[BIG] pytorch-transformers => transformers
This commit is contained in:
thomwolf
3
transformers/data/processors/__init__.py
Normal file
3
transformers/data/processors/__init__.py
Normal file
@@ -0,0 +1,3 @@
|
||||
from .utils import InputExample, InputFeatures, DataProcessor
|
||||
from .glue import glue_output_modes, glue_processors, glue_tasks_num_labels, glue_convert_examples_to_features
|
||||
|
||||
471
transformers/data/processors/glue.py
Normal file
471
transformers/data/processors/glue.py
Normal file
@@ -0,0 +1,471 @@
|
||||
# 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
|
||||
from ...file_utils import is_tf_available
|
||||
|
||||
if is_tf_available():
|
||||
import tensorflow as tf
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
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):
|
||||
"""
|
||||
Loads a data file into a list of `InputBatch`s
|
||||
"""
|
||||
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)}
|
||||
|
||||
features = []
|
||||
for (ex_index, example) in enumerate(examples):
|
||||
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'),
|
||||
str(example['label'].numpy()))
|
||||
|
||||
inputs = tokenizer.encode_plus(
|
||||
example.text_a,
|
||||
example.text_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_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))
|
||||
|
||||
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
|
||||
|
||||
|
||||
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",
|
||||
}
|
||||
101
transformers/data/processors/utils.py
Normal file
101
transformers/data/processors/utils.py
Normal file
@@ -0,0 +1,101 @@
|
||||
# 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.
|
||||
|
||||
import csv
|
||||
import sys
|
||||
import copy
|
||||
import json
|
||||
|
||||
class InputExample(object):
|
||||
"""A single training/test example for simple sequence classification."""
|
||||
def __init__(self, guid, text_a, text_b=None, label=None):
|
||||
"""Constructs a InputExample.
|
||||
|
||||
Args:
|
||||
guid: Unique id for the example.
|
||||
text_a: string. The untokenized text of the first sequence. For single
|
||||
sequence tasks, only this sequence must be specified.
|
||||
text_b: (Optional) string. The untokenized text of the second sequence.
|
||||
Only must be specified for sequence pair tasks.
|
||||
label: (Optional) string. The label of the example. This should be
|
||||
specified for train and dev examples, but not for test examples.
|
||||
"""
|
||||
self.guid = guid
|
||||
self.text_a = text_a
|
||||
self.text_b = text_b
|
||||
self.label = label
|
||||
|
||||
def __repr__(self):
|
||||
return str(self.to_json_string())
|
||||
|
||||
def to_dict(self):
|
||||
"""Serializes this instance to a Python dictionary."""
|
||||
output = copy.deepcopy(self.__dict__)
|
||||
return output
|
||||
|
||||
def to_json_string(self):
|
||||
"""Serializes this instance to a JSON string."""
|
||||
return json.dumps(self.to_dict(), indent=2, sort_keys=True) + "\n"
|
||||
|
||||
|
||||
class InputFeatures(object):
|
||||
"""A single set of features of data."""
|
||||
|
||||
def __init__(self, input_ids, attention_mask, token_type_ids, label):
|
||||
self.input_ids = input_ids
|
||||
self.attention_mask = attention_mask
|
||||
self.token_type_ids = token_type_ids
|
||||
self.label = label
|
||||
|
||||
def __repr__(self):
|
||||
return str(self.to_json_string())
|
||||
|
||||
def to_dict(self):
|
||||
"""Serializes this instance to a Python dictionary."""
|
||||
output = copy.deepcopy(self.__dict__)
|
||||
return output
|
||||
|
||||
def to_json_string(self):
|
||||
"""Serializes this instance to a JSON string."""
|
||||
return json.dumps(self.to_dict(), indent=2, sort_keys=True) + "\n"
|
||||
|
||||
|
||||
class DataProcessor(object):
|
||||
"""Base class for data converters for sequence classification data sets."""
|
||||
|
||||
def get_train_examples(self, data_dir):
|
||||
"""Gets a collection of `InputExample`s for the train set."""
|
||||
raise NotImplementedError()
|
||||
|
||||
def get_dev_examples(self, data_dir):
|
||||
"""Gets a collection of `InputExample`s for the dev set."""
|
||||
raise NotImplementedError()
|
||||
|
||||
def get_labels(self):
|
||||
"""Gets the list of labels for this data set."""
|
||||
raise NotImplementedError()
|
||||
|
||||
@classmethod
|
||||
def _read_tsv(cls, input_file, quotechar=None):
|
||||
"""Reads a tab separated value file."""
|
||||
with open(input_file, "r", encoding="utf-8-sig") as f:
|
||||
reader = csv.reader(f, delimiter="\t", quotechar=quotechar)
|
||||
lines = []
|
||||
for line in reader:
|
||||
if sys.version_info[0] == 2:
|
||||
line = list(unicode(cell, 'utf-8') for cell in line)
|
||||
lines.append(line)
|
||||
return lines
|
||||
Reference in New Issue
Block a user