def test_dist_dataloader(tmpdir, num_server, drop_last):
ip_config = open("mp_ip_config.txt", "w")
for _ in range(num_server):
ip_config.write('{} 1\n'.format(get_local_usable_addr()))
ip_config.close()
g = CitationGraphDataset("cora")[0]
print(g.idtype)
num_parts = num_server
num_hops = 1
partition_graph(g,
'test_sampling',
num_parts,
tmpdir,
num_hops=num_hops,
part_method='metis',
reshuffle=False)
num_workers = 4
pserver_list = []
ctx = mp.get_context('spawn')
for i in range(num_server):
p = ctx.Process(target=start_server,
args=(i, tmpdir, num_server > 1, num_workers + 1))
p.start()
time.sleep(1)
pserver_list.append(p)
time.sleep(3)
sampled_graph = start_client(0, tmpdir, num_server > 1, num_workers,
drop_last)
def test_dist_dataloader(tmpdir, num_server, num_workers, drop_last, reshuffle):
ip_config = open("mp_ip_config.txt", "w")
for _ in range(num_server):
ip_config.write('{}\n'.format(get_local_usable_addr()))
ip_config.close()
g = CitationGraphDataset("cora")[0]
print(g.idtype)
num_parts = num_server
num_hops = 1
orig_nid, orig_eid = partition_graph(g, 'test_sampling', num_parts, tmpdir,
num_hops=num_hops, part_method='metis',
reshuffle=reshuffle, return_mapping=True)
pserver_list = []
ctx = mp.get_context('spawn')
for i in range(num_server):
p = ctx.Process(target=start_server, args=(
i, tmpdir, num_server > 1, num_workers+1))
p.start()
time.sleep(1)
pserver_list.append(p)
time.sleep(3)
os.environ['DGL_DIST_MODE'] = 'distributed'
os.environ['DGL_NUM_SAMPLER'] = str(num_workers)
ptrainer = ctx.Process(target=start_dist_dataloader, args=(
0, tmpdir, num_server, drop_last, orig_nid, orig_eid))
ptrainer.start()
time.sleep(1)
for p in pserver_list:
p.join()
ptrainer.join()
def test_dist_dataloader(tmpdir, num_server, num_workers, drop_last):
ip_config = open("mp_ip_config.txt", "w")
for _ in range(num_server):
ip_config.write('{}\n'.format(get_local_usable_addr()))
ip_config.close()
g = CitationGraphDataset("cora")[0]
print(g.idtype)
num_parts = num_server
num_hops = 1
partition_graph(g, 'test_sampling', num_parts, tmpdir,
num_hops=num_hops, part_method='metis', reshuffle=False)
pserver_list = []
ctx = mp.get_context('spawn')
for i in range(num_server):
p = ctx.Process(target=start_server, args=(
i, tmpdir, num_server > 1, num_workers+1))
p.start()
time.sleep(1)
pserver_list.append(p)
time.sleep(3)
os.environ['DGL_DIST_MODE'] = 'distributed'
start_client(0, tmpdir, num_server > 1, num_workers, drop_last)
dgl.distributed.exit_client() # this is needed since there's two test here in one process
def check_rpc_sampling(tmpdir, num_server):
ip_config = open("rpc_ip_config.txt", "w")
for _ in range(num_server):
ip_config.write('{} 1\n'.format(get_local_usable_addr()))
ip_config.close()
g = CitationGraphDataset("cora")[0]
g.readonly()
print(g.idtype)
num_parts = num_server
num_hops = 1
partition_graph(g, 'test_sampling', num_parts, tmpdir,
num_hops=num_hops, part_method='metis', reshuffle=False)
pserver_list = []
ctx = mp.get_context('spawn')
for i in range(num_server):
p = ctx.Process(target=start_server, args=(i, tmpdir, num_server > 1, 'test_sampling'))
p.start()
time.sleep(1)
pserver_list.append(p)
time.sleep(3)
sampled_graph = start_sample_client(0, tmpdir, num_server > 1)
print("Done sampling")
for p in pserver_list:
p.join()
src, dst = sampled_graph.edges()
assert sampled_graph.number_of_nodes() == g.number_of_nodes()
assert np.all(F.asnumpy(g.has_edges_between(src, dst)))
eids = g.edge_ids(src, dst)
