-
Notifications
You must be signed in to change notification settings - Fork 2
/
utils.py
304 lines (237 loc) · 7.94 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
"""
Utility functions.
"""
import math
import os
from collections import Counter
import numpy as np
from keras.utils import Sequence, get_file
def download(url):
"""Download a trained weights, config and preprocessor.
Args:
url (str): target url.
"""
filepath = get_file(fname='tmp.zip', origin=url, extract=True)
base_dir = os.path.dirname(filepath)
weights_file = os.path.join(base_dir, 'weights.h5')
params_file = os.path.join(base_dir, 'params.json')
preprocessor_file = os.path.join(base_dir, 'preprocessor.pickle')
return weights_file, params_file, preprocessor_file
def load_data_and_labels(filename, encoding='utf-8'):
"""Loads data and label from a file.
Args:
filename (str): path to the file.
encoding (str): file encoding format.
The file format is tab-separated values.
A blank line is required at the end of a sentence.
For example:
```
EU B-ORG
rejects O
German B-MISC
call O
to O
boycott O
British B-MISC
lamb O
. O
Peter B-PER
Blackburn I-PER
...
```
Returns:
tuple(numpy array, numpy array): data and labels.
Example:
>>> filename = 'conll2003/en/ner/train.txt'
>>> data, labels = load_data_and_labels(filename)
"""
sents, labels = [], []
words, tags = [], []
with open(filename, encoding=encoding) as f:
for line in f:
line = line.rstrip()
if line:
word, tag = line.split('\t')
words.append(word)
tags.append(tag)
else:
sents.append(words)
labels.append(tags)
words, tags = [], []
return sents, labels
class NERSequence_D2V(Sequence):
def __init__(self, x, y, d2v_vectors, batch_size=1, preprocess=None):
self.x = x
self.y = y
self.batch_size = batch_size
self.preprocess = preprocess
self.d2v_vectors = d2v_vectors
def __getitem__(self, idx):
batch_x = self.x[idx * self.batch_size: (idx + 1) * self.batch_size]
batch_y = self.y[idx * self.batch_size: (idx + 1) * self.batch_size]
batch_d2v = self.d2v_vectors[idx * self.batch_size: (idx + 1) * self.batch_size]
return self.preprocess(batch_x, y=batch_y, d2v_vectors=batch_d2v)
def __len__(self):
return math.ceil(len(self.x) / self.batch_size)
class NERSequence(Sequence):
def __init__(self, x, y, batch_size=1, preprocess=None):
self.x = x
self.y = y
self.batch_size = batch_size
self.preprocess = preprocess
def __getitem__(self, idx):
batch_x = self.x[idx * self.batch_size: (idx + 1) * self.batch_size]
batch_y = self.y[idx * self.batch_size: (idx + 1) * self.batch_size]
return self.preprocess(batch_x, batch_y)
def __len__(self):
return math.ceil(len(self.x) / self.batch_size)
class Vocabulary(object):
"""A vocabulary that maps tokens to ints (storing a vocabulary).
Attributes:
_token_count: A collections.Counter object holding the frequencies of tokens
in the data used to build the Vocabulary.
_token2id: A collections.defaultdict instance mapping token strings to
numerical identifiers.
_id2token: A list of token strings indexed by their numerical identifiers.
"""
def __init__(self, max_size=None, lower=True, unk_token=True, specials=('<pad>',)):
"""Create a Vocabulary object.
Args:
max_size: The maximum size of the vocabulary, or None for no
maximum. Default: None.
lower: boolean. Whether to convert the texts to lowercase.
unk_token: boolean. Whether to add unknown token.
specials: The list of special tokens (e.g., padding or eos) that
will be prepended to the vocabulary. Default: ('<pad>',)
"""
self._max_size = max_size
self._lower = lower
self._unk = unk_token
self._token2id = {token: i for i, token in enumerate(specials)}
self._id2token = list(specials)
self._token_count = Counter()
def __len__(self):
return len(self._token2id)
def add_token(self, token):
"""Add token to vocabulary.
Args:
token (str): token to add.
"""
token = self.process_token(token)
self._token_count.update([token])
def add_documents(self, docs):
"""Update dictionary from a collection of documents. Each document is a list
of tokens.
Args:
docs (list): documents to add.
"""
for sent in docs:
sent = map(self.process_token, sent)
self._token_count.update(sent)
def doc2id(self, doc):
"""Get the list of token_id given doc.
Args:
doc (list): document.
Returns:
list: int id of doc.
"""
doc = map(self.process_token, doc)
return [self.token_to_id(token) for token in doc]
def id2doc(self, ids):
"""Get the token list.
Args:
ids (list): token ids.
Returns:
list: token list.
"""
return [self.id_to_token(idx) for idx in ids]
def build(self):
"""
Build vocabulary.
"""
token_freq = self._token_count.most_common(self._max_size)
idx = len(self.vocab)
for token, _ in token_freq:
self._token2id[token] = idx
self._id2token.append(token)
idx += 1
if self._unk:
unk = '<unk>'
self._token2id[unk] = idx
self._id2token.append(unk)
def process_token(self, token):
"""Process token before following methods:
* add_token
* add_documents
* doc2id
* token_to_id
Args:
token (str): token to process.
Returns:
str: processed token string.
"""
if self._lower:
token = token.lower()
return token
def token_to_id(self, token):
"""Get the token_id of given token.
Args:
token (str): token from vocabulary.
Returns:
int: int id of token.
"""
token = self.process_token(token)
return self._token2id.get(token, len(self._token2id) - 1)
def id_to_token(self, idx):
"""token-id to token (string).
Args:
idx (int): token id.
Returns:
str: string of given token id.
"""
return self._id2token[idx]
@property
def vocab(self):
"""Return the vocabulary.
Returns:
dict: get the dict object of the vocabulary.
"""
return self._token2id
@property
def reverse_vocab(self):
"""Return the vocabulary as a reversed dict object.
Returns:
dict: reversed vocabulary object.
"""
return self._id2token
def filter_embeddings(embeddings, vocab, dim):
"""Loads word vectors in numpy array.
Args:
embeddings (dict): a dictionary of numpy array.
vocab (dict): word_index lookup table.
Returns:
numpy array: an array of word embeddings.
"""
if not isinstance(embeddings, dict):
return
_embeddings = np.zeros([len(vocab), dim])
for word in vocab:
if word in embeddings:
word_idx = vocab[word]
_embeddings[word_idx] = embeddings[word]
return _embeddings
def load_glove(file):
"""Loads GloVe vectors in numpy array.
Args:
file (str): a path to a glove file.
Return:
dict: a dict of numpy arrays.
"""
model = {}
with open(file) as f:
for line in f:
line = line.split(' ')
word = line[0]
vector = np.array([float(val) for val in line[1:]])
model[word] = vector
return model