-
Notifications
You must be signed in to change notification settings - Fork 51
/
predict_ner.py
355 lines (298 loc) · 14.2 KB
/
predict_ner.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
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
# coding=utf-8
# David Adelani
'''
from transformers import AutoTokenizer, AutoModelForTokenClassification
from transformers import pipeline
tokenizer = AutoTokenizer.from_pretrained("Davlan/distilbert-base-multilingual-cased-masakhaner")
model = AutoModelForTokenClassification.from_pretrained("Davlan/distilbert-base-multilingual-cased-masakhaner")
nlp = pipeline("ner", model=model, tokenizer=tokenizer)
example = "Emir of Kano turban Zhang wey don spend 18 years for Nigeria"
ner_results = nlp(example)
print(ner_results)
'''
import logging
import os
from transformers import AutoConfig, AutoTokenizer, AutoModelForTokenClassification
from seqeval.metrics import f1_score, precision_score, recall_score, classification_report
from torch.utils.data import DataLoader, RandomSampler, SequentialSampler, TensorDataset
from torch.nn import CrossEntropyLoss
import torch
import string
from tqdm import tqdm
import numpy as np
logger = logging.getLogger(__name__)
def get_labels():
return ["O", "B-DATE", "I-DATE", "B-PER", "I-PER", "B-ORG", "I-ORG", "B-LOC", "I-LOC"]
class InputExample(object):
"""A single training/test example for token classification."""
def __init__(self, guid, words, labels):
"""Constructs a InputExample.
Args:
guid: Unique id for the example.
words: list. The words of the sequence.
labels: (Optional) list. The labels for each word of the sequence. This should be
specified for train and dev examples, but not for test examples.
"""
self.guid = guid
self.words = words
self.labels = labels
class InputFeatures(object):
"""A single set of features of data."""
def __init__(self, input_ids, input_mask, segment_ids, label_ids):
self.input_ids = input_ids
self.input_mask = input_mask
self.segment_ids = segment_ids
self.label_ids = label_ids
def read_examples(text):
guid_index = 1
examples = []
sentences = text.splitlines()
mode = 'test'
for sent in sentences:
sent = sent.translate(str.maketrans({key: " {0} ".format(key) for key in string.punctuation}))
words = sent.split()
labels = ['O']*len(words)
if words:
examples.append(InputExample(guid="{}-{}".format(mode, guid_index), words=words, labels=labels))
guid_index += 1
return examples
def convert_examples_to_features(
examples,
label_list,
max_seq_length,
tokenizer,
cls_token_at_end=False,
cls_token="[CLS]",
cls_token_segment_id=1,
sep_token="[SEP]",
sep_token_extra=False,
pad_on_left=False,
pad_token=0,
pad_token_segment_id=0,
pad_token_label_id=-100,
sequence_a_segment_id=0,
mask_padding_with_zero=True,
):
""" Loads a data file into a list of `InputBatch`s
`cls_token_at_end` define the location of the CLS token:
- False (Default, BERT/XLM pattern): [CLS] + A + [SEP] + B + [SEP]
- True (XLNet/GPT pattern): A + [SEP] + B + [SEP] + [CLS]
`cls_token_segment_id` define the segment id associated to the CLS token (0 for BERT, 2 for XLNet)
"""
label_map = {label: i for i, label in enumerate(label_list)}
features = []
for (ex_index, example) in enumerate(examples):
#print(ex_index, len(example.words))
if ex_index % 10000 == 0:
logger.info("Writing example %d of %d", ex_index, len(examples))
tokens = []
label_ids = []
for word, label in zip(example.words, example.labels):
word_tokens = tokenizer.tokenize(word)
tokens.extend(word_tokens)
# Use the real label id for the first token of the word, and padding ids for the remaining tokens
label_ids.extend([label_map[label]] + [pad_token_label_id] * (len(word_tokens) - 1))
# Account for [CLS] and [SEP] with "- 2" and with "- 3" for RoBERTa.
special_tokens_count = 3 if sep_token_extra else 2
if len(tokens) > max_seq_length - special_tokens_count:
tokens = tokens[: (max_seq_length - special_tokens_count)]
label_ids = label_ids[: (max_seq_length - special_tokens_count)]
