-
Notifications
You must be signed in to change notification settings - Fork 2
/
data_utils.py
245 lines (201 loc) · 7.95 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
import os
import sys
root_path = "/".join(os.path.realpath(__file__).split("/")[:-2])
if root_path not in sys.path:
sys.path.insert(0, root_path)
import csv
import random
import logging
import argparse
import numpy as np
from tqdm import tqdm
import torch
import torch.nn as nn
from torch.utils.data import Dataset, DataLoader, RandomSampler, SequentialSampler
class TextDataset(Dataset):
def __init__(self, *texts):
assert all(len(texts[0]) == len(text) for text in texts)
self.texts = texts
def __getitem__(self, index):
return tuple(text[index] for text in self.texts)
def __len__(self):
return len(self.texts[0])
class DataProcessor(object):
# processor for the query-based ner dataset
def get_train_examples(self, data_dir):
data = self._read_tsv(os.path.join(data_dir, "train.tsv"))
return data#[:len(data)//32]
def get_dev_examples(self, data_dir):
return self._read_tsv(os.path.join(data_dir, "dev.tsv"))
def get_test_examples(self, data_dir):
return self._read_tsv(os.path.join(data_dir, "dev.tsv"))
@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)
# if len(line) < 5:
# print(line)
# continue
lines.append(line)
return lines
class MRPCProcessor(DataProcessor):
def get_labels(self, ):
return ["0", "1"]
def get_train_examples(self, data_dir):
"""See base class."""
# logger.info("LOOKING AT {}".format(os.path.join(data_dir, "train.tsv")))
print(data_dir)
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, path=None):
"""See base class."""
if path is None:
return self._create_examples(
self._read_tsv(os.path.join(data_dir, "dev.tsv")), "test")
else:
return self._create_examples(
self._read_tsv(os.path.join(data_dir, path)), "test")
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]
try:
text_b = line[4]
except:
continue
if text_b.strip() == '':
continue
label = line[0]
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")
def get_test_examples(self, data_dir, path=None):
"""See base class."""
if path is None:
return self._create_examples(
self._read_tsv(os.path.join(data_dir, "dev.tsv")), "test")
else:
return self._create_examples(
self._read_tsv(os.path.join(data_dir, path)), "test")
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 SSTProcessor(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, path=None):
"""See base class."""
if path is None:
return self._create_examples(
self._read_tsv(os.path.join(data_dir, "dev.tsv")), "test")
else:
return self._create_examples(
self._read_tsv(os.path.join(data_dir, path)), "test")
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 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_test_examples(self, data_dir, path=None):
"""See base class."""
if path is None:
return self._create_examples(
self._read_tsv(os.path.join(data_dir, "dev_matched.tsv")), "dev_matched")
else:
return self._create_examples(
self._read_tsv(os.path.join(data_dir, path)), "test")
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]
if i < 6:
print(text_a)
print(text_b)
print(label)
examples.append(
InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label))
return examples
class InputExample(object):
def __init__(self, guid, text_a, text_b=None, label=None):
self.guid = guid
self.text_a = text_a
self.text_b = text_b
self.label = label