-
Notifications
You must be signed in to change notification settings - Fork 0
/
data_processor.py
221 lines (175 loc) · 7.68 KB
/
data_processor.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
import os
import csv
import sys
from transformers import InputExample
class DataProcessor(object):
"""Base class for data converters for sequence classification data sets."""
def get_example_from_tensor_dict(self, tensor_dict):
"""Gets an example from a dict with tensorflow tensors
Args:
tensor_dict: Keys and values should match the corresponding Glue
tensorflow_dataset examples.
"""
raise NotImplementedError()
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=",", quotechar=quotechar)
lines = []
for line in reader:
if sys.version_info[0] == 2:
line = list(str(cell, 'utf-8') for cell in line)
lines.append(line)
return lines
class AggressionProcessor(DataProcessor):
def get_train_examples(self, data_dir):
"""See base class."""
train_examples,_=self._create_examples(self._read_tsv(os.path.join(data_dir, "all_data.tsv")), "train")
return train_examples
def get_dev_examples(self, data_dir):
"""See base class."""
_,dev_examples, = self._create_examples(self._read_tsv(os.path.join(data_dir, "all_data.tsv")), "dev")
return dev_examples
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."""
train_examples = []
dev_examples=[]
for i in range(len(lines)):
if i>0:
line=lines[i]
guid = "%s-%s" % (set_type, i)
text_a = ''.join(line[1:-8])
text_a = text_a.replace("NEWLINE_TOKEN", "")
text_a = text_a.replace("TAB_TOKEN", "")
mode=line[-4]
label = line[-3]
'''
attack=line[-2]
toxicity=line[-1]
'''
if label=='True':
label='1'
elif label=='False':
label='0'
if mode=='train':
train_examples.append(InputExample(guid=guid, text_a=text_a, text_b=None, label=label))
elif mode=='dev':
dev_examples.append(InputExample(guid=guid, text_a=text_a, text_b=None, label=label))
return train_examples,dev_examples
class AttackProcessor(DataProcessor):
def get_train_examples(self, data_dir):
"""See base class."""
train_examples,_=self._create_examples(self._read_tsv(os.path.join(data_dir, "all_data.tsv")), "train")
return train_examples
def get_dev_examples(self, data_dir):
"""See base class."""
_,dev_examples, = self._create_examples(self._read_tsv(os.path.join(data_dir, "all_data.tsv")), "dev")
return dev_examples
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."""
train_examples = []
dev_examples=[]
for i in range(len(lines)):
if i>0:
line=lines[i]
guid = "%s-%s" % (set_type, i)
text_a = ''.join(line[1:-8])
text_a = text_a.replace("NEWLINE_TOKEN", "")
text_a = text_a.replace("TAB_TOKEN", "")
mode=line[-4]
label = line[-2]
if label=='True':
label='1'
elif label=='False':
label='0'
if mode=='train':
train_examples.append(InputExample(guid=guid, text_a=text_a, text_b=None, label=label))
elif mode=='dev':
dev_examples.append(InputExample(guid=guid, text_a=text_a, text_b=None, label=label))
return train_examples,dev_examples
class ToxicityProcessor(DataProcessor):
def get_train_examples(self, data_dir):
"""See base class."""
train_examples,_=self._create_examples(self._read_tsv(os.path.join(data_dir, "all_data.tsv")), "train")
return train_examples
def get_dev_examples(self, data_dir):
"""See base class."""
_,dev_examples, = self._create_examples(self._read_tsv(os.path.join(data_dir, "all_data.tsv")), "dev")
return dev_examples
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."""
train_examples = []
dev_examples=[]
for i in range(len(lines)):
if i>0:
line=lines[i]
guid = "%s-%s" % (set_type, i)
text_a = ''.join(line[1:-8])
text_a = text_a.replace("NEWLINE_TOKEN", "")
text_a = text_a.replace("TAB_TOKEN", "")
mode=line[-4]
label = line[-1]
if label=='True':
label='1'
elif label=='False':
label='0'
if mode=='train':
train_examples.append(InputExample(guid=guid, text_a=text_a, text_b=None, label=label))
elif mode=='dev':
dev_examples.append(InputExample(guid=guid, text_a=text_a, text_b=None, label=label))
return train_examples,dev_examples
class Multi_Task_Processor(DataProcessor):
def get_train_examples(self, data_dir):
"""See base class."""
train_examples, _ = self._create_examples(self._read_tsv(os.path.join(data_dir, "all_data.tsv")), "train")
return train_examples
def get_dev_examples(self, data_dir):
"""See base class."""
_, dev_examples, = self._create_examples(self._read_tsv(os.path.join(data_dir, "all_data.tsv")), "dev")
return dev_examples
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."""
train_examples = []
dev_examples = []
for i in range(len(lines)):
if i > 0:
line = lines[i]
guid = "%s-%s" % (set_type, i)
text_a = ''.join(line[1:-8])
text_a = text_a.replace("NEWLINE_TOKEN", "")
text_a = text_a.replace("TAB_TOKEN", "")
mode = line[-4]
aggression_label = line[-3]
attack_label=line[-2]
toxicity_label=line[-1]
label=[]
label.append('1' if aggression_label=='True' else '0')
label.append('1' if attack_label == 'True' else '0')
label.append('1' if toxicity_label == 'True' else '0')
if mode == 'train':
train_examples.append(InputExample(guid=guid, text_a=text_a, text_b=None, label=label))
elif mode == 'dev':
dev_examples.append(InputExample(guid=guid, text_a=text_a, text_b=None, label=label))
return train_examples, dev_examples