private static void Step3()
{
Console.WriteLine("Step 3: Normalize Training and Evaluation Data");
//Analyst
var analyst = new EncogAnalyst();
//Wizard
var wizard = new AnalystWizard(analyst);
wizard.Wizard(Config.BaseFile, true, AnalystFileFormat.DecpntComma);
//Norm for Training
var norm = new AnalystNormalizeCSV();
norm.Analyze(Config.TrainingFile, true, CSVFormat.English, analyst);
norm.ProduceOutputHeaders = true;
norm.Normalize(Config.NormalizedTrainingFile);
//Norm for evaluation
norm.Analyze(Config.EvaluateFile, true, CSVFormat.English, analyst);
norm.ProduceOutputHeaders = true;
norm.Normalize(Config.NormalizedEvaluateFile);
analyst.Save(Config.AnalystFile);
}
/// <summary>
/// Program entry point.
/// </summary>
/// <param name="app">Holds arguments and other info.</param>
public void Execute(IExampleInterface app)
{
Console.WriteLine("Running wizard...");
var analyst = new EncogAnalyst();
var wizard = new AnalystWizard(analyst);
wizard.TargetFieldName = "field:1";
wizard.Wizard(sourceCSV,
false, AnalystFileFormat.DecpntComma);
// customer id
analyst.Script.Normalize.NormalizedFields[0].Action = Encog.Util.Arrayutil.NormalizationAction.PassThrough;
var norm = new AnalystNormalizeCSV();
norm.Report = new ConsoleStatusReportable();
Console.WriteLine("Analyze for normalize...");
norm.Analyze(sourceCSV, false, CSVFormat.English, analyst);
norm.ProduceOutputHeaders = true;
Console.WriteLine("Normalize...");
norm.Normalize(targetCSV);
analyst.Save(scriptEGA);
}
/// <see cref="INetwork.Normalize"/>
public INetwork Normalize()
{
//Analyst
var analyst = new EncogAnalyst();
//Wizard
var wizard = new AnalystWizard(analyst);
wizard.Wizard(BaseFile, true, AnalystFileFormat.DecpntComma);
// Configure normalized fields
ConfigureNormalizedFields(analyst);
//Norm for Trainng
var norm = new AnalystNormalizeCSV();
norm.Analyze(TrainingFile, true, CSVFormat.English, analyst);
norm.ProduceOutputHeaders = true;
norm.Normalize(NormalizedTrainingFile);
//Norm of evaluation
norm.Analyze(EvaluateFile, true, CSVFormat.English, analyst);
norm.ProduceOutputHeaders = true;
norm.Normalize(NormalizedEvaluateFile);
//Save the analyst file
analyst.Save(AnalystFile);
return(this);
}
public void Wizard(AnalystGoal goal, WizardMethodType methodType, bool headers)
{
EncogAnalyst.MaxIteration = MaxIterations;
var wiz = new AnalystWizard(EncogAnalyst)
{
Goal = goal, MethodType = methodType, EvidenceSegements = 3
};
wiz.Wizard(_rawFile, headers, FileFormat);
EncogAnalyst.Save(_analystFile);
EncogAnalyst.Load(_analystFile);
}
static void Step3()
{
Console.WriteLine("Step 3: Normalize Training and Evaluation Data");
//Analyst
var analyst = new EncogAnalyst();
//Wizard
var wizard = new AnalystWizard(analyst);
wizard.Wizard(Config.BaseFile, true, AnalystFileFormat.DecpntComma);
//Cylinders
analyst.Script.Normalize.NormalizedFields[0].Action = Encog.Util.Arrayutil.NormalizationAction.Equilateral; // multivalued discreste field type
//displacement
analyst.Script.Normalize.NormalizedFields[1].Action = Encog.Util.Arrayutil.NormalizationAction.Normalize; // continues
//HorsePower
analyst.Script.Normalize.NormalizedFields[2].Action = Encog.Util.Arrayutil.NormalizationAction.Normalize;
//weight
analyst.Script.Normalize.NormalizedFields[3].Action = Encog.Util.Arrayutil.NormalizationAction.Normalize;
//Acceleration
analyst.Script.Normalize.NormalizedFields[4].Action = Encog.Util.Arrayutil.NormalizationAction.Normalize;
//year
