C# Class Encog.Util.Simple.EncogUtility

ファイルを表示 Open project: encog/encog-silverlight-core Class Usage Examples

Public Methods

Method	Description
CalculateClassificationError ( IMLClassification method, IMLDataSet data ) : double	Calculate an error for a method that makes use of classification.
CalculateRegressionError ( IMLRegression method, IMLDataSet data ) : double	Calculate a regression error.
ConvertCSV2Binary ( FileInfo csvFile, CSVFormat format, FileInfo binFile, int input, int ideal, bool headers ) : void	Convert a CSV file to binary.
ConvertCSV2Binary ( String csvFile, CSVFormat format, String binFile, int inputCount, int outputCount, bool headers, bool expectSignificance ) : void	Convert a CSV file to a binary training file.
Evaluate ( IMLRegression network, IMLDataSet training ) : void	Evaluate the network and display (to the console) the output for every value in the training set. Displays ideal and actual.
LoadCSV2Memory ( String filename, int input, int ideal, bool headers, CSVFormat format, bool expectSignificance ) : IMLDataSet	Load CSV to memory.
LoadEGB2Memory ( FileInfo filename ) : IMLDataSet	Load an EGB file to memory.
SaveCSV ( FileInfo targetFile, CSVFormat format, IMLDataSet set ) : void	Save the dataset to a CSV file.
SaveEGB ( FileInfo egbFile, IMLDataSet data ) : void	Save the training set to an EGB file.
SimpleFeedForward ( int input, int hidden1, int hidden2, int output, bool tanh ) : BasicNetwork	Create a simple feedforward neural network.
TrainConsole ( BasicNetwork network, IMLDataSet trainingSet, int minutes ) : void	Train the neural network, using SCG training, and output status to the console.
TrainConsole ( IMLTrain train, BasicNetwork network, IMLDataSet trainingSet, int minutes ) : void	Train the network, using the specified training algorithm, and send the output to the console.
TrainDialog ( BasicNetwork network, IMLDataSet trainingSet ) : void	Train using RPROP and display progress to a dialog box.
TrainDialog ( IMLTrain train, BasicNetwork network, IMLDataSet trainingSet ) : void	Train, using the specified training method, display progress to a dialog box.
TrainToError ( BasicNetwork network, IMLDataSet trainingSet, double error ) : void	Train the network, to a specific error, send the output to the console.
TrainToError ( IMLTrain train, IMLDataSet trainingSet, double error ) : void	Train to a specific error, using the specified training method, send the output to the console.
TrainToError ( IMLTrain train, double error ) : void	Train to a specific error, using the specified training method, send the output to the console.

Private Methods

Method	Description
EncogUtility ( ) : System	Private constructor.
FormatNeuralData ( IMLData data ) : String	Format neural data as a list of numbers.

Method Details

CalculateClassificationError() public static method

Calculate an error for a method that makes use of classification.

public static CalculateClassificationError ( IMLClassification method, IMLDataSet data ) : double
method	IMLClassification	The method to check.
data	IMLDataSet	The data to check.
return	double

CalculateRegressionError() public static method

Calculate a regression error.

public static CalculateRegressionError ( IMLRegression method, IMLDataSet data ) : double
method	IMLRegression	The method to check.
data	IMLDataSet	The data to check.
return	double

ConvertCSV2Binary() public static method

Convert a CSV file to binary.

public static ConvertCSV2Binary ( FileInfo csvFile, CSVFormat format, FileInfo binFile, int input, int ideal, bool headers ) : void
csvFile	System.IO.FileInfo	The CSV file to convert.
format	Encog.Util.CSV.CSVFormat	The format.
binFile	System.IO.FileInfo	The binary file.
input	int	The input.
ideal	int	The ideal.
headers	bool	True, if headers are present.
return	void

ConvertCSV2Binary() public static method

Convert a CSV file to a binary training file.

public static ConvertCSV2Binary ( String csvFile, CSVFormat format, String binFile, int inputCount, int outputCount, bool headers, bool expectSignificance ) : void
csvFile	String	The CSV file.
format	Encog.Util.CSV.CSVFormat	The format.
binFile	String	The binary file.
inputCount	int	The number of input values.
outputCount	int	The number of output values.
headers	bool	True, if there are headers on the3 CSV.
expectSignificance	bool	Should a significance column be expected.
return	void

