utils_data_prep.py

2 F841: local variable 'node_feature_flag' is assigned to but never used (and 1 similar)
- Local variable 'node_feature_flag' is assigned to but never used:
  88 node_feature_flag = False
- Local variable 'deg_list' is assigned to but never used:
  111 deg_list = list(dict(g.g.degree(range(len(g.g)))).values())
1 F401: 'random' imported but unused
- 7 import random
23 W293: blank line contains whitespace
- 17
- 38
- 140
- 142
- 145
- 147
- 149
- 154
- 164
- 168
- 170
- 178
- 180
- 184
- 201
- 214
- 219
- 221
- 231
- 243
- 245
- 253
- 257
21 E501: line too long (119 > 79 characters) (and 14 similar)
- Line too long (119 > 79 characters):
  21 node_features: a torch float tensor, one-hot representation of the tag that is used as input to neural nets
- Line too long (104 > 79 characters):
  22 edge_mat: a torch long tensor, contain edge list, will be used to create torch sparse tensor
- Line too long (100 > 79 characters):
  70 row, attr = [int(w) for w in row[:tmp]], np.array([float(w) for w in row[tmp:]])
- Line too long (93 > 79 characters):
  128 g.node_features[range(len(g.node_tags)), [tag2index[tag] for tag in g.node_tags]] = 1
- Line too long (81 > 79 characters):
  139 def load_zinc_data(path, name, degree_as_tag, num_atom_type=28, num_bond_type=4):
- Line too long (148 > 79 characters):
  141 ### splits and preprocessing according to https://github.com/graphdeeplearning/benchmarking-gnns/blob/master/main_molecules_graph_regression.py
- Line too long (88 > 79 characters):
  144 Graph = namedtuple('Graph', ['node_features', 'edge_mat', 'edge_features', 'label'])
- Line too long (83 > 79 characters):
  156 graph = Graph(node_features, edge_list.permute(1, 0), edge_features, label)
- Line too long (92 > 79 characters):
  162 with open(os.path.join(path,'molecules','{}.pickle'.format(split_name)), "rb") as f:
- Line too long (90 > 79 characters):
  166 with open(os.path.join(path, 'indices', '{}.index'.format(split_name)), "r") as f:
- Line too long (83 > 79 characters):
  179 ### splits and preprocessing according to https://github.com/snap-stanford/ogb
- Line too long (84 > 79 characters):
  188 dataset = PygGraphPropPredDataset(name=name, root=path, transform=transform)
- Line too long (88 > 79 characters):
  191 Graph = namedtuple('Graph', ['node_features', 'edge_mat', 'edge_features', 'label'])
- Line too long (82 > 79 characters):
  196 num_classes = dataset.num_classes if name == 'ogbg-ppa' else dataset.num_tasks
- Line too long (106 > 79 characters):
  202 ### code used to load SR graphs obtained from here http://users.cecs.anu.edu.au/~bdm/data/graphs.html
- Line too long (130 > 79 characters):
  203 ### we don't split the data, because no training is performed (the network is used with random weights for the SR experiment)
- Line too long (84 > 79 characters):
  210 edge_index = to_undirected(torch.tensor(list(datum.edges())).transpose(1,0))
- Line too long (143 > 79 characters):
  246 assert -1 <= fold_idx and fold_idx < 10, "Parameter fold_idx must be from -1 to 9, with -1 referring to the special model selection split."
- Line too long (92 > 79 characters):
  248 train_filename = os.path.join(path, '10fold_idx', 'train_idx-{}.txt'.format(fold_idx+1))
- Line too long (90 > 79 characters):
  249 test_filename = os.path.join(path, '10fold_idx', 'test_idx-{}.txt'.format(fold_idx+1))
- Line too long (88 > 79 characters):
  250 val_filename = os.path.join(path, '10fold_idx', 'val_idx-{}.txt'.format(fold_idx+1))
8 E231: missing whitespace after ',' (and 1 similar)
- Missing whitespace after ',':
  112 g.edge_mat = torch.LongTensor(edges).transpose(0,1)
- Missing whitespace after ':':
  124 tag2index = {tagset[i]:i for i in range(len(tagset))}
- Missing whitespace after ',' (in 2 places):
  162 with open(os.path.join(path,'molecules','{}.pickle'.format(split_name)), "rb") as f:
- Missing whitespace after ',':
  206 Graph = namedtuple('Graph', ['node_features', 'edge_mat','label'])
- Missing whitespace after ',':
  208 for i,datum in enumerate(dataset):
- Missing whitespace after ',':
  209 x = torch.ones(datum.number_of_nodes(),1)
- Missing whitespace after ',':
  210 edge_index = to_undirected(torch.tensor(list(datum.edges())).transpose(1,0))
6 E266: too many leading '#' for block comment
4 E114: indentation is not a multiple of 4 (comment)
4 E117: over-indented (comment)
4 E251: unexpected spaces around keyword / parameter equals
- Unexpected spaces around keyword / parameter equals (in 4 places):
  223 skf = StratifiedKFold(n_splits=10, shuffle = True, random_state = seed)
3 W291: trailing whitespace
2 E265: block comment should start with '# '
- 94 #add labels and edge_mat
- 118 #Extracting unique tag labels
2 E302: expected 2 blank lines, found 1
- 13 class S2VGraph(object):
- 242 def separate_data_given_split(graph_list, path, fold_idx):
1 E201: whitespace after '['
- 169 split_data = [ split_data[i] for i in data_idx[0] ]
1 E202: whitespace before ']'
- 169 split_data = [ split_data[i] for i in data_idx[0] ]
1 E303: too many blank lines (2)
- 131 print('# classes: %d' % len(label_dict))
1 E713: test for membership should be 'not in'
- 54 if not l in label_dict:
1 E741: ambiguous variable name 'l'
- 53 n, l = [int(w) for w in row]