assasin浅说高低词频

# -*- coding: utf-8 -*-
#-----------------------------------------------------------------------------------------------------------------------
__Author__ = 'assasin'
__DateTime__ = '2020/1/4 0:49'
#-----------------------------------------------------------------------------------------------------------------------

'''
自定义去掉高低词频
'''
from nltk_word import *
from stop_words import *

# 选择高低词频
def h1_freqword(fdist):
    wordlist = []
    print('=' * 10, '打印统计的词频', '=' * 10)
    for key in fdist.keys():
        if fdist.get(key) > 1 and fdist.get(key) < 15:
            wordlist.append(key + ':' + str(fdist.get(key)))

    return wordlist


if __name__ == '__main__':
    path = r'./datas/体育/11.txt'
    str_doc = readFile(path)
    word_list = seg_doc(str_doc)
    # nltk_word(word_list)

    fdist = nltk_word(word_list)
    wordlist = h1_freqword(fdist)
    print(wordlist)