/
test_zzz_shallownlp.py
152 lines (126 loc) · 5.24 KB
/
test_zzz_shallownlp.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
#!/usr/bin/env python3
"""
Tests of ktrain shallownlp module:
2020-05-26: renamed test_zzz_shallownlp.py because
causes issues for tests following it when run in conjunction with test_regression.py.
"""
import os
from unittest import TestCase, main, skip
import numpy as np
import testenv
os.environ["DISABLE_V2_BEHAVIOR"] = "1"
from ktrain.text import shallownlp as snlp
class TestShallowNLP(TestCase):
# @skip('temporarily disabled')
def test_classifier(self):
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
classes = train_b.target_names
clf = snlp.Classifier()
clf.fit(x_train, y_train, ctype="nbsvm")
self.assertGreaterEqual(clf.evaluate(x_test, y_test), 0.93)
test_doc = "god christ jesus mother mary church sunday lord heaven amen"
self.assertEqual(clf.predict(test_doc), 3)
# @skip('temporarily disabled')
def test_classifier_chinese(self):
fpath = "./resources/text_data/chinese_hotel_reviews.csv"
(x_train, y_train, label_names) = snlp.Classifier.load_texts_from_csv(
fpath, text_column="content", label_column="pos", sep="|"
)
print("label names: %s" % (label_names))
clf = snlp.Classifier()
clf.fit(x_train, y_train, ctype="nbsvm")
self.assertGreaterEqual(clf.evaluate(x_train, y_train), 0.98)
neg_text = "我讨厌和鄙视这家酒店。"
pos_text = "我喜欢这家酒店。"
self.assertEqual(clf.predict(pos_text), 1)
self.assertEqual(clf.predict(neg_text), 0)
# @skip('temporarily disabled')
def test_ner(self):
ner = snlp.NER("en")
text = """
Xuetao Cao was head of the Chinese Academy of Medical Sciences and is
the current president of Nankai University.
"""
result = ner.predict(text)
self.assertEqual(len(result), 3)
self.assertEqual(result[0][1], "PER")
self.assertEqual(result[1][1], "ORG")
self.assertEqual(result[2][1], "ORG")
self.assertEqual(
len(
snlp.sent_tokenize(
"Paul Newman is a good actor. Tommy Wisseau is not."
)
),
2,
)
ner = snlp.NER("zh")
text = """
曹雪涛曾任中国医学科学院院长,现任南开大学校长。
"""
result = ner.predict(text)
self.assertEqual(len(result), 3)
self.assertEqual(result[0][1], "PER")
self.assertEqual(result[1][1], "ORG")
self.assertEqual(result[2][1], "ORG")
self.assertEqual(len(snlp.sent_tokenize("这是关于史密斯博士的第一句话。第二句话是关于琼斯先生的。")), 2)
ner = snlp.NER("ru")
text = """Владимир Владимирович Путин - российский политик, который является президентом России с 2012 года."""
result = ner.predict(text)
self.assertEqual(len(result), 2)
self.assertEqual(result[0][1], "PER")
self.assertEqual(result[1][1], "LOC")
# @skip('temporarily disabled')
def test_search(self):
document1 = """
Hello there,
Hope this email finds you well.
Are you available to talk about our meeting?
If so, let us plan to schedule the meeting
at the Hefei National Laboratory for Physical Sciences at the Microscale.
As I always say: живи сегодня надейся на завтра
Sincerely,
John Doe
合肥微尺度国家物理科学实验室
"""
document2 = """
This is a random document with Arabic about our meeting.
عش اليوم الأمل ليوم غد
Bye for now.
"""
docs = [document1, document2]
result = snlp.search(
["physical sciences", "meeting", "Arabic"], docs, keys=["doc1", "doc2"]
)
self.assertEqual(len(result), 4)
self.assertEqual(result[0][2], 1)
self.assertEqual(result[1][2], 2)
self.assertEqual(result[2][1], "meeting")
self.assertEqual(result[3][1], "Arabic")
result = snlp.search("合肥微尺度国家物理科学实验室", docs, keys=["doc1", "doc2"])
self.assertEqual(len(result), 1)
self.assertEqual(result[0][2], 7)
result = snlp.search("сегодня надейся на завтра", docs, keys=["doc1", "doc2"])
self.assertEqual(len(result), 1)
self.assertEqual(result[0][2], 1)
if __name__ == "__main__":
main()