FcEchoStateANN: Forecasting with Echo state ANN

In Mthrun/TSAT: Time Series Analysis Tools (TSAT)

Forecasting with Echo state ANN

Description

Forecast Echo state ANN

Usage

FcEchoStateANN(Datavector, Percentage = 90, 

Forecasthorizon = 1, Seasonality = 28, Scaled = TRUE,

Time, PlotIt = FALSE, ...)

Arguments

Datavector	[1:n] numerical vector of regular (equidistant) time series data.
SplitAt	Index of row where the DataVec is divided into test and train data. If not given n is used
Forecasthorizon	Number of time steps to forecast into the future
Seasonality	Main saisonality of data, is used for generating batches of data
Scaled	TRUE: automatic scaling
Time	[1:n] character vector of Time in the length of data. Time should be equidistant.
PlotIt	FALSE (default), do nothing. TRUE: plots the forecast versus the validation set.
...	Further arguments for train_esn

Details

Requires internally also tsibble

Value

List of

Model	ANN model generated by echos
FitStats	Output of forecast_esn in [echos]
Forecast	Forecast generated by the ANN model where we put in the last portion of the training set of length forecast_length as data to predict from. The test data stays untouched.
TestData	[(k+1):n], the part of Response not used in the model
TestTime	[(k+1):n], time of response not used in the model
TrainData	[1:k], the part of Response used in the model
TrainTime	[1:k], time of Training data if given
TrainingForecast	[1:k], forecasted value using TrainData

Note

devtools::install_github("ahaeusser/echos",dependencies = T)

Author(s)

Michael Thrun

References

Jaeger H. (2003): Adaptive nonlinear system identification with echo state networks. In Advances in Neural Information Processing Systems 15, S. Becker, S. Thrun, K. Obermayer (Eds), (MIT Press, Cambridge, MA, 2003) pp. 593-600

See Also

train_esn

Examples

if(requireNamespace('ggfortify')){
library(ggfortify)
x=fortify(datasets::sunspot.month)
#Example for a bad forecast
results=FcEchoStateANN(DataVec = x$Data,Time = x$Index,Seasonality=12)
}

Mthrun/TSAT documentation built on Feb. 5, 2024, 11:15 p.m.