analyst.Script.Normalize.NormalizedFields[5].Action = Encog.Util.Arrayutil.NormalizationAction.Equilateral; // multivalued discreste field type
//Origin
analyst.Script.Normalize.NormalizedFields[6].Action = Encog.Util.Arrayutil.NormalizationAction.Equilateral; // multivalued discreste field type
//Name
analyst.Script.Normalize.NormalizedFields[7].Action = Encog.Util.Arrayutil.NormalizationAction.Ignore; // will not use
//mpg
analyst.Script.Normalize.NormalizedFields[8].Action = Encog.Util.Arrayutil.NormalizationAction.Normalize; // contniues
//Norm for Trainng
var norm = new AnalystNormalizeCSV();
norm.ProduceOutputHeaders = true;
norm.Analyze(Config.TrainingFile, true, CSVFormat.English, analyst);
norm.Normalize(Config.NormalizedTrainingFile);
//Norm of evaluation
norm.Analyze(Config.EvaluateFile, true, CSVFormat.English, analyst);
norm.Normalize(Config.NormalizedEvaluateFile);
//save the analyst file
analyst.Save(Config.AnalystFile);
}
private void Normalize()
{
//Analyst
var analyst = new EncogAnalyst();
//Wizard
var wizard = new AnalystWizard(analyst);
wizard.Wizard(Config.BaseFile, true, AnalystFileFormat.DecpntComma);
//Cylinders
analyst.Script.Normalize.NormalizedFields[0].Action = Encog.Util.Arrayutil.NormalizationAction.Equilateral;
//displacement
analyst.Script.Normalize.NormalizedFields[1].Action = Encog.Util.Arrayutil.NormalizationAction.Normalize;
//HorsePower
analyst.Script.Normalize.NormalizedFields[2].Action = Encog.Util.Arrayutil.NormalizationAction.Normalize;
//weight
analyst.Script.Normalize.NormalizedFields[3].Action = Encog.Util.Arrayutil.NormalizationAction.Normalize;
//Acceleration
analyst.Script.Normalize.NormalizedFields[4].Action = Encog.Util.Arrayutil.NormalizationAction.Normalize;
//year
analyst.Script.Normalize.NormalizedFields[5].Action = Encog.Util.Arrayutil.NormalizationAction.Equilateral;
//Origin
analyst.Script.Normalize.NormalizedFields[6].Action = Encog.Util.Arrayutil.NormalizationAction.Equilateral;
//Name
analyst.Script.Normalize.NormalizedFields[7].Action = Encog.Util.Arrayutil.NormalizationAction.Ignore;
//mpg
analyst.Script.Normalize.NormalizedFields[8].Action = Encog.Util.Arrayutil.NormalizationAction.Normalize;
//Norm for Trainng
var norm = new AnalystNormalizeCSV();
norm.ProduceOutputHeaders = true;
norm.Analyze(Config.TrainingFile, true, CSVFormat.English, analyst);
norm.Normalize(Config.NormalizedTrainingFile);
//Norm of Cross Validation
norm.Analyze(Config.CrossValidationFile, true, CSVFormat.English, analyst);
norm.Normalize(Config.NormalizedCrossValidationFile);
//Norm of evaluation
norm.Analyze(Config.EvaluateFile, true, CSVFormat.English, analyst);
norm.Normalize(Config.NormalizedEvaluateFile);
//save the analyst file
analyst.Save(Config.AnalystFile);
}
public void Normalize(FileInfo baseFile, FileInfo trainingFile, FileInfo normalizedTrainingFile, FileInfo evaluateFile, FileInfo normalizedEvaluateFile, FileInfo analystFile)
{
var encogAnalyst = new EncogAnalyst();
var analystWizard = new AnalystWizard(encogAnalyst);
analystWizard.Wizard(baseFile, true, AnalystFileFormat.DecpntComma);
var normalizer = new AnalystNormalizeCSV();
normalizer.Analyze(trainingFile, true, CSVFormat.English, encogAnalyst);
normalizer.ProduceOutputHeaders = true;
normalizer.Normalize(normalizedTrainingFile);
normalizer.Analyze(evaluateFile, true, CSVFormat.English, encogAnalyst);
normalizer.Normalize(normalizedEvaluateFile);
encogAnalyst.Save(analystFile);
}
/// <summary>
/// Metodo responsavel por normalizar as informacoes para adequar a execucao da rede neural
/// </summary>
