-
Notifications
You must be signed in to change notification settings - Fork 2
/
utils.py
327 lines (268 loc) · 9.35 KB
/
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
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
import os
import json
import shutil
import logging
import tensorflow as tf
from conlleval import return_report
models_path = "./models"
eval_path = "./evaluation"
eval_temp = os.path.join(eval_path, "temp")
eval_script = os.path.join(eval_path, "conlleval")
def get_logger(log_file):
logger = logging.getLogger(log_file)
logger.setLevel(logging.DEBUG)
fh = logging.FileHandler(log_file)
fh.setLevel(logging.DEBUG)
ch = logging.StreamHandler()
ch.setLevel(logging.INFO)
formatter = logging.Formatter("%(asctime)s - %(name)s - %(levelname)s - %(message)s")
ch.setFormatter(formatter)
fh.setFormatter(formatter)
logger.addHandler(ch)
logger.addHandler(fh)
return logger
# def test_ner(results, path):
# """
# Run perl script to evaluate model
# """
# script_file = "conlleval"
# output_file = os.path.join(path, "ner_predict.utf8")
# result_file = os.path.join(path, "ner_result.utf8")
# with open(output_file, "w") as f:
# to_write = []
# for block in results:
# for line in block:
# to_write.append(line + "\n")
# to_write.append("\n")
#
# f.writelines(to_write)
# os.system("perl {} < {} > {}".format(script_file, output_file, result_file))
# eval_lines = []
# with open(result_file) as f:
# for line in f:
# eval_lines.append(line.strip())
# return eval_lines
def test_ner(results, path):
"""
Run perl script to evaluate model
"""
output_file = os.path.join(path, "ner_predict.utf8")
with open(output_file, "w",encoding='utf8') as f:
to_write = []
for block in results:
for line in block:
to_write.append(line + "\n")
to_write.append("\n")
f.writelines(to_write)
eval_lines = return_report(output_file)
return eval_lines
def print_config(config, logger):
"""
Print configuration of the model
"""
for k, v in config.items():
logger.info("{}:\t{}".format(k.ljust(15), v))
def make_path(params):
"""
Make folders for training and evaluation
"""
if not os.path.isdir(params.result_path):
os.makedirs(params.result_path)
if not os.path.isdir(params.ckpt_path):
os.makedirs(params.ckpt_path)
if not os.path.isdir("log"):
os.makedirs("log")
def clean(params):
"""
Clean current folder
remove saved model and training log
"""
if os.path.isfile(params.vocab_file):
os.remove(params.vocab_file)
if os.path.isfile(params.map_file):
os.remove(params.map_file)
if os.path.isdir(params.ckpt_path):
shutil.rmtree(params.ckpt_path)
if os.path.isdir(params.summary_path):
shutil.rmtree(params.summary_path)
if os.path.isdir(params.result_path):
shutil.rmtree(params.result_path)
if os.path.isdir("log"):
shutil.rmtree("log")
if os.path.isdir("__pycache__"):
shutil.rmtree("__pycache__")
if os.path.isfile(params.config_file):
os.remove(params.config_file)
if os.path.isfile(params.vocab_file):
os.remove(params.vocab_file)
def save_config(config, config_file):
"""
Save configuration of the model
parameters are stored in json format
"""
with open(config_file, "w", encoding="utf8") as f:
json.dump(config, f, ensure_ascii=False, indent=4)
def load_config(config_file):
"""
Load configuration of the model
parameters are stored in json format
"""
with open(config_file, encoding="utf8") as f:
return json.load(f)
def convert_to_text(line):
"""
Convert conll data to text
"""
to_print = []
for item in line:
try:
if item[0] == " ":
to_print.append(" ")
continue
word, gold, tag = item.split(" ")
if tag[0] in "SB":
to_print.append("[")
to_print.append(word)
if tag[0] in "SE":
to_print.append("@" + tag.split("-")[-1])
to_print.append("]")
except:
print(list(item))
return "".join(to_print)
def save_model(sess, model, path, logger):
checkpoint_path = os.path.join(path, "ner.ckpt")
model.saver.save(sess, checkpoint_path)
logger.info("model saved")
def create_model(session, Model_class, path, load_vec, config, id_to_char, logger):
# create model, reuse parameters if exists
model = Model_class(config)
ckpt = tf.train.get_checkpoint_state(path)
if ckpt and tf.train.checkpoint_exists(ckpt.model_checkpoint_path):
logger.info("Reading model parameters from %s" % ckpt.model_checkpoint_path)
model.saver.restore(session, ckpt.model_checkpoint_path)
else:
# 加载模型默认参数与预处理的词嵌入
logger.info("Created model with fresh parameters.")
