自学Python2.7-collections系列

Python collections系列

Python拥有一些内置的数据类型,比如str, int, list, tuple, dict等, collections模块在这些内置数据类型的基础上,提供了几个额外的数据类型:
1.Counter: 计数器,主要用来计数
2.OrderedDict: 有序字典
3.defaultdict: 带有默认值的字典
4.namedtuple(): 可命名元组,生成可以使用名字来访问元素内容的tuple子类
5.deque: 双端队列,可以快速的从另外一侧追加和推出对象

一、Counter: 计数器

    Counter是对字典类型的补充,用于追踪值的出现次数。   ps:具备字典的所有功能 + 自己的功能

########################################################################
###  Counter
########################################################################

class Counter(dict):
    '''Dict subclass for counting hashable items.  Sometimes called a bag
    or multiset.  Elements are stored as dictionary keys and their counts
    are stored as dictionary values.

    >>> c = Counter('abcdeabcdabcaba')  # count elements from a string

    >>> c.most_common(3)                # three most common elements
    [('a', 5), ('b', 4), ('c', 3)]
    >>> sorted(c)                       # list all unique elements
    ['a', 'b', 'c', 'd', 'e']
    >>> ''.join(sorted(c.elements()))   # list elements with repetitions
    'aaaaabbbbcccdde'
    >>> sum(c.values())                 # total of all counts

    >>> c['a']                          # count of letter 'a'
    >>> for elem in 'shazam':           # update counts from an iterable
    ...     c[elem] += 1                # by adding 1 to each element's count
    >>> c['a']                          # now there are seven 'a'
    >>> del c['b']                      # remove all 'b'
    >>> c['b']                          # now there are zero 'b'

    >>> d = Counter('simsalabim')       # make another counter
    >>> c.update(d)                     # add in the second counter
    >>> c['a']                          # now there are nine 'a'

    >>> c.clear()                       # empty the counter
    >>> c
    Counter()

    Note:  If a count is set to zero or reduced to zero, it will remain
    in the counter until the entry is deleted or the counter is cleared:

    >>> c = Counter('aaabbc')
    >>> c['b'] -= 2                     # reduce the count of 'b' by two
    >>> c.most_common()                 # 'b' is still in, but its count is zero
    [('a', 3), ('c', 1), ('b', 0)]

    '''
    # References:
    #   http://en.wikipedia.org/wiki/Multiset
    #   http://www.gnu.org/software/smalltalk/manual-base/html_node/Bag.html
    #   http://www.demo2s.com/Tutorial/Cpp/0380__set-multiset/Catalog0380__set-multiset.htm
    #   http://code.activestate.com/recipes/259174/
    #   Knuth, TAOCP Vol. II section 4.6.3

    def __init__(self, iterable=None, **kwds):
        '''Create a new, empty Counter object.  And if given, count elements
        from an input iterable.  Or, initialize the count from another mapping
        of elements to their counts.

        >>> c = Counter()                           # a new, empty counter
        >>> c = Counter('gallahad')                 # a new counter from an iterable
        >>> c = Counter({'a': 4, 'b': 2})           # a new counter from a mapping
        >>> c = Counter(a=4, b=2)                   # a new counter from keyword args

        '''
        super(Counter, self).__init__()
        self.update(iterable, **kwds)

    def __missing__(self, key):
        """ 对于不存在的元素,返回计数器为0 """
        'The count of elements not in the Counter is zero.'
        # Needed so that self[missing_item] does not raise KeyError
        return 0

    def most_common(self, n=None):
        """ 数量从大到写排列,获取前N个元素 """
        '''List the n most common elements and their counts from the most
        common to the least.  If n is None, then list all element counts.

        >>> Counter('abcdeabcdabcaba').most_common(3)
        [('a', 5), ('b', 4), ('c', 3)]

        '''
        # Emulate Bag.sortedByCount from Smalltalk
        if n is None:
            return sorted(self.iteritems(), key=_itemgetter(1), reverse=True)
        return _heapq.nlargest(n, self.iteritems(), key=_itemgetter(1))

    def elements(self):
        """ 计数器中的所有元素,注:此处非所有元素集合,而是包含所有元素集合的迭代器 """
        '''Iterator over elements repeating each as many times as its count.

        >>> c = Counter('ABCABC')
        >>> sorted(c.elements())
        ['A', 'A', 'B', 'B', 'C', 'C']

        # Knuth's example for prime factors of 1836:  2**2 * 3**3 * 17**1
        >>> prime_factors = Counter({2: 2, 3: 3, 17: 1})
        >>> product = 1
        >>> for factor in prime_factors.elements():     # loop over factors
        ...     product *= factor                       # and multiply them
        >>> product

        Note, if an element's count has been set to zero or is a negative
        number, elements() will ignore it.

        '''
        # Emulate Bag.do from Smalltalk and Multiset.begin from C++.
        return _chain.from_iterable(_starmap(_repeat, self.iteritems()))

    # Override dict methods where necessary

    @classmethod
    def fromkeys(cls, iterable, v=None):
        # There is no equivalent method for counters because setting v=1
        # means that no element can have a count greater than one.
        raise NotImplementedError(
            'Counter.fromkeys() is undefined.  Use Counter(iterable) instead.')

    def update(self, iterable=None, **kwds):
        """ 更新计数器,其实就是增加;如果原来没有,则新建,如果有则加一 """
        '''Like dict.update() but add counts instead of replacing them.