assert np.array_equal(
F.asnumpy(sampled_graph.edata[dgl.EID]), F.asnumpy(eids))
def test_standalone(tmpdir):
ip_config = open("mp_ip_config.txt", "w")
for _ in range(1):
ip_config.write('{}\n'.format(get_local_usable_addr()))
ip_config.close()
g = CitationGraphDataset("cora")[0]
print(g.idtype)
num_parts = 1
num_hops = 1
orig_nid, orig_eid = partition_graph(g,
'test_sampling',
num_parts,
tmpdir,
num_hops=num_hops,
part_method='metis',
reshuffle=True,
return_mapping=True)
os.environ['DGL_DIST_MODE'] = 'standalone'
try:
start_dist_dataloader(0, tmpdir, 1, True, orig_nid, orig_eid)
except Exception as e:
print(e)
dgl.distributed.exit_client(
) # this is needed since there's two test here in one process
def check_rpc_hetero_etype_sampling_empty_shuffle(tmpdir, num_server):
ip_config = open("rpc_ip_config.txt", "w")
for _ in range(num_server):
ip_config.write('{}\n'.format(get_local_usable_addr()))
ip_config.close()
g = create_random_hetero(dense=True, empty=True)
num_parts = num_server
num_hops = 1
orig_nids, _ = partition_graph(g, 'test_sampling', num_parts, tmpdir,
num_hops=num_hops, part_method='metis',
reshuffle=True, return_mapping=True)
pserver_list = []
ctx = mp.get_context('spawn')
for i in range(num_server):
p = ctx.Process(target=start_server, args=(i, tmpdir, num_server > 1, 'test_sampling'))
p.start()
time.sleep(1)
pserver_list.append(p)
time.sleep(3)
fanout = 3
deg = get_degrees(g, orig_nids['n3'], 'n3')
empty_nids = F.nonzero_1d(deg == 0)
block, gpb = start_hetero_etype_sample_client(0, tmpdir, num_server > 1, fanout,
nodes={'n3': empty_nids})
print("Done sampling")
for p in pserver_list:
p.join()
assert block.number_of_edges() == 0
assert len(block.etypes) == len(g.etypes)
def check_rpc_find_edges(tmpdir, num_server):
ip_config = open("rpc_ip_config.txt", "w")
for _ in range(num_server):
ip_config.write('{} 1\n'.format(get_local_usable_addr()))
ip_config.close()
g = CitationGraphDataset("cora")[0]
g.readonly()
num_parts = num_server
partition_graph(g,
'test_find_edges',
num_parts,
tmpdir,
num_hops=1,
part_method='metis',
reshuffle=False)
pserver_list = []
ctx = mp.get_context('spawn')
for i in range(num_server):
p = ctx.Process(target=start_server,
args=(i, tmpdir, num_server > 1, 'test_find_edges'))
p.start()
time.sleep(1)
pserver_list.append(p)
time.sleep(3)
eids = F.tensor(np.random.randint(g.number_of_edges(), size=100))
u, v = g.find_edges(eids)
du, dv = start_find_edges_client(0, tmpdir, num_server > 1, eids)
assert F.array_equal(u, du)
assert F.array_equal(v, dv)
def check_rpc_hetero_find_edges_shuffle(tmpdir, num_server):
ip_config = open("rpc_ip_config.txt", "w")
for _ in range(num_server):
ip_config.write('{}\n'.format(get_local_usable_addr()))
ip_config.close()
g = create_random_hetero()
num_parts = num_server
orig_nid, orig_eid = partition_graph(g, 'test_find_edges', num_parts, tmpdir,
num_hops=1, part_method='metis',
reshuffle=True, return_mapping=True)
pserver_list = []
ctx = mp.get_context('spawn')
for i in range(num_server):
p = ctx.Process(target=start_server, args=(i, tmpdir, num_server > 1,
'test_find_edges', ['csr', 'coo']))
p.start()
time.sleep(1)
pserver_list.append(p)
time.sleep(3)
eids = F.tensor(np.random.randint(g.number_of_edges('r1'), size=100))
u, v = g.find_edges(orig_eid['r1'][eids], etype='r1')
du, dv = start_find_edges_client(0, tmpdir, num_server > 1, eids, etype='r1')
du = orig_nid['n1'][du]
dv = orig_nid['n2'][dv]
assert F.array_equal(u, du)
