def main():
parser = argparse.ArgumentParser()
parser.add_argument('graph')
args = parser.parse_args()
#vertices, edges = read_graph_from_file(args.graph)
G = nx.read_edgelist(args.graph)
n = G.number_of_nodes()
print "nodes:", n
print "edges:", G.number_of_edges()
core_exponent = 0.5
core_vertices = filter(lambda v: G.degree(v) >= n**core_exponent,
G.nodes())
print "core vertices:", len(core_vertices)
core = G.subgraph(core_vertices)
print "number of connected components in core:", nx.number_connected_components(
core)
# BFS-traversal
fringe_fraction = 0.1
max_fringe_size = int(n * fringe_fraction)
core_vertices = set(core_vertices)
for i in range(int(1 / fringe_fraction) + 1):
fringe_vertices = set(
sorted(fringe(G, core_vertices),
key=lambda v: -G.degree(v))[:max_fringe_size])
if not fringe_vertices:
break
print "{}: core={}, fringe={}".format(i + 1, len(core_vertices),
len(fringe_vertices))
core_vertices |= fringe_vertices
def main():
parser = argparse.ArgumentParser()
parser.add_argument('graph')
args = parser.parse_args()
#vertices, edges = read_graph_from_file(args.graph)
G = nx.read_edgelist(args.graph)
n = G.number_of_nodes()
print "nodes:", n
print "edges:", G.number_of_edges()
core_exponent = 0.5
core_vertices = filter(lambda v: G.degree(v) >= n**core_exponent, G.nodes())
print "core vertices:", len(core_vertices)
core = G.subgraph(core_vertices)
print "number of connected components in core:", nx.number_connected_components(core)
# BFS-traversal
fringe_fraction = 0.1
max_fringe_size = int(n * fringe_fraction)
core_vertices = set(core_vertices)
for i in range(int(1/fringe_fraction)+1):
fringe_vertices = set(sorted(fringe(G, core_vertices), key=lambda v: -G.degree(v))[:max_fringe_size])
if not fringe_vertices:
break
print "{}: core={}, fringe={}".format(i+1, len(core_vertices), len(fringe_vertices))
core_vertices |= fringe_vertices
def find_embeddings(
vertices,
edges,
mode,
learning_rate=0.1,
n_epoch=100,
ratio_to_second=2.0,
ratio_between_first=1.0,
ratio_random=1.0,
silent=False,
):
"find (r, phi) for each vertex"
vertices = list(vertices)
n = len(vertices)
R = 2 * np.log(n)
print "mode: {}".format(mode)
np.random.seed(0)
degrees = defaultdict(int)
print "count degrees"
for v1, v2 in edges:
degrees[v1] += 1
degrees[v2] += 1
if mode == "random":
# phi=rand(0, 2pi), r = rand(0,R)
return {v: (np.random.uniform(0.0, R), np.random.uniform(0.0, 2 * np.pi)) for v in vertices}
elif mode == "degrees":
# phi=rand(0,2pi), r = 2log(n/k)
return {v: (2 * np.log(n / degrees[v]), np.random.uniform(0.0, 2 * np.pi)) for v in vertices}
elif mode.startswith("fit"):
x0 = []
for (r, phi) in zip(
[2 * np.log(n / degrees[v]) for v in vertices], [np.random.uniform(0.0, 2 * np.pi) for v in vertices]
):
x0.append(r)
x0.append(phi)
x0 = np.array(x0)
nedges = set()
all_nedges = set()
for (v1, v2) in combinations(vertices, 2):
# if (v1, v2) not in edges and (v2, v1) not in edges:
e = make_edge(v1, v2)
if e not in edges:
all_nedges.add(e)
if mode == "fit_random":
a = list(all_nedges)
random.shuffle(a)
nedges = set(a[: len(edges)])
elif mode == "fit_degrees":
K = float(ratio_to_second) # ratio of nedges to second neighbour
L = float(ratio_between_first) # ratio of nedges between first neighbours
M = float(ratio_random) # ratio of random nedges
# free_nedges = all_nedges.copy()
G = nx.Graph()
G.add_edges_from(edges)
srt_vertices = sorted(degrees.keys(), key=lambda v: -degrees[v])
