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 = line[3]
label = line[1]
examples.append(
InputExample(guid=guid, text_a=text_a, text_b=None, label=label))
return examples
def _create_examples(self, lst, set_type):
"""Creates examples for the training and dev sets."""
examples = []
for _id, data in tqdm(enumerate(lst), desc='Processing NLI'):
guid = "%s-%s" % (set_type, _id)
text_a = data['data'][0]
text_b = data['data'][1]
label = data['label']
assert label in self.get_labels(), f"Label: {label}, data:{data}"
examples.append(
InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label))
return examples
def _create_examples(self, data, set_type):
#dict_keys(['orig_title', 'duplicate_title', 'duplicate_id', 'orig_id', 'label'])
"""Creates examples for the training and dev sets."""
examples = []
for datum in tqdm(data, desc="parsing"):
guid = "%s-%s-%s" % (set_type, datum["orig_id"], datum["duplicate_id"])
text_a = datum['orig_title']
text_b = datum['duplicate_title']
label = int(datum['label'])
assert label in self.get_labels()
examples.append(
InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label)
)
return examples
def _create_examples(self, df, set_type):
"""Creates examples for the training and dev sets."""
examples = []
for _id, row in tqdm(df.iterrows(), desc="Preparing Data", total=len(df)):
guid = "%s-%s" % (set_type, row["id"])
text_a = str(row["question1"])
text_b = str(row["question2"])
label = int(row["is_duplicate"])
assert label in self.get_labels()
examples.append(
InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label)
)
return examples
def _create_examples(self, lst, set_type):
"""Creates examples for the training and dev sets."""
examples = []
lst = lst[0]
for _id, key in tqdm(enumerate(lst), desc="Preparing Data", total=len(lst)):
data = lst[key]
guid = "%s-%s" % (set_type, _id)
text_a = data["data"][0]
text_b = data["data"][1]
label = int(data["label"])
assert label in self.get_labels()
examples.append(
InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label)
)
return examples
def _create_examples(self, questions, set_type):
"""Creates examples for the training and dev sets."""
examples = []
def process_text(s, sent_a=True):
return s
for qid in questions:
question_text = questions[qid].text
for answer in questions[qid].answers:
guid = "%s-%s" % (set_type, str(qid)+"_"+str(answer.aid))
answer_text = answer.text
text_a = process_text(question_text)
text_b = process_text(answer_text, sent_a=False)
label = 1 if answer.reference_score > 2 else 0
examples.append(
InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label))
return examples
def get_example_from_tensor_dict(self, tensor_dict):
"""See base class."""
return InputExample(tensor_dict['idx'].numpy(),
tensor_dict['sentence1'].numpy().decode('utf-8'),
tensor_dict['sentence2'].numpy().decode('utf-8'),
str(tensor_dict['label'].numpy()))
def glue_convert_examples_to_features(examples, tokenizer,
max_length=512,
task=None,
label_list=None,
output_mode=None,
pad_on_left=False,
pad_token=0,
pad_token_segment_id=0,
mask_padding_with_zero=True,
tokenize=True):
"""
Loads a data file into a list of ``InputFeatures``
Args:
examples: List of ``InputExamples`` or ``tf.data.Dataset`` containing the examples.
tokenizer: Instance of a tokenizer that will tokenize the examples
max_length: Maximum example length
task: GLUE task
label_list: List of labels. Can be obtained from the processor using the ``processor.get_labels()`` method
output_mode: String indicating the output mode. Either ``regression`` or ``classification``
pad_on_left: If set to ``True``, the examples will be padded on the left rather than on the right (default)
pad_token: Padding token
pad_token_segment_id: The segment ID for the padding token (It is usually 0, but can vary such as for XLNet where it is 4)
mask_padding_with_zero: If set to ``True``, the attention mask will be filled by ``1`` for actual values
and by ``0`` for padded values. If set to ``False``, inverts it (``1`` for padded values, ``0`` for
actual values)
Returns:
If the ``examples`` input is a ``tf.data.Dataset``, will return a ``tf.data.Dataset``
containing the task-specific features. If the input is a list of ``InputExamples``, will return
a list of task-specific ``InputFeatures`` which can be fed to the model.
