def process(self):
data_list = []
indices_train = []
indices_val = []
indices_test = []
infile = open("test_al_50.index", "r")
for line in infile:
indices_test = line.split(",")
indices_test = [int(i) for i in indices_test]
infile = open("val_al_50.index", "r")
for line in infile:
indices_val = line.split(",")
indices_val = [int(i) for i in indices_val]
infile = open("train_al_50.index", "r")
for line in infile:
indices_train = line.split(",")
indices_train = [int(i) for i in indices_train]
targets = dp.get_dataset("alchemy_full", multigregression=True)
tmp_1 = targets[indices_train].tolist()
tmp_2 = targets[indices_val].tolist()
tmp_3 = targets[indices_test].tolist()
targets = tmp_1
targets.extend(tmp_2)
targets.extend(tmp_3)
node_labels = pre.get_all_node_labels_allchem(True, True,
indices_train,
indices_val,
indices_test)
matrices = pre.get_all_matrices("alchemy_full", indices_train)
matrices.extend(pre.get_all_matrices("alchemy_full", indices_val))
matrices.extend(pre.get_all_matrices("alchemy_full", indices_test))
for i, m in enumerate(matrices):
print(i)
edge_index_1 = torch.tensor(matrices[i][0]).t().contiguous()
edge_index_2 = torch.tensor(matrices[i][1]).t().contiguous()
data = Data()
data.edge_index_1 = edge_index_1
data.edge_index_2 = edge_index_2
one_hot = np.eye(83)[node_labels[i]]
data.x = torch.from_numpy(one_hot).to(torch.float)
data.y = data.y = torch.from_numpy(np.array([targets[i]
])).to(torch.float)
data_list.append(data)
data, slices = self.collate(data_list)
torch.save((data, slices), self.processed_paths[0])
def process(self):
data_list = []
indices_train = []
indices_val = []
indices_test = []
infile = open("test.index.txt", "r")
for line in infile:
indices_test = line.split(",")
indices_test = [int(i) for i in indices_test]
infile = open("val.index.txt", "r")
for line in infile:
indices_val = line.split(",")
indices_val = [int(i) for i in indices_val]
infile = open("train.index.txt", "r")
for line in infile:
indices_train = line.split(",")
indices_train = [int(i) for i in indices_train]
dp.get_dataset("ZINC_train")
dp.get_dataset("ZINC_test")
dp.get_dataset("ZINC_val")
node_labels = pre.get_all_node_labels_ZINC(True, True, indices_train,
indices_val, indices_test)
targets = pre.read_targets("ZINC_train", indices_train)
targets.extend(pre.read_targets("ZINC_val", indices_val))
targets.extend(pre.read_targets("ZINC_test", indices_test))
matrices = pre.get_all_matrices("ZINC_train", indices_train)
matrices.extend(pre.get_all_matrices("ZINC_val", indices_val))
matrices.extend(pre.get_all_matrices("ZINC_test", indices_test))
for i, m in enumerate(matrices):
edge_index_1 = torch.tensor(matrices[i][0]).t().contiguous()
edge_index_2 = torch.tensor(matrices[i][1]).t().contiguous()
data = Data()
data.edge_index_1 = edge_index_1
data.edge_index_2 = edge_index_2
one_hot = np.eye(445)[node_labels[i]]
data.x = torch.from_numpy(one_hot).to(torch.float)
data.y = data.y = torch.from_numpy(np.array([targets[i]
])).to(torch.float)
data_list.append(data)
data, slices = self.collate(data_list)
torch.save((data, slices), self.processed_paths[0])
def process(self):
data_list = []
targets = dp.get_dataset("alchemy_full",
multigregression=True).tolist()
node_labels = pre.get_all_node_labels("alchemy_full", True, True)
matrices = pre.get_all_matrices("alchemy_full", list(range(202579)))
for i, m in enumerate(matrices):
edge_index_1 = torch.tensor(matrices[i][0]).t().contiguous()
edge_index_2 = torch.tensor(matrices[i][1]).t().contiguous()
data = Data()
data.edge_index_1 = edge_index_1
data.edge_index_2 = edge_index_2
one_hot = np.eye(83)[node_labels[i]]
data.x = torch.from_numpy(one_hot).to(torch.float)
data.y = data.y = torch.from_numpy(np.array([targets[i]
])).to(torch.float)
data_list.append(data)
data, slices = self.collate(data_list)
torch.save((data, slices), self.processed_paths[0])
def process(self):
data_list = []
targets = dp.get_dataset("QM9", multigregression=True).tolist()
attributes = pre.get_all_attributes("QM9")
node_labels = pre.get_all_node_labels("QM9", False, False)
matrices = pre.get_all_matrices("QM9", list(range(129433)))
for i, m in enumerate(matrices):
edge_index_1 = torch.tensor(matrices[i][0]).t().contiguous()
edge_index_2 = torch.tensor(matrices[i][1]).t().contiguous()
data = Data()
data.edge_index_1 = edge_index_1
data.edge_index_2 = edge_index_2
one_hot = np.eye(3)[node_labels[i]]
data.x = torch.from_numpy(one_hot).to(torch.float)
# Continuous information.
data.first = torch.from_numpy(np.array(
attributes[i][0])[:, 0:13]).to(torch.float)
data.first_coord = torch.from_numpy(
np.array(attributes[i][0])[:, 13:]).to(torch.float)
data.second = torch.from_numpy(
np.array(attributes[i][1])[:, 0:13]).to(torch.float)
data.second_coord = torch.from_numpy(
np.array(attributes[i][1])[:, 13:]).to(torch.float)
data.dist = torch.norm(data.first_coord - data.second_coord,
p=2,
dim=-1).view(-1, 1)
data.edge_attr = torch.from_numpy(np.array(attributes[i][2])).to(
torch.float)
data.y = torch.from_numpy(np.array([targets[i]])).to(torch.float)
data_list.append(data)
data, slices = self.collate(data_list)
torch.save((data, slices), self.processed_paths[0])
