forked from intel/neural-compressor
-
Notifications
You must be signed in to change notification settings - Fork 0
/
prepare_dataset.py
155 lines (137 loc) · 6.5 KB
/
prepare_dataset.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
#!/usr/bin/env python
# -*- coding: utf-8 -*-
#
# Copyright (c) 2021 Intel Corporation
#
# 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 io
import os
import sys
import shutil
import argparse
import tempfile
import urllib.request
import zipfile
TASKS = ["CoLA", "SST", "MRPC", "QQP", "STS", "MNLI", "QNLI", "RTE", "WNLI", "diagnostic"]
TASK2PATH = {"CoLA":'https://dl.fbaipublicfiles.com/glue/data/CoLA.zip',
"SST":'https://dl.fbaipublicfiles.com/glue/data/SST-2.zip',
"QQP":'https://dl.fbaipublicfiles.com/glue/data/STS-B.zip',
"STS":'https://dl.fbaipublicfiles.com/glue/data/QQP-clean.zip',
"MNLI":'https://dl.fbaipublicfiles.com/glue/data/MNLI.zip',
"QNLI":'https://dl.fbaipublicfiles.com/glue/data/QNLIv2.zip',
"RTE":'https://dl.fbaipublicfiles.com/glue/data/RTE.zip',
"WNLI":'https://dl.fbaipublicfiles.com/glue/data/WNLI.zip',
"MRPC":"https://raw.githubusercontent.com/MegEngine/Models/master/"\
"official/nlp/bert/glue_data/MRPC/dev_ids.tsv",
"diagnostic":'https://dl.fbaipublicfiles.com/glue/data/AX.tsv'}
MRPC_TRAIN = 'https://dl.fbaipublicfiles.com/senteval/senteval_data/msr_paraphrase_train.txt'
MRPC_TEST = 'https://dl.fbaipublicfiles.com/senteval/senteval_data/msr_paraphrase_test.txt'
def download_and_extract(task, output_dir):
print("Downloading and extracting %s..." % task)
if task == "MNLI":
print("\tNote (12/10/20): This script no longer downloads SNLI. " \
"You will need to manually download and format the data to use SNLI.")
data_file = "%s.zip" % task
urllib.request.urlretrieve(TASK2PATH[task], data_file)
with zipfile.ZipFile(data_file) as zip_ref:
zip_ref.extractall(output_dir)
os.remove(data_file)
print("\tCompleted!")
def format_mrpc(output_dir, path_to_data):
print("Processing MRPC...")
mrpc_dir = os.path.join(output_dir, "MRPC")
if not os.path.isdir(mrpc_dir):
os.mkdir(mrpc_dir)
if path_to_data:
mrpc_train_file = os.path.join(path_to_data, "msr_paraphrase_train.txt")
mrpc_test_file = os.path.join(path_to_data, "msr_paraphrase_test.txt")
else:
try:
mrpc_train_file = os.path.join(mrpc_dir, "msr_paraphrase_train.txt")
mrpc_test_file = os.path.join(mrpc_dir, "msr_paraphrase_test.txt")
urllib.request.urlretrieve(MRPC_TRAIN, mrpc_train_file)
urllib.request.urlretrieve(MRPC_TEST, mrpc_test_file)
except urllib.error.HTTPError:
print("Error downloading MRPC")
return
assert os.path.isfile(mrpc_train_file), "Train data not found at %s" % mrpc_train_file
assert os.path.isfile(mrpc_test_file), "Test data not found at %s" % mrpc_test_file
with io.open(mrpc_test_file, encoding='utf-8') as data_fh, \
io.open(os.path.join(mrpc_dir, "test.tsv"), 'w', encoding='utf-8') as test_fh:
header = data_fh.readline()
test_fh.write("index\t#1 ID\t#2 ID\t#1 String\t#2 String\n")
for idx, row in enumerate(data_fh):
label, id1, id2, s1, s2 = row.strip().split('\t')
test_fh.write("%d\t%s\t%s\t%s\t%s\n" % (idx, id1, id2, s1, s2))
try:
urllib.request.urlretrieve(TASK2PATH["MRPC"], os.path.join(mrpc_dir, "dev_ids.tsv"))
except KeyError or urllib.error.HTTPError:
print("\tError downloading standard development IDs for MRPC. " \
"You will need to manually split your data.")
return
dev_ids = []
with io.open(os.path.join(mrpc_dir, "dev_ids.tsv"), encoding='utf-8') as ids_fh:
for row in ids_fh:
dev_ids.append(row.strip().split('\t'))
with io.open(mrpc_train_file, encoding='utf-8') as data_fh, \
io.open(os.path.join(mrpc_dir, "train.tsv"), 'w', encoding='utf-8') as train_fh, \
io.open(os.path.join(mrpc_dir, "dev.tsv"), 'w', encoding='utf-8') as dev_fh:
header = data_fh.readline()
train_fh.write(header)
dev_fh.write(header)
for row in data_fh:
label, id1, id2, s1, s2 = row.strip().split('\t')
if [id1, id2] in dev_ids:
dev_fh.write("%s\t%s\t%s\t%s\t%s\n" % (label, id1, id2, s1, s2))
else:
train_fh.write("%s\t%s\t%s\t%s\t%s\n" % (label, id1, id2, s1, s2))
print("\tCompleted!")
def download_diagnostic(output_dir):
print("Downloading and extracting diagnostic...")
if not os.path.isdir(os.path.join(output_dir, "diagnostic")):
os.mkdir(os.path.join(output_dir, "diagnostic"))
data_file = os.path.join(output_dir, "diagnostic", "diagnostic.tsv")
urllib.request.urlretrieve(TASK2PATH["diagnostic"], data_file)
print("\tCompleted!")
return
def get_tasks(task_names):
task_names = task_names.split(',')
if "all" in task_names:
tasks = TASKS
else:
tasks = []
for task_name in task_names:
assert task_name in TASKS, "Task %s not found!" % task_name
tasks.append(task_name)
return tasks
def main(arguments):
parser = argparse.ArgumentParser()
parser.add_argument('--output_dir', help='directory to save data to', type=str, default='data')
parser.add_argument('--tasks', help='tasks to download data for as a comma separated string',
type=str, default='all')
parser.add_argument('--path_to_mrpc', help='path to directory containing extracted MRPC data,"\
msr_paraphrase_train.txt and msr_paraphrase_text.txt',
type=str, default='')
args = parser.parse_args(arguments)
if not os.path.isdir(args.output_dir):
os.mkdir(args.output_dir)
tasks = get_tasks(args.tasks)
for task in tasks:
if task == 'MRPC':
format_mrpc(args.output_dir, args.path_to_mrpc)
elif task == 'diagnostic':
download_diagnostic(args.output_dir)
else:
download_and_extract(task, args.output_dir)
if __name__ == '__main__':
sys.exit(main(sys.argv[1:]))