private static void Normalization()
{
var analyst = new EncogAnalyst();
var wizard = new AnalystWizard(analyst);
wizard.Wizard(Config.ClassificationFile, true, AnalystFileFormat.DecpntComma);
var norm = new AnalystNormalizeCSV();
norm.Analyze(Config.TrainingClassificationFile, true, CSVFormat.English, analyst);
norm.ProduceOutputHeaders = true;
norm.Normalize(Config.NormalizedTrainingClassificationFile);
norm.Analyze(Config.EvaluateClassificationFile, true, CSVFormat.English, analyst);
norm.Normalize(Config.NormalizedEvaluateClassificationFile);
analyst.Save(Config.AnalystClassificationFile);
}
/// <summary>
/// Metodo responsavel por normalizar as informacoes para adequar a execucao da rede neural
/// </summary>
private static void Normalization()
{
var analyst = new EncogAnalyst();
//Wizard
var wizard = new AnalystWizard(analyst);
wizard.Wizard(Config.RegressionFile, true, AnalystFileFormat.DecpntComma);
//Cilindros
analyst.Script.Normalize.NormalizedFields[0].Action = Encog.Util.Arrayutil.NormalizationAction.Equilateral;
//displacement
analyst.Script.Normalize.NormalizedFields[1].Action = Encog.Util.Arrayutil.NormalizationAction.Normalize;
//HorsePower
analyst.Script.Normalize.NormalizedFields[2].Action = Encog.Util.Arrayutil.NormalizationAction.Normalize;
//Peso
analyst.Script.Normalize.NormalizedFields[3].Action = Encog.Util.Arrayutil.NormalizationAction.Normalize;
//Aceleração
analyst.Script.Normalize.NormalizedFields[4].Action = Encog.Util.Arrayutil.NormalizationAction.Normalize;
//Ano
analyst.Script.Normalize.NormalizedFields[5].Action = Encog.Util.Arrayutil.NormalizationAction.Equilateral;
//Origem
analyst.Script.Normalize.NormalizedFields[6].Action = Encog.Util.Arrayutil.NormalizationAction.Equilateral;
//Nome
analyst.Script.Normalize.NormalizedFields[7].Action = Encog.Util.Arrayutil.NormalizationAction.Ignore;
//MPG
analyst.Script.Normalize.NormalizedFields[8].Action = Encog.Util.Arrayutil.NormalizationAction.Normalize;
var norm = new AnalystNormalizeCSV();
norm.ProduceOutputHeaders = true;
norm.Analyze(Config.TrainingRegressionFile, true, CSVFormat.English, analyst);
norm.Normalize(Config.NormalizedTrainingRegressionFile);
//Norm of evaluation
norm.Analyze(Config.EvaluateRegressionFile, true, CSVFormat.English, analyst);
norm.Normalize(Config.NormalizedEvaluateRegressionFile);
//save the analyst file
analyst.Save(Config.AnalystRegressionFile);
}
public void IrisExample(FileInfo dir)
{
Console.WriteLine("Starting Iris dataset example.");
var url = new Uri(IRIS_SOURCE);
FileInfo analystFile = FileUtil.CombinePath(dir, "iris.ega");
FileInfo rawFile = FileUtil.CombinePath(dir, "iris_raw.csv");
var encog = new EncogAnalyst();
encog.AddAnalystListener(new ConsoleAnalystListener());
var wiz = new AnalystWizard(encog);
wiz.Wizard(url, analystFile, rawFile, false, AnalystFileFormat.DecpntComma);
encog.Save(analystFile);
encog.ExecuteTask("task-full");
var report = new AnalystReport(encog);
report.ProduceReport(FileUtil.CombinePath(dir, "report.html"));
}
private void Normalize(FileInfo BaseFile, FileInfo TrainingFile, FileInfo NormalizedTrainingFile, FileInfo EvaluateFile, FileInfo NormalizedEvaluateFile, FileInfo AnalystFile)
{
//Analyst
var analyst = new EncogAnalyst();
//Wizard
var wizard = new AnalystWizard(analyst);
wizard.Wizard(BaseFile, true, AnalystFileFormat.DecpntComma);
//Norm for Trainng
var norm = new AnalystNormalizeCSV();
norm.Analyze(TrainingFile, true, CSVFormat.English, analyst);
norm.ProduceOutputHeaders = true;
norm.Normalize(NormalizedTrainingFile);
