Search found 124 matches
- 15 Jan 2012 20:48
- Forum: Layouts
- Topic: Force Atlas squares off
- Replies: 12
- Views: 13690
Re: Force Atlas squares off
I've tested the FA2 with graphs of 50k-200k nodes and 100k-2M edges. It's nice that FA2 is very fast with Barnes-Hut optimization (Approximate repulsion). Hey! how long did it take you to process such amount of data and get a nice result visually? I let FA2 run for several hours or occasionally ove...
- 21 Dec 2011 18:35
- Forum: Statistics, Clustering & Data Lab
- Topic: [SOLVED] Modularity is varying between different runs
- Replies: 1
- Views: 2857
[SOLVED] Modularity is varying between different runs
Computing the modularity statistic is varying maybe too much between different runs. Here are two images to clarify the differences (7600 nodes, 164000 edges): http://i.imgur.com/zI3q1.png - Modularity: 0.477, 18 communities http://i.imgur.com/JAhOp.png - Modularity: 0.445, 17 communities Time to co...
- 21 Dec 2011 18:03
- Forum: Statistics, Clustering & Data Lab
- Topic: [SOLVED] Modularity using weights in fully connected graph?
- Replies: 1
- Views: 6665
Re: Modularity/clusters using weights in fully connected gra
You can use Gephi's "Modularity" statistic to find communities in the graph. Each node gets assigned a module class. You can then assign colors to nodes by using "Modularity Class" as the ranking method for color. This is good visual cue to group communities. Then run one of the layout algorithms. F...
- 21 Dec 2011 17:25
- Forum: Layouts
- Topic: Force Atlas squares off
- Replies: 12
- Views: 13690
Re: Force Atlas squares off
I had this same problem with Force Atlas 2 on Gephi 0.8 alpha. The latest Force Atlas 2 in Gephi 0.8 beta has "stronger gravity" setting. Enabling stronger gravity and lowering gravity to a low value (eg. 0.001) provided good results for me. With the previous version of FA2 it was quite impossible t...