def mcl_cluster(vs, es):
g = nx.Graph()
for i in range(len(vs)):
g.add_node(i)
for n0, n1 in es:
g.add_edge(n0, n1)
M, clusters = networkx_mcl(g)
locations = []
for _, cluster in clusters.items():
locations.append(set(cluster))
return locations
def mcl_cluster(G):
t0 = time.time()
M, cluster = networkx_mcl(G,
expand_factor=2,
inflate_factor=2,
max_loop=10,
mult_factor=1)
t1 = time.time() - t
print t1
print type(M), type(cluster)
f1 = open('mcl_m.txt', 'w')
f1.write(M)
f1.close()
f2 = open('mcl_cluster.txt', 'w')
f2.write(json.dumps(cluster))
f2.close()
begin = time.time()
# graph = readDataToGraph("interactions.tsv")
originalGraph = sampleData("interactions.tsv", 1000)
graph = originalGraph
print "ORIGINAL GRAPH:"
# print "finished extracting interactions"
displayGraphStats(graph)
# print "displayed graph stats"
end = time.time()
print "Graph Creation Time:", end - begin
print ""
begin = time.time()
# nodes in cluster are identified by the same number as they were given
M, clusters = networkx_mcl(graph, inflate_factor=1.8, max_loop=60)
# print "finished clustering algorithm"
clusters = convertClustersOfNodeIDsToClustersOfGeneIdentifiers(graph, clusters)
clusters = removeDuplicateClusters(clusters)
displayClusterStats(clusters)
# print "displayed cluster stats"
end = time.time()
print "Clustering Time:", end - begin
print ""
begin = time.time()
pathways = readPathwayData("pathways.tsv")
# print "finished extracting pathways"
displayPathwayStats(pathways)
# print "displayed pathway stats"
G.add_edge(1,2)
G.add_edge(1,3)
G.add_edge(1,4)
G.add_edge(3,4)
G.add_edge(2,3)
G.add_edge(2,0)
G.add_edge(2,5)
G.add_edge(0,8)
G.add_edge(0,6)
G.add_edge(5,8)
G.add_edge(4,5)
G.add_edge(5,6)
G.add_edge(8,6)
G.add_edge(5,9)
G.add_edge(6,7)
G.add_edge(5,7)
G.add_edge(6,9)
G.add_edge(7,9)
M, clusters = networkx_mcl(G, inflate_factor = 1.8,
max_loop = 100)
print clusters
print nx.get_node_attributes(G, "num")
#nx.draw_networkx(G)
#plt.show()
# M = output matrix
# clusters = dict with keys = [<cluster id>] values = [<vertex id>]
M.append(l)
G = nx.from_numpy_matrix(np.matrix(M))
M = np.array(M)
from mcl_clustering import get_graph, networkx_mcl, draw
#M, G = get_graph("example.csv")
print(" number of nodes: %s\n" % M.shape[0])
M, clusters = networkx_mcl(G)
draw(G, M, clusters)
if not marked[e[0]]:
location.add(e[0])
marked[e[0]] = True
locations.append(location)
return locations
if __name__ == '__main__':
user = '******'
records = load_loc_records(user)
print('Loaded %d records' % len(records))
raw_g = create_raw_graph(user, records, False)
loc_g = create_loc_graph(user, records, False)
raw_M, raw_clusters = networkx_mcl(
raw_g,
)
print("Raw clusters", len(raw_clusters))
print("Clusters:")
t = 0
for k, v in raw_clusters.items():
t += len(v)
print(k, len(v))
print(t)
def get_mcl_communities(G):
M, clusters = networkx_mcl(G, max_loop=100)
node_map = convert_to_node_comm_map(clusters)
return node_map