# The convention in BERT is:
# (a) For sequence pairs:
# tokens: [CLS] is this jack ##son ##ville ? [SEP] no it is not . [SEP]
# type_ids: 0 0 0 0 0 0 0 0 1 1 1 1 1 1
# (b) For single sequences:
# tokens: [CLS] the dog is hairy . [SEP]
# type_ids: 0 0 0 0 0 0 0
#
# Where "type_ids" are used to indicate whether this is the first
# sequence or the second sequence. The embedding vectors for `type=0` and
# `type=1` were learned during pre-training and are added to the wordpiece
# embedding vector (and position vector). This is not *strictly* necessary
# since the [SEP] token unambiguously separates the sequences, but it makes
# it easier for the model to learn the concept of sequences.
#
# For classification tasks, the first vector (corresponding to [CLS]) is
# used as as the "sentence vector". Note that this only makes sense because
# the entire model is fine-tuned.
tokens += [sep_token]
label_ids += [pad_token_label_id]
if sep_token_extra:
# roberta uses an extra separator b/w pairs of sentences
tokens += [sep_token]
label_ids += [pad_token_label_id]
segment_ids = [sequence_a_segment_id] * len(tokens)
if cls_token_at_end:
tokens += [cls_token]
label_ids += [pad_token_label_id]
segment_ids += [cls_token_segment_id]
else:
tokens = [cls_token] + tokens
label_ids = [pad_token_label_id] + label_ids
segment_ids = [cls_token_segment_id] + segment_ids
input_ids = tokenizer.convert_tokens_to_ids(tokens)
# The mask has 1 for real tokens and 0 for padding tokens. Only real
# tokens are attended to.
input_mask = [1 if mask_padding_with_zero else 0] * len(input_ids)
# Zero-pad up to the sequence length.
padding_length = max_seq_length - len(input_ids)
if pad_on_left:
input_ids = ([pad_token] * padding_length) + input_ids
input_mask = ([0 if mask_padding_with_zero else 1] * padding_length) + input_mask
segment_ids = ([pad_token_segment_id] * padding_length) + segment_ids
label_ids = ([pad_token_label_id] * padding_length) + label_ids
else:
input_ids += [pad_token] * padding_length
input_mask += [0 if mask_padding_with_zero else 1] * padding_length
segment_ids += [pad_token_segment_id] * padding_length
label_ids += [pad_token_label_id] * padding_length
assert len(input_ids) == max_seq_length
assert len(input_mask) == max_seq_length
assert len(segment_ids) == max_seq_length
try:
assert len(label_ids) == max_seq_length
except:
continue
if ex_index < 5:
logger.info("*** Example ***")
logger.info("guid: %s", example.guid)
logger.info("tokens: %s", " ".join([str(x) for x in tokens]))
logger.info("input_ids: %s", " ".join([str(x) for x in input_ids]))
logger.info("input_mask: %s", " ".join([str(x) for x in input_mask]))
logger.info("segment_ids: %s", " ".join([str(x) for x in segment_ids]))
logger.info("label_ids: %s", " ".join([str(x) for x in label_ids]))
features.append(
InputFeatures(input_ids=input_ids, input_mask=input_mask, segment_ids=segment_ids, label_ids=label_ids)
)
return features
def load_and_cache_examples(text, tokenizer, labels, pad_token_label_id, max_seq_length, model_type):
examples = read_examples(text)
features = convert_examples_to_features(
examples,
labels,
max_seq_length,
tokenizer,
cls_token_at_end=bool(model_type in ["xlnet"]),
# xlnet has a cls token at the end
cls_token=tokenizer.cls_token,
cls_token_segment_id=2 if model_type in ["xlnet"] else 0,
sep_token=tokenizer.sep_token,
sep_token_extra=bool(model_type in ["roberta"]),
# roberta uses an extra separator b/w pairs of sentences, cf. github.com/pytorch/fairseq/commit/1684e166e3da03f5b600dbb7855cb98ddfcd0805
pad_on_left=bool(model_type in ["xlnet"]),
# pad on the left for xlnet
pad_token=tokenizer.convert_tokens_to_ids([tokenizer.pad_token])[0],
pad_token_segment_id=4 if model_type in ["xlnet"] else 0,
pad_token_label_id=pad_token_label_id,
)
# Convert to Tensors and build dataset
all_input_ids = torch.tensor([f.input_ids for f in features], dtype=torch.long)
all_input_mask = torch.tensor([f.input_mask for f in features], dtype=torch.long)
all_segment_ids = torch.tensor([f.segment_ids for f in features], dtype=torch.long)
all_label_ids = torch.tensor([f.label_ids for f in features], dtype=torch.long)
dataset = TensorDataset(all_input_ids, all_input_mask, all_segment_ids, all_label_ids)
return dataset
def evaluate(model, tokenizer, labels, pad_token_label_id, text, max_seq_length, model_type, device):
