def dict_mining():
nlp = BosonNLP('6cfIzKI1.27567.fLaZOvRXwl8f')
s = ['整流级逆变级滤波器负载三相检测abcdq双SVM控制dqabcADRCADRCaubucu*du*quotωotωinvTrecTuqud图3基于ADRC的TSMC闭环控制系统框图Fig.3Closed-loopcontroldiagramofTSMCbasedonADRCADRC采用图1结构。',
'但励磁绕组时间常数较大，闭环控制系统的截止频率较低，影响发电机输出端电压的响应速度。']
data = nlp.depparser(s)
nouns = extract_noun(data)
print(nouns)
class CNSegment:
"""
封装分词工具。
使用bosonnlp提供API
"""
#停用词表
stopwords = []
def __init__(self):
self.nlp=BosonNLP(bosonkey)
def get_tags(self,sentences):
"""
获取分词
:param sentences:分词的句子或者句子list
:return: 分词结果list
"""
result= self.nlp.tag(sentences)
return result
def denoisingOne(self,tagdict , uTag = None,useStopWord = False):
"""通过词性和停用词去除噪声
:param tagList : 分词过后得到的列表
:param uTag : 需要去噪的词性标记列表，默认为('w','o','y','u')
:return: 分词结果list
"""
if (uTag):
uselessTag = uTag
else:
uselessTag = ('w', 'o', 'y', 'u')
tagdict
word_list = []
for index, it in enumerate(tagdict['tag']):
if it[0] not in uselessTag:
if not useStopWord:
word_list.append(tagdict['word'][index])
elif tagdict['word'][index] not in self.stopwords:
word_list.append(tagdict['word'][index])
return word_list
def cut(self,sentences):
"""
分词
:param sentences:需要分词的语料集
:return: 去噪后的单词list
"""
tags=self.get_tags(sentences)
cutedSentences=[]
for sentence in tags:
cutedSentences.append(self.denoisingOne(sentence))
return cutedSentences
def depenPars(self,sentences):
return self.nlp.depparser(sentences)
def get_BosDepT(self, text):
bos = BosonNLP(bosonkey)
return bos.depparser(text)
class BosonNlpp:
def __init__(self):
self.bonlp = BosonNLP('IKBIoANy.14545.A7GCYBnT9jIB')
#情感分析
def testSentiment(self, s):
result = self.bonlp.sentiment(s)
return result
#print(result)
#命名实体识别
def lexicalAnalysis(self, s):
result = self.bonlp.ner(s)[0]
return result
#依存文法分析
def textDependency(self, s):
result = self.bonlp.depparser(s)
return result
#关键词提取
def testKeywords(self, s):
result = self.bonlp.extract_keywords(s, top_k=10)
return result
#新闻分类
def textClassify(self, s):
resultlist = self.bonlp.classify(s)
classifys = {
0: '体育',
1: '教育',
2: '财经',
3: '社会',
4: '娱乐',
5: '军事',
6: '国内',
7: '科技',
8: '互联网',
9: '房产',
10: '国际',
11: '女人',
12: '汽车',
13: '游戏'
}
return (classifys[resultlist[0]])
#语义联想
def lexicalSynonym(self, term):
result = self.bonlp.suggest(term, top_k=10)
return result
#分词与词性标注
def fenci(self, s):
result = self.bonlp.tag(s)
return result
def newssubstract(self, s):
#s=s.encode('utf8')
s = s.decode('utf-8')
result = self.bonlp.summary('', s)
return result
