def test_out_subgraph(index_dtype):
g1 = dgl.graph([(1,0),(2,0),(3,0),(0,1),(2,1),(3,1),(0,2)], 'user', 'follow', index_dtype=index_dtype)
g2 = dgl.bipartite([(0,0),(0,1),(1,2),(3,2)], 'user', 'play', 'game', index_dtype=index_dtype)
g3 = dgl.bipartite([(2,0),(2,1),(2,2),(1,0),(1,3),(0,0)], 'game', 'liked-by', 'user', index_dtype=index_dtype)
g4 = dgl.bipartite([(0,0),(1,0),(2,0),(3,0)], 'user', 'flips', 'coin', index_dtype=index_dtype)
hg = dgl.hetero_from_relations([g1, g2, g3, g4])
subg = dgl.out_subgraph(hg, {'user' : [0,1], 'game' : 0})
assert subg._idtype_str == index_dtype
assert len(subg.ntypes) == 3
assert len(subg.etypes) == 4
u, v = subg['follow'].edges()
edge_set = set(zip(list(F.asnumpy(u)), list(F.asnumpy(v))))
assert edge_set == {(1,0),(0,1),(0,2)}
assert F.array_equal(hg['follow'].edge_ids(u, v), subg['follow'].edata[dgl.EID])
u, v = subg['play'].edges()
edge_set = set(zip(list(F.asnumpy(u)), list(F.asnumpy(v))))
assert edge_set == {(0,0),(0,1),(1,2)}
assert F.array_equal(hg['play'].edge_ids(u, v), subg['play'].edata[dgl.EID])
u, v = subg['liked-by'].edges()
edge_set = set(zip(list(F.asnumpy(u)), list(F.asnumpy(v))))
assert edge_set == {(0,0)}
assert F.array_equal(hg['liked-by'].edge_ids(u, v), subg['liked-by'].edata[dgl.EID])
u, v = subg['flips'].edges()
edge_set = set(zip(list(F.asnumpy(u)), list(F.asnumpy(v))))
assert edge_set == {(0,0),(1,0)}
assert F.array_equal(hg['flips'].edge_ids(u, v), subg['flips'].edata[dgl.EID])
def test_out_subgraph(idtype):
hg = dgl.heterograph({
('user', 'follow', 'user'): ([1, 2, 3, 0, 2, 3, 0], [0, 0, 0, 1, 1, 1, 2]),
('user', 'play', 'game'): ([0, 0, 1, 3], [0, 1, 2, 2]),
('game', 'liked-by', 'user'): ([2, 2, 2, 1, 1, 0], [0, 1, 2, 0, 3, 0]),
('user', 'flips', 'coin'): ([0, 1, 2, 3], [0, 0, 0, 0])
}, idtype=idtype)
subg = dgl.out_subgraph(hg, {'user' : [0,1], 'game' : 0})
assert subg.idtype == idtype
assert len(subg.ntypes) == 3
assert len(subg.etypes) == 4
u, v = subg['follow'].edges()
edge_set = set(zip(list(F.asnumpy(u)), list(F.asnumpy(v))))
assert edge_set == {(1,0),(0,1),(0,2)}
assert F.array_equal(hg['follow'].edge_ids(u, v), subg['follow'].edata[dgl.EID])
u, v = subg['play'].edges()
edge_set = set(zip(list(F.asnumpy(u)), list(F.asnumpy(v))))
assert edge_set == {(0,0),(0,1),(1,2)}
assert F.array_equal(hg['play'].edge_ids(u, v), subg['play'].edata[dgl.EID])
u, v = subg['liked-by'].edges()
edge_set = set(zip(list(F.asnumpy(u)), list(F.asnumpy(v))))
assert edge_set == {(0,0)}
assert F.array_equal(hg['liked-by'].edge_ids(u, v), subg['liked-by'].edata[dgl.EID])
u, v = subg['flips'].edges()
edge_set = set(zip(list(F.asnumpy(u)), list(F.asnumpy(v))))
assert edge_set == {(0,0),(1,0)}
assert F.array_equal(hg['flips'].edge_ids(u, v), subg['flips'].edata[dgl.EID])
