def generate_target():
target_matrix = generate_target_matrix(data[TARGET_REL_ID],
args.target_n_samples,
args.target_pos_rate, device)
data_target = SparseMatrixData(target_schema)
data_target[TARGET_REL_ID] = target_matrix
data_target.to(device)
return data_target
embedding_entity = schema.entities[TARGET_NODE_TYPE]
input_channels = {
rel.id: data[rel.id].n_channels
for rel in schema.relations
}
embedding_schema = DataSchema(
schema.entities,
Relation(0, [embedding_entity, embedding_entity], is_set=True))
n_instances = embedding_entity.n_instances
data_embedding = SparseMatrixData(embedding_schema)
data_embedding[0] = SparseMatrix(
indices=torch.arange(n_instances, dtype=torch.int64).repeat(2, 1),
values=torch.zeros([n_instances, args.embedding_dim]),
shape=(n_instances, n_instances, args.embedding_dim),
is_set=True)
data_embedding.to(device)
target_schema = DataSchema(schema.entities,
schema.relations[TARGET_REL_ID])
target_node_idx_to_id = dataloader.target_node_idx_to_id
#%%
net = SparseMatrixAutoEncoder(schema,
input_channels,
layers=args.layers,
embedding_dim=args.embedding_dim,
embedding_entities=[embedding_entity],
activation=eval('nn.%s()' % args.act_fn),
final_activation=nn.Sigmoid(),
dropout=args.dropout_rate,
norm=args.norm,
pool_op=args.pool_op,
norm_affine=args.norm_affine,
rel_movie_director = Relation(1, [ent_movie, ent_director])
rel_movie_keyword = Relation(2, [ent_movie, ent_keyword])
rel_movie_feature = Relation(3, [ent_movie, ent_movie], is_set=True)
relations = [rel_movie_actor, rel_movie_director, rel_movie_keyword, rel_movie_feature]
schema = DataSchema(entities, relations)
schema_out = DataSchema([ent_movie], [Relation(0, [ent_movie, ent_movie], is_set=True)])
data = SparseMatrixData(schema)
for rel_i, rel_name in enumerate(relation_names):
if rel_name == 'movie_feature':
values = preprocess_features(raw_data[rel_name])
data[rel_i] = SparseMatrix.from_embed_diag(values)
else:
data[rel_i] = SparseMatrix.from_scipy_sparse(raw_data[rel_name])
data = data.to(device)
indices_identity, indices_transpose = data.calculate_indices()
input_channels = {rel.id: data[rel.id].n_channels for rel in relations}
data_target = Data(schema_out)
n_movies = ent_movie.n_instances
labels = []
with open(data_file_dir + 'index_label.txt', 'r') as label_file:
lines = label_file.readlines()
for line in lines:
label = line.rstrip().split(',')[1]
labels.append(int(label))
labels = torch.LongTensor(labels).to(device) - min(labels)
shuffled_indices = random.sample(range(n_movies), n_movies)
val_start = 0
test_start = int(args.val_pct * (n_movies/100.))