//Norm of evaluation
norm.Analyze(EvaluateFile, true, CSVFormat.English, analyst);
norm.Normalize(NormalizedEvaluateFile);
//save the analyst file
analyst.Save(AnalystFile);
}
public void Normalize(FileInfo baseFile, FileInfo trainingFile, FileInfo normalizedTrainingFile, FileInfo evaluateFile, FileInfo normalizedEvaluateFile, FileInfo analystFile)
{
var encogAnalyst = new EncogAnalyst();
var analystWizard = new AnalystWizard(encogAnalyst);
analystWizard.Wizard(baseFile, true, AnalystFileFormat.DecpntComma);
//Cylinders:
encogAnalyst.Script.Normalize.NormalizedFields[0].Action = NormalizationAction.Equilateral;
//Displacement:
encogAnalyst.Script.Normalize.NormalizedFields[1].Action = NormalizationAction.Normalize;
//Horsepower:
encogAnalyst.Script.Normalize.NormalizedFields[2].Action = NormalizationAction.Normalize;
//Weight:
encogAnalyst.Script.Normalize.NormalizedFields[3].Action = NormalizationAction.Normalize;
//Acceleration:
encogAnalyst.Script.Normalize.NormalizedFields[4].Action = NormalizationAction.Normalize;
//Year:
encogAnalyst.Script.Normalize.NormalizedFields[5].Action = NormalizationAction.Equilateral;
//Origin:
encogAnalyst.Script.Normalize.NormalizedFields[6].Action = NormalizationAction.Equilateral;
//Name:
encogAnalyst.Script.Normalize.NormalizedFields[7].Action = NormalizationAction.Ignore;
//Mpg:
encogAnalyst.Script.Normalize.NormalizedFields[8].Action = NormalizationAction.Normalize;
var normalizer = new AnalystNormalizeCSV();
normalizer.Analyze(trainingFile, true, CSVFormat.English, encogAnalyst);
normalizer.ProduceOutputHeaders = true;
normalizer.Normalize(normalizedTrainingFile);
normalizer.Analyze(evaluateFile, true, CSVFormat.English, encogAnalyst);
normalizer.Normalize(normalizedEvaluateFile);
encogAnalyst.Save(analystFile);
}
public void ForestExample(FileInfo dir)
{
Console.WriteLine("Starting forest cover dataset example.");
var url = new Uri(FOREST_SOURCE);
FileInfo analystFile = FileUtil.CombinePath(dir, "forest.ega");
FileInfo rawFile = FileUtil.CombinePath(dir, "forest_raw.csv");
var encog = new EncogAnalyst();
encog.AddAnalystListener(new ConsoleAnalystListener());
var wiz = new AnalystWizard(encog);
wiz.TaskBalance = true;
wiz.Wizard(url, analystFile, rawFile, false, AnalystFileFormat.DecpntComma);
encog.MaxIteration = 300;
encog.ExecuteTask("task-full");
encog.Save(analystFile);
var report = new AnalystReport(encog);
report.ProduceReport(FileUtil.CombinePath(dir, "report.html"));
}
public static int epoch; // to be provided by user
private static void Main(string[] args)
{
Console.WriteLine("Press 1 for selecting Regresssion and 2 for classification");
int whatToperform = int.Parse(Console.ReadLine());
Console.WriteLine("Please provide number of layers assuming first layer is input layer and last is output layer");
int numberOfLayers = int.Parse(Console.ReadLine());
var network = new BasicNetwork();
for (int i = 1; i <= numberOfLayers; i++)
{
Console.WriteLine("Please select the activation function for layer- {0}", i); // Activtion function Input
Console.WriteLine("Press 1 for ActivationBiPolar ");
Console.WriteLine("Press 2 for ActivationCompetitive ");
Console.WriteLine("Press 3 for ActivationLinear ");
Console.WriteLine("Press 4 for ActivationLog ");
Console.WriteLine("Press 5 for ActivationSigmoid ");
Console.WriteLine("Press 6 for ActivationSoftMax ");
Console.WriteLine("Press 7 for ActivationTanh ");
Console.WriteLine("Press 8 for default ");
int whichActivation = int.Parse(Console.ReadLine());
