forked from deeptextlab/BioPREP
-
Notifications
You must be signed in to change notification settings - Fork 0
/
cnn_lstm.py
167 lines (130 loc) · 6.66 KB
/
cnn_lstm.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
from tensorflow.keras.callbacks import ModelCheckpoint
from tensorflow.keras.layers import Embedding, SpatialDropout1D, Conv1D, MaxPooling1D, LSTM, Dense
from tensorflow.keras.models import model_from_json, Sequential
import numpy as np
from tensorflow.keras.preprocessing.sequence import pad_sequences
from utility.tensorflow_utils import export_keras_to_tensorflow, export_text_model_to_csv
from utility.tokenizer_utils import word_tokenize
from keras.utils import np_utils
from sklearn.model_selection import train_test_split
import keras.backend as K
class WordVecCnnLstm(object):
model_name = 'wordvec_cnn_lstm_predicate'
def __init__(self):
self.model = None
self.word2idx = None
self.idx2word = None
self.max_len = None
self.config = None
self.vocab_size = None
self.labels = None
@staticmethod
def get_architecture_file_path(model_dir_path):
return model_dir_path + '/' + WordVecCnnLstm.model_name + '_architecture.json'
@staticmethod
def get_weight_file_path(model_dir_path):
return model_dir_path + '/' + WordVecCnnLstm.model_name + '_weights.h5'
@staticmethod
def get_config_file_path(model_dir_path):
return model_dir_path + '/' + WordVecCnnLstm.model_name + '_config.npy'
def load_model(self, model_dir_path):
json = open(self.get_architecture_file_path(model_dir_path), 'r').read()
self.model = model_from_json(json)
self.model.load_weights(self.get_weight_file_path(model_dir_path))
self.model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
config_file_path = self.get_config_file_path(model_dir_path)
self.config = np.load(config_file_path).item()
self.idx2word = self.config['idx2word']
self.word2idx = self.config['word2idx']
self.max_len = self.config['max_len']
self.vocab_size = self.config['vocab_size']
self.labels = self.config['labels']
def create_model(self):
lstm_output_size = 128
embedding_size = 300
self.model = Sequential()
self.model.add(Embedding(input_dim=self.vocab_size, input_length=self.max_len, output_dim=embedding_size))
self.model.add(SpatialDropout1D(0.2))
self.model.add(Conv1D(filters=256, kernel_size=5, padding='same', activation='relu'))
self.model.add(MaxPooling1D(pool_size=4))
self.model.add(LSTM(lstm_output_size))
self.model.add(Dense(units=len(self.labels), activation='softmax'))
self.model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=[self.get_f1]) # default 1e-4
def fit(self, text_data_model, text_label_pairs, model_dir_path, batch_size=64, epochs=20,
test_size=0.2, random_state=42):
self.config = text_data_model
self.idx2word = self.config['idx2word']
self.word2idx = self.config['word2idx']
self.max_len = self.config['max_len']
self.vocab_size = self.config['vocab_size']
self.labels = self.config['labels']
np.save(self.get_config_file_path(model_dir_path), self.config)
self.create_model()
json = self.model.to_json()
open(self.get_architecture_file_path(model_dir_path), 'w').write(json)
xs = []
ys = []
for text, label in text_label_pairs:
tokens = [x for x in word_tokenize(text)]
wid_list = list()
for w in tokens:
wid = 0
if w in self.word2idx:
wid = self.word2idx[w]
wid_list.append(wid)
xs.append(wid_list)
ys.append(self.labels[str(label)])
X = pad_sequences(xs, maxlen=self.max_len)
Y = np_utils.to_categorical(ys, len(self.labels))
x_train, x_test, y_train, y_test = train_test_split(X, Y,
test_size=test_size,
stratify=Y,
random_state=random_state)
weight_file_path = self.get_weight_file_path(model_dir_path)
checkpoint = ModelCheckpoint(weight_file_path)
print('===========================================')
print('Below is the shape of train/test dataset.')
print('===========================================')
print(x_train.shape, x_test.shape, y_train.shape, y_test.shape)
print('===========================================')
print()
print('===========================================')
print('======== Now we are on training... ========')
print('===========================================')
history = self.model.fit(x=x_train, y=y_train, batch_size=batch_size, epochs=epochs,
validation_data=(x_test, y_test), callbacks=[checkpoint],
verbose=1)
self.model.save_weights(weight_file_path)
np.save(model_dir_path + '/' + WordVecCnnLstm.model_name + '-history.npy', history.history)
# score = self.model.evaluate(x=x_test, y=y_test, batch_size=batch_size, verbose=1)
# print('score: ', score[0])
# print('accuracy: ', score[1])
# print('f1: ', score[2])
# print('precision: ', score[3])
# print('recall: ', score[4])
return history
def get_f1(self, y_true, y_pred):
true_pos = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
possible_pos = K.sum(K.round(K.clip(y_true, 0, 1)))
predicted_pos = K.sum(K.round(K.clip(y_pred, 0, 1)))
precision = true_pos / (predicted_pos + K.epsilon())
recall = true_pos / (possible_pos + K.epsilon())
f1_val = 2 * (precision * recall) / (precision + recall + K.epsilon())
return f1_val
def predict(self, sentence):
xs = []
tokens = [w for w in word_tokenize(sentence)]
wid = [self.word2idx[token] if token in self.word2idx else len(self.word2idx) for token in tokens]
xs.append(wid)
x = pad_sequences(xs, self.max_len)
output = self.model.predict(x)
return output[0]
def predict_class(self, sentence):
predicted = self.predict(sentence)
idx2label = dict([(idx, label) for label, idx in self.labels.items()])
return idx2label[np.argmax(predicted)]
def test_run(self, sentence):
print(self.predict(sentence))
def export_tensorflow_model(self, output_fld):
export_keras_to_tensorflow(self.model, output_fld, output_model_file=WordVecCnnLstm.model_name + '.pb')
export_text_model_to_csv(self.config, output_fld, output_model_file=WordVecCnnLstm.model_name + '.csv')