python jieba 库分词结合Wordcloud词云统计

import jieba
jieba.add_word("福军")
jieba.add_word("少安")
excludes={"一个","他们","自己","现在","已经","什么","这个","没有","这样","知道","两个"}
txt = open("D:\\Users\\Benny\平凡的世界.txt", "r", encoding='utf-8').read()
words = jieba.lcut(txt) # 使用精确模式对文本进行分词
counts = {} # 通过键值对的形式存储词语及其出现的次数
for word in words:
    if len(word)==1:
        continue
    elif word =="少平":
        rword="孙少平"
    elif word =="少安":
        rword="孙少平"
    elif word =="玉厚"or word=="父亲":
        rword="孙玉厚"
    elif word =="福军":
        rword="田福军"
    else:
        rword=word
    counts[rword]=counts.get(rword,0)+1 
for word in excludes:
    del(counts[word])
items=list(counts.items()) 
items.sort(key=lambda x: x[1], reverse=True) # 根据词语出现的次数进行从大到小排序

for i in range(30):
    word, count = items[i]
    print("{0:<5}{1:>5}".format(word, count))

　　

 

转载于:https://www.cnblogs.com/shuxincheng/p/10651937.html