Console.WriteLine("Please the bias for this layer : 1 for True and 0 for false "); // Bias input
int whichBias = int.Parse(Console.ReadLine());
Console.WriteLine("Please the enter the neuron count for this layer"); // Neuron count input
int countNeuron = int.Parse(Console.ReadLine());
switch (whichActivation) // building the network
{
case 1: network.AddLayer(new BasicLayer(new ActivationBiPolar(), Convert.ToBoolean(whichBias), countNeuron));
break;
case 2: network.AddLayer(new BasicLayer(new ActivationCompetitive(), Convert.ToBoolean(whichBias), countNeuron));
break;
case 3: network.AddLayer(new BasicLayer(new ActivationLinear(), Convert.ToBoolean(whichBias), countNeuron));
break;
case 4: network.AddLayer(new BasicLayer(new ActivationLOG(), Convert.ToBoolean(whichBias), countNeuron));
break;
case 5: network.AddLayer(new BasicLayer(new ActivationSigmoid(), Convert.ToBoolean(whichBias), countNeuron));
break;
case 6: network.AddLayer(new BasicLayer(new ActivationSoftMax(), Convert.ToBoolean(whichBias), countNeuron));
break;
case 7: network.AddLayer(new BasicLayer(new ActivationTANH(), Convert.ToBoolean(whichBias), countNeuron));
break;
case 8: network.AddLayer(new BasicLayer(null, Convert.ToBoolean(whichBias), countNeuron));
break;
default:
Console.WriteLine("Wrong data entered - Application will stop ");
break;
}
}
network.Structure.FinalizeStructure(); //complete the newtork settings
network.Reset();
Console.WriteLine("Please enter the learning rate "); // learning rate input
learningRate = double.Parse(Console.ReadLine());
Console.WriteLine("Please enter the momentum value"); // Momentum input
UMomentum = double.Parse(Console.ReadLine());
Console.WriteLine("Please the enter the number of epochs "); // epoch input
epoch = int.Parse(Console.ReadLine());
// For Regression we do this piece of code
if (whatToperform == 1)
{
var sourceFile = new FileInfo(@"C:\Users\smandia\Desktop\Attachments_20161015\regression_train.csv"); //fetch training file
var targetFile = new FileInfo(@"C:\Users\smandia\Desktop\Attachments_20161015\Attachments_20161029\Result\khicharNormClassificationTrainData.csv"); //save train normalized file
var sourceFileTest = new FileInfo(@"C:\Users\smandia\Desktop\Attachments_20161015\regression_train.csv"); //fetch testing file
var targetFileTest = new FileInfo(@"C:\Users\smandia\Desktop\Attachments_20161015\Attachments_20161029\Result\khicharNormClassificationTestData.csv"); //Save test normalized file
//Analyst
var analyst = new EncogAnalyst();
//Wizard
var wizard = new AnalystWizard(analyst);
wizard.TargetFieldName = "y"; //set the output variable for regression . it is not necessary when using mutliple attributes
wizard.Wizard(sourceFile, true, AnalystFileFormat.DecpntComma);
//norm for Training
var norm = new AnalystNormalizeCSV();
norm.Analyze(sourceFile, true, CSVFormat.English, analyst);
norm.ProduceOutputHeaders = true;
norm.Normalize(targetFile);
//norm for testing
norm.Analyze(sourceFileTest, true, CSVFormat.English, analyst);
norm.Normalize(targetFileTest);
analyst.Save(new FileInfo("stt.ega"));
var trainingset1 = EncogUtility.LoadCSV2Memory(targetFile.ToString(), network.InputCount, network.OutputCount, true, CSVFormat.English, false);
var train = new Backpropagation(network, trainingset1);
int epo = 1;
do
{
train.Iteration();
Console.WriteLine(@"Epoch #" + epo + @" Error:" + train.Error);
epo++;
if (epo > epoch)
{
break;
}
} while (train.Error > 0.05);
var evaluationSet = EncogUtility.LoadCSV2Memory(targetFileTest.ToString(), network.InputCount, network.OutputCount, true, CSVFormat.English, false);
