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_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_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_full_sample(self):
q = self.g.V(self._node2_type).batch(4).alias('a') \
.outV(self._edge2_type).sample(3).by("full").alias('b') \
.values(lambda x: (x['a'].ids, x['b'].ids, x['b'].offsets))
dataset = gl.Dataset(q)
while True:
try:
src, nbrs, offsets = dataset.next()
start = 0
for idx, offset in enumerate(offsets):
expected_nbrs = utils.fixed_dst_ids(src[idx], self._node1_range)
assert offset == min(len(expected_nbrs), 3)
utils.check_subset(nbrs[start: start + offset], expected_nbrs)
start += offset
except gl.OutOfRangeError:
break
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()