中英文词频统计

#英文小说 词频统计
fo = open('gc.txt', 'r', encoding='utf-8')#提取字符串
gc = fo.read().lower()
fo.close()
print(gc)

运行结果：

strgc = str.lower(gc)   #换小写

sep ='''.,;;!?~~-_...'''  #替换字符

for ch in sep:
    gc = gc.replace(ch,' ')
print(gc)

运行结果：

strList = gc.split() #用 list 分解提取单词
print(len(strList),strList)

运行结果：

strSet = set(strList) #用 set 计数
print(len(strSet),strSet)

运行结果：

strDict = {} #用 dict 计数
for word in strSet:
    strDict[word] = strList.count(word)
    print(len(strDict),strDict)

运行结果：

strList = list(strDict.items()) #词频排序 list.sort(key=)
print(strList)
strList.sort(key = lambda x:x[1],reverse = True)
print(strList)

运行结果：

strSet = set(strSet) #排除语法型词汇，代词、冠词、连词等无语义词
include = {'a','the','and','oh','you'}
strSet = strSet-include
print(len(strSet),strSet)

运行结果：

for i in range(20): #输出TOP(20)
    print(strList[i])

运行结果：

 #中文小说 词频统计

import jieba

to = open('sbe.txt', 'r', encoding='utf-8')#提取字符串
sbe = to.read()
to.close()

sep ='，。？/：；\<>!'  #替换字符
for ch in sep:
    sbe = sbe.replace(ch,' ')
print(sbe)

strList = sbe.split() #用 list 分解提取单词
print(len(strList),strList)

strSet = set(strList) #用 set 计数
print(len(strSet),strSet)

strDict = {} #用 dict 计数
for word in strSet:
    strDict[word] = strList.count(word)
    print(len(strDict),strDict)

strList = list(strDict.items()) #词频排序 list.sort(key=)
print(strList)
strList.sort(key = lambda x:x[1],reverse = True)
print(strList)

strSet = set(strSet) #排除语法型词汇，代词、冠词、连词等无语义词
include = {'的','和','啊','呢','啦'}
strSet = strSet-include
print(len(strSet),strSet)

for i in range(20): #输出TOP(20)
    print(strList[i])