List <Tuple <double, double> > inputExcel = new List <Tuple <double, double> >();
foreach (var item in evaluationSet)
{
var output = network.Compute(item.Input);
inputExcel.Add(new Tuple <double, double>(item.Input[0], output[0]));
}
PlotRegressionTest(inputExcel);
Console.WriteLine("----------------Execution over - check the Regression output excel ------------------------------------");
Console.ReadKey();
EncogFramework.Instance.Shutdown();
}
//End of Regression
// For classification we do this piece of code
if (whatToperform == 2)
{
// fetch train file
var sourceFile = new FileInfo(@"C:\Users\smandia\Desktop\Attachments_20161015\Attachments_20161029\data.circles.test.1000.csv");
var targetFile = new FileInfo(@"C:\Users\smandia\Desktop\Attachments_20161015\Attachments_20161029\result\khicharNormClassificationTrainData.csv");
///fetch test file
var sourceFileTest = new FileInfo(@"C:\Users\smandia\Desktop\Attachments_20161015\Attachments_20161029\data.circles.test.1000.csv");
var targetFileTest = new FileInfo(@"C:\Users\smandia\Desktop\Attachments_20161015\Attachments_20161029\result\khicharNormClassificationTestData.csv");
//Analyst
var analyst = new EncogAnalyst();
//Wizard
var wizard = new AnalystWizard(analyst);
wizard.Wizard(sourceFile, true, AnalystFileFormat.DecpntComma);
//norm for Training
var norm = new AnalystNormalizeCSV();
norm.Analyze(sourceFile, true, CSVFormat.English, analyst);
norm.ProduceOutputHeaders = true;
norm.Normalize(targetFile);
//norm for testing
norm.Analyze(sourceFileTest, true, CSVFormat.English, analyst);
norm.Normalize(targetFileTest);
analyst.Save(new FileInfo("stt.ega"));
var trainingset1 = EncogUtility.LoadCSV2Memory(targetFile.ToString(), network.InputCount, network.OutputCount, true, CSVFormat.English, false);
var train = new Backpropagation(network, trainingset1);
int epo = 1;
do
{
train.Iteration();
Console.WriteLine(@"Epoch #" + epo + @" Error:" + train.Error);
epo++;
if (epo > epoch)
{
break;
}
} while (train.Error > 0.05);
var evaluationSet = EncogUtility.LoadCSV2Memory(targetFileTest.ToString(), network.InputCount, network.OutputCount, true, CSVFormat.English, false);
int count = 0;
int CorrectCount = 0;
List <Tuple <double, double, double> > inputExcel = new List <Tuple <double, double, double> >();
foreach (var item in evaluationSet)
{
count++;
var output = network.Compute(item.Input);
// int classCount = analyst.Script.Normalize.NormalizedFields[4].Classes.Count;
int classCount = analyst.Script.Normalize.NormalizedFields[2].Classes.Count;
double normalizationHigh = analyst.Script.Normalize.NormalizedFields[2].NormalizedHigh;
double normalizationLow = analyst.Script.Normalize.NormalizedFields[2].NormalizedLow;
var eq = new Encog.MathUtil.Equilateral(classCount, normalizationHigh, normalizationLow);
var predictedClassInt = eq.Decode(output);
var predictedClass = analyst.Script.Normalize.NormalizedFields[2].Classes[predictedClassInt].Name;
var idealClassInt = eq.Decode(item.Ideal);
var idealClass = analyst.Script.Normalize.NormalizedFields[2].Classes[idealClassInt].Name;
if (predictedClassInt == idealClassInt)
{
CorrectCount++;
}
inputExcel.Add(new Tuple <double, double, double>(item.Input[0], item.Input[1], Convert.ToDouble(predictedClass)));
}
Console.WriteLine("Total Test Count : {0}", count);
Console.WriteLine("Total Correct Prediction Count : {0}", CorrectCount);
Console.WriteLine("% Success : {0}", ((CorrectCount * 100.0) / count));