        Source can be an iterable, a dictionary, or another Counter instance.

        >>> c = Counter('which')
        >>> c.update('witch')           # add elements from another iterable
        >>> d = Counter('watch')
        >>> c.update(d)                 # add elements from another counter
        >>> c['h']                      # four 'h' in which, witch, and watch

        '''
        # The regular dict.update() operation makes no sense here because the
        # replace behavior results in the some of original untouched counts
        # being mixed-in with all of the other counts for a mismash that
        # doesn't have a straight-forward interpretation in most counting
        # contexts.  Instead, we implement straight-addition.  Both the inputs
        # and outputs are allowed to contain zero and negative counts.

        if iterable is not None:
            if isinstance(iterable, Mapping):
                if self:
                    self_get = self.get
                    for elem, count in iterable.iteritems():
                        self[elem] = self_get(elem, 0) + count
                else:
                    super(Counter, self).update(iterable) # fast path when counter is empty
            else:
                self_get = self.get
                for elem in iterable:
                    self[elem] = self_get(elem, 0) + 1
        if kwds:
            self.update(kwds)

    def subtract(self, iterable=None, **kwds):
        """ 相减,原来的计数器中的每一个元素的数量减去后添加的元素的数量 """
        '''Like dict.update() but subtracts counts instead of replacing them.
        Counts can be reduced below zero.  Both the inputs and outputs are
        allowed to contain zero and negative counts.

        Source can be an iterable, a dictionary, or another Counter instance.

        >>> c = Counter('which')
        >>> c.subtract('witch')             # subtract elements from another iterable
        >>> c.subtract(Counter('watch'))    # subtract elements from another counter
        >>> c['h']                          # 2 in which, minus 1 in witch, minus 1 in watch
        >>> c['w']                          # 1 in which, minus 1 in witch, minus 1 in watch
        -1

        '''
        if iterable is not None:
            self_get = self.get
            if isinstance(iterable, Mapping):
                for elem, count in iterable.items():
                    self[elem] = self_get(elem, 0) - count
            else:
                for elem in iterable:
                    self[elem] = self_get(elem, 0) - 1
        if kwds:
            self.subtract(kwds)

    def copy(self):
        """ 拷贝 """
        'Return a shallow copy.'
        return self.__class__(self)

    def __reduce__(self):
        """ 返回一个元组(类型,元组) """
        return self.__class__, (dict(self),)

    def __delitem__(self, elem):
        """ 删除元素 """
        'Like dict.__delitem__() but does not raise KeyError for missing values.'
        if elem in self:
            super(Counter, self).__delitem__(elem)

    def __repr__(self):
        if not self:
            return '%s()' % self.__class__.__name__
        items = ', '.join(map('%r: %r'.__mod__, self.most_common()))
        return '%s({%s})' % (self.__class__.__name__, items)

    # Multiset-style mathematical operations discussed in:
    #       Knuth TAOCP Volume II section 4.6.3 exercise 19
    #       and at http://en.wikipedia.org/wiki/Multiset
    #
    # Outputs guaranteed to only include positive counts.
    #
    # To strip negative and zero counts, add-in an empty counter:
    #       c += Counter()

    def __add__(self, other):
        '''Add counts from two counters.

        >>> Counter('abbb') + Counter('bcc')
        Counter({'b': 4, 'c': 2, 'a': 1})

        '''
        if not isinstance(other, Counter):
            return NotImplemented
        result = Counter()
        for elem, count in self.items():
            newcount = count + other[elem]
            if newcount > 0:
                result[elem] = newcount
        for elem, count in other.items():
            if elem not in self and count > 0:
                result[elem] = count
        return result

    def __sub__(self, other):
        ''' Subtract count, but keep only results with positive counts.

        >>> Counter('abbbc') - Counter('bccd')
        Counter({'b': 2, 'a': 1})

        '''
        if not isinstance(other, Counter):
            return NotImplemented
        result = Counter()
        for elem, count in self.items():
            newcount = count - other[elem]
            if newcount > 0:
                result[elem] = newcount
        for elem, count in other.items():
            if elem not in self and count < 0:
                result[elem] = 0 - count
        return result

    def __or__(self, other):
        '''Union is the maximum of value in either of the input counters.

        >>> Counter('abbb') | Counter('bcc')
        Counter({'b': 3, 'c': 2, 'a': 1})

        '''
        if not isinstance(other, Counter):
            return NotImplemented
        result = Counter()
        for elem, count in self.items():
            other_count = other[elem]
            newcount = other_count if count < other_count else count
            if newcount > 0:
                result[elem] = newcount
        for elem, count in other.items():
            if elem not in self and count > 0:
                result[elem] = count
        return result

    def __and__(self, other):
        ''' Intersection is the minimum of corresponding counts.

