recipe__clique_analysis.py

# -*- coding: utf-8 -*-

import sys
import json
import networkx as nx

G = sys.argv[1]

g = nx.read_gpickle(G)

# Finding cliques is a hard problem, so this could
# take a while for large graphs.
# See http://en.wikipedia.org/wiki/NP-complete and 
# http://en.wikipedia.org/wiki/Clique_problem

cliques = [c for c in nx.find_cliques(g)]

num_cliques = len(cliques)

clique_sizes = [len(c) for c in cliques]
max_clique_size = max(clique_sizes)
avg_clique_size = sum(clique_sizes) / num_cliques

max_cliques = [c for c in cliques if len(c) == max_clique_size]

num_max_cliques = len(max_cliques)

max_clique_sets = [set(c) for c in max_cliques]
people_in_every_max_clique = list(reduce(lambda x, y: x.intersection(y),
                                  max_clique_sets))

print 'Num cliques:', num_cliques
print 'Avg clique size:', avg_clique_size
print 'Max clique size:', max_clique_size
print 'Num max cliques:', num_max_cliques
print
print 'People in all max cliques:'
print json.dumps(people_in_every_max_clique, indent=4)
print
print 'Max cliques:'
print json.dumps(max_cliques, indent=4)