Clustering Azimuths: Algorithm & Link

  • Context: Undergrad 
  • Thread starter Thread starter billiards
  • Start date Start date
Click For Summary

Discussion Overview

The discussion revolves around the problem of clustering a set of azimuths, particularly addressing the challenge of treating the circular nature of azimuths where values near 0 and 360 are considered close. Participants seek algorithms or methods suitable for this specific clustering task.

Discussion Character

  • Exploratory, Technical explanation, Debate/contested

Main Points Raised

  • One participant presents a set of azimuths and asks for clustering methods that account for the circular nature of the data.
  • Another participant suggests that algorithms exist for clustering on a one-dimensional torus and proposes transforming the azimuths into a two-dimensional circular representation using sine and cosine functions.
  • A further inquiry is made about the best clustering algorithm to use, with a preference for one that can determine the optimal number of clusters from the data, specifically in the context of using Python.
  • One participant expresses uncertainty and does not provide additional input.

Areas of Agreement / Disagreement

Participants have not reached a consensus on a specific clustering algorithm or method, and multiple approaches are suggested without agreement on their effectiveness.

billiards
Messages
765
Reaction score
16
Hi all,

If I have a set of azimuths, e.g. [ 0, 10, 11, 67, 68, 69, 70, 124, 127, 136, 355].

How can I cluster these directions bearing in mind that 355 is close to 0?

Can someone point me to a link, preferably with an algorithm I can use.

Cheers
 
Physics news on Phys.org
I'm sure there are algorithms for clustering on a (1-dimensional) torus. A quick google search pointed me to this.
If you don't find one, this hack might work: transform your one-dimensional distribution to a circle in 2 dimensions: x -> (sin x, cos x), and look for clusters there.
 
Nice idea to use sinx, cosx.

Any idea what the best clustering algorithm to use would be? Ideally I want something that can figure out the optimum number of clusters itself from the data.

(Incidentally I am trying to do this using python -- so any python specific help would be particularly appreciated)
 
No idea, sorry.
 

Similar threads

  • · Replies 4 ·
Replies
4
Views
2K
  • · Replies 18 ·
Replies
18
Views
15K
  • · Replies 1 ·
Replies
1
Views
2K
  • · Replies 41 ·
2
Replies
41
Views
6K
  • · Replies 3 ·
Replies
3
Views
1K
  • · Replies 3 ·
Replies
3
Views
2K
  • · Replies 36 ·
2
Replies
36
Views
4K
  • · Replies 5 ·
Replies
5
Views
4K
  • · Replies 2 ·
Replies
2
Views
2K
Replies
29
Views
6K