def evaluate(g, field_ids, author_rank, true_relevance, field_paper):
predict_rank = {}
field_feat = g.nodes['field'].data['feat']
apg = g['paper', 'writes_rev', 'author']
for i, f in enumerate(field_ids):
pid = field_paper[f]
paper_score = torch.matmul(g.nodes['paper'].data['feat'][pid],
field_feat[f])
sg = dgl.out_subgraph(apg, {'paper': pid}, relabel_nodes=True)
sg.nodes['paper'].data['score'] = paper_score
sg.update_all(fn.copy_u('score', 's'), fn.sum('s', 's'))
predict_rank[f] = (sg.nodes['author'].data[dgl.NID],
sg.nodes['author'].data['s'])
return calc_metrics(field_ids, author_rank, true_relevance, predict_rank)
def recall_paper(g, field_ids, num_recall):
"""预先计算论文召回
:param g: DGLGraph 异构图
:param field_ids: List[int] 目标领域id
:param num_recall: 每个领域召回的论文数
:return: Dict[int, List[int]] {field_id: [paper_id]}
"""
similarity = torch.zeros(len(field_ids), g.num_nodes('paper'))
sg = dgl.out_subgraph(g['has_field_rev'], {'field': field_ids},
relabel_nodes=True)
sg.apply_edges(fn.u_dot_v('feat', 'feat', 's'))
f, p = sg.edges()
similarity[f, sg.nodes['paper'].data[dgl.NID][p]] = sg.edata['s'].squeeze(
dim=1)
_, pid = similarity.topk(num_recall, dim=1)
return {f: pid[i].tolist() for i, f in enumerate(field_ids)}
def test_out_subgraph(idtype):
hg = dgl.heterograph(
{
('user', 'follow', 'user'):
([1, 2, 3, 0, 2, 3, 0], [0, 0, 0, 1, 1, 1, 2]),
('user', 'play', 'game'): ([0, 0, 1, 3], [0, 1, 2, 2]),
('game', 'liked-by', 'user'):
([2, 2, 2, 1, 1, 0], [0, 1, 2, 0, 3, 0]),
('user', 'flips', 'coin'): ([0, 1, 2, 3], [0, 0, 0, 0])
},
idtype=idtype)
subg = dgl.out_subgraph(hg, {'user': [0, 1], 'game': 0})
assert subg.idtype == idtype
assert len(subg.ntypes) == 3
assert len(subg.etypes) == 4
u, v = subg['follow'].edges()
edge_set = set(zip(list(F.asnumpy(u)), list(F.asnumpy(v))))
assert edge_set == {(1, 0), (0, 1), (0, 2)}
assert F.array_equal(hg['follow'].edge_ids(u, v),
subg['follow'].edata[dgl.EID])
u, v = subg['play'].edges()
edge_set = set(zip(list(F.asnumpy(u)), list(F.asnumpy(v))))
assert edge_set == {(0, 0), (0, 1), (1, 2)}
assert F.array_equal(hg['play'].edge_ids(u, v),
subg['play'].edata[dgl.EID])
u, v = subg['liked-by'].edges()
edge_set = set(zip(list(F.asnumpy(u)), list(F.asnumpy(v))))
assert edge_set == {(0, 0)}
assert F.array_equal(hg['liked-by'].edge_ids(u, v),
subg['liked-by'].edata[dgl.EID])
u, v = subg['flips'].edges()
edge_set = set(zip(list(F.asnumpy(u)), list(F.asnumpy(v))))
assert edge_set == {(0, 0), (1, 0)}
assert F.array_equal(hg['flips'].edge_ids(u, v),
subg['flips'].edata[dgl.EID])
for ntype in subg.ntypes:
assert dgl.NID not in subg.nodes[ntype].data
# Test store_ids
subg = dgl.out_subgraph(hg, {'user': [0, 1], 'game': 0}, store_ids=False)
for etype in subg.canonical_etypes:
assert dgl.EID not in subg.edges[etype].data
for ntype in subg.ntypes:
