使用louvain包的Python模块化统计

Question

我正在尝试批处理运行python的网络至少100次的模块化分区。我需要保存分区并在分区后保存模块化分数。有没有办法获得它们？我已经尝试了文档和示例，它只返回分区但没有模块化统计信息。请指出正确的方向，我将非常感谢你的帮助。

Answer 1

您可以使用igraph.Graph.community()计算模块化分数：

import igraph

g = igraph.Graph.Erdos_Renyi(n=100, p=0.1)
clusters = g.community_multilevel()
modularity_score = g.modularity(clusters.membership)

Answer 2

以下是在Q中使用louvain算法估算模块性igraph的方法。

重要：如果您已加权邻接矩阵，请不要忘记以下函数中的weights=graph.es['weight']参数！

import numpy as np
from igraph import *

W = np.random.rand(10,10)
np.fill_diagonal(W,0.0)

graph = Graph.Weighted_Adjacency(W.tolist(), mode=ADJ_UNDIRECTED, attr="weight", loops=False)

louvain_partition = graph.community_multilevel(weights=graph.es['weight'], return_levels=False)

modularity1 = graph.modularity(louvain_partition, weights=graph.es['weight'])

print("The modularity Q based on igraph is {}".format(modularity1))

The modularity Q based on igraph is 0.02543865641866777