PlotClassificationTest(inputExcel);
Console.WriteLine("----------------Execution over - check the Classification output excel ------------------------------------");
Console.ReadKey();
EncogFramework.Instance.Shutdown();
} //End of classification
}
/// <summary>
/// Create normalised traning, testing files with encoh analist file
/// </summary>
/// <param name="baseFile"></param>
/// <param name="trainingFile"></param>
/// <param name="testingFile"></param>
/// <param name="normalisedTrainingFile"></param>
/// <param name="normalisedTestingFile"></param>
/// <param name="analystFile"></param>
public void Normalise(FileInfo baseFile, FileInfo trainingFile, FileInfo testingFile, FileInfo normalisedTrainingFile, FileInfo normalisedTestingFile, FileInfo analystFile)
{
try
{
//Analyst
var analyst = new EncogAnalyst();
//Wizard
var wizard = new AnalystWizard(analyst);
wizard.Wizard(baseFile, true, AnalystFileFormat.DecpntComma);
// inputs
// 1 - fixed acidity
analyst.Script.Normalize.NormalizedFields[0].Action = NormalizationAction.Normalize; // contniues
// 2 - volatile acidity
analyst.Script.Normalize.NormalizedFields[1].Action = NormalizationAction.Normalize; // contniues
// 3 - citric acid
analyst.Script.Normalize.NormalizedFields[2].Action = NormalizationAction.Normalize; // contniues
// 4 - residual sugar
analyst.Script.Normalize.NormalizedFields[3].Action = NormalizationAction.Normalize; // contniues
// 5 - chlorides
analyst.Script.Normalize.NormalizedFields[4].Action = NormalizationAction.Normalize; // contniues
// 6 - free sulfur dioxide
analyst.Script.Normalize.NormalizedFields[5].Action = NormalizationAction.Normalize; // discrete
// 7 - total sulfur dioxide
analyst.Script.Normalize.NormalizedFields[6].Action = NormalizationAction.Normalize; // discrete
// 8 - density
analyst.Script.Normalize.NormalizedFields[7].Action = NormalizationAction.Normalize; // contniues
// 9 - pH
analyst.Script.Normalize.NormalizedFields[8].Action = NormalizationAction.Normalize; // contniues
// 10 - sulphates
analyst.Script.Normalize.NormalizedFields[9].Action = NormalizationAction.Normalize; // contniues
// 11 - alcohol
analyst.Script.Normalize.NormalizedFields[10].Action = NormalizationAction.Normalize; // contniues
// output
// 12 - quality
analyst.Script.Normalize.NormalizedFields[11].Action = NormalizationAction.Equilateral; // discrete
//Norm for Trainng
var norm = new AnalystNormalizeCSV
{
ProduceOutputHeaders = true
};
norm.Analyze(trainingFile, true, CSVFormat.English, analyst);
norm.Normalize(normalisedTrainingFile);
//Norm of evaluation
norm.Analyze(Config.TestingFile, true, CSVFormat.English, analyst);
norm.Normalize(normalisedTestingFile);
//save the analyst file
analyst.Save(analystFile);
}
catch (Exception e)
{
Console.WriteLine(e);
throw;
}
}
private void WizardCommand()
{
String targetCSVFile = _cmd.Args[0];
String egaFile = FileUtil.ForceExtension(targetCSVFile, "ega");
var analyst = new EncogAnalyst();
var wizard = new AnalystWizard(analyst);
bool headers = _cmd.PromptBoolean("headers", true);
AnalystFileFormat format =
ConvertStringConst.String2AnalystFileFormat(_cmd.PromptString("format", "decpnt|comma"));
String goal = _cmd.PromptString("goal", "c").ToLower().Trim();
if (goal.Equals("c"))
{
wizard.Goal = AnalystGoal.Classification;
}
else if (goal.Equals("r"))
{
wizard.Goal = AnalystGoal.Regression;
}
else
{
Console.WriteLine(@"Invalid goal: " + goal);
return;
}
wizard.TargetFieldName = _cmd.PromptString("targetField", "");