shuf_vertices = srt_vertices[:]
random.shuffle(shuf_vertices)
for v in srt_vertices:
# get first neighbours
first_neigh = set(G.neighbors(v))
# get second neighbours
second_neigh = set()
for neigh in first_neigh:
second_neigh.update(G.neighbors(neigh))
second_neigh.remove(v)
n_vertex_nedges = 0
# from v to second neighbours
for i, sec_n in enumerate(second_neigh):
# print "i: {}".format(i)
if i + 1 > degrees[v] * K:
continue
e = make_edge(v, sec_n)
if e not in nedges:
nedges.add(e)
n_vertex_nedges += 1
# between first neighbours
for j, pair in enumerate(combinations(first_neigh, 2)):
# print "j: {}".format(j)
if j + 1 > degrees[v] * L:
continue
v1, v2 = pair
e = make_edge(v1, v2)
if e not in nedges:
nedges.add(e)
# random edges
max_n_random_vertices = int(degrees[v] * M)
n_random_vertices = 0
for rand_v in shuf_vertices:
if n_random_vertices >= max_n_random_vertices:
break
e = make_edge(v, rand_v)
if e not in nedges and e not in edges:
nedges.add(e)
n_random_vertices += 1
else:
nedges = all_nedges.copy()
print "number of nedges={}".format(len(nedges))
q = Q(vertices, edges, nedges)
grad_q = GradQ(vertices, edges, nedges)
if mode == "fit_degrees_sgd":
print "Learning rate: {}".format(learning_rate)
print "Ratio to second: {}".format(ratio_to_second)
print "Ratio between first: {}".format(ratio_between_first)
print "Ratio random: {}".format(ratio_random)
G = nx.Graph()
G.add_edges_from(edges)
# construct connected(!) core
core_exponent = 0.4
core_vertices, fringe_vertices = [], []
# one-pass split by condition
for v in vertices:
core_vertices.append(v) if degrees[v] >= n ** core_exponent else fringe_vertices.append(v)
# add vertices to ensure connectivity of core
fringe_vertices.sort(key=lambda v: -degrees[v])
while not nx.is_connected(G.subgraph(core_vertices)):
core_vertices.append(fringe_vertices.pop(0))
print "Core size: {}".format(len(core_vertices))
G_core = G.subgraph(core_vertices)
print "Is core connected:", nx.is_connected(G_core)
# loss_function = MSE(binary_edges=True)
loss_function = LogLoss(binary_edges=True)
optimizer = SGD(n_epoch=n_epoch, learning_rate=learning_rate, verbose=not silent)
FRINGE_FRACTION = 0.1
max_fringe_size = int(G.number_of_nodes() * FRINGE_FRACTION)
curr_graph = G.subgraph(core_vertices)
curr_core_vertices = set(core_vertices)
curr_embedding_model = PoincareModel(curr_graph, fit_radius=False)
curr_pair_generator = BinaryPairGenerator(curr_graph, batch_size=1)
optimizer.optimize_embedding(curr_embedding_model, loss_function, curr_pair_generator)
for i in range(int(1 / FRINGE_FRACTION) + 1):
total_fringe = fringe(G, curr_core_vertices)
# print "DEBUG:", curr_graph. number_of_nodes(), len(curr_core_vertices), len(total_fringe)
fringe_vertices = set(sorted(total_fringe, key=lambda v: -G.degree(v))[:max_fringe_size])
# print "DEBUG:", i+1, fringe_vertices
if not fringe_vertices:
break
curr_graph = G.subgraph(curr_core_vertices | fringe_vertices)
curr_embedding_model = PoincareModel(curr_graph, fit_radius=False, init_embedding=curr_embedding_model)
curr_pair_generator = BinaryPairGenerator(curr_graph, batch_size=1)
optimizer.optimize_embedding(
curr_embedding_model, loss_function, curr_pair_generator, fixed_vertices=curr_core_vertices
)
curr_core_vertices |= fringe_vertices
embedding_model = curr_embedding_model
"""
core_embedding_model = PoincareModel(G_core, fit_radius=False)
core_pair_generator = BinaryPairGenerator(G_core, batch_size=1)
