def _create_example(self, lines, set_type):
examples = []
for (i, line) in enumerate(lines):
guid = "%s-%s" % (set_type, i)
text_a = tokenization.convert_to_unicode(line[1])
text_b = tokenization.convert_to_unicode(line[2])
label = tokenization.convert_to_unicode(line[0])
examples.append(InputExample(
guid=guid, text_a=text_a, text_b=text_b, label=label))
return examples
def _create_example(self, lines, set_type):
examples = []
for (i, line) in enumerate(lines):
guid = "%s-%s" % (set_type, i)
text = tokenization.convert_to_unicode(line[1])
label = tokenization.convert_to_unicode(line[0])
# if i == 0:
# print('label: ', label)
examples.append(InputExample(guid=guid, text=text, label=label))
return examples
def _create_example(self, lines, set_type):
examples = []
for (i, line) in enumerate(lines):
guid = "%s-%s" % (set_type, i)
text_a = tokenization.convert_to_unicode(line[0])
# 多标签分类的label
label = np.zeros(shape=[50], dtype=np.int32)
l_list = line[1].strip().split(' ')
for l in l_list:
label[self.labels.index(l)] = 1
examples.append(InputExample(
guid=guid, text_a=text_a, text_b=None, label=label))
return examples
def _create_examples(self, df, set_type):
"""Creates examples for the training and dev sets."""
# lines
# [
# ['O O O O B-LOC B-LOC O B-LOC B- O O', '你 好 啊 啊 啊 啊 '],
# ['O O O O B-LOC B-LOC O B-LOC B- O O', '你 好 啊 啊 啊 啊 ']
# ]
# """
examples = []
for (i, line) in df.iterrows():
# if i == 0:
# continue
guid = "%s-%s" % (set_type, i)
texts = tokenization.convert_to_unicode(line['texts'])
label = tokenization.convert_to_unicode(line['labels'])
examples.append(
InputExample(guid=guid, text=texts, label=label))
return examples