        >>> Counter('abbb') & Counter('bcc')
        Counter({'b': 1})

        '''
        if not isinstance(other, Counter):
            return NotImplemented
        result = Counter()
        for elem, count in self.items():
            other_count = other[elem]
            newcount = count if count < other_count else other_count
            if newcount > 0:
                result[elem] = newcount
        return result

Counter
Counter源码
import collections   # 先导入模块才能使用Conuter
c=collections.Counter('afafaefaefaefaesfefaseg') # 记住Counter C大写
print(c)

输出
Counter({'a': 7, 'f': 7, 'e': 6, 's': 2, 'g': 1})     #将输入的字符以字典的形式显示出来(但不是字典,前面有个Counter),展现出每个字符出现的次数 

1、  most_common(self, n=None) 数量从大到写排列,获取前N个元素

import collections
c=collections.Counter('afafaefaefaefaesfefaseg')
c1=c.most_common(2)
print(c)
print(c1)

输出

Counter({'a': 7, 'f': 7, 'e': 6, 's': 2, 'g': 1})
[('a', 7), ('f', 7)]

2、elements(self)计数器中的所有元素,注:此处非所有元素集合,而是包含所有元素集合的迭代器

import collections
c=collections.Counter('afafaefaefaefaesfefaseg')
c1=c.elements()
print(c)
print(c1)

输出

Counter({'a': 7, 'f': 7, 'e': 6, 's': 2, 'g': 1})
<itertools.chain object at 0x002F4690>

import collections
c=collections.Counter('afafaefaefaefaesfefaseg')
for k,v in c.items():
  print(k,v)

输出

a 7
f 7
e 6
s 2
g 1

3、update(self, iterable=None, **kwds) 更新计数器,其实就是增加;如果原来没有,则新建,如果有则加1

import collections
c=collections.Counter(['11','22','33','78','11'])
print(c)
c.update(['22','11','calos'])
print(c)

输出

Counter({'11': 2, '22': 1, '33': 1, '78': 1})
Counter({'11': 3, '22': 2, '33': 1, '78': 1, 'calos': 1})

4、subtract(self, iterable=None, **kwds) 相减,原来的计数器中的每一个元素的数量减去后添加的元素的数量

import collections
c=collections.Counter(['11','22','33','78','11'])
print(c)
c.subtract(['22','11','calos'])
print(c)

输出

Counter({'11': 2, '22': 1, '33': 1, '78': 1})
Counter({'11': 1, '33': 1, '78': 1, '22': 0, 'calos': -1})

二、OrderedDict: 有序字典

在Python中,dict这个数据结构由于hash的特性,是无序的,这在有的时候会给我们带来一些麻烦, 幸运的是,collections模块为我们提供了OrderedDict,当你要获得一个有序的字典对象时,用它就对了。

class OrderedDict(dict):
    'Dictionary that remembers insertion order'
    # An inherited dict maps keys to values.
    # The inherited dict provides __getitem__, __len__, __contains__, and get.
    # The remaining methods are order-aware.
    # Big-O running times for all methods are the same as regular dictionaries.

    # The internal self.__map dict maps keys to links in a doubly linked list.
    # The circular doubly linked list starts and ends with a sentinel element.
    # The sentinel element never gets deleted (this simplifies the algorithm).
    # The sentinel is in self.__hardroot with a weakref proxy in self.__root.
    # The prev links are weakref proxies (to prevent circular references).
    # Individual links are kept alive by the hard reference in self.__map.
    # Those hard references disappear when a key is deleted from an OrderedDict.

    def __init__(*args, **kwds):
        '''Initialize an ordered dictionary.  The signature is the same as
        regular dictionaries, but keyword arguments are not recommended because
        their insertion order is arbitrary.

        '''
        if not args:
            raise TypeError("descriptor '__init__' of 'OrderedDict' object "
                            "needs an argument")
        self, *args = args
        if len(args) > 1:
            raise TypeError('expected at most 1 arguments, got %d' % len(args))
        try:
            self.__root
        except AttributeError:
            self.__hardroot = _Link()
            self.__root = root = _proxy(self.__hardroot)
            root.prev = root.next = root
            self.__map = {}
        self.__update(*args, **kwds)

    def __setitem__(self, key, value,
                    dict_setitem=dict.__setitem__, proxy=_proxy, Link=_Link):
        'od.__setitem__(i, y) <==> od[i]=y'
        # Setting a new item creates a new link at the end of the linked list,
        # and the inherited dictionary is updated with the new key/value pair.
        if key not in self:
            self.__map[key] = link = Link()
            root = self.__root
            last = root.prev
            link.prev, link.next, link.key = last, root, key
            last.next = link
            root.prev = proxy(link)
        dict_setitem(self, key, value)

    def __delitem__(self, key, dict_delitem=dict.__delitem__):
        'od.__delitem__(y) <==> del od[y]'
        # Deleting an existing item uses self.__map to find the link which gets
        # removed by updating the links in the predecessor and successor nodes.
        dict_delitem(self, key)
        link = self.__map.pop(key)
        link_prev = link.prev
        link_next = link.next
        link_prev.next = link_next
        link_next.prev = link_prev
        link.prev = None
        link.next = None

