def test_node_iterate_using_gsl(self):
gl.set_eager_mode(True)
file_path = self.gen_test_data([utils.ATTRIBUTED])
decoder = gl.Decoder(attr_types=utils.ATTR_TYPES)
g = gl.Graph() \
.node(source=file_path, node_type=self.node_type_, decoder=decoder)
g.init(tracker=utils.TRACKER_PATH)
batch_size = 4
query = g.V('user').batch(batch_size).values()
res_ids = []
max_iter = 100
for i in range(max_iter):
try:
nodes = g.run(query)
utils.check_node_attrs(nodes)
res_ids.extend(list(nodes.ids))
except gl.OutOfRangeError:
break
ids = range(self.value_range_[0], self.value_range_[1])
utils.check_sorted_equal(res_ids, ids)
query = g.V('user').batch(batch_size).shuffle().values()
max_iter = 10
for i in range(max_iter):
nodes = g.run(query)
utils.check_node_attrs(nodes)
utils.check_subset(nodes.ids, ids)
g.close()
def test_edge_shuffle(self):
file_path = self.gen_test_data([utils.WEIGHTED], False)
decoder = gl.Decoder(weighted=True)
g = gl.Graph() \
.edge(source=file_path, edge_type=self.edge_tuple_, decoder=decoder)
g.init(tracker=utils.TRACKER_PATH)
batch_size = 4
sampler = g.E('first').batch(batch_size).shuffle(
traverse=True).values()
res_src = []
res_dst = []
max_iter = 100
for i in range(max_iter):
try:
edges = sampler.next()
utils.check_edge_weights(edges)
res_src.extend(list(edges.src_ids))
res_dst.extend(list(edges.dst_ids))
except gl.OutOfRangeError:
break
src_ids = range(self.src_range_[0], self.src_range_[1])
dst_ids = range(self.dst_range_[0], self.dst_range_[1])
utils.check_sorted_equal(res_src, src_ids)
utils.check_sorted_equal(res_dst, dst_ids)
g.close()
def test_edge_iterate_using_gremlin(self):
file_path = self.gen_test_data([utils.WEIGHTED], False)
decoder = gl.Decoder(weighted=True)
g = gl.Graph() \
.edge(source=file_path, edge_type=self.edge_tuple_, decoder=decoder)
g.init(server_id=0, server_count=1, tracker=utils.TRACKER_PATH)
batch_size = 4
query = g.E('first').batch(batch_size).values()
res_src = []
res_dst = []
max_iter = 100
for i in range(max_iter):
try:
edges = g.run(query)
utils.check_edge_weights(edges)
res_src.extend(list(edges.src_ids))
res_dst.extend(list(edges.dst_ids))
except gl.OutOfRangeError:
break
src_ids = range(self.src_range_[0], self.src_range_[1])
dst_ids = range(self.dst_range_[0], self.dst_range_[1])
utils.check_sorted_equal(res_src, src_ids)
utils.check_sorted_equal(res_dst, dst_ids)
query = g.E('first').batch(batch_size).shuffle().values()
max_iter = 10
src_ids = range(self.src_range_[0], self.src_range_[1])
dst_ids = range(self.dst_range_[0], self.dst_range_[1])
for i in range(max_iter):
edges = g.run(query)
utils.check_edge_weights(edges)
utils.check_subset(edges.src_ids, src_ids)
utils.check_subset(edges.dst_ids, dst_ids)
def test_sampling_with_mask_eager_mode(self):
gl.set_eager_mode(True)
bs = 8
q = self.g.E(self._edge1_type, mask=gl.Mask.VAL).batch(bs).alias('val') \
.each(
lambda e:
(e.outV().alias('src'),
e.inV().alias('dst') \
.outV(self._edge2_type).sample(3).by('topk').alias('nbr'))
).values(lambda x:
(x['src'].ids,
x['val'].labels,
x['dst'].ids, x['dst'].weights, x['dst'].labels,
x['nbr'].ids, x['nbr'].int_attrs))
iteration = 0
