def _create_examples(self, lines, set_type):
"""Creates examples for the training and dev sets."""
examples = []
for (i, line) in enumerate(lines):
guid = '%s-%s' % (set_type, i)
# print(line)
text_a = tokenization.convert_to_unicode(line[1])
label = tokenization.convert_to_unicode(line[0])
examples.append(InputExample(guid=guid, text_a=text_a, label=label))
return examples
def _create_examples(self, lines, set_type):
"""Creates examples for the training and dev sets."""
examples = []
for (i, line) in enumerate(lines):
guid = "%s-%s" % (set_type, i)
text_a = tokenization.convert_to_unicode(line[0])
text_b = tokenization.convert_to_unicode(line[1])
if set_type == "test":
label = "0"
examples.append(
InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label))
return examples
def _create_examples(self, lines, set_type):
"""Creates examples for the training and dev sets."""
examples = []
for (i, line) in enumerate(lines):
if set_type == 'test':
json_str = json.loads(line)
text_a = tokenization.convert_to_unicode(json_str['text'])
tag = None
guid = json_str['id']
else:
text_tag = line.split('\t')
guid = "%s-%s" % (set_type, i)
text_a = tokenization.convert_to_unicode(text_tag[0])
tag = tokenization.convert_to_unicode(text_tag[1])
examples.append(
InputExample(guid=guid, text_a=text_a, text_b=None, tag=tag))
return examples
def _create_examples(self, lines, set_type):
"""Creates examples for the training and dev sets."""
examples = []
print(len(lines))
for (i, line) in enumerate(lines):
if i == 0:
continue
guid = "%s-%s" % (set_type, i)
line = line[0].split('***') #*************
text_a = tokenization.convert_to_unicode(line[1])
label = tokenization.convert_to_unicode(line[0])
examples.append(
InputExample(guid=guid,
text_a=text_a,
text_b=None,
label=label))
return examples
def _create_examples(self, lines, set_type):
"""Creates examples for the training and dev sets."""
examples = []
for (i, line) in enumerate(lines):
# Only the test set has a header
if set_type == "test":
continue
guid = "%s-%s" % (set_type, i)
if set_type == "test":
text_a = tokenization.convert_to_unicode(line[0])
label = "0"
else:
text_a = tokenization.convert_to_unicode(line[0])
label = tokenization.convert_to_unicode(line[1])
examples.append(
InputExample(guid=guid, text_a=text_a, text_b=None, label=label))
return examples
def _create_examples(self, lines, set_type):
"""Creates examples for the training and dev sets."""
examples = []
for (i, line) in enumerate(lines):
json_str = json.loads(line)
guid = "%s-%s" % (set_type, i)
if set_type == "test":
text_a = tokenization.convert_to_unicode(json_str['sentence'])
label = None
guid = json_str['id']
else:
text_a = tokenization.convert_to_unicode(json_str['sentence'])
label = tokenization.convert_to_unicode(json_str['label'])
examples.append(
InputExample(guid=guid,
text_a=text_a,
text_b=None,
label=label))
return examples
def read_examples(case):
"""Read a list of `InputExample`s from a case from
Shelf :: {'headings': String, 'body': [String]}."""
examples = []
unique_id = 0
sentence_list = [case['headings']] + case['body']
for sentence in sentence_list:
line = tokenization.convert_to_unicode(sentence)
line = line.strip()
text_a = None
text_b = None
m = re.match(r"^(.*) \|\|\| (.*)$", line)
if m is None:
text_a = line
else:
text_a = m.group(1)
text_b = m.group(2)
examples.append(
InputExample(unique_id=unique_id, text_a=text_a, text_b=text_b))
unique_id += 1
return examples
def _create_examples(self, lines, set_type):
"""Creates examples for the training and dev sets."""
examples = []
for (i, line) in enumerate(lines):
guid = "%s-%s" % (set_type, i)
# line 是一个字典
text_a = [
tokenization.convert_to_unicode(sent) for sent in line['src']
]
# text_a = tokenization.convert_to_unicode(line[1])
if set_type == 'train' or set_type == 'dev':
label = line['ids']
examples.append(
InputExample(guid=guid,
text_a=text_a,
text_b=None,
label=label))
else:
examples.append(
InputExample(guid=guid, text_a=text_a, text_b=None))
# 返回的text_a label 都是list
return examples
def _create_examples(self, emotion_lines, news_lines, nli_lines, set_type):
"""Creates examples for the training and dev sets."""
examples = []
# emotion
for (i, line) in enumerate(emotion_lines):
guid = "%s-%s" % (set_type, i)
if set_type == "test":
text_a = tokenization.convert_to_unicode(line[1])
label = None
guid = line[0]
else:
text_a = tokenization.convert_to_unicode(line[0])
label = tokenization.convert_to_unicode(line[1])
examples.append(
InputExample(guid=guid, text_a=text_a, text_b=None, label=label, task='1'))
# news
for i, line in enumerate(news_lines):
guid = f'news_{set_type}_{i}'
if set_type == 'test':
text_a = tokenization.convert_to_unicode(line[1])
label = None
guid = line[0]
else:
text_a = tokenization.convert_to_unicode(line[0])
label = tokenization.convert_to_unicode(str(line[1]))
examples.append(
InputExample(guid=guid, text_a=text_a, text_b=None, label=label, task='2'))
# nli
for i, line in enumerate(nli_lines):
guid = f'news_{set_type}_{i}'
if set_type == 'test':
text_a = tokenization.convert_to_unicode(line[1])
text_b = tokenization.convert_to_unicode(line[2])
label = None
guid = line[0]
else:
text_a = tokenization.convert_to_unicode(line[0])
text_b = tokenization.convert_to_unicode(line[1])
label = tokenization.convert_to_unicode(str(line[2]))
examples.append(
InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label, task='3'))
return examples