Python3--集合

集合 

本节重点

1.了解什么是集合以及集合的作用
2.掌握集合的定义和集合的基本特征
3.掌握集合的关系运算和常用操作

集合的常用操作

#作用：去重，关系运算，

#定义：
            知识点回顾
            可变类型是不可hash类型
            不可变类型是可hash类型

#定义集合:
            集合：可以包含多个元素，用逗号分割，
            集合的元素遵循三个原则：
             1：每个元素必须是不可变类型(可hash，可作为字典的key)
             2:没有重复的元素
             3：无序

注意集合的目的是将不同的值存放到一起，不同的集合间用来做关系运算，无需纠结于集合中单个值
 

#优先掌握的操作：
#1、长度len
#2、成员运算in和not in

#3、|合集
#4、&交集
#5、-差集
#6、^对称差集
#7、==
#8、父集：>,>= 
#9、子集：<,<=    

 集合的工厂函数

class set(object):
    """
    set() -> new empty set object
    set(iterable) -> new set object
    
    Build an unordered collection of unique elements.
    """
    def add(self, *args, **kwargs): # real signature unknown
        """
        Add an element to a set.
        
        This has no effect if the element is already present.
        """
        pass

    def clear(self, *args, **kwargs): # real signature unknown
        """ Remove all elements from this set. """
        pass

    def copy(self, *args, **kwargs): # real signature unknown
        """ Return a shallow copy of a set. """
        pass

    def difference(self, *args, **kwargs): # real signature unknown
        """
        Return the difference of two or more sets as a new set.
        
        (i.e. all elements that are in this set but not the others.)
        """
        pass

    def difference_update(self, *args, **kwargs): # real signature unknown
        """ Remove all elements of another set from this set. """
        pass

    def discard(self, *args, **kwargs): # real signature unknown
        """
        Remove an element from a set if it is a member.
        
        If the element is not a member, do nothing.
        """
        pass

    def intersection(self, *args, **kwargs): # real signature unknown
        """
        Return the intersection of two sets as a new set.
        
        (i.e. all elements that are in both sets.)
        """
        pass

    def intersection_update(self, *args, **kwargs): # real signature unknown
        """ Update a set with the intersection of itself and another. """
        pass

    def isdisjoint(self, *args, **kwargs): # real signature unknown
        """ Return True if two sets have a null intersection. """
        pass

    def issubset(self, *args, **kwargs): # real signature unknown
        """ Report whether another set contains this set. """
        pass

    def issuperset(self, *args, **kwargs): # real signature unknown
        """ Report whether this set contains another set. """
        pass

    def pop(self, *args, **kwargs): # real signature unknown
        """
        Remove and return an arbitrary set element.
        Raises KeyError if the set is empty.
        """
        pass

    def remove(self, *args, **kwargs): # real signature unknown
        """
        Remove an element from a set; it must be a member.
        
        If the element is not a member, raise a KeyError.
        """
        pass

    def symmetric_difference(self, *args, **kwargs): # real signature unknown
        """
        Return the symmetric difference of two sets as a new set.
        
        (i.e. all elements that are in exactly one of the sets.)
        """
        pass

    def symmetric_difference_update(self, *args, **kwargs): # real signature unknown
        """ Update a set with the symmetric difference of itself and another. """
        pass

    def union(self, *args, **kwargs): # real signature unknown
        """
        Return the union of sets as a new set.
        
        (i.e. all elements that are in either set.)
        """
        pass

    def update(self, *args, **kwargs): # real signature unknown
        """ Update a set with the union of itself and others. """
        pass

    def __and__(self, *args, **kwargs): # real signature unknown
        """ Return self&value. """
        pass

    def __contains__(self, y): # real signature unknown; restored from __doc__
        """ x.__contains__(y) <==> y in x. """
        pass

    def __eq__(self, *args, **kwargs): # real signature unknown
        """ Return self==value. """
        pass

    def __getattribute__(self, *args, **kwargs): # real signature unknown
        """ Return getattr(self, name). """
        pass

    def __ge__(self, *args, **kwargs): # real signature unknown
        """ Return self>=value. """
        pass

    def __gt__(self, *args, **kwargs): # real signature unknown
        """ Return self>value. """
        pass

    def __iand__(self, *args, **kwargs): # real signature unknown
        """ Return self&=value. """
        pass

    def __init__(self, seq=()): # known special case of set.__init__
        """
        set() -> new empty set object
        set(iterable) -> new set object
        
        Build an unordered collection of unique elements.
        # (copied from class doc)
        """
        pass

    def __ior__(self, *args, **kwargs): # real signature unknown
        """ Return self|=value. """
        pass

    def __isub__(self, *args, **kwargs): # real signature unknown
        """ Return self-=value. """
        pass

    def __iter__(self, *args, **kwargs): # real signature unknown
        """ Implement iter(self). """
        pass

    def __ixor__(self, *args, **kwargs): # real signature unknown
        """ Return self^=value. """
        pass

    def __len__(self, *args, **kwargs): # real signature unknown
        """ Return len(self). """
        pass

    def __le__(self, *args, **kwargs): # real signature unknown
        """ Return self<=value. """
        pass

    def __lt__(self, *args, **kwargs): # real signature unknown
        """ Return self<value. """
        pass