assert F.array_equal(v, dv)
def check_rpc_hetero_sampling_shuffle(tmpdir, num_server):
ip_config = open("rpc_ip_config.txt", "w")
for _ in range(num_server):
ip_config.write('{}\n'.format(get_local_usable_addr()))
ip_config.close()
g = create_random_hetero()
num_parts = num_server
num_hops = 1
partition_graph(g, 'test_sampling', num_parts, tmpdir,
num_hops=num_hops, part_method='metis', reshuffle=True)
pserver_list = []
ctx = mp.get_context('spawn')
for i in range(num_server):
p = ctx.Process(target=start_server, args=(i, tmpdir, num_server > 1, 'test_sampling'))
p.start()
time.sleep(1)
pserver_list.append(p)
time.sleep(3)
block, gpb = start_hetero_sample_client(0, tmpdir, num_server > 1,
nodes = {'n3': [0, 10, 99, 66, 124, 208]})
print("Done sampling")
for p in pserver_list:
p.join()
orig_nid_map = {ntype: F.zeros((g.number_of_nodes(ntype),), dtype=F.int64) for ntype in g.ntypes}
orig_eid_map = {etype: F.zeros((g.number_of_edges(etype),), dtype=F.int64) for etype in g.etypes}
for i in range(num_server):
part, _, _, _, _, _, _ = load_partition(tmpdir / 'test_sampling.json', i)
ntype_ids, type_nids = gpb.map_to_per_ntype(part.ndata[dgl.NID])
for ntype_id, ntype in enumerate(g.ntypes):
idx = ntype_ids == ntype_id
F.scatter_row_inplace(orig_nid_map[ntype], F.boolean_mask(type_nids, idx),
F.boolean_mask(part.ndata['orig_id'], idx))
etype_ids, type_eids = gpb.map_to_per_etype(part.edata[dgl.EID])
for etype_id, etype in enumerate(g.etypes):
idx = etype_ids == etype_id
F.scatter_row_inplace(orig_eid_map[etype], F.boolean_mask(type_eids, idx),
F.boolean_mask(part.edata['orig_id'], idx))
for src_type, etype, dst_type in block.canonical_etypes:
src, dst = block.edges(etype=etype)
# These are global Ids after shuffling.
shuffled_src = F.gather_row(block.srcnodes[src_type].data[dgl.NID], src)
shuffled_dst = F.gather_row(block.dstnodes[dst_type].data[dgl.NID], dst)
shuffled_eid = block.edges[etype].data[dgl.EID]
orig_src = F.asnumpy(F.gather_row(orig_nid_map[src_type], shuffled_src))
orig_dst = F.asnumpy(F.gather_row(orig_nid_map[dst_type], shuffled_dst))
orig_eid = F.asnumpy(F.gather_row(orig_eid_map[etype], shuffled_eid))
# Check the node Ids and edge Ids.
orig_src1, orig_dst1 = g.find_edges(orig_eid, etype=etype)
assert np.all(F.asnumpy(orig_src1) == orig_src)
assert np.all(F.asnumpy(orig_dst1) == orig_dst)
def check_rpc_in_subgraph_shuffle(tmpdir, num_server):
ip_config = open("rpc_ip_config.txt", "w")
for _ in range(num_server):
ip_config.write('{}\n'.format(get_local_usable_addr()))
ip_config.close()
g = CitationGraphDataset("cora")[0]
g.readonly()
num_parts = num_server
partition_graph(g,
'test_in_subgraph',
num_parts,
tmpdir,
num_hops=1,
part_method='metis',
reshuffle=True)
pserver_list = []
ctx = mp.get_context('spawn')
for i in range(num_server):
p = ctx.Process(target=start_server,
args=(i, tmpdir, num_server > 1, 'test_in_subgraph'))
p.start()
time.sleep(1)
pserver_list.append(p)
nodes = [0, 10, 99, 66, 1024, 2008]
time.sleep(3)
sampled_graph = start_in_subgraph_client(0, tmpdir, num_server > 1, nodes)
for p in pserver_list:
p.join()
orig_nid = F.zeros((g.number_of_nodes(), ), dtype=F.int64, ctx=F.cpu())
orig_eid = F.zeros((g.number_of_edges(), ), dtype=F.int64, ctx=F.cpu())
for i in range(num_server):
part, _, _, _, _, _, _ = load_partition(
tmpdir / 'test_in_subgraph.json', i)
orig_nid[part.ndata[dgl.NID]] = part.ndata['orig_id']
orig_eid[part.edata[dgl.EID]] = part.edata['orig_id']
src, dst = sampled_graph.edges()
