def test_karate_club():
nodes, edges = PyLouvain.from_file("data/karate.txt")
pyl = PyLouvain(nodes, edges)
partition, q = pyl.apply_method(gamma=1.0)
odds = bayes_model_selection(nodes, edges, partition)
print(partition, q, odds)
def test(graphname, gnc=None):
nodes, edges = PyLouvain.from_file("data/%s.txt" % graphname)
pyl = PyLouvain(nodes, edges)
name_pickle = 'fig/save_%s_%d.p' % (graphname, len(nodes))
if not os.path.isfile(name_pickle):
print("pickle file", name_pickle, "is missing. Recompute.")
start = time.time()
partition, q = pyl.apply_method()
print("Modularity Time", time.time() - start)
start = time.time()
partition2 = multiscale(nodes, edges, 0.5)
print("Multiscale Time", time.time() - start)
results = {"LV": partition, "MS": partition2}
sizes_distri = {
"Modularity": [len(p) for p in partition],
"MultiScale": [len(p) for p in partition2]
}
pickle.dump(results, open(name_pickle, 'wb'))
print("Pickle save", name_pickle)
else:
print("pickle file", name_pickle, "is found.")
results = pickle.load(open(name_pickle, "rb"))
sizes_distri = {
"Modularity": [len(p) for p in results["LV"]],
"MultiScale": [len(p) for p in results["MS"]]
}
if gnc:
gnc_fp = open(gnc, "r+")
gnc_map = {}
sizes_distri["Ground Truth"] = []
for i, line in enumerate(gnc_fp):
x = line.split()
sizes_distri["Ground Truth"].append(len(x))
for j in x:
gnc_map[int(j)] = i
gnc_list = [gnc_map[k] for k in nodes]
lv_map = {v: i for i, c in enumerate(partition) for v in c}
lv_list = [lv_map[k] for k in nodes]
ms_map = {v: i for i, c in enumerate(partition2) for v in c}
ms_list = [ms_map[k] for k in nodes]
print("Louvain NMI=", normalized_mutual_info_score(lv_list, gnc_list))
print("Multi-scale NMI=",
normalized_mutual_info_score(ms_list, gnc_list))
hist(sizes_distri, graphname)
def test_small_networks(nodes, edges, gamma0):
pyl = PyLouvain(nodes, edges)
partition0, q0 = pyl.apply_method(gamma0)
c0 = cmap(nodes, partition0)
NMI = []
gamma_list = np.linspace(0.2, 3.5, num=200)
for gamma in gamma_list:
partition, q = PyLouvain(nodes, edges).apply_method(gamma)
c = cmap(nodes, partition)
NMI.append(metrics.normalized_mutual_info_score(c0, c))
plt.plot(gamma_list, NMI, 'b-*', markersize=10)
plt.show()
def test_karate_club(self):
pyl = PyLouvain.from_file("data/karate.txt")
partition, q = pyl.apply_method()
q_ = q * 10000
self.assertEqual(4, len(partition))
self.assertEqual(4298, math.floor(q_))
self.assertEqual(4299, math.ceil(q_))
def test_karate_club(self):
pyl = PyLouvain.from_file("data/karate.txt")
partition, q = pyl.apply_method()
q_ = q * 10000
self.assertEqual(4, len(partition))
self.assertEqual(4298, math.floor(q_))
self.assertEqual(4299, math.ceil(q_))
def findGZCommunity():
dbm = dbManager2('sina11', host='127.0.0.1', passwd='root')
pyl = PyLouvain.from_db(dbm,
"select uid,fid from afrelation11 limit 0,10000")
partition, q = pyl.apply_method()
values = []
j = 0
print partition
f = open("output.txt", "w")
f.write(str(partition))
f.close()
def test_football():
# load GNC ground truth by txt file (as defined by conference)
fconf = open("data/football.gnc.txt", "r")
gnc = {str(i): int(line.strip()) for i, line in enumerate(fconf)}
order_ = {i: stri for i, stri in enumerate(sorted(gnc.keys()))}
x, y, z, r = [], [], [], []
for gamma in np.linspace(0.5, 8.5, num=35):
nodes, edges = PyLouvain.from_file("data/football.txt")
pyl = PyLouvain(nodes, edges)
partition, q = pyl.apply_method(gamma)
odds = bayes_model_selection(nodes, edges, partition)
print(len(partition), odds)
x.append(gamma)
y.append(odds)
z.append(len(partition))
comm = {n: i for i, ns in enumerate(partition) for n in ns}
a = [comm[i] for i in nodes]
b = [gnc[order_[i]] for i in nodes]
#print("NMI=", metrics.adjusted_mutual_info_score(a, b))
r.append(metrics.adjusted_mutual_info_score(a, b))
#r.append(metrics.adjusted_rand_score(a, b))
plt.plot(x, y, 'r-*', markersize=10)
ax1 = plt.gca()
ax1.tick_params(axis='x', labelsize=18)
ax1.tick_params(axis='y', labelcolor='r', labelsize=15)
ax2 = ax1.twinx()
ax2.plot(x, z, 'm-^', markersize=10)
ax2.tick_params(axis='y', labelcolor='m', labelsize=15)
plt.tight_layout()
plt.savefig("fig/football2.png")
def do(path, source_data):
start_time = time.time()
print 'start time: ',start_time
print 'louvain算法社团划分开始...'
