Timeline for Random selection of points in SpatialPointsDataFrame R object with distance constraint
Current License: CC BY-SA 4.0
10 events
when toggle format | what | by | license | comment | |
---|---|---|---|---|---|
Oct 25, 2018 at 18:32 | vote | accept | Nielson Pasqualotto | ||
Oct 22, 2018 at 21:17 | answer | added | Jeffrey Evans | timeline score: 3 | |
Oct 22, 2018 at 11:23 | history | edited | PolyGeo♦ | CC BY-SA 4.0 |
deleted 26 characters in body
|
Oct 21, 2018 at 17:24 | comment | added | Spacedman |
You have N points, and there are N-choose-N/2 subsets of half the points, M of which satisfy your distance constraint, with 0 < M < (N-choose-N/2) . Do you want to select one of these constraint-satisfying selections with uniform probability over the set of all constraint-satisfying solutions?
|
|
Oct 21, 2018 at 17:19 | comment | added | Spacedman | @JeffreyEvans the last answer (by raff-k) in the linked question uses spatstat::rSSI which is generating sets of points rather than sampling from existing points, unless I've misunderstood the somewhat curly twisty code... | |
Oct 21, 2018 at 15:56 | comment | added | Nielson Pasqualotto | Because the only solution that works for me is the ArcGIS one. @JeffreyEvans , your suggestion for using distance matrix return repeted points and do not set a fixed number of points. How can I solve it? | |
Oct 21, 2018 at 15:07 | comment | added | Jeffrey Evans | Why not use the solution in the post you linked to? The last answer is entirely in R. | |
Oct 21, 2018 at 13:42 | comment | added | Spacedman | You could repeatedly select points at random from your input, and create a 3km buffer zone for each selected point, and remove any input points in that buffer zone from the input points. But you can't guarantee this will not remove all points such that you cant select 50% of the input points. Also, it may or may not complete depending on which points are selected at random. | |
Oct 21, 2018 at 13:15 | review | First posts | |||
Oct 21, 2018 at 16:35 | |||||
Oct 21, 2018 at 13:12 | history | asked | Nielson Pasqualotto | CC BY-SA 4.0 |