for i in range(2):
res = []
while True:
try:
sid, elb, did, dwei, dlb, nid, ni = q.next()
utils.check_id_weights(did, dwei)
utils.check_equal(dlb, did)
iteration += 1
res += list(sid)
except gl.OutOfRangeError:
break
whole = range(self._val_node_range[0], self._val_node_range[1])
expected = []
for elem in whole:
expected += [elem] * len(
utils.fixed_dst_ids(elem, self._node2_range))
utils.check_sorted_equal(res, expected)
def test_node_iterate(self):
file_path = self.gen_test_data([utils.ATTRIBUTED])
decoder = gl.Decoder(attr_types=utils.ATTR_TYPES)
g = gl.Graph() \
.node(source=file_path, node_type=self.node_type_, decoder=decoder)
g.init(tracker=utils.TRACKER_PATH)
batch_size = 4
sampler = g.node_sampler('user',
batch_size=batch_size,
strategy="by_order")
res_ids = []
max_iter = 100
for i in range(max_iter):
try:
nodes = sampler.get()
utils.check_node_attrs(nodes)
res_ids.extend(list(nodes.ids))
except gl.OutOfRangeError:
break
ids = range(self.value_range_[0][0], self.value_range_[0][1])
utils.check_sorted_equal(res_ids, ids)
sampler = g.node_sampler('user',
batch_size=batch_size,
strategy="random")
max_iter = 10
for i in range(max_iter):
nodes = sampler.get()
utils.check_node_attrs(nodes)
utils.check_subset(nodes.ids, ids)
g.close()
def test_node_iterate_from_graph(self):
file_path = self.gen_test_data([utils.ATTRIBUTED], False)
decoder = gl.Decoder(attr_types=utils.ATTR_TYPES)
g = gl.Graph() \
.edge(source=file_path, edge_type=self.edge_tuple_, decoder=decoder)
g.init(tracker=utils.TRACKER_PATH)
batch_size = 4
sampler = g.node_sampler('first',
batch_size=batch_size,
strategy="by_order",
node_from=gl.EDGE_SRC)
res_ids = []
max_iter = 100
for i in range(max_iter):
try:
nodes = sampler.get()
utils.check_node_type(nodes, "user")
res_ids.extend(list(nodes.ids))
except gl.OutOfRangeError:
break
ids = range(self.src_range_[0], self.src_range_[1])
utils.check_sorted_equal(res_ids, ids)
sampler = g.node_sampler('first',
batch_size=batch_size,
strategy="random",
node_from=gl.EDGE_SRC)
max_iter = 10
for i in range(max_iter):
nodes = sampler.get()
utils.check_subset(nodes.ids, ids)
sampler = g.node_sampler('first',
batch_size=batch_size,
strategy="by_order",
node_from=gl.EDGE_DST)
res_ids = []
max_iter = 100
for i in range(max_iter):
try:
nodes = sampler.get()
utils.check_node_type(nodes, "item")
res_ids.extend(list(nodes.ids))
except gl.OutOfRangeError:
break
ids = range(self.dst_range_[0], self.dst_range_[1])
utils.check_sorted_equal(res_ids, ids)
sampler = g.node_sampler('first',
batch_size=batch_size,
strategy="random",
node_from=gl.EDGE_DST)
max_iter = 10
for i in range(max_iter):
nodes = sampler.get()
utils.check_subset(nodes.ids, ids)
g.close()
def test_1hop(self):
""" Sample full neighbors.
"""
ids = self._seed_node1_ids
nbr_s = self.g.neighbor_sampler(self._edge1_type, 1, strategy="full")
nbrs = nbr_s.get(ids)
edges = nbrs.layer_edges(1)
nodes = nbrs.layer_nodes(1)
index = 0
for node in nodes:
utils.check_sorted_equal(
utils.fixed_dst_ids(ids[index], self._node2_range), node.ids)
index += 1
def test_1hop_using_gremlin(self):
""" Full neighbor sample with gremlin-like api.