pyl = PyLouvain.from_file(path, source_data)
partition, q = pyl.apply_method()
# print partition
out_file = open(path+"community_result.txt", 'w')
#读取节点信息文件
nodes_file = open(path+'nodes_tmp.txt', 'r')
nodes_lines = nodes_file.readlines()
nodes_file.close()
nodes = {} #保存 节点序号-节点名称 信息
for line in nodes_lines:
n = line.split()
if not n:
break
nodes[n[1]] = n[0]
#社团信息 格式：标记 成员数
print '统计社团信息 写入社团状态文件'
community_status = open(path+'community_status.txt', 'w')
i = 1
label = {} # 格式 节点名称-社团标记
for community in partition:
community_status.write(str(i)+'\t'+str(len(community))+'\n') #社团标记 成员数
#成员贴上社团标记
for per in community:
label[nodes[str(per)]] = str(i)
i += 1
community_status.close()
#关联用户互动
print '关联用户互动数据 写入结果文件'
relationship_file = open(path+source_data, 'r')
relationship_lines = relationship_file.readlines()
relationship_file.close()
for rela in relationship_lines:
r = rela.split()
if not r:
break
out_file.write('-\t'+r[0]+'\t'+label[r[0]]+'\t'+r[1]+'\t'+label[r[1]]+'\t'+r[2]+'\n')
out_file.close()
print 'end time: ',time.time()
print '花费时间: ',(time.time()-start_time)/60,' min'
def test_football2():
for gamma in np.linspace(0.4, 0.9, num=10):
print()
print("gamma=", gamma)
nodes, edges = PyLouvain.from_file("data/football.txt")
partition = multiscale(nodes, edges, gamma)
# load GNC ground truth by txt file (as defined by conference)
fconf = open("data/football.gnc.txt", "r")
gnc = {str(i): int(line.strip()) for i, line in enumerate(fconf)}
order_ = {i: stri for i, stri in enumerate(sorted(gnc.keys()))}
comm = {n: i for i, ns in enumerate(partition) for n in ns}
a = [comm[i] for i in nodes]
b = [gnc[order_[i]] for i in nodes]
print("NMI=", metrics.adjusted_mutual_info_score(a, b))
#test_football2()
def test_citations(self):
pyl = PyLouvain.from_file("data/hep-th-citations")
partition, q = pyl.apply_method()
def test_lesmis(self):
pyl = PyLouvain.from_gml_file("data/lesmis.gml")
partition, q = pyl.apply_method()
def test_arxiv(self):
pyl = PyLouvain.from_file("data/facebook_combined.txt", 0.5)
partition, q = pyl.apply_method()
print(len(partition), q)
def test_arxiv(self):
pyl = PyLouvain.from_file("data/arxiv.txt")
partition, q = pyl.apply_method()
def test_citations():
nodes, edges = PyLouvain.from_file("data/hep-th-citations")
pyl = PyLouvain(nodes, edges)
partition, q = pyl.apply_method()
print(partition, q)
def main():
if not has_pyimpfuzzy:
sys.exit("[!] pyimpfuzzy must be installed for this script.")
if not has_py2neo:
sys.exit("[!] py2neo must be installed for this script.")
if not has_pylouvain and not args.nocluster:
sys.exit("[!] Please download the pylouvain from https://github.com/patapizza/pylouvain.")
