文本词频统计2

gzj137070928

# 文本词频统计2
# threekingdomsV1：找一个三国演义的文件，保存为threekingdoms.txt，放在同一目录里面
# 记录输出出现次数最多的前十五个人物名输出

import jieba

filename = "threekingdoms.txt"
txt = open(filename, "r", encoding="utf-8").read()
words = jieba.lcut(txt)
counts = {}
for word in words:
    if len(word)==1:
        continue
    else:
        counts[word] = counts.get(word, 0) + 1
items = list(counts.items())
items.sort(key=lambda x:x[1],reverse=True)
# 将出现次数最多的前十五个人物名输出
for i in range(15):
    word, count = items[i]
    print("{0:<10}{1:>5}".format(word, count))