"""
expand_factor = 2
ids = self._seed_node1_ids
nbrs = self.g.V(self._node1_type, feed=ids) \
.outE(self._edge1_type).sample().by("full") \
.inV().emit()
nodes = nbrs[2]
index = 0
for node in nodes:
utils.check_sorted_equal(
utils.fixed_dst_ids(ids[index], self._node2_range), node.ids)
index += 1
utils.check_node_ids(nodes, self._node2_ids)
utils.check_node_type(nodes, node_type=self._node2_type)
utils.check_node_weights(nodes)
utils.check_node_labels(nodes)
def test_traverse_with_mask(self):
bs = 8
q = self.g.V(self._node1_type, mask=gl.Mask.TEST).batch(bs).alias('test') \
.values(lambda x:
(x['test'].ids, x['test'].int_attrs, x['test'].float_attrs, x['test'].string_attrs))
dataset = gl.Dataset(q)
iteration = 0
for i in range(2):
res = []
while True:
try:
ids, i, f, s = dataset.next()
utils.check_i_attrs(i, ids)
utils.check_f_attrs(f, ids)
utils.check_s_attrs(s, ids)
iteration += 1
res += list(ids)
except gl.OutOfRangeError:
break
utils.check_sorted_equal(res, range(self._test_node_range[0], self._test_node_range[1]))
def test_node_iterate(self):
file_path = self.gen_test_data([utils.ATTRIBUTED])
decoder = gl.Decoder(attr_types=utils.ATTR_TYPES)
g = gl.Graph() \
.node(source=file_path, node_type=self.node_type_, decoder=decoder)
g.init(server_id=0, server_count=1, tracker=utils.TRACKER_PATH)
batch_size = 4
sampler = g.V('user').batch(batch_size).shuffle(traverse=True).values()
res_ids = []
max_iter = 100
for i in range(max_iter):
try:
nodes = sampler.next()
utils.check_node_attrs(nodes)
res_ids.extend(list(nodes.ids))
except gl.OutOfRangeError:
break
ids = range(self.value_range_[0][0], self.value_range_[0][1])
utils.check_sorted_equal(res_ids, ids)
def test_traverse_with_mask_eager_mode(self):
gl.set_eager_mode(True)
bs = 8
q = self.g.V(self._node1_type, mask=gl.Mask.TRAIN).batch(bs).alias('train') \
.values(lambda x:
(x['train'].ids, x['train'].int_attrs, x['train'].float_attrs, x['train'].string_attrs))
iteration = 0
res = []
while True:
try:
ids, i, f, s = q.next()
utils.check_i_attrs(i, ids)
utils.check_f_attrs(f, ids)
utils.check_s_attrs(s, ids)
iteration += 1
res += list(ids)
except gl.OutOfRangeError:
break
utils.check_sorted_equal(
res, range(self._train_node_range[0], self._train_node_range[1]))
def test_edge_iterate(self):
file_path = self.gen_test_data([utils.WEIGHTED], False)
decoder = gl.Decoder(weighted=True)
g = gl.Graph() \
.edge(source=file_path, edge_type=self.edge_tuple_, decoder=decoder)
g.init(tracker=utils.TRACKER_PATH)
batch_size = 4
sampler = g.edge_sampler('first',
batch_size=batch_size,
strategy="by_order")
res_src = []
res_dst = []
max_iter = 100
for _ in range(max_iter):
try:
edges = sampler.get()
utils.check_edge_weights(edges)
res_src.extend(list(edges.src_ids))
res_dst.extend(list(edges.dst_ids))
except gl.OutOfRangeError:
break
src_ids = range(self.src_range_[0], self.src_range_[1])
dst_ids = range(self.dst_range_[0], self.dst_range_[1])
utils.check_sorted_equal(res_src, src_ids)
utils.check_sorted_equal(res_dst, dst_ids)
sampler = g.edge_sampler('first',
batch_size=batch_size,
strategy="random")
max_iter = 10
src_ids = range(self.src_range_[0], self.src_range_[1])
dst_ids = range(self.dst_range_[0], self.dst_range_[1])
for i in range(max_iter):
edges = sampler.get()
utils.check_edge_weights(edges)
utils.check_subset(edges.src_ids, src_ids)
utils.check_subset(edges.dst_ids, dst_ids)
g.close()
