1、Hamlet英文词频统计

txt = open('hamlet.txt','r').read()

# 将大写变小写，排除大小写差异的干扰
txt = txt.lower()

# 将文本中的特殊字符转化为空格，统一分割方式
for ch in ',./?;:'"<>=+-[]{}!~%@()#':
    txt.replace(ch, ' ')     

words = txt.split()    # 按空格分隔，列表形式返回
counts = {}         #计数器
for word in words:
    counts[word] = counts.get(word, 0) + 1

# 按照词频从高到低排序
counts = sorted(counts.items(), key = lambda x: x[1], reverse = True)

for i in range(10):
    word, count = counts[i]
    print('{0:<10}:{0:>5}'.format(word,count)

运行之后发现高频单词大多数是冠词、代词、连接词等语法型词汇，并不能代表文章含义
建立一个排除词库encludes

excludes = {'the','and','of','you','a','i','my','in'}
txt = open('hamlet.txt', 'r').read()

txt = txt.lower()    # 排除大小写干扰

for ch in ',./?;:'"<>=+-[]{}!~%@()#':   # 统一分割字符
	txt = txt.replace(ch, ' ') 

words = txt.split()      # 按空格分词

counts = {}        # 计数器
for word in words:
	counts[word] = counts.get(word, 0) + 1
for word in excludes:
	del counts[word]
# 词频从高到低排序
counts = sorted(counts.items(), key = lambda x:x[1],reverse = True)

for i in range(10):
	print('{:<10}:{:>5}'.format(counts[i][0],counts[i][1])

2、python之jieba库

1）重要的第三方中文分词函数库
2）安装pip3 install jieba
3）常用函数

3、《三国演义》中文人物出场统计

import jieba
txt = open('三国演义.txt','r', encoding='utf-8').read()
words = jieba.lcut(txt)      # 精确模式，返回列表类型

counts = {}
for word in words:
    if len(word) == 1:     # 排除单个字符分词的影响
        continue
    else:
        counts[word] = counts.get(word, 0) + 1
# 按词频从高到低排序
counts = sorted(counts.items(), key = lambda x: x[1], reverse = True)

for i in range(5):
    word, count = counts[i]
    print('{:<10}{:>5}'.format(word, count))

【代码改进】
1、排除与人名无关的词汇
2、同一个人有不同称谓

encludes = {'将军','却说','荆州','二人','不可','不能','如此'}
import jieba
txt = open('三国演义.txt','r', encoding='utf-8').read()

words = jiaba.lcut(s)   # 精确模式分词，返回list

counts = {}
for word in words:
	if len(word) == 1:   # 排除单字符
		continue
	# 将一人多称谓统一
	elif word == '诸葛亮' or '孔明曰':
		rword = '孔明'
	elif word == '关公' or '云长':
		rword = '关羽'
	elif word == '玄德' or '玄德曰':
		rword = '刘备'
	elif word == '孟德' or '丞相':
		rword = '曹操'
	else:
		rword = word
	counts[rword] = counts.get(rword, 0) + 1

# 排除与人名无关的词
for word in excludes:
	del counts[word]
#按词频排序
counts = sorted(counts.items(), key = lambda x:x[1], reverse=True)

for i in range(10):
	print('{:<10}:{:>5}'.format(counts[i][0], counts[i][1]))