assert dgl.NID not in subg.nodes[ntype].data
# Test relabel nodes
subg = dgl.out_subgraph(hg, {'user': [1], 'game': 0}, relabel_nodes=True)
assert subg.idtype == idtype
assert len(subg.ntypes) == 3
assert len(subg.etypes) == 4
u, v = subg['follow'].edges()
old_u = F.gather_row(subg.nodes['user'].data[dgl.NID], u)
old_v = F.gather_row(subg.nodes['user'].data[dgl.NID], v)
edge_set = set(zip(list(F.asnumpy(old_u)), list(F.asnumpy(old_v))))
assert edge_set == {(1, 0)}
assert F.array_equal(hg['follow'].edge_ids(old_u, old_v),
subg['follow'].edata[dgl.EID])
u, v = subg['play'].edges()
old_u = F.gather_row(subg.nodes['user'].data[dgl.NID], u)
old_v = F.gather_row(subg.nodes['game'].data[dgl.NID], v)
edge_set = set(zip(list(F.asnumpy(old_u)), list(F.asnumpy(old_v))))
assert edge_set == {(1, 2)}
assert F.array_equal(hg['play'].edge_ids(old_u, old_v),
subg['play'].edata[dgl.EID])
u, v = subg['liked-by'].edges()
old_u = F.gather_row(subg.nodes['game'].data[dgl.NID], u)
old_v = F.gather_row(subg.nodes['user'].data[dgl.NID], v)
edge_set = set(zip(list(F.asnumpy(old_u)), list(F.asnumpy(old_v))))
assert edge_set == {(0, 0)}
assert F.array_equal(hg['liked-by'].edge_ids(old_u, old_v),
subg['liked-by'].edata[dgl.EID])
u, v = subg['flips'].edges()
old_u = F.gather_row(subg.nodes['user'].data[dgl.NID], u)
old_v = F.gather_row(subg.nodes['coin'].data[dgl.NID], v)
edge_set = set(zip(list(F.asnumpy(old_u)), list(F.asnumpy(old_v))))
assert edge_set == {(1, 0)}
assert F.array_equal(hg['flips'].edge_ids(old_u, old_v),
subg['flips'].edata[dgl.EID])
assert subg.num_nodes('user') == 2
assert subg.num_nodes('game') == 2
assert subg.num_nodes('coin') == 1
num_edges = data.num_edges()
num_edges = data.num_edges()
trainval_div = int(VALID_SPLIT * num_edges)
# Select new node from test set and remove them from entire graph
test_split_ts = data.edata['timestamp'][trainval_div]
test_nodes = torch.cat(
[data.edges()[0][trainval_div:],
data.edges()[1][trainval_div:]]).unique().numpy()
test_new_nodes = np.random.choice(test_nodes,
int(0.1 * len(test_nodes)),
replace=False)
in_subg = dgl.in_subgraph(data, test_new_nodes)
out_subg = dgl.out_subgraph(data, test_new_nodes)
# Remove edge who happen before the test set to prevent from learning the connection info
new_node_in_eid_delete = in_subg.edata[dgl.EID][
in_subg.edata['timestamp'] < test_split_ts]
new_node_out_eid_delete = out_subg.edata[dgl.EID][
out_subg.edata['timestamp'] < test_split_ts]
new_node_eid_delete = torch.cat(
[new_node_in_eid_delete, new_node_out_eid_delete]).unique()
graph_new_node = copy.deepcopy(data)
# relative order preseved
graph_new_node.remove_edges(new_node_eid_delete)
# Now for no new node graph, all edge id need to be removed
in_eid_delete = in_subg.edata[dgl.EID]
out_eid_delete = out_subg.edata[dgl.EID]