    def __iter__(self):
        'od.__iter__() <==> iter(od)'
        # Traverse the linked list in order.
        root = self.__root
        curr = root.next
        while curr is not root:
            yield curr.key
            curr = curr.next

    def __reversed__(self):
        'od.__reversed__() <==> reversed(od)'
        # Traverse the linked list in reverse order.
        root = self.__root
        curr = root.prev
        while curr is not root:
            yield curr.key
            curr = curr.prev

    def clear(self):
        'od.clear() -> None.  Remove all items from od.'
        root = self.__root
        root.prev = root.next = root
        self.__map.clear()
        dict.clear(self)

    def popitem(self, last=True):
        '''od.popitem() -> (k, v), return and remove a (key, value) pair.
        Pairs are returned in LIFO order if last is true or FIFO order if false.

        '''
        if not self:
            raise KeyError('dictionary is empty')
        root = self.__root
        if last:
            link = root.prev
            link_prev = link.prev
            link_prev.next = root
            root.prev = link_prev
        else:
            link = root.next
            link_next = link.next
            root.next = link_next
            link_next.prev = root
        key = link.key
        del self.__map[key]
        value = dict.pop(self, key)
        return key, value

    def move_to_end(self, key, last=True):
        '''Move an existing element to the end (or beginning if last==False).

        Raises KeyError if the element does not exist.
        When last=True, acts like a fast version of self[key]=self.pop(key).

        '''
        link = self.__map[key]
        link_prev = link.prev
        link_next = link.next
        soft_link = link_next.prev
        link_prev.next = link_next
        link_next.prev = link_prev
        root = self.__root
        if last:
            last = root.prev
            link.prev = last
            link.next = root
            root.prev = soft_link
            last.next = link
        else:
            first = root.next
            link.prev = root
            link.next = first
            first.prev = soft_link
            root.next = link

    def __sizeof__(self):
        sizeof = _sys.getsizeof
        n = len(self) + 1                       # number of links including root
        size = sizeof(self.__dict__)            # instance dictionary
        size += sizeof(self.__map) * 2          # internal dict and inherited dict
        size += sizeof(self.__hardroot) * n     # link objects
        size += sizeof(self.__root) * n         # proxy objects
        return size

    update = __update = MutableMapping.update

    def keys(self):
        "D.keys() -> a set-like object providing a view on D's keys"
        return _OrderedDictKeysView(self)

    def items(self):
        "D.items() -> a set-like object providing a view on D's items"
        return _OrderedDictItemsView(self)

    def values(self):
        "D.values() -> an object providing a view on D's values"
        return _OrderedDictValuesView(self)

    __ne__ = MutableMapping.__ne__

    __marker = object()

    def pop(self, key, default=__marker):
        '''od.pop(k[,d]) -> v, remove specified key and return the corresponding
        value.  If key is not found, d is returned if given, otherwise KeyError
        is raised.

        '''
        if key in self:
            result = self[key]
            del self[key]
            return result
        if default is self.__marker:
            raise KeyError(key)
        return default

    def setdefault(self, key, default=None):
        'od.setdefault(k[,d]) -> od.get(k,d), also set od[k]=d if k not in od'
        if key in self:
            return self[key]
        self[key] = default
        return default

    @_recursive_repr()
    def __repr__(self):
        'od.__repr__() <==> repr(od)'
        if not self:
            return '%s()' % (self.__class__.__name__,)
        return '%s(%r)' % (self.__class__.__name__, list(self.items()))

    def __reduce__(self):
        'Return state information for pickling'
        inst_dict = vars(self).copy()
        for k in vars(OrderedDict()):
            inst_dict.pop(k, None)
        return self.__class__, (), inst_dict or None, None, iter(self.items())

    def copy(self):
        'od.copy() -> a shallow copy of od'
        return self.__class__(self)

    @classmethod
    def fromkeys(cls, iterable, value=None):
        '''OD.fromkeys(S[, v]) -> New ordered dictionary with keys from S.
        If not specified, the value defaults to None.

        '''
        self = cls()
        for key in iterable:
            self[key] = value
        return self

    def __eq__(self, other):
        '''od.__eq__(y) <==> od==y.  Comparison to another OD is order-sensitive
        while comparison to a regular mapping is order-insensitive.

        '''
        if isinstance(other, OrderedDict):
            return dict.__eq__(self, other) and all(map(_eq, self, other))
        return dict.__eq__(self, other)


try:
    from _collections import OrderedDict
except ImportError:
    # Leave the pure Python version in place.
    pass
OrderedDict源码
import collections
c=collections.OrderedDict()   #输出字典定是有序的
c['k1']='v1'
c['k2']='v2'
c['k3']='v3'
print(c)

输出
OrderedDict([('k1', 'v1'), ('k2', 'v2'), ('k3', 'v3')])

import collections
c=dict()   # 生成字典是无序的
c['k1']='v1'
c['k2']='v2'
c['k3']='v3'
print(c)

