列表、元祖、字典、集合

1.列表的增删查改

>>> ls=list('112233123')
>>> ls
['1', '1', '2', '2', '3', '3', '1', '2', '3']
>>> ls.sort()
>>> ls
['1', '1', '1', '2', '2', '2', '3', '3', '3']
>>> ls.pop()
'3'
>>> ls
['1', '1', '1', '2', '2', '2', '3', '3']
>>> ls.append(5)
>>> ls
['1', '1', '1', '2', '2', '2', '3', '3', 5]
>>> ls.insert(1,4)
>>> ls
['1', 4, '1', '1', '2', '2', '2', '3', '3', 5]
>>> ls.index(4)
1
>>> ls[1]=6
>>> ls
['1', 6, '1', '1', '2', '2', '2', '3', '3', 5]
>>> 

>>> s=list('turtle')
>>> s
['t', 'u', 'r', 't', 'l', 'e']
>>>

 2.字典

>>> d={'广东':'广州','广西':'南宁','福建':'福州','江西':'南昌'}
>>> d
{'广东': '广州', '广西': '南宁', '福建': '福州', '江西': '南昌'}
>>> d[广东]
Traceback (most recent call last):
  File "<pyshell#17>", line 1, in <module>
    d[广东]
NameError: name '广东' is not defined
>>> d['广东']
'广州'
>>> d.pop('广州')
Traceback (most recent call last):
  File "<pyshell#19>", line 1, in <module>
    d.pop('广州')
KeyError: '广州'
>>> d
{'广东': '广州', '广西': '南宁', '福建': '福州', '江西': '南昌'}
>>> d.pop('广东')
'广州'
>>> d
{'广西': '南宁', '福建': '福州', '江西': '南昌'}
>>> d.keys()
dict_keys(['广西', '福建', '江西'])
>>> d.values()
dict_values(['南宁', '福州', '南昌'])
>>> d.items()
dict_items([('广西', '南宁'), ('福建', '福州'), ('江西', '南昌')])
>>> d.get('江西')
'南昌'
>>> d['湖南']='长沙'
>>> d
{'广西': '南宁', '福建': '福州', '江西': '南昌', '湖南': '长沙'}
>>> 

 3.列表、元组、集合、字典。

>>> d
{'广西': '南宁', '福建': '福州', '江西': '南昌', '湖南': '长沙'}
>>> s=set(ls)
>>> s
{'1', 5, 6, '2', '3'}
>>> s=set('112233123')
>>> 
>>> s
{'1', '3', '2'}
>>> a=set(d)
>>> a
{'江西', '广西', '福建', '湖南'}
>>> tu=tuple('112233123456')
>>> tu
('1', '1', '2', '2', '3', '3', '1', '2', '3', '4', '5', '6')
>>> for i in ls:
    print(i)

    
1
6
1
1
2
2
2
3
3
5
>>> for i in tu:
    print(i,end=' ')

    
1 1 2 2 3 3 1 2 3 4 5 6 
>>> for i in s:
    print(i)

    
1
3
2
>>> for i in d:
    print(i)

    
广西
福建
江西
湖南
>>> for i in d:
    print(d[i])

    
南宁
福州
南昌
长沙
>>> for i in d:
    printi,(d[i])

    
Traceback (most recent call last):
  File "<pyshell#53>", line 2, in <module>
    printi,(d[i])
NameError: name 'printi' is not defined
>>> for i in d:
    print(i,d[i])

    
广西 南宁
福建 福州
江西 南昌
湖南 长沙
>>> 

 4.词频统计

news='''My father was a self-taught mandolin player.
He was one of the best string instrument players in our town.
He could not read music, but if he heard a tune a few times,
he could play it. When he was younger, he was a member of a small
country music band. They would play at local dances and on a few occasions
would play for the local radio station. He often told us how he had
auditioned and earned a position in a band that featured Patsy Cline as
their lead singer. He told the family that after he was hired he never
went back. Dad was a very religious man. He stated that there was a lot of
drinking and cursing the day of his audition and he did not
want to be around that type of environment. '''
news=news.lower()
for i in ',.':
    news=news.replace(i,' ')
words=news.split(' ')
dict={}
keys=set(words)
for i in words:
    dict[i]=words.count(i)
count=list(dict.items())

count.sort(key=lambda x:x[1],reverse=True)
for i in range(10):
    print(count[i])

 

wc.sort(key=lambda x:x[1],reverse=True

fo=open('a.txt','w')
fo.write('''My father was a self-taught mandolin player.
He was one of the best string instrument players in our town.
He could not read music, but if he heard a tune a few times,
he could play it. When he was younger, he was a member of a small
country music band. They would play at local dances and on a few occasions
would play for the local radio station. He often told us how he had
auditioned and earned a position in a band that featured Patsy Cline as
their lead singer. He told the family that after he was hired he never
went back. Dad was -a very religious man. He stated that there was a lot of
drinking and cursing the day of his audition and he did not
want to be around that type of environment.''')
fo.close()
fo=open('a.txt','r')
news=fo.read()
news=news.lower()
for i in ',.':
    news=news.replace(i,' ')
words=news.split(' ')#所有单词的列表
exp={'','the','a','was','of','and','that','he','in'}#要排除的语法型词汇
dict={}
keys=set(words)-exp#要统计词频的单词——键
for i in keys:
    dict[i]=words.count(i)#计算每个键的值
count=list(dict.items())

#转换成可排序的列表

count.sort(key=lambda x:x[1],reverse=True) #按元组的第二个值（出现的次数）排序

for i in range(10):#输出TOP10
   print(count[i]) fo.close()