forked from rahulremanan/python_tutorial
/
05_Bidirectional_LSTM_classifier.py
215 lines (186 loc) · 7.74 KB
/
05_Bidirectional_LSTM_classifier.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
# -*- coding: utf-8 -*-
"""
Created on Fri Jul 21 23:41:03 2017
@author: Rahul
"""
# Example code from Spacy: https://github.com/explosion/spaCy/blob/master/examples/deep_learning_keras.py
# Detailed documentation: https://explosion.ai/blog/spacy-deep-learning-keras
import plac
import collections
import random
import pathlib
import cytoolz
import numpy
from keras.models import Sequential, model_from_json
from keras.layers import LSTM, Dense, Embedding, Dropout, Bidirectional
from keras.layers import TimeDistributed
from keras.optimizers import Adam
import cPickle as pickle
import spacy
class SentimentAnalyser(object):
@classmethod
def load(cls, path, nlp, max_length=100):
with (path / 'config.json').open() as file_:
model = model_from_json(file_.read())
with (path / 'model').open('rb') as file_:
lstm_weights = pickle.load(file_)
embeddings = get_embeddings(nlp.vocab)
model.set_weights([embeddings] + lstm_weights)
return cls(model, max_length=max_length)
def __init__(self, model, max_length=100):
self._model = model
self.max_length = max_length
def __call__(self, doc):
X = get_features([doc], self.max_length)
y = self._model.predict(X)
self.set_sentiment(doc, y)
def pipe(self, docs, batch_size=1000, n_threads=2):
for minibatch in cytoolz.partition_all(batch_size, docs):
minibatch = list(minibatch)
sentences = []
for doc in minibatch:
sentences.extend(doc.sents)
Xs = get_features(sentences, self.max_length)
ys = self._model.predict(Xs)
for sent, label in zip(sentences, ys):
sent.doc.sentiment += label - 0.5
for doc in minibatch:
yield doc
def set_sentiment(self, doc, y):
doc.sentiment = float(y[0])
# Sentiment has a native slot for a single float.
# For arbitrary data storage, there's:
# doc.user_data['my_data'] = y
def get_labelled_sentences(docs, doc_labels):
labels = []
sentences = []
for doc, y in zip(docs, doc_labels):
for sent in doc.sents:
sentences.append(sent)
labels.append(y)
return sentences, numpy.asarray(labels, dtype='int32')
def get_features(docs, max_length):
docs = list(docs)
Xs = numpy.zeros((len(docs), max_length), dtype='int32')
for i, doc in enumerate(docs):
j = 0
for token in doc:
if token.has_vector and not token.is_punct and not token.is_space:
Xs[i, j] = token.rank + 1
j += 1
if j >= max_length:
break
return Xs
def train(train_texts, train_labels, dev_texts, dev_labels,
lstm_shape, lstm_settings, lstm_optimizer, batch_size=100, nb_epoch=5,
by_sentence=True):
print("Loading spaCy")
nlp = spacy.load('en', entity=False)
embeddings = get_embeddings(nlp.vocab)
model = compile_lstm(embeddings, lstm_shape, lstm_settings)
print("Parsing texts...")
