tnetwork.DCD.smoothed_louvain¶

tnetwork.DCD.smoothed_louvain(dynNetSN, match_function=<function jaccard>, threshold=0.3, **kwargs)[source]¶

Community Detection using smoothed louvain

This algorithm is a naive implementation of the method proposed by [1]. The idea is that for each snapshots, the louvain algorithm is ran, but instead of being initialized with each node in its own community as usual, the partition obtained in the previous partition is used.

The label attribution process is the same described in the paper XXX, see method simple_matching for details.

Internally, it calls the simple_matching method, the same parameters can be passed to it.

[1]Aynaud, T., & Guillaume, J. L. (2010, May). Static community detection algorithms for evolving networks. In 8th International symposium on modeling and optimization in mobile, Ad Hoc, and wireless networks (pp. 513-519). IEEE.

Parameters:	dynNetSN – a dynamic network
Returns:	DynCommunitiesSN