def process(self):
data_list = []
indices_train = []
indices_val = []
indices_test = []
infile = open("train.index.txt", "r")
for line in infile:
indices_train = line.split(",")
indices_train = [int(i) for i in indices_train]
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("test.index.txt", "r")
for line in infile:
indices_test = line.split(",")
indices_test = [int(i) for i in indices_test]
dp.get_dataset("ZINC_train", regression=True)
dp.get_dataset("ZINC_test", regression=True)
dp.get_dataset("ZINC_val", regression=True)
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_dwl("ZINC_train", indices_train)
matrices.extend(pre.get_all_matrices_dwl("ZINC_val", indices_val))
matrices.extend(pre.get_all_matrices_dwl("ZINC_test", indices_test))
for i, m in enumerate(matrices):
edge_index_1_l = torch.tensor(matrices[i][0]).t().contiguous()
edge_index_1_g = torch.tensor(matrices[i][1]).t().contiguous()
edge_index_2_l = torch.tensor(matrices[i][2]).t().contiguous()
edge_index_2_g = torch.tensor(matrices[i][3]).t().contiguous()
data = Data()
data.edge_index_1_l = edge_index_1_l
data.edge_index_1_g = edge_index_1_g
data.edge_index_2_l = edge_index_2_l
data.edge_index_2_g = edge_index_2_g
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 = []
indices_train = []
indices_val = []
indices_test = []
indices_train = []
indices_val = []
infile = open("train_50.index.txt", "r")
for line in infile:
indices_train = line.split(",")
indices_train = [int(i) for i in indices_train]
infile = open("val_50.index.txt", "r")
for line in infile:
indices_val = line.split(",")
indices_val = [int(i) for i in indices_val]
indices_test = list(range(0, 5000))
dp.get_dataset("ZINC_train")
dp.get_dataset("ZINC_test")
dp.get_dataset("ZINC_val")
node_labels = pre.get_all_node_labels_ZINC_connected(
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_connected("ZINC_train", indices_train)
matrices.extend(pre.get_all_matrices_connected("ZINC_val",
indices_val))
matrices.extend(
pre.get_all_matrices_connected("ZINC_test", indices_test))
for i, m in enumerate(matrices):
edge_index_1 = torch.tensor(matrices[i][0]).t().contiguous().long()
edge_index_2 = torch.tensor(matrices[i][1]).t().contiguous().long()
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 = []
dp.get_dataset("ZINC_test", regression=True)
# TODO Change this
node_labels = pre.get_all_node_labels("ZINC_full", True, True)
targets = pre.read_targets("ZINC_test", list(range(0, 5000)))
node_labels_1 = node_labels[220011:225011]
matrices = pre.get_all_matrices_wl("ZINC_test", list(range(0, 5000)))
targets_1 = targets
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(492)[node_labels[i]]
data.x = torch.from_numpy(np.array(node_labels_1[i])).to(
torch.float)
data.y = data.y = torch.from_numpy(np.array([targets_1[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_val = list(range(225011, 249456))
dp.get_dataset("ZINC_val", regression=True)
node_labels = pre.get_all_node_labels("ZINC_full", True, True)
targets = pre.read_targets("ZINC_val", list(range(0, 24445)))
node_labels_1 = node_labels[225011:249456]
matrices = pre.get_all_matrices_wl("ZINC_val", list(range(0, 24445)))
targets_1 = targets
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
data.x = torch.from_numpy(np.array(node_labels_1[i])).to(
torch.float)
data.y = data.y = torch.from_numpy(np.array([targets_1[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 = list(range(0, 220011))
indices_val = list(range(0, 24445))
indices_test = list(range(0, 5000))
dp.get_dataset("ZINC_train", regression=True)
dp.get_dataset("ZINC_test", regression=True)
dp.get_dataset("ZINC_val", regression=True)
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))
node_labels = node_labels[0:50000]
matrices = pre.get_all_matrices_dwl("ZINC_train", list(range(0,
50000)))
targets = targets[0:50000]
for i, m in enumerate(matrices):
edge_index_1_l = torch.tensor(matrices[i][0]).t().contiguous()
edge_index_1_g = torch.tensor(matrices[i][1]).t().contiguous()
edge_index_2_l = torch.tensor(matrices[i][2]).t().contiguous()
edge_index_2_g = torch.tensor(matrices[i][3]).t().contiguous()
data = Data()
data.edge_index_1_l = edge_index_1_l
data.edge_index_1_g = edge_index_1_g
data.edge_index_2_l = edge_index_2_l
data.edge_index_2_g = edge_index_2_g
data.x = torch.from_numpy(np.array(node_labels[i])).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])
