词频统计
import jieba
excludes={"将军","却说","荆州","二人","不可","不能","如此","商议","如何","军士","主公","左右","军马",
"引兵","次日","大喜","天下","东吴","于是","今日","不敢","魏兵","陛下","一人","都督","人马",
"不知"}
txt=open("threekingdoms.txt","r",encoding='UTF-8').read()#注意要在该源文件路径下存在“threekingdoms.txt"
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))
图形展示
import matplotlib.pyplot as plt
import matplotlib
d={'孔明':145,'刘备':138,'关羽':125,'张飞':78,'吕布':30,'赵云':28,'孙权':26,'司马懿':22,'周瑜':21}
matplotlib.rcParams['font.family']='SimHei'#想要显示中文必须有该语句
x1=list(d.keys())
y1=list(d.values())
print(x1)
print(y1)
plt.bar(x1,y1)
plt.show()