The toolkit collects many academic graph clustering programs and make them avaliable as package. Docker image is provided for easy access.
Use docker is convenient as
docker pull lizhen0909/graph_clustering_toolkit
For more information, please refer to online document for a full description
Start python from docker:
docker run -it --rm lizhen0909/graph_clustering_toolkit python
Run the script from the command line:
import gct
from gct.dataset import random_dataset
#create a random graph use LFR generator
ds=random_dataset.generate_undirected_unweighted_random_graph_LFR(name="random_graph", \
N=128, k=16, maxk=32, mu=0.2, minc=32)
# run pScan graph algorithm
pscan_clustering=gct.scan_pScan("get_start_pscan", ds)See more to visit online usage.
Please cite Comparison and Benchmark of Graph Clustering Algorithms for this work.
For individual algorithms, see Algorithms for their publications.