def test_corpus(self):
self.assertIsInstance(thai_negations(), frozenset)
self.assertIsInstance(thai_stopwords(), frozenset)
self.assertIsInstance(thai_syllables(), frozenset)
self.assertIsInstance(thai_words(), frozenset)
self.assertIsInstance(countries(), frozenset)
self.assertIsInstance(provinces(), frozenset)
self.assertIsInstance(provinces(details=True), list)
self.assertEqual(len(provinces(details=False)),
len(provinces(details=True)))
self.assertIsInstance(thai_family_names(), frozenset)
self.assertIsInstance(list(thai_family_names())[0], str)
self.assertIsInstance(thai_female_names(), frozenset)
self.assertIsInstance(thai_male_names(), frozenset)
self.assertIsInstance(
get_corpus_db("https://example.com/XXXXXX0lkjasd/SXfmskdjKKXXX"),
Response,
) # URL does not exist, should get 404 response
self.assertIsNone(get_corpus_db("XXXlkja3sfdXX")) # Invalid URL
self.assertEqual(get_corpus_db_detail("XXXmx3KSXX"),
{}) # corpus does not exist
self.assertEqual(get_corpus_db_detail("XXXmx3KSXX", version="0.2"),
{}) # corpus does not exist
self.assertTrue(download("test")) # download the first time
self.assertTrue(download(name="test", force=True)) # force download
self.assertTrue(download(name="test")) # try download existing
self.assertFalse(download(name="test",
url="wrongurl")) # URL not exist
self.assertFalse(
download(name="XxxXXxxx817d37sf")) # corpus name not exist
self.assertIsNotNone(get_corpus_db_detail("test")) # corpus exists
self.assertIsNotNone(get_corpus_path("test")) # corpus exists
self.assertTrue(remove("test")) # remove existing
self.assertFalse(remove("test")) # remove non-existing
self.assertIsNone(get_corpus_path("XXXkdjfBzc")) # query non-existing
self.assertFalse(download(name="test", version="0.0"))
self.assertFalse(download(name="test", version="0.0.0"))
self.assertFalse(download(name="test", version="0.0.1"))
self.assertFalse(download(name="test", version="0.0.2"))
self.assertFalse(download(name="test", version="0.0.3"))
self.assertFalse(download(name="test", version="0.0.4"))
self.assertIsNotNone(download(name="test", version="0.0.5"))
self.assertTrue(download("test"))
self.assertIsNotNone(remove("test")) # remove existing
self.assertIsNotNone(download(name="test", version="0.0.6"))
self.assertIsNotNone(download(name="test", version="0.0.7"))
self.assertIsNotNone(download(name="test", version="0.0.8"))
self.assertIsNotNone(download(name="test", version="0.0.9"))
self.assertIsNotNone(download(name="test", version="0.0.10"))
with self.assertRaises(Exception) as context:
self.assertIsNotNone(download(name="test", version="0.0.11"))
self.assertTrue(
"Hash does not match expected." in str(context.exception))
self.assertIsNotNone(download(name="test", version="0.1"))
self.assertIsNotNone(remove("test"))
def tag_provinces(tokens: List[str]) -> List[Tuple[str, str]]:
"""
This function recognize Thailand provinces in text.
:param list[str] tokens: a list of words
:reutrn: a list of tuple indicating NER for `LOCATION` in IOB format
:rtype: list[tuple[str, str]]
:Example:
::
from pythainlp.tag import tag_provinces
text = ['หนองคาย', 'น่าอยู่']
tag_provinces(text)
# output: [('หนองคาย', 'B-LOCATION'), ('น่าอยู่', 'O')]
text = ['อำเภอ', 'ฝาง','เป็น','ส่วน','หนึ่ง','ของ', 'จังหวัด', \\
'เชียงใหม่']
tag_provinces(text)
# output: [('อำเภอ', 'O'), ('ฝาง', 'O'), ('เป็น', 'O'), ('ส่วน', 'O'),
# ('หนึ่ง', 'O'), ('ของ', 'O'), ('จังหวัด', 'O'),
# ('เชียงใหม่', 'B-LOCATION')]
"""
province_list = provinces()
output = []
for token in tokens:
if token in province_list:
output.append((token, "B-LOCATION"))
else:
output.append((token, "O"))
return output
def test_corpus(self):
self.assertIsInstance(thai_negations(), frozenset)
self.assertIsInstance(thai_stopwords(), frozenset)
self.assertIsInstance(thai_syllables(), frozenset)
self.assertIsInstance(thai_words(), frozenset)
self.assertIsInstance(countries(), frozenset)
self.assertIsInstance(provinces(), frozenset)
