def __init__(self, data, word2idx, tolower=True):
super(GraphData, self).__init__()
g_p = utils.doc2graph(Document(data[config.pf]))
g_h = utils.doc2graph(Document(data[config.hf]))
self.edge_index_p = g_p.edge_index
self.edge_index_h = g_h.edge_index
#print(g_p.node_attr)
# care [ROOT] [UNK] should not get lower!!!
if tolower == True:
self.x_p = torch.tensor([
word2idx[w.lower() if w[0] != "[" or w[-1] != "]" else w]
for w in g_p.node_attr
],
dtype=torch.long)
self.x_h = torch.tensor([
word2idx[w.lower() if w[0] != "[" or w[-1] != "]" else w]
for w in g_h.node_attr
],
dtype=torch.long)
else:
print("not to lower")
self.x_p = torch.tensor([word2idx[w] for w in g_p.node_attr],
dtype=torch.long)
self.x_h = torch.tensor([word2idx[w] for w in g_h.node_attr],
dtype=torch.long)
label_onehot = torch.zeros([1, config.NUM_CLASSES])
label_onehot[0][data[config.lf]] = 1
#label_onehot = label_onehot.squeeze()
#print(label_onehot.size())
self.label = label_onehot.to(dtype=torch.float)
self.pid = data[config.idf]
def __init__(self, data, word2idx, tolower=True):
super(GraphData, self).__init__()
g_p = utils.doc2graph(Document(data[config.pf]))
g_h = utils.doc2graph(Document(data[config.hf]))
self.edge_index_p = g_p.edge_index
self.edge_index_h = g_h.edge_index
#print(g_p.node_attr)
# care [ROOT] [UNK] should not get lower!!!
if tolower == True:
self.x_p = torch.tensor([
word2idx[w.lower() if w[0] != "[" or w[-1] != "]" else w]
for w in g_p.node_attr
],
dtype=torch.long)
self.x_h = torch.tensor([
word2idx[w.lower() if w[0] != "[" or w[-1] != "]" else w]
for w in g_h.node_attr
],
dtype=torch.long)
else:
print("not to lower")
self.x_p = torch.tensor([word2idx[w] for w in g_p.node_attr],
dtype=torch.long)
self.x_h = torch.tensor([word2idx[w] for w in g_h.node_attr],
dtype=torch.long)
self.label = data[config.lf]
self.pid = data[config.idf]
def check_mwt(filename):
"""
Checks whether or not there are MWTs in the given conll file
"""
doc = Document(CoNLL.conll2dict(filename))
data = doc.get_mwt_expansions(False)
return len(data) > 0