The goal of comat is to create co-occurrence matrices based on spatial data, including a weighted co-occurrence matrix (wecoma) and an integrated co-occurrence matrix (incoma).
You can install the released version of comat from CRAN with:
You can install the development version from GitHub with:
This is a basic example which shows you how to create a weighted co-occurrence matrix (wecoma) based on two simple rasters (for simplicity presented as matrices). The first one raster_x represents some categories, and the second one raster_w represents weights.
library(comat)
library(raster)
#> Loading required package: sp
data(raster_x, package = "comat")
data(raster_w, package = "comat")
raster_x
#> [,1] [,2] [,3]
#> [1,] 1 1 3
#> [2,] 1 3 3
#> [3,] 2 2 3
raster_w
#> [,1] [,2] [,3]
#> [1,] 2 2 9
#> [2,] 6 4 9
#> [3,] 4 8 9The get_wecoma() function can be next used to create a weighted co-occurrence matrix.
get_wecoma(
raster_x,
raster_w,
neighbourhood = 4
)
#> 1 2 3
#> 1 12.0 5.0 13.5
#> 2 5.0 12.0 14.5
#> 3 13.5 14.5 49.0This function allows for some parametrization using additional arguments, e.g.:
get_wecoma(
raster_x,
raster_w,
neighbourhood = 4,
fun = "focal",
na_action = "keep"
)
#> 1 2 3
#> 1 12 6 10
#> 2 4 12 16
#> 3 17 13 49For more examples see the package’s vignettes:
Contributions to this package are welcome. The preferred method of contribution is through a GitHub pull request. Feel free to contact me by creating an issue.
To cite the comat package in publications, please use this paper:
Nowosad J, Stepinski TF (2021) Pattern-based identification and mapping of landscape types using multi-thematic data, International Journal of Geographical Information Science, DOI: 10.1080/13658816.2021.1893324
LaTeX/BibTeX version can be obtained with:
library(comat)
citation("comat")