# coding=utf-8
# Copyright 2018 The Google AI Language Team Authors and The HuggingFace Inc. team.
# Copyright (c) 2018, NVIDIA CORPORATION. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
""" GLUE processors and helpers """
import logging
import os
from enum import Enum
from typing import List, Optional, Union
from ...file_utils import is_tf_available
from ...tokenization_utils import PreTrainedTokenizer
from .utils import DataProcessor, InputExample, InputFeatures
if is_tf_available():
import tensorflow as tf
logger = logging.getLogger(__name__)
[docs]def glue_convert_examples_to_features(
examples: Union[List[InputExample], "tf.data.Dataset"],
tokenizer: PreTrainedTokenizer,
max_length: Optional[int] = None,
task=None,
label_list=None,
output_mode=None,
):
"""
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. Defaults to the tokenizer's max_len
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``
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.
"""
if is_tf_available() and isinstance(examples, tf.data.Dataset):
if task is None:
raise ValueError("When calling glue_convert_examples_to_features from TF, the task parameter is required.")
return _tf_glue_convert_examples_to_features(examples, tokenizer, max_length=max_length, task=task)
return _glue_convert_examples_to_features(
examples, tokenizer, max_length=max_length, task=task, label_list=label_list, output_mode=output_mode
)
if is_tf_available():
def _tf_glue_convert_examples_to_features(
examples: tf.data.Dataset, tokenizer: PreTrainedTokenizer, task=str, max_length: Optional[int] = None,
) -> tf.data.Dataset:
"""
Returns:
A ``tf.data.Dataset`` containing the task-specific features.
"""
processor = glue_processors[task]()
examples = [processor.tfds_map(processor.get_example_from_tensor_dict(example)) for example in examples]
features = glue_convert_examples_to_features(examples, tokenizer, max_length=max_length, task=task)
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([]),
),
)
def _glue_convert_examples_to_features(
examples: List[InputExample],
tokenizer: PreTrainedTokenizer,
max_length: Optional[int] = None,
task=None,
label_list=None,
output_mode=None,
):
if max_length is None:
max_length = tokenizer.max_len
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)}
def label_from_example(example: InputExample) -> Union[int, float, None]:
if example.label is None:
return None
if output_mode == "classification":
return label_map[example.label]
elif output_mode == "regression":
return float(example.label)
raise KeyError(output_mode)
labels = [label_from_example(example) for example in examples]
batch_encoding = tokenizer.batch_encode_plus(
[(example.text_a, example.text_b) for example in examples], max_length=max_length, pad_to_max_length=True,
)
features = []
for i in range(len(examples)):
inputs = {k: batch_encoding[k][i] for k in batch_encoding}
feature = InputFeatures(**inputs, label=labels[i])
features.append(feature)
for i, example in enumerate(examples[:5]):
logger.info("*** Example ***")
logger.info("guid: %s" % (example.guid))
logger.info("features: %s" % features[i])
return features
class OutputMode(Enum):
classification = "classification"
regression = "regression"
class MrpcProcessor(DataProcessor):
"""Processor for the MRPC data set (GLUE version)."""
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 get_train_examples(self, data_dir):
"""See base class."""
logger.info("LOOKING AT {}".format(os.path.join(data_dir, "train.tsv")))
return self._create_examples(self._read_tsv(os.path.join(data_dir, "train.tsv")), "train")
def get_dev_examples(self, data_dir):
"""See base class."""
return self._create_examples(self._read_tsv(os.path.join(data_dir, "dev.tsv")), "dev")
def get_test_examples(self, data_dir):
"""See base class."""
return self._create_examples(self._read_tsv(os.path.join(data_dir, "test.tsv")), "test")
def get_labels(self):
"""See base class."""
return ["0", "1"]
def _create_examples(self, lines, set_type):
"""Creates examples for the training, dev and test sets."""
examples = []
for (i, line) in enumerate(lines):
if i == 0:
continue
guid = "%s-%s" % (set_type, i)
text_a = line[3]
text_b = line[4]
label = None if set_type == "test" else line[0]
examples.append(InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label))
return examples
class MnliProcessor(DataProcessor):
"""Processor for the MultiNLI data set (GLUE version)."""
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()),
)
def get_train_examples(self, data_dir):
"""See base class."""
return self._create_examples(self._read_tsv(os.path.join(data_dir, "train.tsv")), "train")
def get_dev_examples(self, data_dir):
"""See base class."""
return self._create_examples(self._read_tsv(os.path.join(data_dir, "dev_matched.tsv")), "dev_matched")
def get_test_examples(self, data_dir):
"""See base class."""
return self._create_examples(self._read_tsv(os.path.join(data_dir, "test_matched.tsv")), "test_matched")
def get_labels(self):
"""See base class."""
return ["contradiction", "entailment", "neutral"]
def _create_examples(self, lines, set_type):
"""Creates examples for the training, dev and test sets."""
