三国演义中的人物
#Hamlet词频统计（含Hamlet原文文本）
#CalHamletV1.py
def getText():
txt = open("hamlet.txt", "r").read()
txt = txt.lower()
for ch in '!"#$%&()*+,-./:;<=>?@[\\]^_‘{|}~':
txt = txt.replace(ch, " ") #将文本中特殊字符替换为空格
return txt
hamletTxt = getText()
words = hamletTxt.split()
counts = {}
for word in words:
counts[word] = counts.get(word,0) + 1
items = list(counts.items())
items.sort(key=lambda x:x[1], reverse=True)
for i in range(10):
word, count = items[i]
print ("{0:<10}{1:>5}".format(word, count))
#《三国演义》人物出场统计（上）（含《三国演义》原文文本）
#CalThreeKingdomsV1.py
import jieba
txt = open("threekingdoms.txt", "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)
for i in range(15):
word, count = items[i]
print ("{0:<10}{1:>5}".format(word, count))
#《三国演义》人物出场统计（下）（含《三国演义》原文文本）
#CalThreeKingdomsV2.py
import jieba
excludes = {"将军","却说","荆州","二人","不可","不能","如此"}
txt = open("threekingdoms.txt", "r", encoding='utf-8').read()
words = jieba.lcut(txt)
counts = {}
for word in words:
if len(word) == 1:
continue
elif word == "诸葛亮" or word == "孔明曰":
rword = "孔明"
elif word == "关公" or word == "云长":
rword = "关羽"
elif word == "玄德" or word == "玄德曰":
rword = "刘备"
elif word == "孟德" or word == "丞相":
rword = "曹操"
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)
for i in range(10):
word, count = items[i]
print ("{0:<10}{1:>5}".format(word, count))
题目来源：中国mooc
相关阅读
读书笔记摘自：奇特的一生：柳比歇夫坚持56年的时间统计法【俄】格拉宁 编者的话 跟人生志向、人生目标密切相关 制订自己的时
PPT中，人物介绍页面经常使用到，今天我用15个复联英雄人物介绍页面，为大家介绍如何把人物介绍页面做的更出彩。举例首先插
人物画像的主要目的是分析人物行为，最终为每个人物打上标签，以及该标签的权重 1.标签是对用户的社会属性、生活习惯、消费行为等
● 每周一言 心中有数，才能气定神闲。 导语 从本周起，小斗开始写统计分析相关的文章。 特征的优劣直接决定了模型是否奏效，而特
2016年淘宝双12与双11经常会被淘宝用户拿来做比较，去年，淘宝双12销售额是912亿元，今年淘宝双11销售额是1207亿元。那么2016双12销售