英文_Hamlet英文词频统计
#CalHamlet.py
def getText():
txt = open("hamlet.txt", "r").read()
txt = txt.lower()
for ch in '!"#$%&()*+,-./:;<=>?@[\\]^_‘{|}~':
txt = txt.replace(ch, " ")
return txt
hamletText = getText()
words = hamletTxt.spilt() #words是一个列表类型
counts = {} #counts是一个字典类型
for word in words:
counts[word] = counts.get(word, 0)
items = list(counts.items())
items.sort(key = lambda x :x[1], reverse = True) #reverse = True:从大到小排序
for i in range(10):
word, count = items[i]
print("{0:<10}{1:>5}".format(word, count))
中文_《三国演义》人物出场统计
将词频和人物相关联,面向问题
#CalThreeKingdoms.py
import jieba
txt = open("threekingdoms.txt", "r", encoding = "utf-8").read()
excludes = {"将军", "却说", "荆州", "二人", "不可", "不能", "如此", "商议", "主公"}
words = jieba.lcut(txt)
counts = {} #counts是一个字典类型
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) #reverse = True:从大到小排序
for i in range(10):
word, count = items[i]
print("{0:<10}{1:>5}".format(word, count))