#load_and_cache_examples(text, tokenizer, labels, pad_token_label_id, max_seq_length, model_type)
eval_dataset = load_and_cache_examples(text, tokenizer, labels, pad_token_label_id, max_seq_length, model_type)
eval_batch_size = 16 #args.per_gpu_eval_batch_size * max(1, args.n_gpu)
# Note that DistributedSampler samples randomly
eval_sampler = SequentialSampler(eval_dataset) #if args.local_rank == -1 else DistributedSampler(eval_dataset)
eval_dataloader = DataLoader(eval_dataset, sampler=eval_sampler, batch_size=eval_batch_size)
eval_loss = 0.0
nb_eval_steps = 0
preds = None
out_label_ids = None
model.eval()
for batch in tqdm(eval_dataloader, desc="Evaluating"):
batch = tuple(t.to(device) for t in batch)
with torch.no_grad():
inputs = {"input_ids": batch[0], "attention_mask": batch[1], "labels": batch[3]}
if model_type != "distilbert":
inputs["token_type_ids"] = (
batch[2] if model_type in ["bert", "xlnet"] else None
) # XLM and RoBERTa don"t use segment_ids
outputs = model(**inputs)
tmp_eval_loss, logits = outputs[:2]
eval_loss += tmp_eval_loss.item()
nb_eval_steps += 1
if preds is None:
preds = logits.detach().cpu().numpy()
out_label_ids = inputs["labels"].detach().cpu().numpy()
else:
preds = np.append(preds, logits.detach().cpu().numpy(), axis=0)
out_label_ids = np.append(out_label_ids, inputs["labels"].detach().cpu().numpy(), axis=0)
eval_loss = eval_loss / nb_eval_steps
preds = np.argmax(preds, axis=2)
label_map = {i: label for i, label in enumerate(labels)}
out_label_list = [[] for _ in range(out_label_ids.shape[0])]
preds_list = [[] for _ in range(out_label_ids.shape[0])]
for i in range(out_label_ids.shape[0]):
for j in range(out_label_ids.shape[1]):
if out_label_ids[i, j] != pad_token_label_id:
out_label_list[i].append(label_map[out_label_ids[i][j]])
preds_list[i].append(label_map[preds[i][j]])
'''
results = {
"loss": eval_loss,
"precision": precision_score(out_label_list, preds_list),
"recall": recall_score(out_label_list, preds_list),
"f1": f1_score(out_label_list, preds_list),
'report': classification_report(out_label_list, preds_list),
}
'''
#for key in sorted(results.keys()):
# logger.info(" %s = %s", key, str(results[key]))
return preds_list
def predict_tags(text, model_name_or_path, model_type):
# Prepare CONLL-2003 task
labels = get_labels()
num_labels = len(labels)
# Use cross entropy ignore index as padding label id so that only real label ids contribute to the loss later
pad_token_label_id = CrossEntropyLoss().ignore_index
model_name_or_path = "Davlan/distilbert-base-multilingual-cased-masakhaner"
config_class, model_class, tokenizer_class = AutoConfig, AutoModelForTokenClassification, AutoTokenizer # MODEL_CLASSES[args.model_type]
'''
config = config_class.from_pretrained(model_name_or_path,
num_labels=num_labels,
id2label={str(i): label for i, label in enumerate(labels)},
label2id={label: i for i, label in enumerate(labels)},
cache_dir=None,
)
tokenizer = tokenizer_class.from_pretrained(model_name_or_path,
cache_dir=None,
)
model = model_class.from_pretrained(model_name_or_path,
from_tf=bool(".ckpt" in model_name_or_path),
config=config,
cache_dir=None,
)
'''
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
n_gpu = torch.cuda.device_count()
# Evaluation
tokenizer = tokenizer_class.from_pretrained(model_name_or_path, do_lower_case=False)
model = model_class.from_pretrained(model_name_or_path)
model.to(device)
max_seq_length = 200
model_type = "distilbert"
predictions = evaluate(model, tokenizer, labels, pad_token_label_id, text, max_seq_length, model_type, device)
# evaluate(model, tokenizer, labels, pad_token_label_id, mode="test")
# Save predictions
sentences = text.splitlines()
output_test_predictions_file = 'test_predictions.txt'
with open(output_test_predictions_file, "w") as writer:
for example_id, sent in enumerate(sentences):
sent = sent.translate(str.maketrans({key: " {0} ".format(key) for key in string.punctuation}))
words = sent.split()
for word in words:
label = predictions[example_id].pop(0)
writer.write(word + " " + label + "\n")
print(word + " " + label + "\n")
writer.write("\n")
print("\n")
if __name__ == "__main__":
text = "Emir of Kano turban Zhang wey don spend 18 years for Nigeria"
model_name = "Davlan/distilbert-base-multilingual-cased-masakhaner"
model_type = 'distilbert'
predict_tags(text, model_name, model_type)