examples = []
for (i, line) in enumerate(lines):
if i == 0:
continue
guid = "%s-%s" % (set_type, line[0])
text_a = line[8]
text_b = line[9]
label = None if set_type.startswith("test") else line[-1]
examples.append(InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label))
return examples
class MnliMismatchedProcessor(MnliProcessor):
"""Processor for the MultiNLI Mismatched data set (GLUE version)."""
def get_dev_examples(self, data_dir):
"""See base class."""
return self._create_examples(self._read_tsv(os.path.join(data_dir, "dev_mismatched.tsv")), "dev_mismatched")
def get_test_examples(self, data_dir):
"""See base class."""
return self._create_examples(self._read_tsv(os.path.join(data_dir, "test_mismatched.tsv")), "test_mismatched")
class ColaProcessor(DataProcessor):
"""Processor for the CoLA data set (GLUE version)."""
def get_example_from_tensor_dict(self, tensor_dict):
"""See base class."""
return InputExample(
tensor_dict["idx"].numpy(),
tensor_dict["sentence"].numpy().decode("utf-8"),
None,
str(tensor_dict["label"].numpy()),
)
def get_train_examples(self, data_dir):
"""See base class."""
return self._create_examples(self._read_tsv(os.path.join(data_dir, "train.tsv")), "train")
def get_dev_examples(self, data_dir):
"""See base class."""
return self._create_examples(self._read_tsv(os.path.join(data_dir, "dev.tsv")), "dev")
def get_test_examples(self, data_dir):
"""See base class."""
return self._create_examples(self._read_tsv(os.path.join(data_dir, "test.tsv")), "test")
def get_labels(self):
"""See base class."""
return ["0", "1"]
def _create_examples(self, lines, set_type):
"""Creates examples for the training, dev and test sets."""
test_mode = set_type == "test"
if test_mode:
lines = lines[1:]
text_index = 1 if test_mode else 3
examples = []
for (i, line) in enumerate(lines):
guid = "%s-%s" % (set_type, i)
text_a = line[text_index]
label = None if test_mode else line[1]
examples.append(InputExample(guid=guid, text_a=text_a, text_b=None, label=label))
return examples
class Sst2Processor(DataProcessor):
"""Processor for the SST-2 data set (GLUE version)."""
def get_example_from_tensor_dict(self, tensor_dict):
"""See base class."""
return InputExample(
tensor_dict["idx"].numpy(),
tensor_dict["sentence"].numpy().decode("utf-8"),
None,
str(tensor_dict["label"].numpy()),
)
def get_train_examples(self, data_dir):
"""See base class."""
return self._create_examples(self._read_tsv(os.path.join(data_dir, "train.tsv")), "train")
def get_dev_examples(self, data_dir):
"""See base class."""
return self._create_examples(self._read_tsv(os.path.join(data_dir, "dev.tsv")), "dev")
def get_test_examples(self, data_dir):
"""See base class."""
return self._create_examples(self._read_tsv(os.path.join(data_dir, "test.tsv")), "test")
def get_labels(self):
"""See base class."""
return ["0", "1"]
def _create_examples(self, lines, set_type):
"""Creates examples for the training, dev and test sets."""
examples = []
for (i, line) in enumerate(lines):
if i == 0:
continue
guid = "%s-%s" % (set_type, i)
text_a = line[0]
label = None if set_type == "test" else line[1]
examples.append(InputExample(guid=guid, text_a=text_a, text_b=None, label=label))
return examples
class StsbProcessor(DataProcessor):
"""Processor for the STS-B data set (GLUE version)."""
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 get_train_examples(self, data_dir):
"""See base class."""
return self._create_examples(self._read_tsv(os.path.join(data_dir, "train.tsv")), "train")
def get_dev_examples(self, data_dir):
"""See base class."""
return self._create_examples(self._read_tsv(os.path.join(data_dir, "dev.tsv")), "dev")
def get_test_examples(self, data_dir):
"""See base class."""
return self._create_examples(self._read_tsv(os.path.join(data_dir, "test.tsv")), "test")
def get_labels(self):
"""See base class."""
return [None]
def _create_examples(self, lines, set_type):
"""Creates examples for the training, dev and test sets."""
examples = []
for (i, line) in enumerate(lines):
if i == 0:
continue
guid = "%s-%s" % (set_type, line[0])
text_a = line[7]
text_b = line[8]
label = None if set_type == "test" else line[-1]
examples.append(InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label))
return examples
class QqpProcessor(DataProcessor):
"""Processor for the QQP data set (GLUE version)."""
def get_example_from_tensor_dict(self, tensor_dict):
"""See base class."""
return InputExample(
tensor_dict["idx"].numpy(),
tensor_dict["question1"].numpy().decode("utf-8"),
tensor_dict["question2"].numpy().decode("utf-8"),
str(tensor_dict["label"].numpy()),
)
def get_train_examples(self, data_dir):
"""See base class."""
return self._create_examples(self._read_tsv(os.path.join(data_dir, "train.tsv")), "train")
def get_dev_examples(self, data_dir):
"""See base class."""
return self._create_examples(self._read_tsv(os.path.join(data_dir, "dev.tsv")), "dev")
def get_test_examples(self, data_dir):
"""See base class."""
