gdverse (version 1.5.1)

cpsd_disc: optimal spatial data discretization based on SPADE q-statistics

Description

Function for determining the optimal spatial data discretization based on SPADE q-statistics.

Usage

cpsd_disc(
  formula,
  data,
  wt,
  discnum = 3:8,
  discmethod = "quantile",
  strategy = 2L,
  increase_rate = 0.05,
  cores = 1,
  seed = 123456789,
  ...
)

Value

A list.

x

discretization variable name

k

optimal number of spatial data discreteization

method

optimal spatial data discretization method

disc

the result of optimal spatial data discretization

Arguments

formula

A formula of optimal spatial data discretization.

data

A data.frame, tibble or sf object of observation data.

wt

The spatial weight matrix.

discnum

(optional) A vector of number of classes for discretization. Default is 3:8.

discmethod

(optional) The discretization methods. Default all use quantile. Noted that rpart will use rpart_disc(); Others use sdsfun::discretize_vector().

strategy

(optional) Discretization strategy. When strategy is 1L, choose the highest SPADE model q-statistics to determinate optimal spatial data discretization parameters. When strategy is 2L, The optimal discrete parameters of spatial data are selected by combining LOESS model.

increase_rate

(optional) The critical increase rate of the number of discretization. Default is 5%.

cores

(optional) Positive integer (default is 1). When cores are greater than 1, use multi-core parallel computing.

seed

(optional) Random seed number, default is 123456789.

...

(optional) Other arguments passed to sdsfun::discretize_vector() or rpart_disc().

Author

Wenbo Lv

References

Yongze Song & Peng Wu (2021) An interactive detector for spatial associations, International Journal of Geographical Information Science, 35:8, 1676-1701, DOI:10.1080/13658816.2021.1882680

Examples

data('sim')
wt = sdsfun::inverse_distance_swm(sf::st_as_sf(sim,coords = c('lo','la')))
cpsd_disc(y ~ xa + xb + xc, data = sim, wt = wt)