macb007的博客

from nltk.probability import FreqDistf = open(r"C:\Users\machuanbin\Desktop\santi.txt",encoding='utf-8')text = f.read()stop_word = ['【', '】', ')', '(', '、', '，', '“', '”', '。', '\n', '《', '》', ' ...

class Candidate(object):    # WORDS_dict={word:freq} def __init__(self,WORDS_dict): self.WORDS=WORDS_dict def P(self,word): "Probability of `word`." # print(word,WORD...

'''# Data downloadEnglish to French sentence pairs.http://www.manythings.org/anki/fra-eng.zipLots of neat sentence pairs datasets can be found at:http://www.manythings.org/anki/# References- Se...

#-*- coding:utf8 -*-from nltk.tokenize import RegexpTokenizerfrom stop_words import get_stop_wordsfrom nltk.stem.porter import PorterStemmerfrom gensim.models.ldamodel import LdaModelfrom gensim ...