输出
{'k3': 'v3', 'k2': 'v2', 'k1': 'v1'}

 有序字典里面的方法和字典里面的方法大致一样(有序字典里面所有的操作都是按顺序取或删除)。

1. move_to_end(self, key, last=True) 将指定的key 移动至最后

import collections
c=collections.OrderedDict() 
c['k1']='v1'
c['k2']='v2'
c['k3']='v3'
print(c)
c.move_to_end('k2')
print(c)

输出

OrderedDict([('k1', 'v1'), ('k2', 'v2'), ('k3', 'v3')])
OrderedDict([('k1', 'v1'), ('k3', 'v3'), ('k2', 'v2')])

2. popitem(self, last=True)   从最后一个元素中取值,后进先出      ‘栈’  

import collections
c=collections.OrderedDict()
c['k1']='v1'
c['k2']='v2'
c['k3']='v3'
print(c)
result=c.popitem()
print(c)
print(result)

输出

OrderedDict([('k1', 'v1'), ('k2', 'v2'), ('k3', 'v3')])
OrderedDict([('k1', 'v1'), ('k2', 'v2')])
('k3', 'v3')

 pop(self, key, default=__marker)  指定取哪一个,并有返回值values

import collections
c=collections.OrderedDict()
c['k1']='v1'
c['k2']='v2'
c['k3']='v3'
print(c)
result=c.pop('k2')
print(c)
print(result)

输出

OrderedDict([('k1', 'v1'), ('k2', 'v2'), ('k3', 'v3')])
OrderedDict([('k1', 'v1'), ('k3', 'v3')])
v2

三、默认字典(defaultdict) 

    即为字典中的values设置一个默认类型:defaultdict的参数默认是dict,也可为list,tuple

class defaultdict(dict):
    """
    defaultdict(default_factory[, ...]) --> dict with default factory
    
    The default factory is called without arguments to produce
    a new value when a key is not present, in __getitem__ only.
    A defaultdict compares equal to a dict with the same items.
    All remaining arguments are treated the same as if they were
    passed to the dict constructor, including keyword arguments.
    """
    def copy(self): # real signature unknown; restored from __doc__
        """ D.copy() -> a shallow copy of D. """
        pass

    def __copy__(self, *args, **kwargs): # real signature unknown
        """ D.copy() -> a shallow copy of D. """
        pass

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

    def __init__(self, default_factory=None, **kwargs): # known case of _collections.defaultdict.__init__
        """
        defaultdict(default_factory[, ...]) --> dict with default factory
        
        The default factory is called without arguments to produce
        a new value when a key is not present, in __getitem__ only.
        A defaultdict compares equal to a dict with the same items.
        All remaining arguments are treated the same as if they were
        passed to the dict constructor, including keyword arguments.
        
        # (copied from class doc)
        """
        pass

    def __missing__(self, key): # real signature unknown; restored from __doc__
        """
        __missing__(key) # Called by __getitem__ for missing key; pseudo-code:
          if self.default_factory is None: raise KeyError((key,))
          self[key] = value = self.default_factory()
          return value
        """
        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

    default_factory = property(lambda self: object(), lambda self, v: None, lambda self: None)  # default
    """Factory for default value called by __missing__()."""
defaultdict源码

原始字典如果value没有值的时候,append是无法使用的,因为append是list的方法,所以定义字典为列表就可以了,如下

dic={'k1':[]}
dic['k1'].append('carlos')
print(dic)

输出
{'k1': ['carlos']} 

使用defaultdict直接设置一个默认类型,可以直接使用append

import collections
dic=collections.defaultdict(list)
dic['k1'].append('carlos')
print(dic)

输出
defaultdict(<class 'list'>, {'k1': ['carlos']})

举例:“11, 22, 33, 44, 55, 66, 77, 88, 99, 90”  将以上大于66的放进一个集合,小于66放进一个集合

①原实现办法

values = [11, 22, 33, 44, 55, 66, 77, 88, 99, 90]
mydic = {}
for value in values:
    if value > 66:
        if 'k1' in mydic: #python2.7中有个.has_key的方法。在3.0以后版本中被废除,用in来替代。python2.7用法:if my_dict.has_key('k1')
            mydic['k1'].append(value)
        else:
             mydic['k1'] = [value]
    else:
         if 'k2' in mydic:
             mydic['k2'].append(value)
         else:
             mydic['k2'] = [value]
print(mydic)

输出

{'k2': [11, 22, 33, 44, 55, 66], 'k1': [77, 88, 99, 90]}

②使用defaultdict实现办法,精简语句

from collections import defaultdict
values = [11, 22, 33, 44, 55, 66, 77, 88, 99, 90]
mydict = defaultdict(list)
for value in values:# v始终都是my_dict中的values,而defaultdict(list)后我们对于keys的指定对比上例就方便很多。不用再做一层if判断了。
    if value > 66:
      mydict['k1'].append(value)
    else:
      mydict['k2'].append(value)
print(mydict)

输出
defaultdict(<class 'list'>, {'k2': [11, 22, 33, 44, 55, 66], 'k1': [77, 88, 99, 90]})  

