOW);
var desc = new MarketDataDescription(
Config.TICKER, MarketDataType.AdjustedClose, true, true);
market.AddDescription(desc);
var end = DateTime.Now; // end today
var begin = new DateTime(end.Ticks); // begin 30 days ago
// Gather training data for the last 2 years, stopping 60 days short of today.
// The 60 days will be used to evaluate prediction.
begin = begin.AddDays(-60);
end = end.AddDays(-60);
begin = begin.AddYears(-2);
market.Load(begin, end);
market.Generate();
EncogUtility.SaveEGB(FileUtil.CombinePath(dataDir, Config.TRAINING_FILE), market);
// create a network
BasicNetwork network = EncogUtility.SimpleFeedForward(
market.InputSize,
Config.HIDDEN1_COUNT,
Config.HIDDEN2_COUNT,
market.IdealSize,
true);
// save the network and the training
EncogDirectoryPersistence.SaveObject(FileUtil.CombinePath(dataDir, Config.NETWORK_FILE), network);
}
public static double Evaluate(FileInfo dataDir, string filename)
{
FileInfo file = FileUtil.CombinePath(dataDir, Config.NETWORK_FILE);
if (!file.Exists)
{
Console.WriteLine(@"Can't read file: " + file);
return(0);
}
var network = (BasicNetwork)EncogDirectoryPersistence.LoadObject(file);
MarketMLDataSet data = GrabData(filename);
int count = 0;
int correct = 0;
foreach (IMLDataPair pair in data)
{
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(@"Day " + 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 static void Generate(string fileName)
{
FileInfo dataDir = new FileInfo(@Environment.CurrentDirectory);
IMarketLoader loader = new CSVFinal();
var market = new MarketMLDataSet(loader, CONFIG.INPUT_WINDOW, CONFIG.PREDICT_WINDOW);
// var desc = new MarketDataDescription(Config.TICKER, MarketDataType.Close, true, true);
var desc = new MarketDataDescription(CONFIG.TICKER, MarketDataType.Close, true, true);
market.AddDescription(desc);
string currentDirectory = @"c:\";
loader.GetFile(fileName);
var end = DateTime.Now; // end today
var begin = new DateTime(end.Ticks); // begin 30 days ago
// Gather training data for the last 2 years, stopping 60 days short of today.
// The 60 days will be used to evaluate prediction.
begin = begin.AddDays(-600);
end = begin.AddDays(200);
Console.WriteLine("You are loading date from:" + begin.ToShortDateString() + " To :" + end.ToShortDateString());
market.Load(begin, end);
market.Generate();
EncogUtility.SaveEGB(FileUtil.CombinePath(dataDir, CONFIG.SVMTRAINING_FILE), market);
// create a network
//BasicNetwork network = EncogUtility.SimpleFeedForward(
// market.InputSize,
// CONFIG.HIDDEN1_COUNT,
// CONFIG.HIDDEN2_COUNT,
// market.IdealSize,
// true);
SupportVectorMachine network = new SupportVectorMachine(CONFIG.INPUT_WINDOW, true);
TrainNetworks(network, market);
// save the network and the training
EncogDirectoryPersistence.SaveObject(FileUtil.CombinePath(dataDir, CONFIG.SVMTRAINING_FILE), network);
}
public static void Generate(string fileName)
{
FileInfo dataDir = new FileInfo(@Environment.CurrentDirectory);
//Lets use the CSVFinal..(and not the CSV Form loader).
IMarketLoader loader = new CSVFinal();
loader.GetFile(fileName);
var market = new MarketMLDataSet(loader, Config.INPUT_WINDOW, Config.PREDICT_WINDOW);
// var desc = new MarketDataDescription(Config.TICKER, MarketDataType.Close, true, true);
var desc = new MarketDataDescription(Config.TICKER, MarketDataType.Close, TemporalDataDescription.Type.PercentChange, true, true);
market.AddDescription(desc);
loader.GetFile(fileName);
var begin = DateTime.ParseExact("01.01.2000", "dd.MM.yyyy", CultureInfo.CurrentCulture); // begin 30 days ago
var end = DateTime.ParseExact("22.06.2005", "dd.MM.yyyy", CultureInfo.CurrentCulture); // begin 30 days ago
begin = begin.AddDays(Config.DAYS_OFFSET);
end = end.AddDays(Config.DAYS_OFFSET);
// Gather training data for the last 2 years, stopping 60 days short of today.
// The 60 days will be used to evaluate prediction.
//begin = begin.AddDays(-200);
//end = begin.AddDays(1);
Console.WriteLine("You are loading date from:" + begin.ToShortDateString() + " To :" + end.ToShortDateString());
market.Load(begin, end);
market.Generate();
EncogUtility.SaveEGB(FileUtil.CombinePath(dataDir, Config.TRAINING_FILE), market);
// create a network
BasicNetwork network = EncogUtility.SimpleFeedForward(
market.InputSize,
Config.HIDDEN1_COUNT,
Config.HIDDEN2_COUNT,
market.IdealSize,
true);
// save the network and the training
EncogDirectoryPersistence.SaveObject(FileUtil.CombinePath(dataDir, Config.NETWORK_FILE), network);
}
public static MarketMLDataSet GrabData()
{
IMarketLoader loader = new YahooFinanceLoader();
var result = new MarketMLDataSet(loader,
Config.INPUT_WINDOW, Config.PREDICT_WINDOW);
var desc = new MarketDataDescription(Config.TICKER,
MarketDataType.AdjustedClose, true, true);
result.AddDescription(desc);
var end = DateTime.Now; // end today
var begin = new DateTime(end.Ticks); // begin 30 days ago
begin = begin.AddDays(-60);
result.Load(begin, end);
result.Generate();
return(result);
}