try:
graph_http = "http://" + NEO4J_USER + ":" + NEO4J_PASSWORD +"@:" + NEO4J_PORT + "/db/data/"
GRAPH = Graph(graph_http)
except:
sys.exit("[!] Can't connect Neo4j Database.")
if len(sys.argv) == 1:
parser.print_help()
sys.exit()
i= 0
hashlist = []
hashlist_new = []
nodes = []
edges = []
relationships = []
# This is a impfuzzys threshold
if args.threshold:
ss_threshold = args.threshold
else:
ss_threshold = 30
print("[*] Impfuzzy threshold is %i." % ss_threshold)
# Delete database data
if args.delete:
GRAPH.delete_all()
print("[*] Delete all nodes and relationships from this Neo4j database.")
# Load database data
database = GRAPH.data("MATCH (m:Malware) RETURN m.id, m.name, m.impfuzzy, m.md5, m.sha1, m.sha256")
if database:
print("[*] Database nodes %d." % len(database))
for d in database:
hashlist.append([d["m.id"], d["m.name"], d["m.impfuzzy"], d["m.md5"], d["m.sha1"], d["m.sha256"]])
nodes_count = len(database)
# Load relationships
relation_data = GRAPH.data("MATCH (m1:Malware)-[s:same]-(m2:Malware) RETURN m1.id,m2.id,s.value")
if relation_data:
print("[*] Database relationships %d." % len(relation_data))
for r in relation_data:
relationships.append([r["m1.id"], r["m2.id"], r["s.value"]])
for x in range(nodes_count):
nodes.append(x)
print("[*] Creating a graph data.")
# Import data from EXE or DLL
if args.file:
if os.path.isfile(args.file):
i = nodes_count
impfuzzy, md5, sha1, sha256 = get_digest(args.file)
query = "MATCH (m:Malware) WHERE m.sha256=\"%s\" RETURN m" % sha256
if impfuzzy:
if not GRAPH.data(query):
nodes.append(i)
hashlist_new.append([i, args.file, impfuzzy, md5, sha1, sha256])
else:
print("[!] This malware is registered already. sha256: %s" % sha256)
else:
print("[!] Can't calculate the impfuzzy hash. sha256: %s" % sha256)
else:
sys.exit("[!] Can't open file {0}.".format(args.file))
# Import data from directory
if args.directory:
try:
files = os.listdir(args.directory)
except OSError:
sys.exit("[!] Can't open directory {0}.".format(args.directory))
outf = args.directory + "_hash.csv"
fl = open(outf, "w")
i = nodes_count
for file in files:
filename = args.directory + "/" + file
impfuzzy, md5, sha1, sha256 = get_digest(filename)
fl.write("%s,%s,%s,%s,%s\n" % (file, impfuzzy, md5, sha1, sha256))
query = "MATCH (m:Malware) WHERE m.sha256=\"%s\" RETURN m" % sha256
if impfuzzy:
if not GRAPH.data(query) and sha256 not in [x[5] for x in hashlist_new]:
nodes.append(i)
hashlist_new.append([i, file, impfuzzy, md5, sha1, sha256])
i += 1
else:
print("[!] This malware is registered already. sha256: %s" % sha256)
else:
print("[!] Can't calculate the impfuzzy hash. sha256: %s" % sha256)
print("[*] Created hash list %s." % outf)
fl.close()
# Import data from csv file
if args.listname:
print("[*] Parse file %s." % args.listname)
try:
csvfile = csv.reader(open(args.listname), delimiter=",")
except IOError:
sys.exit("[!] Can't open file {0}.".format(args.listname))
i = nodes_count
for array in csvfile:
query = "MATCH (m:Malware) WHERE m.sha256=\"%s\" RETURN m" % array[4]
if array[1]:
if not GRAPH.data(query):
nodes.append(i)
array.insert(0, i)
hashlist_new.append(array)
i += 1
else:
print("[!] This malware is registered already. sha256: %s" % array[4])
else:
print("[!] Impfuzzy hash is blank. sha256: %s" % array[4])
# Compare impfuzzy
print("[*] The total number of malware is %i." % i)
result_list = impfuzzy_comp(hashlist, hashlist_new)
if len(database) != len(nodes):
# Clustering
if not args.nocluster:
for edge in result_list + relationships:
if edge[2] > ss_threshold:
edges.append([[edge[0], edge[1]], edge[2]])
else:
edges.append([[edge[0], edge[1]], 0])
pyl = PyLouvain(nodes, edges)
partition, modularity = pyl.apply_method()
print("[*] The number of clusters is %i." % (len(partition) - 1))
else:
print("[*] No clustering option.")
