def exhaustive_ll(N, nparts, parallel=True):
global ex_ll_graph, ex_ll_nparts, ex_ll_author_prod_map, ex_ll_ref_prt
ex_ll_graph, ex_ll_author_prod_map, cluster_sizes = gen_synthetic_graph(N, nparts)
N = sum(cluster_sizes) # sum of cluster sizes is close to N but does not always match
ex_ll_nparts = nparts
ex_ll_graph, ex_ll_author_prod_map = HardEM._preprocess_graph_and_map(ex_ll_graph, ex_ll_author_prod_map)
# reference partitioning
ex_ll_ref_prt = []
for i in range(len(cluster_sizes)):
ex_ll_ref_prt.extend([i]*cluster_sizes[i])
ex_ll_ref_prt = tuple(ex_ll_ref_prt)
# all possible partitioning of at most `nparts` partitions
partitions = itertools.chain(*[gen_partition(N, nparts_i) for nparts_i in range(1, nparts + 1)])
logging.info('Processing %d partitions' % sum(stirling2(N, nparts_i) for nparts_i in range(1, nparts + 1)))
if parallel:
p = Pool()
v = p.imap(em_ll_map, partitions)
p.close(); p.join()
else:
v = itertools.imap(em_ll_map, partitions)
v = list(v) # since v is a generator, keeps them in a list so reading from it won't consume it
# find the logl for the presumed correct partitioning
ref_ll = 0
for vv in v:
if vv[0] == ex_ll_ref_prt:
ref_ll = vv[1]
break
else:
logging.error('The correct partitioning was not found')
# keep only one from set of permutations with the same loglikelihood
# v_dict = {ll: prt for prt, ll in v}
# v = v_dict.items()
# v.sort(key=lambda tup: tup[0], reverse=True)
# for i in range(0, min(10, len(v))):
# print '#%d\t%s' % (i, v[i])
# print '##\t%s' % ((ref_ll, ex_ll_ref_prt),)
return v, cluster_sizes, ex_ll_graph
