知微
fa45d8aa5f
- health_checklist.json: 192.168.1.122→node122
- ocr_client.py: docstring IP→node122
- docs/market-data-requirements.md: IP→node122
- 所有API调用通过ProxyHandler({})绕过系统代理
Privoxy对node122:18003返回500，直连正常
35 lines
990 B
Python
35 lines
990 B
Python
"""
|
|
Tests for Brill tagger.
|
|
"""
|
|
|
|
import unittest
|
|
|
|
from nltk.corpus import treebank
|
|
from nltk.tag import UnigramTagger, brill, brill_trainer
|
|
from nltk.tbl import demo
|
|
|
|
|
|
class TestBrill(unittest.TestCase):
|
|
def test_pos_template(self):
|
|
train_sents = treebank.tagged_sents()[:1000]
|
|
tagger = UnigramTagger(train_sents)
|
|
trainer = brill_trainer.BrillTaggerTrainer(
|
|
tagger, [brill.Template(brill.Pos([-1]))]
|
|
)
|
|
brill_tagger = trainer.train(train_sents)
|
|
# Example from https://github.com/nltk/nltk/issues/769
|
|
result = brill_tagger.tag("This is a foo bar sentence".split())
|
|
expected = [
|
|
("This", "DT"),
|
|
("is", "VBZ"),
|
|
("a", "DT"),
|
|
("foo", None),
|
|
("bar", "NN"),
|
|
("sentence", None),
|
|
]
|
|
self.assertEqual(result, expected)
|
|
|
|
@unittest.skip("Should be tested in __main__ of nltk.tbl.demo")
|
|
def test_brill_demo(self):
|
|
demo()
|