The hardware and bandwidth for this mirror is donated by METANET, the Webhosting and Full Service-Cloud Provider.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]metanet.ch.

NVAR: Nonlinear Vector Autoregression Models

R-CMD-check CRAN status

Estimate nonlinear vector autoregression models (also known as the next generation reservoir computing) for nonlinear dynamic systems. The algorithm was described by Gauthier et al. (2021) doi:10.1038/s41467-021-25801-2.

Installation

You can install the development version of NVAR from GitHub with:

# install.packages("devtools")
devtools::install_github("Sciurus365/NVAR")

Example

This is an example for the Lorenz model.

library(NVAR)

testdata <- nonlinearTseries::lorenz()
testdata <- tibble::as_tibble(testdata)
t1 <- NVAR(data = testdata, vars = c("x", "y", "z"), s = 2, k = 2, p = 2, alpha = 1e-3)
t1_sim <- sim_NVAR(t1, length = 5000)


realdata <- nonlinearTseries::lorenz(time = seq(0, 100, by = .01)) %>% tibble::as_tibble()

library(ggplot2)
ggplot(realdata) +
  geom_line(aes(x = 1:10001, y = x), color = "red", alpha = 0.4) +
  geom_line(aes(x = 1:10001, y = x), data = t1_sim, color = "blue", alpha = 0.4) +
  geom_vline(xintercept = 5000) +
  theme_bw() +
  xlim(c(4900, 8000)) +
  labs(x = "time", y = "x")


# Red line: real data.
# Blue line: simulated data with the NVAR.
# Black vertical line: when the simulation starts.

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.