四、namedtuple(): 可命名元组  

     namedtuple主要用来产生可以使用名称来访问元素的数据对象,通常用来增强代码的可读性, 在访问一些tuple类型的数据时尤其好用。 

    元组访问只能通过索引去访问
    命名访问可以通过名字去访问

    使用collections模块中的namedtuple方法可以给每个元素起别名,通过名称调用的方式来获取值使用。而普通元组的方法必须通过下标的方式来取值。
    创建一个自己的可扩展tuple的类(包含tuple所有功能以及其他功能的类型),在根据类创建对象,然后调用对象最长用于坐标,普通的元组类似于列表以index编号来访问,而自定义可扩展的可以类似于字典的keys进行访问。

import collections
mytuple=collections.namedtuple('mytuple',['x','y','z']) #创建类
a=mytuple(3,8,9)  #创建对象,赋值给变量a
print(a)  # 赋值x=3, y=8, z=9

输出mytuple(x=3, y=8, z=9) 

mytuple=(3,8,9)
print(mytuple)
print(mytuple[0],mytuple[1],mytuple[2])

输出

(3, 8, 9)
3 8 9

查看一下这个类的方法 print(help(mytuple))

Help on tuple object:

class tuple(object)
 |  tuple() -> empty tuple
 |  tuple(iterable) -> tuple initialized from iterable's items
 |  
 |  If the argument is a tuple, the return value is the same object.
 |  
 |  Methods defined here:
 |  
 |  __add__(self, value, /)
 |      Return self+value.
 |  
 |  __contains__(self, key, /)
 |      Return key in self.
 |  
 |  __eq__(self, value, /)
 |      Return self==value.
 |  
 |  __ge__(self, value, /)
 |      Return self>=value.
 |  
 |  __getattribute__(self, name, /)
 |      Return getattr(self, name).
 |  
 |  __getitem__(self, key, /)
 |      Return self[key].
 |  
 |  __getnewargs__(...)
 |  
 |  __gt__(self, value, /)
 |      Return self>value.
 |  
 |  __hash__(self, /)
 |      Return hash(self).
 |  
 |  __iter__(self, /)
 |      Implement iter(self).
 |  
 |  __le__(self, value, /)
 |      Return self<=value.
 |  
 |  __len__(self, /)
 |      Return len(self).
 |  
 |  __lt__(self, value, /)
 |      Return self<value.
 |  
 |  __mul__(self, value, /)
 |      Return self*value.n
 |  
 |  __ne__(self, value, /)
 |      Return self!=value.
 |  
 |  __new__(*args, **kwargs) from builtins.type
 |      Create and return a new object.  See help(type) for accurate signature.
 |  
 |  __repr__(self, /)
 |      Return repr(self).
 |  
 |  __rmul__(self, value, /)
 |      Return self*value.
 |  
 |  count(...)
 |      T.count(value) -> integer -- return number of occurrences of value
 |  
 |  index(...)
 |      T.index(value, [start, [stop]]) -> integer -- return first index of value.
 |      Raises ValueError if the value is not present.
mytuple源码

举例子: 

from collections import namedtuple  # 通过from import的方式直接调用collections模块中namedtuple这个方法。而import collections是导入这个模块中所有的方法。这种调用在使用时必须collections.namedtuple的方式来使用。
websites = [
    ('Sohu', 'http://www.google.com/', u'liupeng'),
    ('Sina', 'http://www.sina.com.cn/', u'tony'),
    ('163', 'http://www.163.com/', u'jack')] # 假设我们有一个列表,列表中有三个元组,每个元组中的元素都是不同格式的字符串
Website = namedtuple('Website_list', ['name', 'url','founder'])  # 通过调用namedtuple,来设置一个列表'Website_list'是这个列表的别名.而['name','url','founder']的命名是分别为了分配给大列表websites中哥哥元组中的各个元素的。
for i in websites: # for循环websites这个大列表,这里的i循环得出的结果是这个大列表中每个元组
    x = Website._make(i)# 从已经存在迭代对象或者序列生成一个新的命名元组。 Website是namedtuple('Website_list', ['name', 'url', 'founder'])的内容,._make(i)是websites各个元组的内容,把这两个元组重组成新的元组。
    print(x) # x打印结果如下,生成了新的命名元组。是使用了namedtuple中._make的方法生成的。

输出

Website_list(name='Sohu', url='http://www.google.com/', founder='liupeng')
Website_list(name='Sina', url='http://www.sina.com.cn/', founder='tony')
Website_list(name='163', url='http://www.163.com/', founder='jack') 

五、deque

 deque其实是 double-ended queue 的缩写,翻译过来就是双端队列/双向队列。

 队列分两种:
1、单向队列(先进先出)
     import queue
        queue.Queue 

class Queue:
    '''Create a queue object with a given maximum size.

    If maxsize is <= 0, the queue size is infinite.
    '''

    def __init__(self, maxsize=0):
        self.maxsize = maxsize
        self._init(maxsize)

        # mutex must be held whenever the queue is mutating.  All methods
        # that acquire mutex must release it before returning.  mutex
        # is shared between the three conditions, so acquiring and
        # releasing the conditions also acquires and releases mutex.
        self.mutex = threading.Lock()

        # Notify not_empty whenever an item is added to the queue; a
        # thread waiting to get is notified then.
        self.not_empty = threading.Condition(self.mutex)

        # Notify not_full whenever an item is removed from the queue;
        # a thread waiting to put is notified then.
        self.not_full = threading.Condition(self.mutex)

        # Notify all_tasks_done whenever the number of unfinished tasks
        # drops to zero; thread waiting to join() is notified to resume
        self.all_tasks_done = threading.Condition(self.mutex)
        self.unfinished_tasks = 0

    def task_done(self):
        '''Indicate that a formerly enqueued task is complete.