src = orig_nid[src]
dst = orig_nid[dst]
assert sampled_graph.number_of_nodes() == g.number_of_nodes()
assert np.all(F.asnumpy(g.has_edges_between(src, dst)))
subg1 = dgl.in_subgraph(g, orig_nid[nodes])
src1, dst1 = subg1.edges()
assert np.all(np.sort(F.asnumpy(src)) == np.sort(F.asnumpy(src1)))
assert np.all(np.sort(F.asnumpy(dst)) == np.sort(F.asnumpy(dst1)))
eids = g.edge_ids(src, dst)
eids1 = orig_eid[sampled_graph.edata[dgl.EID]]
assert np.array_equal(F.asnumpy(eids1), F.asnumpy(eids))
def check_dataloader(g, tmpdir, num_server, num_workers, dataloader_type):
ip_config = open("mp_ip_config.txt", "w")
for _ in range(num_server):
ip_config.write('{}\n'.format(get_local_usable_addr()))
ip_config.close()
num_parts = num_server
num_hops = 1
orig_nid, orig_eid = partition_graph(g,
'test_sampling',
num_parts,
tmpdir,
num_hops=num_hops,
part_method='metis',
reshuffle=True,
return_mapping=True)
if not isinstance(orig_nid, dict):
orig_nid = {g.ntypes[0]: orig_nid}
if not isinstance(orig_eid, dict):
orig_eid = {g.etypes[0]: orig_eid}
pserver_list = []
ctx = mp.get_context('spawn')
for i in range(num_server):
p = ctx.Process(target=start_server,
args=(i, tmpdir, num_server > 1, num_workers + 1))
p.start()
time.sleep(1)
pserver_list.append(p)
time.sleep(3)
os.environ['DGL_DIST_MODE'] = 'distributed'
os.environ['DGL_NUM_SAMPLER'] = str(num_workers)
ptrainer_list = []
if dataloader_type == 'node':
p = ctx.Process(target=start_node_dataloader,
args=(0, tmpdir, num_server, num_workers, orig_nid,
orig_eid, g))
p.start()
time.sleep(1)
ptrainer_list.append(p)
elif dataloader_type == 'edge':
p = ctx.Process(target=start_edge_dataloader,
args=(0, tmpdir, num_server, num_workers, orig_nid,
orig_eid, g))
p.start()
time.sleep(1)
ptrainer_list.append(p)
for p in pserver_list:
p.join()
for p in ptrainer_list:
p.join()
def check_rpc_sampling_shuffle(tmpdir):
num_server = 2
ip_config = open("rpc_sampling_ip_config.txt", "w")
for _ in range(num_server):
ip_config.write('{} 1\n'.format(get_local_usable_addr()))
ip_config.close()
g = CitationGraphDataset("cora")[0]
g.readonly()
num_parts = num_server
num_hops = 1
partition_graph(g,
'test_sampling',
num_parts,
tmpdir,
num_hops=num_hops,
part_method='metis',
reshuffle=True)
pserver_list = []
ctx = mp.get_context('spawn')
for i in range(num_server):
p = ctx.Process(target=start_server, args=(i, tmpdir))
p.start()
time.sleep(1)
pserver_list.append(p)
time.sleep(3)
sampled_graph = start_client(0, tmpdir)
print("Done sampling")
for p in pserver_list:
p.join()
orig_nid = F.zeros((g.number_of_nodes(), ), dtype=F.int64)
orig_eid = F.zeros((g.number_of_edges(), ), dtype=F.int64)
for i in range(num_server):
part, _, _, _ = load_partition(tmpdir / 'test_sampling.json', i)
orig_nid[part.ndata[dgl.NID]] = part.ndata['orig_id']
orig_eid[part.edata[dgl.EID]] = part.edata['orig_id']
src, dst = sampled_graph.edges()
src = orig_nid[src]
dst = orig_nid[dst]
assert sampled_graph.number_of_nodes() == g.number_of_nodes()
assert np.all(F.asnumpy(g.has_edges_between(src, dst)))
eids = g.edge_ids(src, dst)
eids1 = orig_eid[sampled_graph.edata[dgl.EID]]
assert np.array_equal(F.asnumpy(eids1), F.asnumpy(eids))
def check_rpc_get_degree_shuffle(tmpdir, num_server):
ip_config = open("rpc_ip_config.txt", "w")
for _ in range(num_server):
ip_config.write('{}\n'.format(get_local_usable_addr()))
ip_config.close()
g = CitationGraphDataset("cora")[0]
g.readonly()
num_parts = num_server
partition_graph(g,
