embedding spatial cross sectional data

Usage

# S4 method for class 'sf'
embedded(
  data,
  target,
  E = 3,
  tau = 1,
  style = 1,
  stack = FALSE,
  detrend = FALSE,
  nb = NULL
)

# S4 method for class 'SpatRaster'
embedded(
  data,
  target,
  E = 3,
  tau = 1,
  style = 1,
  stack = FALSE,
  detrend = FALSE,
  grid.coord = TRUE,
  embed.direction = 0
)

Arguments

data: observation data.
target: name of target variable.
E: (optional) embedding dimensions.
tau: (optional) step of spatial lags.
style: (optional) embedding style (0 includes current state, 1 excludes it).
stack: (optional) whether to stack embeddings.
detrend: (optional) whether to remove the linear trend.
nb: (optional) neighbours list.
grid.coord: (optional) whether to detrend using cell center coordinates (TRUE) or row/column numbers (FALSE).
embed.direction: (optional) direction selector for embeddings (0 returns all directions, 1-8 correspond to NW, N, NE, W, E, SW, S, SE).

Value

A matrix (when stack is FALSE) or list.

Examples

columbus = sf::read_sf(system.file("case/columbus.gpkg", package="spEDM"))
v = embedded(columbus,"crime")
v[1:5,]
#>          [,1]     [,2]     [,3]
#> [1,] 24.71427 41.55964 43.45135
#> [2,] 26.24684 44.57868 40.73529
#> [3,] 29.41175 43.45135 37.55683
#> [4,] 34.64648 37.95647 38.69064
#> [5,] 40.46533 34.43484 42.28334

cu = terra::rast(system.file("case/cu.tif", package="spEDM"))
r = embedded(cu,"cu")
r[1:5,]
#>          [,1]     [,2]     [,3]
#> [1,] 14.13616 13.86900 13.60871
#> [2,] 14.09866 13.59174 13.77765
#> [3,] 13.57425 13.91658 14.02535
#> [4,] 13.61885 13.81650 14.26563
#> [5,] 13.82547 13.76455 14.03200