train_docs = list(nlp.pipe(train_texts, batch_size=5000, n_threads=3))
dev_docs = list(nlp.pipe(dev_texts, batch_size=5000, n_threads=3))
if by_sentence:
train_docs, train_labels = get_labelled_sentences(train_docs, train_labels)
dev_docs, dev_labels = get_labelled_sentences(dev_docs, dev_labels)
train_X = get_features(train_docs, lstm_shape['max_length'])
dev_X = get_features(dev_docs, lstm_shape['max_length'])
model.fit(train_X, train_labels, validation_data=(dev_X, dev_labels),
nb_epoch=nb_epoch, batch_size=batch_size)
return model
def compile_lstm(embeddings, shape, settings):
model = Sequential()
model.add(
Embedding(
embeddings.shape[0],
embeddings.shape[1],
input_length=shape['max_length'],
trainable=False,
weights=[embeddings],
mask_zero=True
)
)
model.add(TimeDistributed(Dense(shape['nr_hidden'], bias=False)))
model.add(Bidirectional(LSTM(shape['nr_hidden'], dropout_U=settings['dropout'],
dropout_W=settings['dropout'])))
model.add(Dense(shape['nr_class'], activation='sigmoid'))
model.compile(optimizer=Adam(lr=settings['lr']), loss='binary_crossentropy',
metrics=['accuracy'])
return model
def get_embeddings(vocab):
max_rank = max(lex.rank+1 for lex in vocab if lex.has_vector)
vectors = numpy.ndarray((max_rank+1, vocab.vectors_length), dtype='float32')
for lex in vocab:
if lex.has_vector:
vectors[lex.rank + 1] = lex.vector
return vectors
def evaluate(model_dir, texts, labels, max_length=100):
def create_pipeline(nlp):
'''
This could be a lambda, but named functions are easier to read in Python.
'''
return [nlp.tagger, nlp.parser, SentimentAnalyser.load(model_dir, nlp,
max_length=max_length)]
nlp = spacy.load('en')
nlp.pipeline = create_pipeline(nlp)
correct = 0
i = 0
for doc in nlp.pipe(texts, batch_size=1000, n_threads=4):
correct += bool(doc.sentiment >= 0.5) == bool(labels[i])
i += 1
return float(correct) / i
def read_data(data_dir, limit=0):
examples = []
for subdir, label in (('pos', 1), ('neg', 0)):
for filename in (data_dir / subdir).iterdir():
with filename.open() as file_:
text = file_.read()
examples.append((text, label))
random.shuffle(examples)
if limit >= 1:
examples = examples[:limit]
return zip(*examples) # Unzips into two lists
@plac.annotations(
train_dir=("Location of training file or directory"),
dev_dir=("Location of development file or directory"),
model_dir=("Location of output model directory",),
is_runtime=("Demonstrate run-time usage", "flag", "r", bool),
nr_hidden=("Number of hidden units", "option", "H", int),
max_length=("Maximum sentence length", "option", "L", int),
dropout=("Dropout", "option", "d", float),
learn_rate=("Learn rate", "option", "e", float),
nb_epoch=("Number of training epochs", "option", "i", int),
batch_size=("Size of minibatches for training LSTM", "option", "b", int),
nr_examples=("Limit to N examples", "option", "n", int)
)
def main(model_dir, train_dir, dev_dir,
is_runtime=False,
nr_hidden=64, max_length=100, # Shape
dropout=0.5, learn_rate=0.001, # General NN config
nb_epoch=5, batch_size=100, nr_examples=-1): # Training params
model_dir = pathlib.Path(model_dir)
train_dir = pathlib.Path(train_dir)
dev_dir = pathlib.Path(dev_dir)
if is_runtime:
dev_texts, dev_labels = read_data(dev_dir)
acc = evaluate(model_dir, dev_texts, dev_labels, max_length=max_length)
print(acc)
else:
print("Read data")
train_texts, train_labels = read_data(train_dir, limit=nr_examples)
dev_texts, dev_labels = read_data(dev_dir, limit=nr_examples)
train_labels = numpy.asarray(train_labels, dtype='int32')
dev_labels = numpy.asarray(dev_labels, dtype='int32')
lstm = train(train_texts, train_labels, dev_texts, dev_labels,
{'nr_hidden': nr_hidden, 'max_length': max_length, 'nr_class': 1},
{'dropout': dropout, 'lr': learn_rate},
{},
nb_epoch=nb_epoch, batch_size=batch_size)
weights = lstm.get_weights()
with (model_dir / 'model').open('wb') as file_:
pickle.dump(weights[1:], file_)
with (model_dir / 'config.json').open('wb') as file_:
file_.write(lstm.to_json())
if __name__ == '__main__':
plac.call(main)