def cut(sentence, HMM=True):
"""
Global `cut` function that supports parallel processing.
Note that this only works using dt, custom POSTokenizer
instances are not supported.
"""
global dt
if jieba.pool is None:
for w in dt.cut(sentence, HMM=HMM):
yield w
else:
parts = strdecode(sentence).splitlines(True)
if HMM:
result = jieba.pool.map(_lcut_internal, parts)
else:
result = jieba.pool.map(_lcut_internal_no_hmm, parts)
for r in result:
for w in r:
yield w
python类dt()的实例源码
def cut(sentence, HMM=True):
"""
Global `cut` function that supports parallel processing.
Note that this only works using dt, custom POSTokenizer
instances are not supported.
"""
global dt
if jieba.pool is None:
for w in dt.cut(sentence, HMM=HMM):
yield w
else:
parts = strdecode(sentence).splitlines(True)
if HMM:
result = jieba.pool.map(_lcut_internal, parts)
else:
result = jieba.pool.map(_lcut_internal_no_hmm, parts)
for r in result:
for w in r:
yield w
def cut(sentence, HMM=True):
"""
Global `cut` function that supports parallel processing.
Note that this only works using dt, custom POSTokenizer
instances are not supported.
"""
global dt
if jieba.pool is None:
for w in dt.cut(sentence, HMM=HMM):
yield w
else:
parts = strdecode(sentence).splitlines(True)
if HMM:
result = jieba.pool.map(_lcut_internal, parts)
else:
result = jieba.pool.map(_lcut_internal_no_hmm, parts)
for r in result:
for w in r:
yield w
def cut(sentence, HMM=True):
"""
Global `cut` function that supports parallel processing.
Note that this only works using dt, custom POSTokenizer
instances are not supported.
"""
global dt
if jieba.pool is None:
for w in dt.cut(sentence, HMM=HMM):
yield w
else:
parts = strdecode(sentence).splitlines(True)
if HMM:
result = jieba.pool.map(_lcut_internal, parts)
else:
result = jieba.pool.map(_lcut_internal_no_hmm, parts)
for r in result:
for w in r:
yield w
def cut(sentence, HMM=True):
"""
Global `cut` function that supports parallel processing.
Note that this only works using dt, custom POSTokenizer
instances are not supported.
"""
global dt
if jieba.pool is None:
for w in dt.cut(sentence, HMM=HMM):
yield w
else:
parts = strdecode(sentence).splitlines(True)
if HMM:
result = jieba.pool.map(_lcut_internal, parts)
else:
result = jieba.pool.map(_lcut_internal_no_hmm, parts)
for r in result:
for w in r:
yield w
def cut(sentence, HMM=True):
"""
Global `cut` function that supports parallel processing.
Note that this only works using dt, custom POSTokenizer
instances are not supported.
"""
global dt
if jieba.pool is None:
for w in dt.cut(sentence, HMM=HMM):
yield w
else:
parts = strdecode(sentence).splitlines(True)
if HMM:
result = jieba.pool.map(_lcut_internal, parts)
else:
result = jieba.pool.map(_lcut_internal_no_hmm, parts)
for r in result:
for w in r:
yield w
def cut(sentence, HMM=True):
"""
Global `cut` function that supports parallel processing.
Note that this only works using dt, custom POSTokenizer
instances are not supported.
"""
global dt
if jieba.pool is None:
for w in dt.cut(sentence, HMM=HMM):
yield w
else:
parts = strdecode(sentence).splitlines(True)
if HMM:
result = jieba.pool.map(_lcut_internal, parts)
else:
result = jieba.pool.map(_lcut_internal_no_hmm, parts)
for r in result:
for w in r:
yield w
def _lcut_internal(s):
return dt._lcut_internal(s)
def _lcut_internal_no_hmm(s):
return dt._lcut_internal_no_hmm(s)
def __init__(self, idf_path=None):
self.tokenizer = jieba.dt
self.postokenizer = jieba.posseg.dt
self.stop_words = self.STOP_WORDS.copy()
self.idf_loader = IDFLoader(idf_path or DEFAULT_IDF)
self.idf_freq, self.median_idf = self.idf_loader.get_idf()
def _lcut_internal(s):
return dt._lcut_internal(s)
def _lcut_internal_no_hmm(s):
return dt._lcut_internal_no_hmm(s)
def __init__(self, idf_path=None):
self.tokenizer = jieba.dt
self.postokenizer = jieba.posseg.dt
self.stop_words = self.STOP_WORDS.copy()
self.idf_loader = IDFLoader(idf_path or DEFAULT_IDF)
self.idf_freq, self.median_idf = self.idf_loader.get_idf()
def _lcut_internal(s):
return dt._lcut_internal(s)
def _lcut_internal_no_hmm(s):
return dt._lcut_internal_no_hmm(s)
def __init__(self, idf_path=None):
self.tokenizer = jieba.dt
self.postokenizer = jieba.posseg.dt
self.stop_words = self.STOP_WORDS.copy()
self.idf_loader = IDFLoader(idf_path or DEFAULT_IDF)
self.idf_freq, self.median_idf = self.idf_loader.get_idf()
def _lcut_internal(s):
return dt._lcut_internal(s)
def _lcut_internal_no_hmm(s):
return dt._lcut_internal_no_hmm(s)
def __init__(self, idf_path=None):
self.tokenizer = jieba.dt
self.postokenizer = jieba.posseg.dt
self.stop_words = self.STOP_WORDS.copy()
self.idf_loader = IDFLoader(idf_path or DEFAULT_IDF)
self.idf_freq, self.median_idf = self.idf_loader.get_idf()
def _lcut_internal(s):
return dt._lcut_internal(s)
def _lcut_internal_no_hmm(s):
return dt._lcut_internal_no_hmm(s)
def __init__(self, idf_path=None):
self.tokenizer = jieba.dt
self.postokenizer = jieba.posseg.dt
self.stop_words = self.STOP_WORDS.copy()
self.idf_loader = IDFLoader(idf_path or DEFAULT_IDF)
self.idf_freq, self.median_idf = self.idf_loader.get_idf()
def _lcut_internal(s):
return dt._lcut_internal(s)
def _lcut_internal_no_hmm(s):
return dt._lcut_internal_no_hmm(s)
def __init__(self, idf_path=None):
self.tokenizer = jieba.dt
self.postokenizer = jieba.posseg.dt
self.stop_words = self.STOP_WORDS.copy()
self.idf_loader = IDFLoader(idf_path or DEFAULT_IDF)
self.idf_freq, self.median_idf = self.idf_loader.get_idf()
def _lcut_internal(s):
return dt._lcut_internal(s)
def __init__(self, idf_path=None):
self.tokenizer = jieba.dt
self.postokenizer = jieba.posseg.dt
self.stop_words = self.STOP_WORDS.copy()
self.idf_loader = IDFLoader(idf_path or DEFAULT_IDF)
self.idf_freq, self.median_idf = self.idf_loader.get_idf()
