cdlib.algorithms.dpclus

dpclus(g_original: object, weights: str = None, d_threshold: float = 0.9, cp_threshold: float = 0.5, overlap: bool = True) → cdlib.classes.node_clustering.NodeClustering

DPClus projects weights onto an unweighted graph using a common neighbors approach. In DPClus, the weight of an edge (u, v) is defined as the number of common neighbors between u and v. Similarly, the weight of a vertex is its weighted degree – the sum of all edges connected to the vertex-

DPClus does not natively generate overlapping clusters but does allow for overlapping cluster nodes to be added in a post-processing step.

Supported Graph Types

Undirected Directed Weighted
Yes No Yes
Parameters:
  • g_original – a networkx/igraph object
  • weights – label used for the edge weights. Default, None.
  • d_threshold – cluster density threshold, default 0.9
  • cp_threshold – cluster property threshold, default 0.5
  • overlap – wheter to output overlapping or crisp communities. Default, True.
Returns:

NodeClustering object
Example: 
>>> from cdlib import algorithms
>>> import networkx as nx
>>> G = nx.karate_club_graph()
>>> coms = algorithms.dpclus(G)
References:

Altaf-Ul-Amin, M., Shinbo, Y., Mihara, K., Kurokawa, K., Kanaya, S. 2006. Development and implementation of an algorithm for detection of protein complexes in large interaction networks. BMC Bioinformatics 7, 207.

Note

Reference Implementation: https://github.com/trueprice/python-graph-clustering