        Used by Queue consumer threads.  For each get() used to fetch a task,
        a subsequent call to task_done() tells the queue that the processing
        on the task is complete.

        If a join() is currently blocking, it will resume when all items
        have been processed (meaning that a task_done() call was received
        for every item that had been put() into the queue).

        Raises a ValueError if called more times than there were items
        placed in the queue.
        '''
        with self.all_tasks_done:
            unfinished = self.unfinished_tasks - 1
            if unfinished <= 0:
                if unfinished < 0:
                    raise ValueError('task_done() called too many times')
                self.all_tasks_done.notify_all()
            self.unfinished_tasks = unfinished

    def join(self):
        '''Blocks until all items in the Queue have been gotten and processed.

        The count of unfinished tasks goes up whenever an item is added to the
        queue. The count goes down whenever a consumer thread calls task_done()
        to indicate the item was retrieved and all work on it is complete.

        When the count of unfinished tasks drops to zero, join() unblocks.
        '''
        with self.all_tasks_done:
            while self.unfinished_tasks:
                self.all_tasks_done.wait()

    def qsize(self):
        '''Return the approximate size of the queue (not reliable!).'''
        with self.mutex:
            return self._qsize()

    def empty(self):
        '''Return True if the queue is empty, False otherwise (not reliable!).

        This method is likely to be removed at some point.  Use qsize() == 0
        as a direct substitute, but be aware that either approach risks a race
        condition where a queue can grow before the result of empty() or
        qsize() can be used.

        To create code that needs to wait for all queued tasks to be
        completed, the preferred technique is to use the join() method.
        '''
        with self.mutex:
            return not self._qsize()

    def full(self):
        '''Return True if the queue is full, False otherwise (not reliable!).

        This method is likely to be removed at some point.  Use qsize() >= n
        as a direct substitute, but be aware that either approach risks a race
        condition where a queue can shrink before the result of full() or
        qsize() can be used.
        '''
        with self.mutex:
            return 0 < self.maxsize <= self._qsize()

    def put(self, item, block=True, timeout=None):
        '''Put an item into the queue.

        If optional args 'block' is true and 'timeout' is None (the default),
        block if necessary until a free slot is available. If 'timeout' is
        a non-negative number, it blocks at most 'timeout' seconds and raises
        the Full exception if no free slot was available within that time.
        Otherwise ('block' is false), put an item on the queue if a free slot
        is immediately available, else raise the Full exception ('timeout'
        is ignored in that case).
        '''
        with self.not_full:
            if self.maxsize > 0:
                if not block:
                    if self._qsize() >= self.maxsize:
                        raise Full
                elif timeout is None:
                    while self._qsize() >= self.maxsize:
                        self.not_full.wait()
                elif timeout < 0:
                    raise ValueError("'timeout' must be a non-negative number")
                else:
                    endtime = time() + timeout
                    while self._qsize() >= self.maxsize:
                        remaining = endtime - time()
                        if remaining <= 0.0:
                            raise Full
                        self.not_full.wait(remaining)
            self._put(item)
            self.unfinished_tasks += 1
            self.not_empty.notify()

    def get(self, block=True, timeout=None):
        '''Remove and return an item from the queue.

        If optional args 'block' is true and 'timeout' is None (the default),
        block if necessary until an item is available. If 'timeout' is
        a non-negative number, it blocks at most 'timeout' seconds and raises
        the Empty exception if no item was available within that time.
        Otherwise ('block' is false), return an item if one is immediately
        available, else raise the Empty exception ('timeout' is ignored
        in that case).
        '''
        with self.not_empty:
            if not block:
                if not self._qsize():
                    raise Empty
            elif timeout is None:
                while not self._qsize():
                    self.not_empty.wait()
            elif timeout < 0:
                raise ValueError("'timeout' must be a non-negative number")
            else:
                endtime = time() + timeout
                while not self._qsize():
                    remaining = endtime - time()
                    if remaining <= 0.0:
                        raise Empty
                    self.not_empty.wait(remaining)
            item = self._get()
            self.not_full.notify()
            return item

    def put_nowait(self, item):
        '''Put an item into the queue without blocking.

        Only enqueue the item if a free slot is immediately available.
        Otherwise raise the Full exception.
        '''
        return self.put(item, block=False)

    def get_nowait(self):
        '''Remove and return an item from the queue without blocking.

