【gensim--dictionary】使用方法

import jieba, os
import codecs
from gensim import corpora, models, similarities
from pprint import pprint
from collections import defaultdict
import sys
import pickle
reload(sys)
sys.setdefaultencoding('utf-8')

def print_dict(dict):
    for key in dict:
        print type(key),key,str(dict[key]),
    print
def test3():
    '''''''
    gensim學習之Dictionary
    '''
    a = [['一','一','二'],['一','二','三']]
    b = ['一','一','三','四','四']
    dictionary = corpora.Dictionary(a)
    print "########dictionary信息##########"
    print str(dictionary) #
    print "字典，{單詞id，在多少文檔中出現}"
    print dictionary.dfs #字典，{單詞id，在多少文檔中出現}
    print "文檔數目"
    print dictionary.num_docs #文檔數目
    print "dictionary.items()"
    print_dict(dict(dictionary.items())) #
    print "字典，{單詞id，對應的詞}"
    print_dict(dictionary.id2token) #字典，{單詞id，對應的詞}
    print "字典，{詞，對應的單詞id}"
    print_dict(dictionary.token2id) #字典，{詞，對應的單詞id}
    print "所有詞的個數"
    print dictionary.num_pos #所有詞的個數
    print "每個文件中不重複詞個數的和"
    print dictionary.num_nnz #每個文件中不重複詞個數的和
    print "########doc2bow##########"
    #dictionary.add_documents([b])
    #allow_update->更新當前字典；return_missing->返回字典中不存在的詞
    #result爲b文章轉換得到的詞袋，列表[(單詞id，詞頻)]
    result, missing = dictionary.doc2bow(b, allow_update=False, return_missing=True)
    print "詞袋b，列表[(單詞id，詞頻)]"
    print result
    print "不在字典中的詞及其詞頻，字典[(單詞，詞頻)]"
    print_dict(missing)
    print "########bow信息##########"
    for id, freq in result:
        print id, dictionary.id2token[id], freq
    print "########dictionary信息##########"
    #過濾文檔頻率大於no_below，小於no_above*num_docs的詞
    dictionary.filter_extremes(no_below=1, no_above=0.5, keep_n=10)

    return

test3()