Evaluate() public static method

Evaluate the network and display (to the console) the output for every value in the training set. Displays ideal and actual.

public static Evaluate ( IMLRegression network, IMLDataSet training ) : void
network	IMLRegression	The network to evaluate.
training	IMLDataSet	The training set to evaluate.
return	void

LoadCSV2Memory() public static method

Load CSV to memory.

public static LoadCSV2Memory ( String filename, int input, int ideal, bool headers, CSVFormat format, bool expectSignificance ) : IMLDataSet
filename	String	The CSV file to load.
input	int	The input count.
ideal	int	The ideal count.
headers	bool	True, if headers are present.
format	Encog.Util.CSV.CSVFormat	The loaded dataset.
expectSignificance	bool	The loaded dataset.
return	IMLDataSet

LoadEGB2Memory() public static method

Load an EGB file to memory.

public static LoadEGB2Memory ( FileInfo filename ) : IMLDataSet
filename	System.IO.FileInfo	The file to load.
return	IMLDataSet

SaveCSV() public static method

Save the dataset to a CSV file.

public static SaveCSV ( FileInfo targetFile, CSVFormat format, IMLDataSet set ) : void
targetFile	System.IO.FileInfo	The target file.
format	Encog.Util.CSV.CSVFormat	The format to use.
set	IMLDataSet	The data set.
return	void

SaveEGB() public static method

Save the training set to an EGB file.

public static SaveEGB ( FileInfo egbFile, IMLDataSet data ) : void
egbFile	System.IO.FileInfo	The EGB file to save to.
data	IMLDataSet	The training data to save.
return	void

SimpleFeedForward() public static method

Create a simple feedforward neural network.

public static SimpleFeedForward ( int input, int hidden1, int hidden2, int output, bool tanh ) : BasicNetwork
input	int	The number of input neurons.
hidden1	int	The number of hidden layer 1 neurons.
hidden2	int	The number of hidden layer 2 neurons.
output	int	The number of output neurons.
tanh	bool	True to use hyperbolic tangent activation function, false to /// use the sigmoid activation function.
return	Encog.Neural.Networks.BasicNetwork

TrainConsole() public static method

Train the neural network, using SCG training, and output status to the console.

public static TrainConsole ( BasicNetwork network, IMLDataSet trainingSet, int minutes ) : void
network	Encog.Neural.Networks.BasicNetwork	The network to train.
trainingSet	IMLDataSet	The training set.
minutes	int	The number of minutes to train for.
return	void

TrainConsole() public static method

Train the network, using the specified training algorithm, and send the output to the console.

public static TrainConsole ( IMLTrain train, BasicNetwork network, IMLDataSet trainingSet, int minutes ) : void
train	IMLTrain	The training method to use.
network	Encog.Neural.Networks.BasicNetwork	The network to train.
trainingSet	IMLDataSet	The training set.
minutes	int	The number of minutes to train for.
return	void

TrainDialog() public static method

Train using RPROP and display progress to a dialog box.

public static TrainDialog ( BasicNetwork network, IMLDataSet trainingSet ) : void
network	Encog.Neural.Networks.BasicNetwork	The network to train.
trainingSet	IMLDataSet	The training set to use.
return	void

TrainDialog() public static method

Train, using the specified training method, display progress to a dialog box.

public static TrainDialog ( IMLTrain train, BasicNetwork network, IMLDataSet trainingSet ) : void
train	IMLTrain	The training method to use.
network	Encog.Neural.Networks.BasicNetwork	The network to train.
trainingSet	IMLDataSet	The training set to use.
return	void

TrainToError() public static method

Train the network, to a specific error, send the output to the console.

public static TrainToError ( BasicNetwork network, IMLDataSet trainingSet, double error ) : void
network	Encog.Neural.Networks.BasicNetwork	The network to train.
trainingSet	IMLDataSet	The training set to use.
error	double	The error level to train to.
return	void

TrainToError() public static method

Train to a specific error, using the specified training method, send the output to the console.

public static TrainToError ( IMLTrain train, IMLDataSet trainingSet, double error ) : void
train	IMLTrain	The training method.
trainingSet	IMLDataSet	The training set to use.
error	double	The desired error level.
return	void

TrainToError() public static method

Train to a specific error, using the specified training method, send the output to the console.

public static TrainToError ( IMLTrain train, double error ) : void
train	IMLTrain	The training method.
error	double	The desired error level.
return	void