'test_get_degrees',
num_parts,
tmpdir,
num_hops=1,
part_method='metis',
reshuffle=True)
pserver_list = []
ctx = mp.get_context('spawn')
for i in range(num_server):
p = ctx.Process(target=start_server,
args=(i, tmpdir, num_server > 1, 'test_get_degrees'))
p.start()
time.sleep(1)
pserver_list.append(p)
orig_nid = F.zeros((g.number_of_nodes(), ), dtype=F.int64, ctx=F.cpu())
for i in range(num_server):
part, _, _, _, _, _, _ = load_partition(
tmpdir / 'test_get_degrees.json', i)
orig_nid[part.ndata[dgl.NID]] = part.ndata['orig_id']
time.sleep(3)
nids = F.tensor(np.random.randint(g.number_of_nodes(), size=100))
in_degs, out_degs, all_in_degs, all_out_degs = start_get_degrees_client(
0, tmpdir, num_server > 1, nids)
print("Done get_degree")
for p in pserver_list:
p.join()
print('check results')
assert F.array_equal(g.in_degrees(orig_nid[nids]), in_degs)
assert F.array_equal(g.in_degrees(orig_nid), all_in_degs)
assert F.array_equal(g.out_degrees(orig_nid[nids]), out_degs)
assert F.array_equal(g.out_degrees(orig_nid), all_out_degs)
def check_rpc_find_edges_shuffle(tmpdir, num_server):
ip_config = open("rpc_ip_config.txt", "w")
for _ in range(num_server):
ip_config.write('{}\n'.format(get_local_usable_addr()))
ip_config.close()
g = CitationGraphDataset("cora")[0]
g.readonly()
num_parts = num_server
partition_graph(g,
'test_find_edges',
num_parts,
tmpdir,
num_hops=1,
part_method='metis',
reshuffle=True)
pserver_list = []
ctx = mp.get_context('spawn')
for i in range(num_server):
p = ctx.Process(target=start_server,
args=(i, tmpdir, num_server > 1, 'test_find_edges',
['csr', 'coo']))
p.start()
time.sleep(1)
pserver_list.append(p)
orig_nid = F.zeros((g.number_of_nodes(), ), dtype=F.int64, ctx=F.cpu())
orig_eid = F.zeros((g.number_of_edges(), ), dtype=F.int64, ctx=F.cpu())
for i in range(num_server):
part, _, _, _, _, _, _ = load_partition(
tmpdir / 'test_find_edges.json', i)
orig_nid[part.ndata[dgl.NID]] = part.ndata['orig_id']
orig_eid[part.edata[dgl.EID]] = part.edata['orig_id']
time.sleep(3)
eids = F.tensor(np.random.randint(g.number_of_edges(), size=100))
u, v = g.find_edges(orig_eid[eids])
du, dv = start_find_edges_client(0, tmpdir, num_server > 1, eids)
du = orig_nid[du]
dv = orig_nid[dv]
assert F.array_equal(u, du)
assert F.array_equal(v, dv)
def check_rpc_in_subgraph(tmpdir, num_server):
ip_config = open("rpc_ip_config.txt", "w")
for _ in range(num_server):
ip_config.write('{} 1\n'.format(get_local_usable_addr()))
ip_config.close()
g = CitationGraphDataset("cora")[0]
g.readonly()
num_parts = num_server
partition_graph(g,
'test_in_subgraph',
num_parts,
tmpdir,
num_hops=1,
part_method='metis',
reshuffle=False)
pserver_list = []
ctx = mp.get_context('spawn')
for i in range(num_server):
p = ctx.Process(target=start_server,
args=(i, tmpdir, num_server > 1, 'test_in_subgraph'))
p.start()
time.sleep(1)
pserver_list.append(p)
nodes = [0, 10, 99, 66, 1024, 2008]
time.sleep(3)
sampled_graph = start_in_subgraph_client(0, tmpdir, num_server > 1, nodes)
for p in pserver_list:
p.join()
src, dst = sampled_graph.edges()
g = dgl.as_heterograph(g)
assert sampled_graph.number_of_nodes() == g.number_of_nodes()
subg1 = dgl.in_subgraph(g, nodes)
src1, dst1 = subg1.edges()
assert np.all(np.sort(F.asnumpy(src)) == np.sort(F.asnumpy(src1)))
assert np.all(np.sort(F.asnumpy(dst)) == np.sort(F.asnumpy(dst1)))
eids = g.edge_ids(src, dst)
assert np.array_equal(F.asnumpy(sampled_graph.edata[dgl.EID]),
F.asnumpy(eids))