optimizer.optimize_embedding(core_embedding_model, loss_function, core_pair_generator)
#optimizer = SGD(n_epoch=n_epoch, learning_rate=learning_rate, verbose=not silent)
embedding_model = PoincareModel(G, fit_radius=False, init_embedding=core_embedding_model)
pair_generator = BinaryPairGenerator(G, batch_size=1)
optimizer.optimize_embedding(embedding_model, loss_function, pair_generator, fixed_vertices=core_vertices)
#print "Radius before: {}".format(embedding_model.embedding['radius'])
#print "Radius after: {}".format(embedding_model.embedding['radius'])
"""
return (embedding_model.embedding["vertices"], {"core": list(G.edges())})
else:
print "Check gradient: ", check_grad(q, grad_q, x0)
res = minimize(q, x0, method="BFGS", jac=grad_q)
# print res
x = res.x
retval = {}
for i in range(len(vertices)):
r = x[2 * i]
phi = x[2 * i + 1]
retval[vertices[i]] = (r, phi)
return retval
else:
raise Exception("unknown mode")
def find_embeddings(vertices,
edges,
mode,
learning_rate=0.1,
n_epoch=100,
ratio_to_second=2.,
ratio_between_first=1.,
ratio_random=1.,
silent=False):
"find (r, phi) for each vertex"
vertices = list(vertices)
n = len(vertices)
R = 2 * np.log(n)
print "mode: {}".format(mode)
np.random.seed(0)
degrees = defaultdict(int)
print "count degrees"
for v1, v2 in edges:
degrees[v1] += 1
degrees[v2] += 1
if mode == 'random':
# phi=rand(0, 2pi), r = rand(0,R)
return {
v: (np.random.uniform(0.0, R), np.random.uniform(0.0, 2 * np.pi))
for v in vertices
}
elif mode == 'degrees':
# phi=rand(0,2pi), r = 2log(n/k)
return {
v: (2 * np.log(n / degrees[v]), np.random.uniform(0.0, 2 * np.pi))
for v in vertices
}
elif mode.startswith('fit'):
x0 = []
for (r,
phi) in zip([2 * np.log(n / degrees[v]) for v in vertices],
[np.random.uniform(0.0, 2 * np.pi)
for v in vertices]):
x0.append(r)
x0.append(phi)
x0 = np.array(x0)
nedges = set()
all_nedges = set()
for (v1, v2) in combinations(vertices, 2):
#if (v1, v2) not in edges and (v2, v1) not in edges:
e = make_edge(v1, v2)
if e not in edges:
all_nedges.add(e)
if mode == 'fit_random':
a = list(all_nedges)
random.shuffle(a)
nedges = set(a[:len(edges)])
elif mode == 'fit_degrees':
K = float(ratio_to_second) # ratio of nedges to second neighbour
L = float(ratio_between_first
) # ratio of nedges between first neighbours
M = float(ratio_random) # ratio of random nedges
#free_nedges = all_nedges.copy()
G = nx.Graph()
G.add_edges_from(edges)
srt_vertices = sorted(degrees.keys(), key=lambda v: -degrees[v])
shuf_vertices = srt_vertices[:]
random.shuffle(shuf_vertices)
for v in srt_vertices:
# get first neighbours
first_neigh = set(G.neighbors(v))
# get second neighbours
second_neigh = set()
for neigh in first_neigh:
second_neigh.update(G.neighbors(neigh))
second_neigh.remove(v)
n_vertex_nedges = 0
# from v to second neighbours
for i, sec_n in enumerate(second_neigh):
#print "i: {}".format(i)
if i + 1 > degrees[v] * K:
continue
e = make_edge(v, sec_n)
if e not in nedges:
nedges.add(e)
n_vertex_nedges += 1
# between first neighbours
for j, pair in enumerate(combinations(first_neigh, 2)):
#print "j: {}".format(j)
if j + 1 > degrees[v] * L:
continue
v1, v2 = pair
e = make_edge(v1, v2)
if e not in nedges:
nedges.add(e)
# random edges
max_n_random_vertices = int(degrees[v] * M)
n_random_vertices = 0
for rand_v in shuf_vertices:
if n_random_vertices >= max_n_random_vertices:
break
e = make_edge(v, rand_v)
if e not in nedges and e not in edges:
