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_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_weighted(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)
edges = g.E("first").batch(self.batch_size_).emit()
utils.check_ids(edges.src_ids,
range(self.src_range_[0], self.src_range_[1]))
utils.check_ids(edges.dst_ids,
range(self.dst_range_[0], self.dst_range_[1]))
utils.check_edge_weights(edges)
def test_2hop(self):
""" Sample 2 hops of neighbors.
"""
gl.set_eager_mode(True)
expand_factor = [3, 2]
ids = self._seed_node1_ids
nbr_s = self.g.neighbor_sampler([self._edge1_type, self._edge2_type],
expand_factor=expand_factor,
strategy="in_degree")
nbrs = nbr_s.get(ids)
edges = nbrs.layer_edges(1)
nodes = nbrs.layer_nodes(1)
utils.check_fixed_edge_dst_ids(edges,
dst_range=self._node2_range,
expected_src_ids=ids)
utils.check_edge_type(edges,
src_type=self._node1_type,
dst_type=self._node2_type,
edge_type=self._edge1_type)
utils.check_edge_shape(edges, ids.size * expand_factor[0])
utils.check_edge_attrs(edges)
utils.check_edge_labels(edges)
utils.check_equal(nodes.ids, edges.dst_ids)
utils.check_node_ids(nodes, self._node2_ids)
utils.check_node_type(nodes, node_type=self._node2_type)
utils.check_node_shape(nodes, ids.size * expand_factor[0])
utils.check_node_weights(nodes)
utils.check_node_labels(nodes)
ids = nodes.ids.reshape(-1)
edges = nbrs.layer_edges(2)
nodes = nbrs.layer_nodes(2)
utils.check_fixed_edge_dst_ids(edges,
dst_range=self._node1_range,
expected_src_ids=ids)
utils.check_edge_type(edges,
src_type=self._node2_type,
dst_type=self._node1_type,
edge_type=self._edge2_type)
utils.check_edge_shape(edges, ids.size * expand_factor[1])
utils.check_edge_attrs(edges)
utils.check_edge_weights(edges)
utils.check_equal(nodes.ids, edges.dst_ids)
utils.check_node_ids(nodes, self._node1_ids)
utils.check_node_type(nodes, node_type=self._node1_type)
utils.check_node_shape(nodes, ids.size * expand_factor[1])
def test_weighted_labeled(self):
gl.set_eager_mode(True)
file_path = self.gen_test_data([utils.WEIGHTED, utils.LABELED], False)
decoder = gl.Decoder(weighted=True, labeled=True)
g = gl.Graph() \
.edge(source=file_path, edge_type=self.edge_tuple_, decoder=decoder)
g.init(tracker=utils.TRACKER_PATH)
edges = g.E("first").batch(self.batch_size_).emit()
utils.check_ids(edges.src_ids,
range(self.src_range_[0], self.src_range_[1]))
utils.check_ids(edges.dst_ids,
range(self.dst_range_[0], self.dst_range_[1]))
utils.check_edge_labels(edges)
utils.check_edge_weights(edges)
g.close()
def test_weighted(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)
query = g.E("first").batch(self.batch_size_).alias('e').values()
ds = gl.Dataset(query, window=1)
edges = ds.next()['e']
utils.check_ids(edges.src_ids,
range(self.src_range_[0], self.src_range_[1]))
utils.check_ids(edges.dst_ids,
range(self.dst_range_[0], self.dst_range_[1]))
utils.check_edge_weights(edges)
g.close()
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()
