smap forecast

Usage

# S4 method for class 'sf'
smap(
  data,
  column,
  target,
  lib = NULL,
  pred = NULL,
  E = 3,
  tau = 1,
  k = E + 2,
  theta = c(0, 1e-04, 3e-04, 0.001, 0.003, 0.01, 0.03, 0.1, 0.3, 0.5, 0.75, 1, 1.5, 2, 3,
    4, 6, 8),
  nb = NULL,
  threads = detectThreads(),
  detrend = TRUE
)

# S4 method for class 'SpatRaster'
smap(
  data,
  column,
  target,
  lib = NULL,
  pred = NULL,
  E = 3,
  tau = 1,
  k = E + 2,
  theta = c(0, 1e-04, 3e-04, 0.001, 0.003, 0.01, 0.03, 0.1, 0.3, 0.5, 0.75, 1, 1.5, 2, 3,
    4, 6, 8),
  threads = detectThreads(),
  detrend = TRUE
)

Arguments

data: observation data.
column: name of library variable.
target: name of target variable.
lib: (optional) libraries indices.
pred: (optional) predictions indices.
E: (optional) embedding dimensions.
tau: (optional) step of spatial lags.
k: (optional) number of nearest neighbors used.
theta: (optional) weighting parameter for distances.
nb: (optional) neighbours list.
threads: (optional) number of threads to use.
detrend: (optional) whether to remove the linear trend.

Value

A list

xmap: forecast performance
varname: name of target variable
method: method of cross mapping

References

Sugihara G. 1994. Nonlinear forecasting for the classification of natural time series. Philosophical Transactions: Physical Sciences and Engineering, 348 (1688):477-495.

Examples

columbus = sf::read_sf(system.file("case/columbus.gpkg", package="spEDM"))
# \donttest{
smap(columbus,"inc","crime",E = 5,k = 6)
#> The suggested theta for variable crime is 4 
# }