nedges.add(e)
n_random_vertices += 1
else:
nedges = all_nedges.copy()
print "number of nedges={}".format(len(nedges))
q = Q(vertices, edges, nedges)
grad_q = GradQ(vertices, edges, nedges)
if mode == 'fit_degrees_sgd':
print "Learning rate: {}".format(learning_rate)
print "Ratio to second: {}".format(ratio_to_second)
print "Ratio between first: {}".format(ratio_between_first)
print "Ratio random: {}".format(ratio_random)
G = nx.Graph()
G.add_edges_from(edges)
# construct connected(!) core
core_exponent = 0.4
core_vertices, fringe_vertices = [], []
# one-pass split by condition
for v in vertices:
core_vertices.append(v) if degrees[
v] >= n**core_exponent else fringe_vertices.append(v)
# add vertices to ensure connectivity of core
fringe_vertices.sort(key=lambda v: -degrees[v])
while not nx.is_connected(G.subgraph(core_vertices)):
core_vertices.append(fringe_vertices.pop(0))
print "Core size: {}".format(len(core_vertices))
G_core = G.subgraph(core_vertices)
print "Is core connected:", nx.is_connected(G_core)
#loss_function = MSE(binary_edges=True)
loss_function = LogLoss(binary_edges=True)
optimizer = SGD(n_epoch=n_epoch,
learning_rate=learning_rate,
verbose=not silent)
FRINGE_FRACTION = 0.1
max_fringe_size = int(G.number_of_nodes() * FRINGE_FRACTION)
curr_graph = G.subgraph(core_vertices)
curr_core_vertices = set(core_vertices)
curr_embedding_model = PoincareModel(curr_graph, fit_radius=False)
curr_pair_generator = BinaryPairGenerator(curr_graph, batch_size=1)
optimizer.optimize_embedding(curr_embedding_model, loss_function,
curr_pair_generator)
for i in range(int(1 / FRINGE_FRACTION) + 1):
total_fringe = fringe(G, curr_core_vertices)
#print "DEBUG:", curr_graph. number_of_nodes(), len(curr_core_vertices), len(total_fringe)
fringe_vertices = set(
sorted(total_fringe,
key=lambda v: -G.degree(v))[:max_fringe_size])
#print "DEBUG:", i+1, fringe_vertices
if not fringe_vertices:
break
curr_graph = G.subgraph(curr_core_vertices | fringe_vertices)
curr_embedding_model = PoincareModel(
curr_graph,
fit_radius=False,
init_embedding=curr_embedding_model)
curr_pair_generator = BinaryPairGenerator(curr_graph,
batch_size=1)
optimizer.optimize_embedding(curr_embedding_model,
loss_function,
curr_pair_generator,
fixed_vertices=curr_core_vertices)
curr_core_vertices |= fringe_vertices
embedding_model = curr_embedding_model
'''
core_embedding_model = PoincareModel(G_core, fit_radius=False)
core_pair_generator = BinaryPairGenerator(G_core, batch_size=1)
optimizer.optimize_embedding(core_embedding_model, loss_function, core_pair_generator)
#optimizer = SGD(n_epoch=n_epoch, learning_rate=learning_rate, verbose=not silent)
embedding_model = PoincareModel(G, fit_radius=False, init_embedding=core_embedding_model)
pair_generator = BinaryPairGenerator(G, batch_size=1)
optimizer.optimize_embedding(embedding_model, loss_function, pair_generator, fixed_vertices=core_vertices)
#print "Radius before: {}".format(embedding_model.embedding['radius'])
#print "Radius after: {}".format(embedding_model.embedding['radius'])
'''
return (embedding_model.embedding['vertices'], {
'core': list(G.edges())
})
else:
print "Check gradient: ", check_grad(q, grad_q, x0)
res = minimize(q, x0, method='BFGS', jac=grad_q)
#print res
x = res.x
retval = {}
for i in range(len(vertices)):
r = x[2 * i]
phi = x[2 * i + 1]
retval[vertices[i]] = (r, phi)
return retval
else:
raise Exception('unknown mode')
