[prev in list] [next in list] [prev in thread] [next in thread] 

List:       r-sig-geo
Subject:    [R-sig-Geo]  random points
From:       adrian () maths ! uwa ! edu ! au
Date:       2008-02-27 1:10:42
Message-ID: 3460.130.116.32.101.1204074642.squirrel () 130 ! 116 ! 32 ! 101
[Download RAW message or body]

Rodrigo W. Soria Auza <wilbersa@armonia-bo.org> writes:

> I'm trying to generate a surface of 'random points' over a defined area.
> By 'randon points' I mean points that are not closer than one km each
> other. I used runifpoints (from spatstat). however, this function
> generates strictly random points, with some of them much closer than I
> expected.

In the spatstat package you have several options:

     rstrat: divides the region into squares and places one random point
             in each square (or k random points)

     rsyst:  makes a square grid of points and gives it a random displacement

     rSSI:  places points at random, one-at-a-time,
            each new point being constrained to lie at least r units away
            from the previously existing points

     rStrauss (with gamma=0): places points at random subject to the
            condition that no two points lie closer than r units apart

If you need something more complicated that that, you could try the
package 'spsample'



Adrian Baddeley

_______________________________________________
R-sig-Geo mailing list
R-sig-Geo@stat.math.ethz.ch
https://stat.ethz.ch/mailman/listinfo/r-sig-geo
[prev in list] [next in list] [prev in thread] [next in thread]