-
Notifications
You must be signed in to change notification settings - Fork 118
/
data_utils.py
401 lines (336 loc) · 14.6 KB
/
data_utils.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
# Copyright 2018 The Google AI Language Team Authors.
#
# 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.
"""
This is the Data Loading Pipeline for Sentence Classifier Task adapted from:
`https://github.com/google-research/bert/blob/master/run_classifier.py`
"""
import csv
import logging
import os
import texar.torch as tx
class InputExample:
r"""A single training/test example for simple sequence classification."""
def __init__(self, guid, text_a, text_b=None, label=None):
r"""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
class InputFeatures:
r"""A single set of features of data."""
def __init__(self, input_ids, input_mask, segment_ids, label_id):
self.input_ids = input_ids
self.input_mask = input_mask
self.segment_ids = segment_ids
self.label_id = label_id
class DataProcessor:
r"""Base class for data converters for sequence classification data sets."""
def get_train_examples(self, data_dir):
r"""Gets a collection of `InputExample`s for the train set."""
raise NotImplementedError()
def get_dev_examples(self, data_dir):
r"""Gets a collection of `InputExample`s for the dev set."""
raise NotImplementedError()
def get_test_examples(self, data_dir):
r"""Gets a collection of `InputExample`s for prediction."""
raise NotImplementedError()
def get_labels(self):
r"""Gets the list of labels for this data set."""
raise NotImplementedError()
@classmethod
def _read_tsv(cls, input_file, quotechar=None):
r"""Reads a tab separated value file."""
with open(input_file, "r") as f:
reader = csv.reader(f, delimiter="\t", quotechar=quotechar)
lines = []
for line in reader:
lines.append(line)
return lines
class SSTProcessor(DataProcessor):
r"""Processor for the MRPC data set (GLUE version)."""
def get_train_examples(self, data_dir):
r"""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):
r"""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):
r"""See base class."""
return self._create_examples(
self._read_tsv(os.path.join(data_dir, "test.tsv")), "test")
def get_labels(self):
r"""See base class."""
return ["0", "1"]
@staticmethod
def _create_examples(lines, set_type):
r"""Creates examples for the training and dev sets."""
examples = []
if set_type in ('train', 'dev'):
for (i, line) in enumerate(lines):
if i == 0:
continue
guid = f"{set_type}-{i}"
text_a = tx.utils.compat_as_text(line[0])
# Single sentence classification, text_b doesn't exist
text_b = None
label = tx.utils.compat_as_text(line[1])
examples.append(InputExample(guid=guid, text_a=text_a,
text_b=text_b, label=label))
if set_type == 'test':
for (i, line) in enumerate(lines):
if i == 0:
continue
guid = f"{set_type}-{i}"
text_a = tx.utils.compat_as_text(line[1])
# Single sentence classification, text_b doesn't exist
text_b = None
label = '0' # arbitrary set as 0
examples.append(InputExample(guid=guid, text_a=text_a,
text_b=text_b, label=label))
return examples
class XnliProcessor(DataProcessor):
r"""Processor for the XNLI data set."""
def __init__(self):
self.language = "zh"
def get_train_examples(self, data_dir):
r"""See base class."""
lines = self._read_tsv(
os.path.join(data_dir, "multinli",
f"multinli.train.{self.language}.tsv"))
examples = []
for (i, line) in enumerate(lines):
if i == 0:
continue
guid = f"train-{i}"
text_a = tx.utils.compat_as_text(line[0])
text_b = tx.utils.compat_as_text(line[1])
label = tx.utils.compat_as_text(line[2])
if label == tx.utils.compat_as_text("contradictory"):
label = tx.utils.compat_as_text("contradiction")
examples.append(InputExample(guid=guid, text_a=text_a,
text_b=text_b, label=label))
return examples
def get_dev_examples(self, data_dir):
r"""See base class."""
lines = self._read_tsv(os.path.join(data_dir, "xnli.dev.tsv"))
examples = []
for (i, line) in enumerate(lines):
if i == 0:
continue
guid = f"dev-{i}"
language = tx.utils.compat_as_text(line[0])
if language != tx.utils.compat_as_text(self.language):
continue
text_a = tx.utils.compat_as_text(line[6])
text_b = tx.utils.compat_as_text(line[7])
label = tx.utils.compat_as_text(line[1])
examples.append(InputExample(guid=guid, text_a=text_a,
text_b=text_b, label=label))
return examples
def get_labels(self):
r"""See base class."""
return ["contradiction", "entailment", "neutral"]
class MnliProcessor(DataProcessor):
r"""Processor for the MultiNLI data set (GLUE version)."""
def get_train_examples(self, data_dir):
r"""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):
r"""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):
r"""See base class."""
return self._create_examples(
self._read_tsv(os.path.join(data_dir, "test_matched.tsv")),
"test")
def get_labels(self):
r"""See base class."""
return ["contradiction", "entailment", "neutral"]
@staticmethod
def _create_examples(lines, set_type):
r"""Creates examples for the training and dev sets."""