return self._create_examples(self._read_tsv(os.path.join(data_dir, "test.tsv")), "test")
def get_labels(self):
"""See base class."""
return ["0", "1"]
def _create_examples(self, lines, set_type):
"""Creates examples for the training, dev and test sets."""
test_mode = set_type == "test"
q1_index = 1 if test_mode else 3
q2_index = 2 if test_mode else 4
examples = []
for (i, line) in enumerate(lines):
if i == 0:
continue
guid = "%s-%s" % (set_type, line[0])
try:
text_a = line[q1_index]
text_b = line[q2_index]
label = None if test_mode else line[5]
except IndexError:
continue
examples.append(InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label))
return examples
class QnliProcessor(DataProcessor):
"""Processor for the QNLI data set (GLUE version)."""
def get_example_from_tensor_dict(self, tensor_dict):
"""See base class."""
return InputExample(
tensor_dict["idx"].numpy(),
tensor_dict["question"].numpy().decode("utf-8"),
tensor_dict["sentence"].numpy().decode("utf-8"),
str(tensor_dict["label"].numpy()),
)
def get_train_examples(self, data_dir):
"""See base class."""
return self._create_examples(self._read_tsv(os.path.join(data_dir, "train.tsv")), "train")
def get_dev_examples(self, data_dir):
"""See base class."""
return self._create_examples(self._read_tsv(os.path.join(data_dir, "dev.tsv")), "dev")
def get_test_examples(self, data_dir):
"""See base class."""
return self._create_examples(self._read_tsv(os.path.join(data_dir, "test.tsv")), "test")
def get_labels(self):
"""See base class."""
return ["entailment", "not_entailment"]
def _create_examples(self, lines, set_type):
"""Creates examples for the training, dev and test sets."""
examples = []
for (i, line) in enumerate(lines):
if i == 0:
continue
guid = "%s-%s" % (set_type, line[0])
text_a = line[1]
text_b = line[2]
label = None if set_type == "test" else line[-1]
examples.append(InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label))
return examples
class RteProcessor(DataProcessor):
"""Processor for the RTE data set (GLUE version)."""
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 get_train_examples(self, data_dir):
"""See base class."""
return self._create_examples(self._read_tsv(os.path.join(data_dir, "train.tsv")), "train")
def get_dev_examples(self, data_dir):
"""See base class."""
return self._create_examples(self._read_tsv(os.path.join(data_dir, "dev.tsv")), "dev")
def get_test_examples(self, data_dir):
"""See base class."""
return self._create_examples(self._read_tsv(os.path.join(data_dir, "test.tsv")), "test")
def get_labels(self):
"""See base class."""
return ["entailment", "not_entailment"]
def _create_examples(self, lines, set_type):
"""Creates examples for the training, dev and test sets."""
examples = []
for (i, line) in enumerate(lines):
if i == 0:
continue
guid = "%s-%s" % (set_type, line[0])
text_a = line[1]
text_b = line[2]
label = None if set_type == "test" else line[-1]
examples.append(InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label))
return examples
class WnliProcessor(DataProcessor):
"""Processor for the WNLI data set (GLUE version)."""
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 get_train_examples(self, data_dir):
"""See base class."""
return self._create_examples(self._read_tsv(os.path.join(data_dir, "train.tsv")), "train")
def get_dev_examples(self, data_dir):
"""See base class."""
return self._create_examples(self._read_tsv(os.path.join(data_dir, "dev.tsv")), "dev")
def get_test_examples(self, data_dir):
"""See base class."""
return self._create_examples(self._read_tsv(os.path.join(data_dir, "test.tsv")), "test")
def get_labels(self):
"""See base class."""
return ["0", "1"]
def _create_examples(self, lines, set_type):
"""Creates examples for the training, dev and test sets."""
examples = []
for (i, line) in enumerate(lines):
if i == 0:
continue
guid = "%s-%s" % (set_type, line[0])
text_a = line[1]
text_b = line[2]
label = None if set_type == "test" else line[-1]
examples.append(InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label))
return examples
glue_tasks_num_labels = {
"cola": 2,
"mnli": 3,
"mrpc": 2,
"sst-2": 2,
"sts-b": 1,
"qqp": 2,
"qnli": 2,
"rte": 2,
"wnli": 2,
}
glue_processors = {
"cola": ColaProcessor,
"mnli": MnliProcessor,
"mnli-mm": MnliMismatchedProcessor,
"mrpc": MrpcProcessor,
"sst-2": Sst2Processor,
"sts-b": StsbProcessor,
"qqp": QqpProcessor,
"qnli": QnliProcessor,
"rte": RteProcessor,
"wnli": WnliProcessor,
}
glue_output_modes = {
"cola": "classification",
"mnli": "classification",
"mnli-mm": "classification",
"mrpc": "classification",
"sst-2": "classification",
"sts-b": "regression",
"qqp": "classification",
"qnli": "classification",
"rte": "classification",
"wnli": "classification",
}