-
Notifications
You must be signed in to change notification settings - Fork 6
/
data_preprocess.py
75 lines (65 loc) · 2.49 KB
/
data_preprocess.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
import os
import argparse
def weibo_preprocessor(dataset, data_path, mode="train"):
with open(data_path, "r", encoding="utf-8") as f:
data = f.read().split("\n")
new_path = "data/{}/{}.txt".format(dataset, mode)
data_dir = "data/{}".format(dataset)
if not os.path.exists(data_dir):
os.mkdir(data_dir)
ret_list = []
for row in data:
if not row:
ret_list.append("")
else:
row = row.split("\t")
if row:
ret_list.append("{} {}".format(row[0][:1], row[1]))
with open(new_path, "w", encoding="utf-8") as f:
f.write("\n".join(ret_list))
def w16_preprocess(dataset, data_path, mode="train"):
with open(data_path, "r", encoding="utf-8") as f:
data = f.read().split("\n")
new_path = "data/{}/{}.txt".format(dataset, mode)
data_dir = "data/{}".format(dataset)
if not os.path.exists(data_dir):
os.mkdir(data_dir)
ret_list = []
for row in data:
ret_list.append(row.replace("\t", " "))
with open(new_path, "w", encoding="utf-8") as f:
f.write("\n".join(ret_list))
def w17_preprocess(dataset, data_path, mode="train"):
with open(data_path, "r", encoding="utf-8") as f:
data = f.read().split("\n")
new_path = "data/{}/{}.txt".format(dataset, mode)
data_dir = "data/{}".format(dataset)
if not os.path.exists(data_dir):
os.mkdir(data_dir)
ret_list = []
for row in data:
ret_list.append(row.replace("\t", " "))
with open(new_path, "w", encoding="utf-8") as f:
f.write("\n".join(ret_list))
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--dataset', type=str, default='WB', choices=['WB', 'W16', 'W17'])
parser.add_argument('--data_dir', type=str, default='')
args = parser.parse_args()
dataset = args.dataset
data_dir = args.data_dir
if dataset == "WB":
modes = ["train", "test", "dev"]
for mode in modes:
data_path = "{}/weiboNER_2nd_conll.{}".format(data_dir, mode)
weibo_preprocessor(dataset, data_path, mode)
elif dataset == "W16":
modes = ["train", "test", "dev"]
for mode in modes:
data_path = "{}/{}".format(data_dir, mode)
w16_preprocess(dataset, data_path, mode)
elif dataset == "W17":
modes = ["dev"]
for mode in modes:
data_path = "{}/emerging.{}.conll".format(data_dir, mode)
w17_preprocess(dataset, data_path, mode)