self.assertIsInstance(thai_female_names(), frozenset)
self.assertIsInstance(thai_male_names(), frozenset)
self.assertEqual(get_corpus_db_detail("XXX"),
{}) # corpus does not exist
self.assertTrue(download("test")) # download the first time
self.assertTrue(download(name="test", force=True)) # force download
self.assertTrue(download(name="test")) # try download existing
self.assertFalse(download(name="test",
url="wrongurl")) # URL not exist
self.assertFalse(
download(name="XxxXXxxx817d37sf")) # corpus name not exist
self.assertIsNotNone(get_corpus_db_detail("test")) # corpus exists
self.assertTrue(remove("test")) # remove existing
self.assertFalse(remove("test")) # remove non-existing
self.assertTrue(download(name="test", version="0.1"))
self.assertTrue(remove("test"))
def test_corpus(self):
self.assertIsNotNone(countries())
self.assertIsNotNone(provinces())
self.assertIsNotNone(thai_negations())
self.assertIsNotNone(thai_stopwords())
self.assertIsNotNone(thai_syllables())
self.assertIsNotNone(thai_words())
download("test")
self.assertIsNotNone(remove("test"))
self.assertIsNotNone(remove("tnc_freq"))
def test_corpus(self):
self.assertIsNotNone(countries())
self.assertIsNotNone(provinces())
self.assertIsNotNone(thai_negations())
self.assertIsNotNone(thai_stopwords())
self.assertIsNotNone(thai_syllables())
self.assertIsNotNone(thai_words())
download("test")
self.assertIsNotNone(remove("test"))
self.assertIsNotNone(remove("tnc_freq"))
def test_corpus(self):
self.assertIsNotNone(countries())
self.assertIsNotNone(provinces())
self.assertIsNotNone(thai_negations())
self.assertIsNotNone(thai_stopwords())
self.assertIsNotNone(thai_syllables())
self.assertIsNotNone(thai_words())
self.assertIsNotNone(thai_female_names())
self.assertIsNotNone(thai_male_names())
self.assertEqual(get_corpus_db_detail("XXX"), {})
self.assertIsNone(download("test"))
self.assertIsNone(download("test", force=True))
self.assertIsNotNone(get_corpus_db_detail("test"))
self.assertIsNotNone(remove("test"))
self.assertFalse(remove("test"))
def tag_provinces(tokens: List[str]) -> List[Tuple[str, str]]:
"""
Recognize Thailand provinces in text
Input is a list of words
Return a list of tuples
Example::
>>> text = ['หนองคาย', 'น่าอยู่']
>>> tag_provinces(text)
[('หนองคาย', 'B-LOCATION'), ('น่าอยู่', 'O')]
"""
province_list = provinces()
output = []
for token in tokens:
if token in province_list:
output.append((token, "B-LOCATION"))
else:
output.append((token, "O"))
return output
def tag_provinces(tokens: List[str]) -> List[Tuple[str, str]]:
"""
This function recognize Thailand provinces in text.
Note that it uses exact match and considers no context.
:param list[str] tokens: a list of words
:reutrn: a list of tuple indicating NER for `LOCATION` in IOB format
:rtype: list[tuple[str, str]]
:Example:
::
from pythainlp.tag import tag_provinces
text = ['หนองคาย', 'น่าอยู่']
tag_provinces(text)
# output: [('หนองคาย', 'B-LOCATION'), ('น่าอยู่', 'O')]
"""
province_list = provinces()
output = [(token, "B-LOCATION") if token in province_list else (token, "O")
for token in tokens]
return output
def update():
global p
if getprovince() != '' and getdistrict() != '':
p = Place(province=getprovince(), amphoe=getdistrict())
elif getprovince() != '':
p = Place(province=getprovince())
else:
p = Place(province="หนองคาย", amphoe="เมืองหนองคาย")
d = PyTMD(key, p)
pattern = r'\<LOCATION\>(.*?)\<\/LOCATION\>'
tokenizer = RegexpTokenizer(pattern)
ner = ThaiNameTagger()
province_list = provinces()
def now():
global d, p
data = d.forecast_daily(day("today"))[0]['forecasts'][0]['data']
text = """
สภาพอากาศที่{place}ตอนนี้ มีสภาพอากาศ{cond}
มีอุณหภูมิ {temp} องศาเซลเซียส
อุณหภูมิสูงสุด {temp_max} องศาเซลเซียส
และมีอุณหภูมิต่ำสุด {temp_min} องศาเซลเซียสค่ะ
""".format(place=p.province,
cond=cond2txt(data['cond']),
temp=int(data['tc']),
temp_max=int(data['tc_max']),
temp_min=int(data['tc_min'])).replace(" ", "")