-
Notifications
You must be signed in to change notification settings - Fork 269
/
test_transformers.py
157 lines (128 loc) · 6.08 KB
/
test_transformers.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
#!/usr/bin/env python3
"""
Tests of ktrain text classification flows
"""
import testenv
import IPython
from unittest import TestCase, main, skip
import numpy as np
import ktrain
from ktrain import text as txt
from ktrain.imports import ACC_NAME, VAL_ACC_NAME
TEST_DOC = 'god christ jesus mother mary church sunday lord heaven amen'
EVAL_BS = 64
class TestTransformers(TestCase):
def setUp(self):
# fetch the dataset using scikit-learn
categories = ['alt.atheism', 'soc.religion.christian',
'comp.graphics', 'sci.med']
from sklearn.datasets import fetch_20newsgroups
train_b = fetch_20newsgroups(subset='train',
categories=categories, shuffle=True, random_state=42)
test_b = fetch_20newsgroups(subset='test',
categories=categories, shuffle=True, random_state=42)
print('size of training set: %s' % (len(train_b['data'])))
print('size of validation set: %s' % (len(test_b['data'])))
print('classes: %s' % (train_b.target_names))
x_train = train_b.data
y_train = train_b.target
x_test = test_b.data
y_test = test_b.target
# convert to string labels
y_train = [train_b.target_names[y] for y in y_train]
y_test = [train_b.target_names[y] for y in y_test]
# setup
self.trn = (x_train, y_train)
self.val = (x_test, y_test)
#self.classes = train_b.target_names
self.classes = [] # discover from string labels
#@skip('temporarily disabled')
def test_transformers_api_1(self):
trn, val, preproc = txt.texts_from_array(x_train=self.trn[0],
y_train=self.trn[1],
x_test=self.val[0],
y_test=self.val[1],
class_names=self.classes,
preprocess_mode='distilbert',
maxlen=500,
max_features=35000)
model = txt.text_classifier('distilbert', train_data=trn, preproc=preproc)
learner = ktrain.get_learner(model, train_data=trn, val_data=val, batch_size=6, eval_batch_size=EVAL_BS)
# test weight decay
# NOTE due to transformers and/or AdamW bug, # val_accuracy is missing in training history if setting weight decay prior to training
#self.assertEqual(learner.get_weight_decay(), None)
#learner.set_weight_decay(1e-2)
#self.assertAlmostEqual(learner.get_weight_decay(), 1e-2)
# train
lr = 5e-5
hist = learner.fit_onecycle(lr, 1)
# test training results
self.assertAlmostEqual(max(hist.history['lr']), lr)
self.assertGreater(max(hist.history[VAL_ACC_NAME]), 0.9)
# test top losses
obs = learner.top_losses(n=1, val_data=None)
self.assertIn(obs[0][0], list(range(len(val.x))))
learner.view_top_losses(preproc=preproc, n=1, val_data=None)
# test weight decay
self.assertEqual(learner.get_weight_decay(), None)
learner.set_weight_decay(1e-2)
self.assertAlmostEqual(learner.get_weight_decay(), 1e-2)
# test load and save model
tmp_folder = ktrain.imports.tempfile.mkdtemp()
learner.save_model(tmp_folder)
learner.load_model(tmp_folder)
# test validate
cm = learner.validate()
print(cm)
for i, row in enumerate(cm):
self.assertEqual(np.argmax(row), i)
# test predictor
p = ktrain.get_predictor(learner.model, preproc, batch_size=EVAL_BS)
self.assertEqual(p.predict([TEST_DOC])[0], 'soc.religion.christian')
tmp_folder = ktrain.imports.tempfile.mkdtemp()
p.save(tmp_folder)
p = ktrain.load_predictor(tmp_folder, batch_size=EVAL_BS)
self.assertEqual(p.predict(TEST_DOC), 'soc.religion.christian')
self.assertEqual(np.argmax(p.predict_proba([TEST_DOC])[0]), 3)
self.assertEqual(type(p.explain(TEST_DOC)), IPython.core.display.HTML)
#@skip('temporarily disabled')
def test_transformers_api_2(self):
MODEL_NAME = 'distilbert-base-uncased'
preproc = txt.Transformer(MODEL_NAME, maxlen=500, classes=self.classes)
trn = preproc.preprocess_train(self.trn[0], self.trn[1])
val = preproc.preprocess_test(self.val[0], self.val[1])
model = preproc.get_classifier()
learner = ktrain.get_learner(model, train_data=trn, val_data=val, batch_size=6, eval_batch_size=EVAL_BS)
lr = 5e-5
hist = learner.fit_onecycle(lr, 1)
# test training results
self.assertAlmostEqual(max(hist.history['lr']), lr)
self.assertGreater(max(hist.history[VAL_ACC_NAME]), 0.9)
# test top losses
obs = learner.top_losses(n=1, val_data=None)
self.assertIn(obs[0][0], list(range(len(val.x))))
learner.view_top_losses(preproc=preproc, n=1, val_data=None)
# test weight decay
self.assertEqual(learner.get_weight_decay(), None)
learner.set_weight_decay(1e-2)
self.assertAlmostEqual(learner.get_weight_decay(), 1e-2)
# test load and save model
tmp_folder = ktrain.imports.tempfile.mkdtemp()
learner.save_model(tmp_folder)
learner.load_model(tmp_folder)
# test validate
cm = learner.validate()
print(cm)
for i, row in enumerate(cm):
self.assertEqual(np.argmax(row), i)
# test predictor
p = ktrain.get_predictor(learner.model, preproc, batch_size=EVAL_BS)
self.assertEqual(p.predict([TEST_DOC])[0], 'soc.religion.christian')
tmp_folder = ktrain.imports.tempfile.mkdtemp()
p.save(tmp_folder)
p = ktrain.load_predictor(tmp_folder, batch_size=EVAL_BS)
self.assertEqual(p.predict(TEST_DOC), 'soc.religion.christian')
self.assertEqual(np.argmax(p.predict_proba([TEST_DOC])[0]), 3)
self.assertEqual(type(p.explain(TEST_DOC)), IPython.core.display.HTML)
if __name__ == "__main__":
main()