def test_dataloader(tmpdir, num_server, num_workers, dataloader_type):
ip_config = open("mp_ip_config.txt", "w")
for _ in range(num_server):
ip_config.write('{}\n'.format(get_local_usable_addr()))
ip_config.close()
g = CitationGraphDataset("cora")[0]
print(g.idtype)
num_parts = num_server
num_hops = 1
partition_graph(g, 'test_sampling', num_parts, tmpdir,
num_hops=num_hops, part_method='metis', reshuffle=False)
pserver_list = []
ctx = mp.get_context('spawn')
for i in range(num_server):
p = ctx.Process(target=start_server, args=(
i, tmpdir, num_server > 1, num_workers+1))
p.start()
time.sleep(1)
pserver_list.append(p)
time.sleep(3)
os.environ['DGL_DIST_MODE'] = 'distributed'
ptrainer_list = []
if dataloader_type == 'node':
p = ctx.Process(target=start_node_dataloader, args=(
0, tmpdir, num_server > 1, num_workers))
p.start()
time.sleep(1)
ptrainer_list.append(p)
for p in pserver_list:
p.join()
for p in ptrainer_list:
p.join()
def check_rpc_hetero_sampling_shuffle(tmpdir, num_server):
ip_config = open("rpc_ip_config.txt", "w")
for _ in range(num_server):
ip_config.write('{}\n'.format(get_local_usable_addr()))
ip_config.close()
g = create_random_hetero()
num_parts = num_server
num_hops = 1
partition_graph(g,
'test_sampling',
num_parts,
tmpdir,
num_hops=num_hops,
part_method='metis',
reshuffle=True)
pserver_list = []
ctx = mp.get_context('spawn')
for i in range(num_server):
p = ctx.Process(target=start_server,
args=(i, tmpdir, num_server > 1, 'test_sampling'))
p.start()
time.sleep(1)
pserver_list.append(p)
time.sleep(3)
block, gpb = start_hetero_sample_client(0, tmpdir, num_server > 1)
print("Done sampling")
for p in pserver_list:
p.join()
orig_nid_map = F.zeros((g.number_of_nodes(), ), dtype=F.int64)
orig_eid_map = F.zeros((g.number_of_edges(), ), dtype=F.int64)
for i in range(num_server):
part, _, _, _, _, _, _ = load_partition(tmpdir / 'test_sampling.json',
i)
F.scatter_row_inplace(orig_nid_map, part.ndata[dgl.NID],
part.ndata['orig_id'])
F.scatter_row_inplace(orig_eid_map, part.edata[dgl.EID],
part.edata['orig_id'])
src, dst = block.edges()
# These are global Ids after shuffling.
shuffled_src = F.gather_row(block.srcdata[dgl.NID], src)
shuffled_dst = F.gather_row(block.dstdata[dgl.NID], dst)
shuffled_eid = block.edata[dgl.EID]
# Get node/edge types.
etype, _ = gpb.map_to_per_etype(shuffled_eid)
src_type, _ = gpb.map_to_per_ntype(shuffled_src)
dst_type, _ = gpb.map_to_per_ntype(shuffled_dst)
etype = F.asnumpy(etype)
src_type = F.asnumpy(src_type)
dst_type = F.asnumpy(dst_type)
# These are global Ids in the original graph.
orig_src = F.asnumpy(F.gather_row(orig_nid_map, shuffled_src))
orig_dst = F.asnumpy(F.gather_row(orig_nid_map, shuffled_dst))
orig_eid = F.asnumpy(F.gather_row(orig_eid_map, shuffled_eid))
etype_map = {g.get_etype_id(etype): etype for etype in g.etypes}
etype_to_eptype = {
g.get_etype_id(etype): (src_ntype, dst_ntype)
for src_ntype, etype, dst_ntype in g.canonical_etypes
}
for e in np.unique(etype):
src_t = src_type[etype == e]
dst_t = dst_type[etype == e]
assert np.all(src_t == src_t[0])
assert np.all(dst_t == dst_t[0])
# Check the node Ids and edge Ids.
orig_src1, orig_dst1 = g.find_edges(orig_eid[etype == e],
etype=etype_map[e])
assert np.all(F.asnumpy(orig_src1) == orig_src[etype == e])
assert np.all(F.asnumpy(orig_dst1) == orig_dst[etype == e])
# Check the node types.
src_ntype, dst_ntype = etype_to_eptype[e]
assert np.all(src_t == g.get_ntype_id(src_ntype))
assert np.all(dst_t == g.get_ntype_id(dst_ntype))