        Only get an item if one is immediately available. Otherwise
        raise the Empty exception.
        '''
        return self.get(block=False)

    # Override these methods to implement other queue organizations
    # (e.g. stack or priority queue).
    # These will only be called with appropriate locks held

    # Initialize the queue representation
    def _init(self, maxsize):
        self.queue = deque()

    def _qsize(self):
        return len(self.queue)

    # Put a new item in the queue
    def _put(self, item):
        self.queue.append(item)

    # Get an item from the queue
    def _get(self):
        return self.queue.popleft()
queue.Queue源码

 ①qsize(self)  队列的个数
 ②full(self)   队列是否满了
 ③put(self, item, block=True, timeout=None) 放数
 ④get(self, block=True, timeout=None)    取数

2、双向队列(随便存取) 在collections中。

class deque(object):
    """
    deque([iterable[, maxlen]]) --> deque object
    
    A list-like sequence optimized for data accesses near its endpoints.
    """
    def append(self, *args, **kwargs): # real signature unknown
        """ Add an element to the right side of the deque. """
        pass

    def appendleft(self, *args, **kwargs): # real signature unknown
        """ Add an element to the left side of the deque. """
        pass

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

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

    def count(self, value): # real signature unknown; restored from __doc__
        """ D.count(value) -> integer -- return number of occurrences of value """
        return 0

    def extend(self, *args, **kwargs): # real signature unknown
        """ Extend the right side of the deque with elements from the iterable """
        pass

    def extendleft(self, *args, **kwargs): # real signature unknown
        """ Extend the left side of the deque with elements from the iterable """
        pass

    def index(self, value, start=None, stop=None): # real signature unknown; restored from __doc__
        """
        D.index(value, [start, [stop]]) -> integer -- return first index of value.
        Raises ValueError if the value is not present.
        """
        return 0

    def insert(self, index, p_object): # real signature unknown; restored from __doc__
        """ D.insert(index, object) -- insert object before index """
        pass

    def pop(self, *args, **kwargs): # real signature unknown
        """ Remove and return the rightmost element. """
        pass

    def popleft(self, *args, **kwargs): # real signature unknown
        """ Remove and return the leftmost element. """
        pass

    def remove(self, value): # real signature unknown; restored from __doc__
        """ D.remove(value) -- remove first occurrence of value. """
        pass

    def reverse(self): # real signature unknown; restored from __doc__
        """ D.reverse() -- reverse *IN PLACE* """
        pass

    def rotate(self, *args, **kwargs): # real signature unknown
        """ Rotate the deque n steps to the right (default n=1).  If n is negative, rotates left. """
        pass

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

    def __bool__(self, *args, **kwargs): # real signature unknown
        """ self != 0 """
        pass

    def __contains__(self, *args, **kwargs): # real signature unknown
        """ Return key in self. """
        pass

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

    def __delitem__(self, *args, **kwargs): # real signature unknown
        """ Delete self[key]. """
        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 __getitem__(self, *args, **kwargs): # real signature unknown
        """ Return self[key]. """
        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 __iadd__(self, *args, **kwargs): # real signature unknown
        """ Implement self+=value. """
        pass

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

    def __init__(self, iterable=(), maxlen=None): # known case of _collections.deque.__init__
        """
        deque([iterable[, maxlen]]) --> deque object
        
        A list-like sequence optimized for data accesses near its endpoints.
        # (copied from class doc)
        """
        pass

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

    def __mul__(self, *args, **kwargs): # real signature unknown
        """ Return self*value.n """
        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 __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 __reversed__(self): # real signature unknown; restored from __doc__
        """ D.__reversed__() -- return a reverse iterator over the deque """
        pass

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

    def __setitem__(self, *args, **kwargs): # real signature unknown
        """ Set self[key] to value. """
        pass

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

    maxlen = property(lambda self: object(), lambda self, v: None, lambda self: None)  # default
    """maximum size of a deque or None if unbounded"""


    __hash__ = None
deque源码

 ①append(self, *args, **kwargs)
 ②appendleft(self, *args, **kwargs)
 ③extend(self, *args, **kwargs) 多个元素一起添加(从右侧)
 ④extendleft(self, *args, **kwargs)   多个元素一起添加(从左侧)

from collections import deque
d=deque(['aaaa','ddddd','eeee'])
print(d)
d.extend(['111','222','333'])
print(d)
d.extendleft(['444','555'])
print(d)

输出

deque(['aaaa', 'ddddd', 'eeee'])
deque(['aaaa', 'ddddd', 'eeee', '111', '222', '333'])
deque(['555', '444', 'aaaa', 'ddddd', 'eeee', '111', '222', '333']) 

 ⑤pop(self, *args, **kwargs) 取元素
 ⑥popleft(self, *args, **kwargs)
 ⑦rotate(self, *args, **kwargs)  首尾连接,向左/向右移动元素

from collections import deque
d=deque(['555', '444', 'aaaa', 'ddddd', 'eeee', '111', '222', '333'])
print(d)
d.rotate(1)
print(d)
d.rotate(-1)
print(d)

输出

deque(['555', '444', 'aaaa', 'ddddd', 'eeee', '111', '222', '333'])
deque(['333', '555', '444', 'aaaa', 'ddddd', 'eeee', '111', '222'])
deque(['555', '444', 'aaaa', 'ddddd', 'eeee', '111', '222', '333'])

posted on 2017-08-22 17:29 CARLOS_CHIANG 阅读(...) 评论(...) 编辑 收藏

导航