1. 简介
Python
标准模块 collections
中的类 Counter
是字典类 dict
的一个子类,该类一般用于对可哈希对象进行计数,有时也被称为多重集合。在 Counter
类的对象中,数据存储方式为:可哈希对象作为键,而可哈希对象的计数作为值进行存储。
2. 使用
-
创建
Counter
对象:>>> from collections import Counter >>> c = Counter('abcdeabcdabcaba')
-
获得出现频率最高的元素:
>>> c.most_common(3) [('a', 5), ('b', 4), ('c', 3)]
-
列出所有的键:
>>> sorted(c) ['a', 'b', 'c', 'd', 'e']
-
列出所有元素:
>>> ''.join(sorted(c.elements())) 'aaaaabbbbcccdde'
-
计算所有键的频率和:
>>> sum(c.values()) 15
-
获得某可哈希对象的计数:
>>> c['a'] 5
-
根据可迭代对象更新计数:
>>> for elem in 'shazam': ... c[elem] += 1 >>> c['a'] 7
-
删除某可迭代对象:
>>> del c['b'] >>> c['b'] 0
-
合并两个
Counter
对象:>>> d = Counter('simsalabim') >>> c.update(d) >>> c['a'] 9 >>> c['i'] 2
-
清空
Counter
对象:>>> c.clear() >>> c['a'] 0
-
需要特别注意的是,当某可哈希对象的计数被设为 0 0 0 或减至 0 0 0 后,该对象将仍然保存在
Counter
对象中直到该对象被删除或Counter
对象本身被清空:>>> c = Counter('aaabbc') >>> c['b'] -= 2 >>> c.most_common() [('a', 3), ('c', 1), ('b', 0)] >>> del c['b'] >>> c.most_common() [('a', 3), ('c', 1)]
关于 Counter
对象的其他详细使用,请见 https://www.demo2s.com/python/python-collections-counter.html 。
3. 分析
########################################################################
### Counter
########################################################################
def _count_elements(mapping, iterable):
'Tally elements from the iterable.'
mapping_get = mapping.get
for elem in iterable:
mapping[elem] = mapping_get(elem, 0) + 1
try: # Load C helper function if available
from _collections import _count_elements
except ImportError:
pass
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
15
>>> c['a'] # count of letter 'a'
5
>>> 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'
7
>>> del c['b'] # remove all 'b'
>>> c['b'] # now there are zero 'b'
0
>>> d = Counter('simsalabim') # make another counter
>>> c.update(d) # add in the second counter
>>> c['a'] # now there are nine 'a'
9
>>> 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):
'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('abracadabra').most_common(3)
[('a', 5), ('b', 2), ('r', 2)]
'''
# 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 the semantics
# would be ambiguous in cases such as Counter.fromkeys('aaabbc', v=2).
# Initializing counters to zero values isn't necessary because zero
# is already the default value for counter lookups. Initializing
# to one is easily accomplished with Counter(set(iterable)). For
# more exotic cases, create a dictionary first using a dictionary
# comprehension or dict.fromkeys().
raise NotImplementedError(
'Counter.fromkeys() is undefined. Use Counter(iterable) instead.')
def update(self, iterable=None, /, **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 iterable is not None:
if isinstance(iterable, _collections_abc.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(self, iterable=None, /, **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 iterable is not None:
self_get = self.get
if isinstance(iterable, _collections_abc.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()
#
# Rich comparison operators for multiset subset and superset tests
# are deliberately omitted due to semantic conflicts with the
# existing inherited dict equality method. Subset and superset
# semantics ignore zero counts and require that p≤q ∧ p≥q → p=q;
# however, that would not be the case for p=Counter(a=1, b=0)
# and q=Counter(a=1) where the dictionaries are not equal.
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'
result = Counter()
for elem, count in self.items():
if count > 0:
result[elem] = count
return result
def __neg__(self):
'''Subtracts from an empty counter. Strips positive and zero counts,
and flips the sign on negative counts.
'''
result = Counter()
for elem, count in self.items():
if count < 0:
result[elem] = 0 - count
return result
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()