utils.py
3.97 KB
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
# Copyright 2020-present Tae Hwan Jung
#
# 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 logging
logging.basicConfig(format = '%(asctime)s - %(levelname)s - %(name)s - %(message)s',
datefmt = '%m/%d/%Y %H:%M:%S',
level = logging.INFO)
logger = logging.getLogger(__name__)
class Example(object):
"""A single training/test example."""
def __init__(self,
idx,
added,
deleted,
target,
):
self.idx = idx
self.added = added
self.deleted = deleted
self.target = target
class InputFeatures(object):
"""A single training/test features for a example."""
def __init__(self,
example_id,
source_ids,
target_ids,
source_mask,
target_mask,
patch_ids,
):
self.example_id = example_id
self.source_ids = source_ids
self.target_ids = target_ids
self.source_mask = source_mask
self.target_mask = target_mask
self.patch_ids = patch_ids
def convert_examples_to_features(examples, tokenizer, args, stage=None):
features = []
for example_index, example in enumerate(examples):
# source
added_tokens = [tokenizer.cls_token] + example.added + [tokenizer.sep_token]
deleted_tokens = example.deleted + [tokenizer.sep_token]
source_tokens = added_tokens + deleted_tokens
patch_ids = [1] * len(added_tokens) + [2] * len(deleted_tokens)
source_ids = tokenizer.convert_tokens_to_ids(source_tokens)
source_mask = [1] * (len(source_tokens))
padding_length = args.max_source_length - len(source_ids)
source_ids += [tokenizer.pad_token_id] * padding_length
patch_ids += [0] * padding_length
source_mask += [0] * padding_length
# target
if stage == "test":
target_tokens = tokenizer.tokenize("None")
else:
target_tokens = (example.target)[:args.max_target_length - 2]
target_tokens = [tokenizer.cls_token] + target_tokens + [tokenizer.sep_token]
target_ids = tokenizer.convert_tokens_to_ids(target_tokens)
target_mask = [1] * len(target_ids)
padding_length = args.max_target_length - len(target_ids)
target_ids += [tokenizer.pad_token_id] * padding_length
target_mask += [0] * padding_length
if example_index < 5:
if stage == 'train':
logger.info("*** Example ***")
logger.info("idx: {}".format(example.idx))
logger.info("source_tokens: {}".format([x.replace('\u0120', '_') for x in source_tokens]))
logger.info("source_ids: {}".format(' '.join(map(str, source_ids))))
logger.info("patch_ids: {}".format(' '.join(map(str, patch_ids))))
logger.info("source_mask: {}".format(' '.join(map(str, source_mask))))
logger.info("target_tokens: {}".format([x.replace('\u0120', '_') for x in target_tokens]))
logger.info("target_ids: {}".format(' '.join(map(str, target_ids))))
logger.info("target_mask: {}".format(' '.join(map(str, target_mask))))
features.append(
InputFeatures(
example_index,
source_ids,
target_ids,
source_mask,
target_mask,
patch_ids,
)
)
return features