    @staticmethod # known case of __new__
    def __new__(*args, **kwargs): # real signature unknown
        """ Create and return a new object.  See help(type) for accurate signature. """
        pass

    def __ne__(self, *args, **kwargs): # real signature unknown
        """ Return self!=value. """
        pass

    def __or__(self, *args, **kwargs): # real signature unknown
        """ Return self|value. """
        pass

    def __rand__(self, *args, **kwargs): # real signature unknown
        """ Return value&self. """
        pass

    def __reduce__(self, *args, **kwargs): # real signature unknown
        """ Return state information for pickling. """
        pass

    def __repr__(self, *args, **kwargs): # real signature unknown
        """ Return repr(self). """
        pass

    def __ror__(self, *args, **kwargs): # real signature unknown
        """ Return value|self. """
        pass

    def __rsub__(self, *args, **kwargs): # real signature unknown
        """ Return value-self. """
        pass

    def __rxor__(self, *args, **kwargs): # real signature unknown
        """ Return value^self. """
        pass

    def __sizeof__(self): # real signature unknown; restored from __doc__
        """ S.__sizeof__() -> size of S in memory, in bytes """
        pass

    def __sub__(self, *args, **kwargs): # real signature unknown
        """ Return self-value. """
        pass

    def __xor__(self, *args, **kwargs): # real signature unknown
        """ Return self^value. """
        pass

    __hash__ = None

练习

　　一.关系运算
　　有如下两个集合，pythons是报名python课程的学员名字集合，linuxs是报名linux课程的学员名字集合
　　pythons={'alex','egon','yuanhao','wupeiqi','gangdan','biubiu'}
　　linuxs={'wupeiqi','oldboy','gangdan'}
　　1. 求出即报名python又报名linux课程的学员名字集合
　　2. 求出所有报名的学生名字集合
　　3. 求出只报名python课程的学员名字
　　4. 求出没有同时这两门课程的学员名字集合

# 有如下两个集合，pythons是报名python课程的学员名字集合，linuxs是报名linux课程的学员名字集合
pythons={'alex','egon','yuanhao','wupeiqi','gangdan','biubiu'}
linuxs={'wupeiqi','oldboy','gangdan'}
# 求出即报名python又报名linux课程的学员名字集合
print(pythons & linuxs)
# 求出所有报名的学生名字集合
print(pythons | linuxs)
# 求出只报名python课程的学员名字
print(pythons - linuxs)
# 求出没有同时这两门课程的学员名字集合
print(pythons ^ linuxs)

 　　二.去重

　　 1. 有列表l=['a','b',1,'a','a']，列表元素均为可hash类型，去重，得到新列表,且新列表无需保持列表原来的顺序

　　 2.在上题的基础上，保存列表原来的顺序

　　 3.去除文件中重复的行，肯定要保持文件内容的顺序不变
　　 4.有如下列表，列表元素为不可hash类型，去重，得到新列表，且新列表一定要保持列表原来的顺序

l=[
    {'name':'egon','age':18,'sex':'male'},
    {'name':'alex','age':73,'sex':'male'},
    {'name':'egon','age':20,'sex':'female'},
    {'name':'egon','age':18,'sex':'male'},
    {'name':'egon','age':18,'sex':'male'},
]　　

#去重,无需保持原来的顺序
l=['a','b',1,'a','a']
print(set(l))

#去重,并保持原来的顺序
#方法一:不用集合
l=[1,'a','b',1,'a']

l1=[]
for i in l:
    if i not in l1:
        l1.append(i)
print(l1)
#方法二:借助集合
l1=[]
s=set()
for i in l:
    if i not in s:
        s.add(i)
        l1.append(i)

print(l1)


#同上方法二,去除文件中重复的行
import os
with open('db.txt','r',encoding='utf-8') as read_f,\
        open('.db.txt.swap','w',encoding='utf-8') as write_f:
    s=set()
    for line in read_f:
        if line not in s:
            s.add(line)
            write_f.write(line)
os.remove('db.txt')
os.rename('.db.txt.swap','db.txt')

#列表中元素为可变类型时,去重,并且保持原来顺序
l=[
    {'name':'egon','age':18,'sex':'male'},
    {'name':'alex','age':73,'sex':'male'},
    {'name':'egon','age':20,'sex':'female'},
    {'name':'egon','age':18,'sex':'male'},
    {'name':'egon','age':18,'sex':'male'},
]
# print(set(l)) #报错:unhashable type: 'dict'
s=set()
l1=[]
for item in l:
    val=(item['name'],item['age'],item['sex'])
    if val not in s:
        s.add(val)
        l1.append(item)

print(l1)






#定义函数,既可以针对可以hash类型又可以针对不可hash类型
def func(items,key=None):
    s=set()
    for item in items:
        val=item if key is None else key(item)
        if val not in s:
            s.add(val)
            yield item

print(list(func(l,key=lambda dic:(dic['name'],dic['age'],dic['sex']))))