https://github.com/upphiminn/jLouvain
Louvain community detection for Javascript (http://arxiv.org/abs/0803.0476) (http://en.wikipedia.org/wiki/Community_structure#The_Louvain_method).
https://github.com/upphiminn/jLouvain
Last synced: 8 months ago
JSON representation
Louvain community detection for Javascript (http://arxiv.org/abs/0803.0476) (http://en.wikipedia.org/wiki/Community_structure#The_Louvain_method).
- Host: GitHub
- URL: https://github.com/upphiminn/jLouvain
- Owner: upphiminn
- License: mit
- Created: 2013-09-04T15:40:59.000Z (over 12 years ago)
- Default Branch: master
- Last Pushed: 2021-07-29T20:08:12.000Z (over 4 years ago)
- Last Synced: 2024-03-27T10:21:47.833Z (almost 2 years ago)
- Language: JavaScript
- Homepage:
- Size: 103 KB
- Stars: 146
- Watchers: 10
- Forks: 51
- Open Issues: 9
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-network-analysis - jLouvain - Louvain community detection for Javascript ([example](http://bl.ocks.org/emeeks/125db75c9b55ddcbdeb5)). (Software / JavaScript)
- awesome-network-analysis - jLouvain - Louvain community detection for Javascript ([example](http://bl.ocks.org/emeeks/125db75c9b55ddcbdeb5)). (Software / JavaScript)
- awesome-community-detection - [Javascript
README
# jLouvain
## Description
Formally, a community detection aims to partition a graph’s vertices in subsets, such that there are many edges connecting between vertices of the same sub-set compared to vertices of different sub-sets; in essence, a community has many more ties between each constituent part than with outsiders. There are numerous algorithms present in the literature for solving this problem, a complete survey can be found in [1].
One of the popular community detection algorithms is presented in [2]. This algorithm separates the network in communities by optimizing greedily a modularity score after trying various grouping operations on the network. By using this simple greedy approach the algorithm is computationally very efficient.
[1] Fortunato, Santo. "Community detection in graphs." Physics Reports 486, no. 3-5 (2010).
[2] V.D. Blondel, J.-L. Guillaume, R. Lambiotte, E. Lefebvre. "Fast unfolding of communities in large networks." J. Stat. Mech., 2008: 1008.
## Usage
### 1. Import the script.
```html
```
### 2. Sample Data Format
#### Node Data
```javascript
let node_data = ['id1', 'id2', 'id3']; // any type of string can be used as id
```
#### Edge Data
```javascript
let edge_data = [
{ source: 'id1', target: 'id2', weight: 10.0 },
{ source: 'id2', target: 'id3', weight: 20.0 },
{ source: 'id3', target: 'id1', weight: 30.0 }
];
```
#### (Optional) Partition Data
```javascript
let init_part = { id1: 0, id2: 0, id3: 1 };
// Object with ids of nodes as properties and community number assigned as value.
```
### 3. Run the algorithm
3. Run the Algorithm on your node and edge set by chaining the **nodes** and **edges** methods, optionally you can provide an intermediary community partition assignement with the **partition_init** method. [ **Order of chaining is important** ]
```javascript
let community = jLouvain()
.nodes(node_data)
.edges(edge_data)
.partition_init(init_part);
let result = community();
```
## Example
See **example.html**, use the console to view the raw input data and raw output.
Initial input graph for community detection.
#### After Community Detection
We can see the partitioned graph vertices with the help of color coding.
