python 之 计数器(counter)
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
c = Counter('abcdeabcdabcaba')
print c
输出:Counter({'a': 5, 'b': 4, 'c': 3, 'd': 2, 'e': 1})
########################################################################
### 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):
""" 数量大于等n的所有元素和计数器 """
'''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
python 之 计数器(counter)的更多相关文章
- 计数器(counter),有序字典(OrderDict),默认字典(defaultdict),可命名元祖(namedtuple),双向队列(deque),单项队列(deuqe.Queue)
Python_Day_05 计数器(counter),有序字典(OrderDict),默认字典(defaultdict),可命名元祖(namedtuple),双向队列(deque),单项队列(deuq ...
- JMeter 配置元件之计数器Counter
配置元件之计数器Counter by:授客 QQ:1033553122 测试环境 apache-jmeter-2.13 1. 计数器简介 允许用户创建一个在线程组范围之内都可以被引用的计数器. ...
- 028_MapReduce中的计数器Counter的使用
一.分析运行wordcount程序屏幕上打印信息 ##运行wordcount单词频率统计程序,基于输出输出路径. [hadoop@hadoop-master hadoop-1.2.1]$ hadoop ...
- CSS计数器:counter
最近的需求,明星字体销售排行榜中,需要对字体的销售情况进行排序. 在早期,只有ol和ul可以对子元素li进行排序:如果不使用这两个标签,就由前台开发去手动填写序号. 当然,在这个需求中,数据不是实时更 ...
- python 计数器Counter
from collections import Counter colours=( ('Yasoob','Yellow',1), ('Ali','Blue',2), ('Arham','Green', ...
- Python_Day_05 计数器(counter),有序字典(OrderDict),默认字典(defaultdict),可命名元祖(namedtuple),双向队列(deque),单项队列(deuqe.Queue)
Counter(计数器) 是一个字典的子类,存储形式同样为字典,其中存储的键为字典的元素,值为元素出现的次数,在使用之前我们需要先导入文件 import collections 初始化一个计数器 im ...
- 计数器:counter
组成:2属性,1方法 属性1: counter-reset 命名 属性2: counter-increment 启动/自增 方法 : counter()/counters() 调用方法 1.计数器 命 ...
- Python:collections.Counter
collections是Python内建的一个集合模块,其中提供了许多有用的集合类: namedtuple:只有属性的简易类 deque:双向增删的List ChainMap:多个字典的链接 Coun ...
- Cassandra 计数器counter类型和它的限制
文档基础 Cassandra 2.* CQL3.1 翻译多数来自这个文档 更新于2015年9月7日,最后有参考资料 作为Cassandra的一种类型之一,Counter类型算是限制最多的一个.Coun ...
随机推荐
- SpringMVC源码情操陶冶-FreeMarker之web配置
前言:本文不讲解FreeMarkerView视图的相关配置,其配置基本由FreeMarkerViewResolver实现,具体可参考>>>SpringMVC源码情操陶冶-ViewRe ...
- PHP删除文件夹及其文件
<?php function deletedir($path){ $openpath = opendir($path); while ($f = readdir($openpath)){ $fi ...
- (转)Sublime Text2 快捷键汇总
场景:最近在编写项目中越发的感觉到一个得心应手的编辑器是多么的重要,而sublime,无疑是让我用着最舒服,最有感觉的编辑器了! 1 快捷键总结 一个好的编辑器,能大大提高编程的效率.如果能熟知软件的 ...
- Android源码博文集锦4
Android精选源码 一款常见的自定义加载动画 android开源记账项目CoCoin Android自定义view:拖拽选择按钮 Android指纹识别 一个折线图,它提供了几个非常实用的功能 一 ...
- cookie原理
cookie原理 一般来说,Cookie通过HTTP Headers从服务器端返回到浏览器上.首先,服务器端在响应中利用Set-Cookie header来创建一个Cookie,然后,浏览器在它的请求 ...
- C语言左值,运算符的优先级以及结合性探讨
刚刚开始看一本书.<C陷阱与缺陷>,相信学习C语言的大家都对这本书有耳闻.今天看到了里面的贪心法则.也即在读到一个字符后,尽可能多的读入更多的字符,直到读入的字符组成的字符串已经不可能再组 ...
- Uva 679 Dropping Ballls 二叉树的编号
这个程序常规处理起来数据量很大,I可以高达2^D-1 /* ....... */ 里面的代码块据此避免了开太大的数组 做太多的循环 #include<cstdio> #include< ...
- VMware NAT端口映射 外网可以访问内网虚拟机
我想尝试的是利用本机的ip+port来访问虚拟机上的web服务器,因为这样的话,我就能够将我的web服务器部署成为一个能让外网访问的服务器了,首先说下我的环境: 主机:系统win7,ip地址172.1 ...
- python--DenyHttp项目(2)--ACM监考服务器端
服务器端: #coding:utf-8 ''' ServerGui.py 设置比赛开始时间 设置比赛结束时间 若时间无误启动监听服务 ''' import time import re import ...
- 汇编总结:mov指令
mov指令的作用: mov指令可能是汇编里用的最多的指令了,完成c语言里的赋值. mov指令种类: 1.普通的mov指令 2.做符号扩展的movs 3.做零扩展的movz 1.普通mov的种类有: m ...