# Create node
tx = GRAPH.begin()
if args.nocluster:
for hash in hashlist_new:
tx.append(statement_c, {"id": hash[0], "name": hash[1], "impfuzzy": hash[2],
"md5": hash[3], "sha1": hash[4], "sha256": hash[5],
"cluster": "NULL"})
else:
for hash in hashlist_new + hashlist:
i=0
for a in partition:
i=i+1
if hash[0] in a:
tx.append(statement_c, {"id": hash[0], "name": hash[1], "impfuzzy": hash[2],
"md5": hash[3], "sha1": hash[4], "sha256": hash[5],
"cluster": i})
# Create relationship
for result in result_list:
if result[2] > ss_threshold:
tx.append(statement_r, {"id1": result[0], "id2": result[1], "value": result[2]})
tx.process()
tx.commit()
print("[*] Created a graph data.\n")
else:
print("[*] Not find a new malware.\n")
print(" Access to http://localhost:7474 via Web browser.")
print(" Use Cypher query. You can see the graph.\n")
print(" == Cypher Query Examples ==")
print(" [Visualizing the all clusters]")
print(" $ MATCH (m:Malware) RETURN m\n")
print(" [Visualizing the clusters that matches the MD5 hash]")
print(" $ MATCH (m1:Malware)-[s]-() WHERE m1.md5 = \"[MD5]\"")
print(" MATCH (m2:Malware) WHERE m2.cluster = m1.cluster")
print(" RETURN m2\n")
print(" [Visualizing the clusters that matches the threshold more than 90]")
print(" $ MATCH (m:Malware)-[s:same]-() WHERE s.value > 90 RETURN m,s")
print(" ===========================\n")
from pylouvain import PyLouvain
import math
from matplotlib import pyplot as plt
import networkx as nx
filepath = 'out.txt'
# 获取社区划分
pyl = PyLouvain.from_file(filepath)
node_dict = pyl.node_dict # key是253916-2的形式，value是编号的形式
reverse_node_dict = dict(zip(node_dict.values(),
node_dict.keys())) # key是编号的形式，value是253916-2的形式
partition, q = pyl.apply_method()
print(partition)
print("模块度：", q)
# 给各个社区节点分配颜色
community_num = len(partition)
print('community_num:', community_num)
color_board = ['red', 'green', 'blue', 'pink', 'orange', 'purple', 'scarlet']
color = {}
for index in range(community_num):
print("社区" + str(index + 1) + ":" + str(len(partition[index])))
for node_id in partition[index]:
color[node_id] = color_board[
index] # color为一个字典，key为编号形式的节点，value为所属社区的颜色
new_color_dict = sorted(color.items(), key=lambda d: d[0],
reverse=False) # 将color字典按照key的大小排序，并返回一个list
node_list = [reverse_node_dict[item[0]]
for item in new_color_dict] #存储编号从小到大顺序对应的253916-2的形式的节点
color_list = [item[1] for item in new_color_dict] #存储node_list中对应的节点颜色
def test_test(self):
pyl = PyLouvain.from_file("data/year1990.txt")
partition, q = pyl.apply_method()
return partition
def test_citations(self):
pyl = PyLouvain.from_file("data/hep-th-citations")
partition, q = pyl.apply_method()
def test_arxiv(self):
pyl = PyLouvain.from_file("data/arxiv.txt")
partition, q = pyl.apply_method()
import matplotlib
from matplotlib import pyplot as plt
from sklearn import metrics
from pylouvain import PyLouvain
from sklearn import metrics
import numpy as np
nodes, edges = PyLouvain.from_file("data/karate.txt")
gamma0 = 0.78
#nodes, edges = PyLouvain.from_gml_file("data/lesmis.gml")
#nodes, edges = PyLouvain.from_gml_file("data/polbooks.gml")
def cmap(nodes, partition):
m = {n: i for i, _ in enumerate(partition) for n in _}
return [m[i] for i in nodes]
def test_small_networks(nodes, edges, gamma0):
pyl = PyLouvain(nodes, edges)
partition0, q0 = pyl.apply_method(gamma0)
c0 = cmap(nodes, partition0)
NMI = []
gamma_list = np.linspace(0.2, 3.5, num=200)
for gamma in gamma_list:
partition, q = PyLouvain(nodes, edges).apply_method(gamma)
c = cmap(nodes, partition)
NMI.append(metrics.normalized_mutual_info_score(c0, c))
def test_polbooks():
nodes, edges = PyLouvain.from_gml_file("data/polbooks.gml")
pyl = PyLouvain(nodes, edges)
partition, q = pyl.apply_method()
print(partition, q)
import matplotlib
matplotlib.use("Agg")
from matplotlib import pyplot as plt
import pickle
import time
import numpy as np
from sklearn import metrics
from pylouvain import PyLouvain
from run import multiscale, bayes_model_selection
x, y, z = [], [], []
