阶段作业1：完整的中英文词频统计

1.英文小说 词频统计

#读取字符串str
f = open('zz.txt','r',encoding='utf-8')
strbig= f.read()
f.close()

sep ='''.,;:?!-_'''
for ch in sep:
    strbig = strbig.replace(ch,' ')

strbig = strbig.lower()
print(strbig)

strlist = strbig.split()
print(len(strlist),strlist)

strset = set(strlist)
exclude = {'a','the','and','i','you'}
strset = strset-exclude
print(len(strset),strset)

strdict ={}
for word in strset:
    strdict[word] = strlist.count(word)
print(len(strdict),strdict)

ccList = list(strdict.items())
print(ccList)
ccList.sort(key=lambda x: x[1], reverse=True)
print(ccList)

for i in range(20):
    b = ccList[i]
    print(b)

 

2.中文小说 词频统计

fo = open('a.txt','r',encoding='utf-8')
shz=fo.read()
fo.close()
print(shz)

# jieba3种模式分词
import jieba
print(list(jieba.cut(shz)))
print(list(jieba.cut(shz,cut_all=True)))
print(list(jieba.cut_for_search(shz)))


s1='''， 。 ； ： - ！ ？ 、 “ ”'''    #标点符号转换成空格
for ch in s1:
    shz=shz.replace(ch,' ')
    print(shz)

strlist=shz.split()
print(len(strlist),strlist)   #分解提取词语


wordsls=jieba.lcut(shz)
wcdict={}
for word in wordsls:   #词为1的删除
    if len(word)==1:
        continue
    else:
        wcdict[word]=wcdict.get(word,0)+1
print(wordsls)

# # 按词频排序
shls=list(wcdict.items())
shls.sort(key=lambda x:x[1],reverse=True)
print(shls)
#
# # 输出TOP15
for i in range(15):
    print(shls[i])