综合练习：词频统计

# 从记事本长读取文件
f = open(‘news.txt‘,‘r‘,encoding=‘UTF-8‘)#打开文件
news = f.read()#读取文件
f.close()#关闭文件
print(news)

s = ‘‘‘,.;:‘"!?”、‘；：，。！’“‘‘‘
# 定义一个不需要的单词列表，即需删除的单词，例如代词、冠词、连词等
exclude = {‘to‘, ‘and‘, ‘a‘, ‘of‘, ‘on‘}
for i in s:
    news = news.lower().replace(i,‘ ‘)

newsList = news.split()
for i in newsList:
    print(i)


#方法1：通过遍历集合创建字典
newsDict = {}
print(‘方法1：‘)
# set集合，去除了重复的键
#去除不必要的单词，直接用列表减去需要去除的列表名
newsSet = set(newsList)-exclude
for w in newsSet:
    newsDict[w] = newsList.count(w)

for w in newsDict:
    print(w, newsDict[w])

# 方法2：通过遍历列表创建字典
newsDict2 = {}
print(‘方法2：‘)
for n in newsList:
    newsDict2[n] = newsDict2.get(n, 0)+1
# 减去不必要的单词
for e in exclude:
    del(newsDict2[e])

for n in newsDict2:
    print(n, newsDict2[n])

print(newsDict2)

# 按歌词出现的次数进行排序
# 将newsDict转变成列表
# newsDict.keys()#获取到newsDict的key值
# newsDict.values()获取到newsDict的values值
# newsDict.items()获取newsDict的key和values的值
dictList = list(newsDict.items())
dictList.sort(key=lambda x:x[1],reverse=True)

print(dictList)

# 输出前20个数据
for i in range(20):
    print(dictList[i])

# 保存文件,
f = open(‘newscount.txt‘,‘a‘)
for i in range(20):
    f.write(dictList[i][0]+‘ ‘+str(dictList[i][1])+‘\n‘)
f.close()