for gamma in np.linspace(0.2, 0.9, num=20):
print("gamma=", gamma)
pyl = PyLouvain.from_file("data/football.txt")
partition = multiscale(pyl.nodes, pyl.edges, gamma)
# load GNC ground truth by txt file (as defined by conference)
fconf = open("data/football.gnc.txt", "r")
gnc = {str(i): int(line.strip()) for i, line in enumerate(fconf)}
order_ = {i: stri for i, stri in enumerate(sorted(gnc.keys()))}
comm = {n: i for i, ns in enumerate(partition) for n in ns}
a = [comm[i] for i in pyl.nodes]
b = [gnc[order_[i]] for i in pyl.nodes]
x.append(gamma)
y.append(len(partition))
z.append(metrics.adjusted_mutual_info_score(a, b))
print("#comm=", len(partition), "NMI=",
metrics.adjusted_mutual_info_score(a, b))
def test_lesmis(self):
pyl = PyLouvain.from_gml_file("data/lesmis.gml")
partition, q = pyl.apply_method()
def process(self):
hashlist = []
hashlist_new = []
nodes = []
edges = []
relationships = []
# recover all actual data
database = self.graph.run(
"MATCH (m:Malware) RETURN m.id, m.name, m.impfuzzy, m.scout_result, m.scout_confidence, m.md5, m.sha1, m.sha256, m.tag"
).data()
if database:
for d in database:
hashlist.append([
d["m.id"], d["m.name"], d["m.impfuzzy"],
d["m.scout_result"], d["m.scout_confidence"], d["m.md5"],
d["m.sha1"], d["m.sha256"], d["m.tag"]
])
nodes_count = len(database)
i = nodes_count
relation_data = self.graph.run(
"MATCH (m1:Malware)-[s:same]-(m2:Malware) RETURN m1.id, m2.id, s.value"
).data()
if relation_data:
for r in relation_data:
relationships.append([r["m1.id"], r["m2.id"], r["s.value"]])
for x in range(nodes_count):
nodes.append(x)
# if massive check for each file
if self.folder_path:
for item in self.files:
scout_result, impfuzzy, md5, sha1, sha256, scout_confidence = self.get_digest(
item[0])
if scout_result in ("", 'A171', None):
continue
query = "MATCH (m:Malware) WHERE m.sha256=\"%s\" RETURN m" % sha256
objs = self.graph.run(query).data()
if not objs and sha256 not in [x[5] for x in hashlist_new]:
nodes.append(i)
hashlist_new.append([
i, item[0].split("/")[-1], impfuzzy, scout_result,
scout_confidence, md5, sha1, sha256, item[1]
])
i += 1
else:
continue
else:
# if single we are in the reporting module
# if file is tested it need to have valid apiscout vector
if self.check_file(self.filepath):
scout_result, impfuzzy, md5, sha1, sha256, scout_confidence = self.get_digest(
self.filepath)
if scout_result in ("", 'A171', None):
return {}
else:
return {}
query = "MATCH (m:Malware) WHERE m.sha256=\"%s\" RETURN m" % sha256
objs = self.graph.run(query).data()
if not objs:
nodes.append(nodes_count)
hashlist_new.append([
nodes_count, self.filename, impfuzzy, scout_result,
scout_confidence, md5, sha1, sha256, None
])
else:
return self.search_hash(sha256)
# Calculate apiscout correlation
result_list = self.scout_comp(hashlist, hashlist_new)
if len(database) != len(nodes):
for edge in result_list + relationships:
if edge[2] > self.threshold:
edges.append([[edge[0], edge[1]], edge[2]])
else:
edges.append([[edge[0], edge[1]], 0])
pyl = PyLouvain(nodes, edges)
partition, modularity = pyl.apply_method()
# Create node
tx = self.graph.begin()
for hash in hashlist_new + hashlist:
i = 0
for a in partition:
i += 1
if hash[0] in a:
tx.append(
statement_c, {
"id": hash[0],
"name": hash[1],
"impfuzzy": hash[2],
"scout_result": hash[3],
"scout_confidence": hash[4],
"md5": hash[5],
"sha1": hash[6],
"sha256": hash[7],
"tag": hash[8],
"cluster": i
})
# Create relationship
for result in result_list:
if result[2] > self.threshold:
tx.append(statement_r, {
"id1": result[0],
"id2": result[1],
"value_scout": result[2]
})
tx.process()
tx.commit()
# recover info
if self.filename:
return self.search_hash(sha256)
def test_polbooks(self):
pyl = PyLouvain.from_gml_file("data/polbooks.gml")
partition, q = pyl.apply_method()
def test_polbooks(self):
pyl = PyLouvain.from_gml_file("data/polbooks.gml")
partition, q = pyl.apply_method()
def multiscale(nodes,
edges,
gamma,
deg=None,
depth=1,
verbose=False,
max_depth=4):
'''
Multi-scale community detection.