"""
is_tf_dataset = False
#if is_tf_available() and isinstance(examples, tf.data.Dataset):
# is_tf_dataset = True
if task is not None:
processor = glue_processors[task]()
if label_list is None:
label_list = processor.get_labels()
logger.info("Using label list %s for task %s" % (label_list, task))
if output_mode is None:
output_mode = glue_output_modes[task]
logger.info("Using output mode %s for task %s" % (output_mode, task))
label_map = {label: i for i, label in enumerate(label_list)}
print(label_map)
features = []
for (ex_index, example) in tqdm(enumerate(examples), desc="Iterating"):
try:
if ex_index % 10000 == 0:
logger.info("Writing example %d" % (ex_index))
if is_tf_dataset:
example = InputExample(example['idx'].numpy(),
example['sentence1'].numpy().decode('utf-8'),
example['sentence2'].numpy().decode('utf-8'),
example['label'].numpy().decode('utf-8'))
tokens_a = tokenizer.tokenize(example.text_a) if tokenize else example.text_a
tokens_b = tokenizer.tokenize(example.text_b) if tokenize else example.text_b
_truncate_seq_pair(tokens_a, tokens_b, max_length-3)
inputs = tokenizer.encode_plus(
tokens_a,
tokens_b,
add_special_tokens=True,
max_length=max_length,
truncate_first_sequence=True # We're truncating the first sequence in priority
)
input_ids, token_type_ids = inputs["input_ids"], inputs["token_type_ids"]
# The mask has 1 for real tokens and 0 for padding tokens. Only real
# tokens are attended to.
attention_mask = [1 if mask_padding_with_zero else 0] * len(input_ids)
# Zero-pad up to the sequence length.
padding_length = max_length - len(input_ids)
if pad_on_left:
input_ids = ([pad_token] * padding_length) + input_ids
attention_mask = ([0 if mask_padding_with_zero else 1] * padding_length) + attention_mask
token_type_ids = ([pad_token_segment_id] * padding_length) + token_type_ids
else:
input_ids = input_ids + ([pad_token] * padding_length)
attention_mask = attention_mask + ([0 if mask_padding_with_zero else 1] * padding_length)
token_type_ids = token_type_ids + ([pad_token_segment_id] * padding_length)
assert len(input_ids) == max_length, "Error with input length {} vs {}".format(len(input_ids), max_length)
assert len(attention_mask) == max_length, "Error with input length {} vs {}".format(len(attention_mask), max_length)
assert len(token_type_ids) == max_length, "Error with input length {} vs {}".format(len(token_type_ids), max_length)
if output_mode == "classification":
label = label_map[example.label]
elif output_mode == "regression":
label = float(example.label)
else:
raise KeyError(output_mode)
if ex_index < 5:
logger.info("*** Example ***")
logger.info("guid: %s" % (example.guid))
logger.info("input_tokens: %s" % (tokenizer.tokenize(example.text_a+
example.text_b)))
logger.info("input_ids: %s" % " ".join([str(x) for x in input_ids]))
logger.info("attention_mask: %s" % " ".join([str(x) for x in attention_mask]))
logger.info("token_type_ids: %s" % " ".join([str(x) for x in token_type_ids]))
logger.info("label: %s (id = %d)" % (example.label, label))
features.append(
InputFeatures(input_ids=input_ids,
attention_mask=attention_mask,
token_type_ids=token_type_ids,
label=label,
tokens_a = tokens_a,
tokens_b = tokens_b))
except ValueError:
print("Bad input", example.text_a, example.text_b)
continue
if is_tf_available() and is_tf_dataset:
def gen():
for ex in features:
yield ({'input_ids': ex.input_ids,
'attention_mask': ex.attention_mask,
'token_type_ids': ex.token_type_ids},
ex.label)
return tf.data.Dataset.from_generator(gen,
({'input_ids': tf.int32,
'attention_mask': tf.int32,
'token_type_ids': tf.int32},
tf.int64),
({'input_ids': tf.TensorShape([None]),
'attention_mask': tf.TensorShape([None]),
'token_type_ids': tf.TensorShape([None])},
tf.TensorShape([])))
return features
def get_example_from_tensor_dict(self, tensor_dict):
"""See base class."""
return InputExample(tensor_dict['idx'].numpy(),
tensor_dict['premise'].numpy().decode('utf-8'),
tensor_dict['hypothesis'].numpy().decode('utf-8'),
str(tensor_dict['label'].numpy()))