examples = []
for (i, line) in enumerate(lines):
if i == 0:
continue
guid = f"{set_type}-{tx.utils.compat_as_text(line[0])}"
text_a = tx.utils.compat_as_text(line[8])
text_b = tx.utils.compat_as_text(line[9])
if set_type == "test":
label = "contradiction"
else:
label = tx.utils.compat_as_text(line[-1])
examples.append(InputExample(guid=guid, text_a=text_a,
text_b=text_b, label=label))
return examples
class MrpcProcessor(DataProcessor):
r"""Processor for the MRPC data set (GLUE version)."""
def get_train_examples(self, data_dir):
r"""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):
r"""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):
r"""See base class."""
return self._create_examples(
self._read_tsv(os.path.join(data_dir, "test.tsv")),
"test")
def get_labels(self):
r"""See base class."""
return ["0", "1"]
@staticmethod
def _create_examples(lines, set_type):
r"""Creates examples for the training and dev sets."""
examples = []
for (i, line) in enumerate(lines):
if i == 0:
continue
guid = f"{set_type}-{i}"
text_a = tx.utils.compat_as_text(line[3])
text_b = tx.utils.compat_as_text(line[4])
if set_type == "test":
label = "0"
else:
label = tx.utils.compat_as_text(line[0])
examples.append(InputExample(guid=guid, text_a=text_a,
text_b=text_b, label=label))
return examples
class ColaProcessor(DataProcessor):
r"""Processor for the CoLA data set (GLUE version)."""
def get_train_examples(self, data_dir):
r"""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):
r"""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):
r"""See base class."""
return ["0", "1"]
@staticmethod
def _create_examples(lines, set_type):
r"""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" and i == 0:
continue
guid = f"{set_type}-{i}"
if set_type == "test":
text_a = tx.utils.compat_as_text(line[1])
label = "0"
else:
text_a = tx.utils.compat_as_text(line[3])
label = tx.utils.compat_as_text(line[1])
examples.append(InputExample(guid=guid, text_a=text_a,
text_b=None, label=label))
return examples
def convert_single_example(ex_index, example, label_list, max_seq_length,
tokenizer):
r"""Converts a single `InputExample` into a single `InputFeatures`."""
label_map = {}
for (i, label) in enumerate(label_list):
label_map[label] = i
input_ids, segment_ids, input_mask = \
tokenizer.encode_text_to_id(text_a=example.text_a,
text_b=example.text_b,
max_seq_length=max_seq_length)
label_id = label_map[example.label]
# here we disable the verbose printing of the data
if ex_index < 0:
logging.info("*** Example ***")
logging.info("guid: %s", example.guid)
logging.info("input_ids: %s", " ".join([str(x) for x in input_ids]))
logging.info("input_ids length: %d", len(input_ids))
logging.info("input_mask: %s", " ".join([str(x) for x in input_mask]))
logging.info("segment_ids: %s", " ".join([str(x) for x in segment_ids]))
logging.info("label: %s (id = %d)", example.label, label_id)
feature = InputFeatures(input_ids=input_ids,
input_mask=input_mask,
segment_ids=segment_ids,
label_id=label_id)
return feature
def convert_examples_to_features_and_output_to_files(
examples, label_list, max_seq_length, tokenizer, output_file,
feature_original_types):
r"""Convert a set of `InputExample`s to a pickled file."""
with tx.data.RecordData.writer(
output_file, feature_original_types) as writer:
for (ex_index, example) in enumerate(examples):
feature = convert_single_example(ex_index, example, label_list,
max_seq_length, tokenizer)
features = {
"input_ids": feature.input_ids,
"input_mask": feature.input_mask,
"segment_ids": feature.segment_ids,
"label_ids": [feature.label_id]
}
writer.write(features)
def prepare_record_data(processor, tokenizer,
data_dir, max_seq_length, output_dir,
feature_original_types):
r"""Prepare record data.
Args:
processor: Data Preprocessor, which must have get_labels,
get_train/dev/test/examples methods defined.
tokenizer: The Sentence Tokenizer. Generally should be
SentencePiece Model.
data_dir: The input data directory.
max_seq_length: Max sequence length.
output_dir: The directory to save the pickled file in.
feature_original_types: The original type of the feature.
"""
label_list = processor.get_labels()
train_examples = processor.get_train_examples(data_dir)
train_file = os.path.join(output_dir, "train.pkl")
convert_examples_to_features_and_output_to_files(
train_examples, label_list, max_seq_length,
tokenizer, train_file, feature_original_types)
eval_examples = processor.get_dev_examples(data_dir)
eval_file = os.path.join(output_dir, "eval.pkl")
convert_examples_to_features_and_output_to_files(
eval_examples, label_list,
max_seq_length, tokenizer, eval_file, feature_original_types)
test_examples = processor.get_test_examples(data_dir)
test_file = os.path.join(output_dir, "predict.pkl")
convert_examples_to_features_and_output_to_files(
test_examples, label_list,
max_seq_length, tokenizer, test_file, feature_original_types)