String m = _cmd.PromptString("method", "ff").ToLower();
if (m.Equals("ff"))
{
wizard.MethodType = WizardMethodType.FeedForward;
}
else if (m.Equals("neat"))
{
wizard.MethodType = WizardMethodType.NEAT;
}
else if (m.Equals("pnn"))
{
wizard.MethodType = WizardMethodType.PNN;
}
else if (m.Equals("rbf"))
{
wizard.MethodType = WizardMethodType.RBF;
}
else if (m.Equals("som"))
{
wizard.MethodType = WizardMethodType.SOM;
}
else if (m.Equals("svm"))
{
wizard.MethodType = WizardMethodType.SVM;
}
else
{
Console.WriteLine(@"Invalid method: " + m);
return;
}
String r = _cmd.PromptString("range", "-1t1").Trim().ToLower();
if (r.Equals("-1t1"))
{
wizard.Range = NormalizeRange.NegOne2One;
}
else if (r.Equals("0t1"))
{
wizard.Range = NormalizeRange.Zero2One;
}
wizard.Missing = TranslateMissing(_cmd.PromptString("missing", "DiscardMissing"));
wizard.LagWindowSize = _cmd.PromptInteger("lagWindow", 0);
wizard.LeadWindowSize = _cmd.PromptInteger("leadWindow", 0);
wizard.IncludeTargetField = _cmd.PromptBoolean("includeTarget", false);
wizard.TaskNormalize = _cmd.PromptBoolean("normalize", true);
wizard.TaskRandomize = _cmd.PromptBoolean("randomize", true);
wizard.TaskSegregate = _cmd.PromptBoolean("segregate", true);
wizard.TaskBalance = _cmd.PromptBoolean("balance", false);
wizard.TaskCluster = _cmd.PromptBoolean("cluster", false);
_sw.Start();
Console.WriteLine(@"Analyzing data");
wizard.Wizard(new FileInfo(targetCSVFile), headers, format);
Console.WriteLine(@"Saving analyst file");
analyst.Save(egaFile);
}
/// <summary> need comments </summary>
public static List <string> Normalise(FileInfo sourceFile, FileInfo normalFile, string path, string dataFile, int outputs, bool inputs)
{
List <string> titles = new List <string>();
//Setup analyst with orignal csv.
var analyst = new EncogAnalyst();
var wizard = new AnalystWizard(analyst);
//Additional validation to check that the file is not empty.
try
{
wizard.Wizard(sourceFile, true, AnalystFileFormat.DecpntComma);
}
catch (Exception)
{
MessageBox.Show("The file you have selected is empty.", "File Access Error");
return(null);
}
if (analyst.Script.Fields.Length - 1 < outputs)
{
MessageBox.Show("You have specified " + outputs + " outputs but there are only " + analyst.Script.Fields.Length + " headings in the file.", "Too Many Outputs Error");
return(null);
}
//Setup max and min range for normalization.
foreach (AnalystField field in analyst.Script.Normalize.NormalizedFields)
{
field.NormalizedHigh = 1;
field.NormalizedLow = -1;
//field.Action = Encog.Util.Arrayutil.NormalizationAction.OneOf; //Use this to change normalizaiton type.
}
analyst.Script.Normalize.MissingValues = new NegateMissing();
//Normalization.
var norm = new AnalystNormalizeCSV();
norm.Analyze(sourceFile, true, CSVFormat.English, analyst);
norm.ProduceOutputHeaders = true;
try
{
norm.Normalize(normalFile);
}
catch (Exception ex)
{
MessageBox.Show(ex.Message + "\n\nUnknown application failure, please report this bug with a screenshot of" +
" the message to the relevant engineer.", "Normalisation Failure");
return(null);
}
if (!inputs)
{
for (int i = outputs; i + analyst.Script.Fields.Length > analyst.Script.Fields.Length; i--)
{
titles.Add(analyst.Script.Fields[analyst.Script.Fields.Length - i].Name);
}
}
else
{
for (int i = 0; i < analyst.Script.Fields.Length - outputs; i++)
{
titles.Add(analyst.Script.Fields[i].Name);
}
}
//Save configuration to be used later.
analyst.Save(new FileInfo(path + @"\normal\" + "normalizationData" + dataFile.Replace(".csv", ".ega")));
return(titles);
}