session.run(tf.global_variables_initializer())
if config["pre_emb"]:
# 加载模型初始化生成的char_lookup参数值
emb_weights = session.run(model.char_lookup.read_value())
# 更新词嵌入权重:如果char在预训练的词嵌入集中存在便替换
emb_weights = load_vec(config["emb_file"], id_to_char, config["char_dim"], emb_weights)
session.run(model.char_lookup.assign(emb_weights)) # 重新赋值
logger.info("Load pre-trained embedding.")
return model
def result_to_json(string, tags):
item = {"string": string, "entities": []}
entity_name = ""
entity_start = 0
idx = 0
for char, tag in zip(string, tags):
if tag[0] == "S":
item["entities"].append({"word": char, "start": idx, "end": idx+1, "type":tag[2:]})
elif tag[0] == "B":
entity_name += char
entity_start = idx
elif tag[0] == "I":
entity_name += char
elif tag[0] == "E":
entity_name += char
item["entities"].append({"word": entity_name, "start": entity_start, "end": idx + 1, "type": tag[2:]})
entity_name = ""
else:
entity_name = ""
entity_start = idx
idx += 1
return item
#import os
#import json
#import shutil
#import logging
#import codecs
#import tensorflow as tf
#from conlleval import return_report
#models_path = "./models"
#eval_path = "./evaluation"
#eval_temp = os.path.join(eval_path, "temp")
#eval_script = os.path.join(eval_path, "conlleval")
#def get_logger(log_file):
#logger = logging.getLogger(log_file)
#logger.setLevel(logging.DEBUG)
#fh = logging.FileHandler(log_file)
#fh.setLevel(logging.DEBUG)
#ch = logging.StreamHandler()
#ch.setLevel(logging.INFO)
#formatter = logging.Formatter("%(asctime)s - %(name)s - %(levelname)s - %(message)s")
#ch.setFormatter(formatter)
#fh.setFormatter(formatter)
#logger.addHandler(ch)
#logger.addHandler(fh)
#return logger
## def test_ner(results, path):
## """
## Run perl script to evaluate model
## """
## script_file = "conlleval"
## output_file = os.path.join(path, "ner_predict.utf8")
## result_file = os.path.join(path, "ner_result.utf8")
## with open(output_file, "w") as f:
## to_write = []
## for block in results:
## for line in block:
## to_write.append(line + "\n")
## to_write.append("\n")
##
## f.writelines(to_write)
## os.system("perl {} < {} > {}".format(script_file, output_file, result_file))
## eval_lines = []
## with open(result_file) as f:
## for line in f:
## eval_lines.append(line.strip())
## return eval_lines
#def make_path(params):
#"""
#Make folders for training and evaluation
#"""
#if not os.path.isdir(params.result_path):
#os.makedirs(params.result_path)
#if not os.path.isdir(params.ckpt_path):
#os.makedirs(params.ckpt_path)
#if not os.path.isdir("log"):
#os.makedirs("log")
#def load_config(config_file):
#"""
#Load configuration of the model
#parameters are stored in json format
#"""
#with codecs.open(config_file,'r', encoding="utf-8") as f:
#return json.load(f)
#def create_model(session, Model_class, path, load_vec, config, id_to_char, logger):
## create model, reuse parameters if exists
#model = Model_class(config)
#ckpt = tf.train.get_checkpoint_state(path)
#if ckpt and tf.train.checkpoint_exists(ckpt.model_checkpoint_path):
#logger.info("Reading model parameters from %s" % ckpt.model_checkpoint_path)
#model.saver.restore(session, ckpt.model_checkpoint_path)
#return model
#def result_to_json(string, tags):
#item = {"string": string, "entities": []}
#entity_name = ""
#entity_start = 0
#idx = 0
#for char, tag in zip(string, tags):
#if tag[0] == "S":
#item["entities"].append({"word": char, "start": idx, "end": idx+1, "type":tag[2:]})
#elif tag[0] == "B":
#entity_name += char
#entity_start = idx
#elif tag[0] == "I":
#entity_name += char
#elif tag[0] == "E":
#entity_name += char
#item["entities"].append({"word": entity_name, "start": entity_start, "end": idx + 1, "type": tag[2:]})
#entity_name = ""
#else:
#entity_name = ""
#entity_start = idx
#idx += 1
#return item