mirror of
https://github.com/huggingface/transformers.git
synced 2025-08-03 03:31:05 +06:00
429 lines
14 KiB
Python
429 lines
14 KiB
Python
# 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 .utils import DataProcessor, InputExample, InputFeatures
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
def glue_convert_examples_to_features(examples, label_list, max_seq_length,
|
|
tokenizer, output_mode,
|
|
pad_on_left=False,
|
|
pad_token=0,
|
|
pad_token_segment_id=0,
|
|
mask_padding_with_zero=True):
|
|
"""
|
|
Loads a data file into a list of `InputBatch`s
|
|
"""
|
|
|
|
label_map = {label: i for i, label in enumerate(label_list)}
|
|
|
|
features = []
|
|
for (ex_index, example) in enumerate(examples):
|
|
if ex_index % 10000 == 0:
|
|
logger.info("Writing example %d of %d" % (ex_index, len(examples)))
|
|
|
|
inputs = tokenizer.encode_plus(
|
|
example.text_a,
|
|
example.text_b,
|
|
add_special_tokens=True,
|
|
max_length=max_seq_length,
|
|
truncate_first_sequence=True # We're truncating the first sequence as a priority
|
|
)
|
|
input_ids, segment_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.
|
|
input_mask = [1 if mask_padding_with_zero else 0] * len(input_ids)
|
|
|
|
# Zero-pad up to the sequence length.
|
|
padding_length = max_seq_length - len(input_ids)
|
|
if pad_on_left:
|
|
input_ids = ([pad_token] * padding_length) + input_ids
|
|
input_mask = ([0 if mask_padding_with_zero else 1] * padding_length) + input_mask
|
|
segment_ids = ([pad_token_segment_id] * padding_length) + segment_ids
|
|
else:
|
|
input_ids = input_ids + ([pad_token] * padding_length)
|
|
input_mask = input_mask + ([0 if mask_padding_with_zero else 1] * padding_length)
|
|
segment_ids = segment_ids + ([pad_token_segment_id] * padding_length)
|
|
|
|
assert len(input_ids) == max_seq_length
|
|
assert len(input_mask) == max_seq_length
|
|
assert len(segment_ids) == max_seq_length
|
|
|
|
if output_mode == "classification":
|
|
label_id = label_map[example.label]
|
|
elif output_mode == "regression":
|
|
label_id = float(example.label)
|
|
else:
|
|
raise KeyError(output_mode)
|
|
|
|
if ex_index < 5:
|
|
logger.info("*** Example ***")
|
|
logger.info("guid: %s" % (example.guid))
|
|
logger.info("input_ids: %s" % " ".join([str(x) for x in input_ids]))
|
|
logger.info("input_mask: %s" % " ".join([str(x) for x in input_mask]))
|
|
logger.info("segment_ids: %s" % " ".join([str(x) for x in segment_ids]))
|
|
logger.info("label: %s (id = %d)" % (example.label, label_id))
|
|
|
|
features.append(
|
|
InputFeatures(input_ids=input_ids,
|
|
input_mask=input_mask,
|
|
segment_ids=segment_ids,
|
|
label_id=label_id))
|
|
return features
|
|
|
|
|
|
class MrpcProcessor(DataProcessor):
|
|
"""Processor for the MRPC data set (GLUE version)."""
|
|
|
|
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_labels(self):
|
|
"""See base class."""
|
|
return ["0", "1"]
|
|
|
|
def _create_examples(self, lines, set_type):
|
|
"""Creates examples for the training and dev 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 = 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_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_labels(self):
|
|
"""See base class."""
|
|
return ["contradiction", "entailment", "neutral"]
|
|
|
|
def _create_examples(self, lines, set_type):
|
|
"""Creates examples for the training and dev 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 = 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_matched")
|
|
|
|
|
|
class ColaProcessor(DataProcessor):
|
|
"""Processor for the CoLA data set (GLUE version)."""
|
|
|
|
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_labels(self):
|
|
"""See base class."""
|
|
return ["0", "1"]
|
|
|
|
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
|
|
|
|
|
|
class Sst2Processor(DataProcessor):
|
|
"""Processor for the SST-2 data set (GLUE version)."""
|
|
|
|
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_labels(self):
|
|
"""See base class."""
|
|
return ["0", "1"]
|
|
|
|
def _create_examples(self, lines, set_type):
|
|
"""Creates examples for the training and dev sets."""
|
|
examples = []
|
|
for (i, line) in enumerate(lines):
|
|
if i == 0:
|
|
continue
|
|
guid = "%s-%s" % (set_type, i)
|
|
text_a = line[0]
|
|
label = 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_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_labels(self):
|
|
"""See base class."""
|
|
return [None]
|
|
|
|
def _create_examples(self, lines, set_type):
|
|
"""Creates examples for the training and dev 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 = 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_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_labels(self):
|
|
"""See base class."""
|
|
return ["0", "1"]
|
|
|
|
def _create_examples(self, lines, set_type):
|
|
"""Creates examples for the training and dev sets."""
|
|
examples = []
|
|
for (i, line) in enumerate(lines):
|
|
if i == 0:
|
|
continue
|
|
guid = "%s-%s" % (set_type, line[0])
|
|
try:
|
|
text_a = line[3]
|
|
text_b = line[4]
|
|
label = 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_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_matched")
|
|
|
|
def get_labels(self):
|
|
"""See base class."""
|
|
return ["entailment", "not_entailment"]
|
|
|
|
def _create_examples(self, lines, set_type):
|
|
"""Creates examples for the training and dev 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 = 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_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_labels(self):
|
|
"""See base class."""
|
|
return ["entailment", "not_entailment"]
|
|
|
|
def _create_examples(self, lines, set_type):
|
|
"""Creates examples for the training and dev 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 = 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_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_labels(self):
|
|
"""See base class."""
|
|
return ["0", "1"]
|
|
|
|
def _create_examples(self, lines, set_type):
|
|
"""Creates examples for the training and dev 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 = 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",
|
|
}
|