Recursively split sub-graph by maximizing generalized modularity.
Terminate at each level of recursion by bayes model selection.
Args:
nodes: a list of nodes
edges: a list of edges ((src, dst), weight)
gamma: the resolution parameter for the generalized modularity
Return:
a list of lists, each contains the nodes in a community
'''
if depth >= max_depth or len(nodes) < 2:
return [nodes]
verbose and print(" " * depth, "***", "depth=", depth, "N=", len(nodes))
nodes.sort()
d = {n: i for i, n in enumerate(nodes)}
rd = {i: n for n, i in d.items()}
nodes = list(range(len(d)))
edges = [((d[e[0][0]], d[e[0][1]]), e[1]) for e in edges]
if deg is None:
deg = {i: 0 for i in nodes}
for e in edges:
deg[e[0][0]] += e[1]
deg[e[0][1]] += e[1]
pyl = PyLouvain(nodes, edges, deg)
# execution
partition, q = pyl.apply_method(gamma)
verbose and print(" " * depth, "gamma=", gamma, "comm=", len(partition))
if len(partition) < 2: return [list(map(rd.get, nodes))]
odds = bayes_model_selection(pyl.nodes, pyl.edges, partition)
verbose and print(" " * depth, "odds=", odds)
if odds <= 1. or math.isnan(odds): return [list(map(rd.get, nodes))]
comm = {n: i for i, ns in enumerate(partition) for n in ns}
edge_list = [[] for _ in range(len(partition))]
for e in edges:
u, v = e[0][0], e[0][1]
if comm[u] == comm[v]:
edge_list[comm[u]].append(e)
R = []
for nodes_, edges_ in zip(partition, edge_list):
groups = multiscale(nodes_, edges_, gamma, deg, depth + 1, verbose,
max_depth)
for grp in groups:
R.append([rd[n] for n in grp])
return R
end = time.time()
commsFG_sizes = sorted([len(commsFG[i]) for i in range(len(commsFG))])
verbose and print(commsFG_sizes)
map_comm = {v:i for i, c in enumerate(commsFG) for v in c}
a = [map_comm[k] for k in G.nodes()]
print("FastGreedy Algorithm ARI=", adjusted_rand_score(a, gnc_list), "NMI=", normalized_mutual_info_score(a, gnc_list))
print("which takes", end - start, "seconds")
'''
#=========== Benchmark Louvain ===============#
print("Start Louvain community detection")
start = time.time()
pyl = PyLouvain(nodes, edges)
commsLV, q = pyl.apply_method(1.0)
end = time.time()
commsLV_sizes = sorted([len(commsLV[i]) for i in range(len(commsLV))])
verbose and print(commsLV_sizes)
verbose and print(len(commsLV_sizes))
map_comm = {v: i for i, c in enumerate(commsLV) for v in c}
LV_list = [map_comm[k] for k in G.nodes()]
print("Louvain Algorithm ARI=", adjusted_rand_score(LV_list, gnc_list),
"NMI=", normalized_mutual_info_score(LV_list, gnc_list))
print("which takes", end - start, "seconds")
print("Size range = ", min(commsLV_sizes), max(commsLV_sizes))
print()