DBSCAN clusters of incidents

Density-based clusters (Ester, Kriegel, Sander and Xu 1996): a core point has at least minpts points within distance eps, itself included; core points within eps of each other share a cluster, and a point that is not core but lies within eps of a core point (a border point) joins the first cluster that reaches it, clusters being grown from the core points in input order. The rest is noise. With border = FALSE border points are noise too (DBSCAN*, Campello, Moulavi and Sander 2013), which makes the result independent of the order. These are the clusters of dbscan::dbscan(), numbered the same way.

Usage

dbscn(x, y = NULL, eps, minpts = 5, border = TRUE, lonlat = FALSE)

Arguments

x, y

The points: x and y numeric vectors of equal length; or x a matrix or data frame with columns named x and y (or X and Y, as sf::st_coordinates() names them, or lon and lat with lonlat = TRUE) and y NULL; or x an sf or sfc object of POINT geometries, whose coordinate reference system must agree with lonlat. An unnamed two-column matrix is read as x then y; other columns are never taken by position. Vectors given separately (x, y, and w or t where a function takes them) are matched by name when every one is named and no name repeats, as elsewhere in the package; otherwise by position. No missing or infinite values.

eps

The neighbourhood radius: positive, in the unit of the coordinates (metres when lonlat = TRUE).

minpts

The fewest points (the point itself included) within eps of a core point: a whole number from 1.

border

TRUE to put border points in clusters.

lonlat

FALSE (the default) when x and y are planar coordinates in one length unit; TRUE when they are longitude and latitude in degrees, which are then projected to metres by eqproj() about their own centre, and centres are returned in degrees. It is never guessed.

Value

A list of class dbscn: cl (each point's cluster from 1, NA for noise), core (whether each point is a core point) and sizes (the points in each cluster).

References

Ester, M., Kriegel, H.-P., Sander, J. and Xu, X. (1996). A density-based algorithm for discovering clusters in large spatial databases with noise. Proceedings of the Second International Conference on Knowledge Discovery and Data Mining, 226-231.

Campello, R. J. G. B., Moulavi, D. and Sander, J. (2013). Density-based clustering based on hierarchical density estimates. Advances in Knowledge Discovery and Data Mining, 160-172. doi:10.1007/978-3-642-37456-2_14

Examples

set.seed(1)
p <- rbind(cbind(x = rnorm(30, 0, 0.2), y = rnorm(30, 0, 0.2)),
           cbind(x = rnorm(30, 3, 0.2), y = rnorm(30, 1, 0.2)),
           cbind(x = runif(10, -2, 5), y = runif(10, -2, 3)))
d <- dbscn(p, eps = 0.3, minpts = 5)
d
#> dbscn: 2 clusters of 70 points, 10 noise
#>  cluster points
#>        1     30
#>        2     30
table(d$cl, useNA = "ifany")
#> 
#>    1    2 <NA> 
#>   30   30   10