Stuttering participle method Encapsulation class
From __future__ import Unicode_literalsimport syssys.path.append (".. /") Import Jiebaimport jieba.possegimport jieba.analyseprint (' = ' *40) print (' 1. Word breaker ') print ('-' *40 ') seg_list = Jieba.cut (" I came to Beijing Tsinghua University ", cut_all=true) print (" Full mode: "+"/". Join (Seg_list)) # seg_list = Jieba.cut (" I came to Beijing Tsinghua University ", Cut_all=false) Print ("default mode:" + "/". Join (Seg_list)) # default Mode seg_list = Jieba.cut ("He came to NetEase Hang Research building") print (",". Join (seg_list)) seg_list = Jieba.cut_for_search ("Xiao Ming Master graduated from the Institute of Chinese Academy of Sciences, post-graduate studies at Kyoto University in Japan") # Search engine mode print (",". Join (Seg_list)) print (' = ' *40) print (' 2. Add custom dictionary/adjust dictionary ') print ('-' *40) ' Print ('/'. Join (Jieba.cut (') error if put in post. ', Hmm=false)) #如果/put in/post//error/. Print (Jieba.suggest_freq (' Medium ', ' will '), True) #494print ('/'. Join (Jieba.cut (') error if put in post. ', Hmm=false)) #如果/Put in/post//will/error/. Print ('/') Join (Jieba.cut (' "Taichung" correctly should not be cut ', Hmm=false))) #"//Middle/"/correct/should/not/BE/cut print (Jieba.suggest_freq (' Taichung ', True) #69print ('/') Join (Jieba.cut (' "Taichung" correctly should not be cut ', Hmm=false))) #"/Taichung/"/Correct/should/not/BE/cut print (' = ' *40) print (' 3. Keyword extraction ') Print ('-' *40) print (' TF-IDF ') print ('-' *40) s = "In addition, the company intends to a wholly-owned subsidiary of Jilin Eurasia Real Estate Co., Ltd. increased capital of 430 million yuan, after the increase in capital, Jilin Eurasian property registered from 70 million yuan to 500 million yuan. The main business scope of Jilin Eurasia property is real estate development and retail business. Currently under construction in Jilin Eurasian City Commercial Complex project. 2013, the realization of revenue of 0 yuan, the realization of net profit-1.3913 million yuan. "For X, W in Jieba.analyse.extract_tags (S, withweight=true): Print ('%s%s '% (x, W)) print ('-' *40 ') print (' Textrank ') prin T ('-' *40) for X, W in Jieba.analyse.textrank (S, withweight=true): Print ('%s%s '% (x, W)) print (' = ' *40) print (' 4. Pos callout ') pr Int ('-' *40) words = Jieba.posseg.cut ("I love Beijing Cheonan") for word, flag in Words:print ('%s%s '% (word, flag)) print (' = ' *40) print ( ' 6. Tokenize: Return the word at the beginning and end of the text ') print ('-' *40 ') print (' default mode ') print ('-' *40 ') result = Jieba.tokenize (' Yonghe Costume Jewelry Co., Ltd. ') for TK in Result:print ("Word%s\t\t start:%d \t\t end:%d"% (tk[0],tk[1],tk[2])) print ('-' *40 ') print (' search mode ') print ('-' *40 ') result = Jieba.tokenize (' Yonghe Costume Ornament Co., Ltd. ', mode= ' search ') for TK in Result:print ("Word%s\t\t start:%d \t\t end:%d"% (Tk[0],tk[1] , tk[2]))
Running results of stuttering participle
The use of stuttering participle in python