Click or drag to resize
Accord.NET (logo)

TimeSeriesPredictionFitness Constructor

Initializes a new instance of the TimeSeriesPredictionFitness class.

Namespace:  Accord.Genetic
Assembly:  Accord.Genetic (in Accord.Genetic.dll) Version: 3.7.0
Syntax
public TimeSeriesPredictionFitness(
	double[] data,
	int windowSize,
	int predictionSize,
	double[] constants
)
Request Example View Source

Parameters

data
Type: SystemDouble
Time series to be predicted.
windowSize
Type: SystemInt32
Window size - number of past samples used to predict future value.
predictionSize
Type: SystemInt32
Prediction size - number of values to be predicted. These values are excluded from training set.
constants
Type: SystemDouble
Array of constants to be used as additional paramters for genetic expression.
Remarks

The data parameter is a one dimensional array, which defines times series to predict. The amount of learning samples is equal to the number of samples in the provided time series, minus window size, minus prediction size.

The predictionSize parameter specifies the amount of samples, which should be excluded from training set. This set of samples may be used for future verification of the prediction model.

The constants parameter is an array of constants, which can be used as additional variables for a genetic expression. The actual amount of variables for genetic expression equals to the amount of constants plus the window size.

See Also