Collcetions系列
一、count计数器
Count主要是提供统计功能，用于统计字符串里某个字符出现的次数。
使用count前需要导入collcetions模块。
>>>import collections >>>obj = collections.Counter('adkloalnflasmfa') >>>print(obj) Counter({'a': 4, 'l': 3, 'f': 2, 'k': 1, 'd': 1, 'm': 1, 's': 1, 'o': 1, 'n': 1})
遍历counter里面的内容
for item in obj.elements(): print(item)
更新
>>>obj = collections.Counter(['11','22','22','33']) >>>print(obj) Counter({'22': 2, '11': 1, '33': 1}) >>>obj.update(['eric','11','11']) >>>print(obj) Counter({'11': 3, '22': 2, 'eric': 1, '33': 1})
内置函数
def __init__(*args, **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 ''' if not args: raise TypeError("descriptor '__init__' of 'Counter' object " "needs an argument") self, *args = args if len(args) > 1: raise TypeError('expected at most 1 arguments, got %d' % len(args)) super(Counter, self).__init__() self.update(*args, **kwds) def __missing__(self, key): '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): '''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.items(), key=_itemgetter(1), reverse=True) return _heapq.nlargest(n, self.items(), key=_itemgetter(1)) def elements(self): '''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 1836 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.items())) # 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(*args, **kwds): '''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 4 ''' # 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 not args: raise TypeError("descriptor 'update' of 'Counter' object " "needs an argument") self, *args = args if len(args) > 1: raise TypeError('expected at most 1 arguments, got %d' % len(args)) iterable = args[0] if args else None if iterable is not None: if isinstance(iterable, Mapping): if self: self_get = self.get for elem, count in iterable.items(): self[elem] = count + self_get(elem, 0) else: super(Counter, self).update(iterable) # fast path when counter is empty else: _count_elements(self, iterable) if kwds: self.update(kwds) def subtract(*args, **kwds): '''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 0 >>> c['w'] # 1 in which, minus 1 in witch, minus 1 in watch -1 ''' if not args: raise TypeError("descriptor 'subtract' of 'Counter' object " "needs an argument") self, *args = args if len(args) > 1: raise TypeError('expected at most 1 arguments, got %d' % len(args)) iterable = args[0] if args else None 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): 'Return a shallow copy.' return self.__class__(self) def __reduce__(self): return self.__class__, (dict(self),) def __delitem__(self, elem): 'Like dict.__delitem__() but does not raise KeyError for missing values.' if elem in self: super().__delitem__(elem) def __repr__(self): if not self: return '%s()' % self.__class__.__name__ try: items = ', '.join(map('%r: %r'.__mod__, self.most_common())) return '%s({%s})' % (self.__class__.__name__, items) except TypeError: # handle case where values are not orderable return '{0}({1!r})'.format(self.__class__.__name__, dict(self)) # 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 def __pos__(self): 'Adds an empty counter, effectively stripping negative and zero counts' return self + Counter() def __neg__(self): '''Subtracts from an empty counter. Strips positive and zero counts, and flips the sign on negative counts. ''' return Counter() - self def _keep_positive(self): '''Internal method to strip elements with a negative or zero count''' nonpositive = [elem for elem, count in self.items() if not count > 0] for elem in nonpositive: del self[elem] return self def __iadd__(self, other): '''Inplace add from another counter, keeping only positive counts. >>> c = Counter('abbb') >>> c += Counter('bcc') >>> c Counter({'b': 4, 'c': 2, 'a': 1}) ''' for elem, count in other.items(): self[elem] += count return self._keep_positive() def __isub__(self, other): '''Inplace subtract counter, but keep only results with positive counts. >>> c = Counter('abbbc') >>> c -= Counter('bccd') >>> c Counter({'b': 2, 'a': 1}) ''' for elem, count in other.items(): self[elem] -= count return self._keep_positive() def __ior__(self, other): '''Inplace union is the maximum of value from either counter. >>> c = Counter('abbb') >>> c |= Counter('bcc') >>> c Counter({'b': 3, 'c': 2, 'a': 1}) ''' for elem, other_count in other.items(): count = self[elem] if other_count > count: self[elem] = other_count return self._keep_positive() def __iand__(self, other): '''Inplace intersection is the minimum of corresponding counts. >>> c = Counter('abbb') >>> c &= Counter('bcc') >>> c Counter({'b': 1}) ''' for elem, count in self.items(): other_count = other[elem] if other_count < count: self[elem] = other_count return self._keep_positive()
二、有序字典
创建字典
>>>dic = collections.OrderedDict() >>>dic['k1'] = 'v1' >>>dic['k2'] = 'v2' >>>dic['k3'] = 'v3'
内置函数
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 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 link_prev.next = link_next link_next.prev = link_prev root = self.__root if last: last = root.prev link.prev = last link.next = root last.next = root.prev = link else: first = root.next link.prev = root link.next = first root.next = first.prev = 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 keys = MutableMapping.keys values = MutableMapping.values items = MutableMapping.items __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)
三、默认字典
创建默认字典
>>>dic = collections.defaultdict(list) >>>dic['k1'].append('alex') >>>print(dic) defaultdict(<class 'list'>, {'k1': ['alex']})
方法与内置函数
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__()."""
四、可命名元组
#创建类 MytupleClass = collections.namedtuple('MytupleClass',['x','y','z']) #创建对象 obj = MytupleClass(11,22,33) print(obj.x) print(obj.y) print(obj.z) 11 22 33
