Python中Collections模块的Counter容器类使用教程

>>> c = Counter() # 创建一个空的Counter类
>>> c = Counter('gallahad') # 从一个可iterable对象（list、tuple、dict、字符串等）创建
>>> c = Counter({'a': 4,'b': 2}) # 从一个字典对象创建
>>> c = Counter(a=4,b=2) # 从一组键值对创建

>>> c = Counter() # 创建一个空的Counter类
>>> c = Counter('gallahad') # 从一个可iterable对象（list、tuple、dict、字符串等）创建
>>> c = Counter({'a': 4,b=2) # 从一组键值对创建

>>> c = Counter("abcdefgab")
>>> c["a"]
2
>>> c["c"]
1
>>> c["h"]
0

>>> c = Counter("abcdefgab")
>>> c["a"]
2
>>> c["c"]
1
>>> c["h"]
0

>>> c = Counter('which')
>>> c.update('witch') # 使用另一个iterable对象更新
>>> c['h']
3
>>> d = Counter('watch')
>>> c.update(d) # 使用另一个Counter对象更新
>>> c['h']
4

>>> c = Counter('which')
>>> c.update('witch') # 使用另一个iterable对象更新
>>> c['h']
3
>>> d = Counter('watch')
>>> c.update(d) # 使用另一个Counter对象更新
>>> c['h']
4

>>> c = Counter('which')
>>> c.subtract('witch') # 使用另一个iterable对象更新
>>> c['h']
1
>>> d = Counter('watch')
>>> c.subtract(d) # 使用另一个Counter对象更新
>>> c['a']
-1

>>> c = Counter('which')
>>> c.subtract('witch') # 使用另一个iterable对象更新
>>> c['h']
1
>>> d = Counter('watch')
>>> c.subtract(d) # 使用另一个Counter对象更新
>>> c['a']
-1

2.4 键的删除

>>> c = Counter("abcdcba")
>>> c
Counter({'a': 2,'c': 2,'b': 2,'d': 1})
>>> c["b"] = 0
>>> c
Counter({'a': 2,'d': 1,'b': 0})
>>> del c["a"]
>>> c
Counter({'c': 2,'d': 1})

>>> c = Counter("abcdcba")
>>> c
Counter({'a': 2,'d': 1})

elements()方法Python

>>> c = Counter(a=4,b=2,c=0,d=-2)
>>> list(c.elements())
['a','a','b','b']

>>> c = Counter(a=4,'b']

>>> c = Counter('abracadabra')
>>> c.most_common()
[('a',5),('r',2),('b',('c',1),('d',1)]
>>> c.most_common(3)
[('a',2)]

>>> c = Counter('abracadabra')
>>> c.most_common()
[('a',2)]

>>> c = Counter("abcdcba")
>>> c
Counter({'a': 2,'d': 1})
>>> d = c.copy()
>>> d
Counter({'a': 2,'d': 1})

>>> c = Counter(a=3,b=1)
>>> d = Counter(a=1,b=2)
>>> c + d # c[x] + d[x]
Counter({'a': 4,'b': 3})
>>> c - d # subtract（只保留正数计数的元素）
Counter({'a': 2})
>>> c & d # 交集: min(c[x],d[x])
Counter({'a': 1,'b': 1})
>>> c | d # 并集: max(c[x],d[x])
Counter({'a': 3,'b': 2})

>>> c = Counter(a=3,'b': 2})

sum(c.values()) # 所有计数的总数
c.clear() # 重置Counter对象，注意不是删除
list(c) # 将c中的键转为列表
set(c) # 将c中的键转为set
dict(c) # 将c中的键值对转为字典
c.items() # 转为(elem,cnt)格式的列表
Counter(dict(list_of_pairs)) # 从(elem,cnt)格式的列表转换为Counter类对象
c.most_common()[:-n:-1] # 取出计数最少的n个元素
c += Counter() # 移除0和负值

sum(c.values()) # 所有计数的总数
c.clear() # 重置Counter对象，注意不是删除
list(c) # 将c中的键转为列表
set(c) # 将c中的键转为set
dict(c) # 将c中的键值对转为字典
c.items() # 转为(elem,cnt)格式的列表转换为Counter类对象
c.most_common()[:-n:-1] # 取出计数最少的n个元素
c += Counter() # 移除0和负值

def is_anagram(word1,word2):
  """Checks whether the words are anagrams.

  word1: string
  word2: string

  returns: boolean
  """

  return Counter(word1) == Counter(word2)

class Multiset(Counter):
  """A multiset is a set where elements can appear more than once."""

  def is_subset(self,other):
    """Checks whether self is a subset of other.

    other: Multiset

    returns: boolean
    """
    for char,count in self.items():
      if other[char] < count:
        return False
    return True

  # map the <= operator to is_subset
  __le__ = is_subset

class Pmf(Counter):
  """A Counter with probabilities."""

  def normalize(self):
    """Normalizes the PMF so the probabilities add to 1."""
    total = float(sum(self.values()))
    for key in self:
      self[key] /= total

  def __add__(self,other):
    """Adds two distributions.

    The result is the distribution of sums of values from the
    two distributions.

    other: Pmf

    returns: new Pmf
    """
    pmf = Pmf()
    for key1,prob1 in self.items():
      for key2,prob2 in other.items():
        pmf[key1 + key2] += prob1 * prob2
    return pmf

  def __hash__(self):
    """Returns an integer hash value."""
    return id(self)

  def __eq__(self,other):
    return self is other

  def render(self):
    """Returns values and their probabilities,suitable for plotting."""
    return zip(*sorted(self.items()))

d6 = Pmf([1,2,3,4,5,6])
d6.normalize()
d6.name = 'one die'
print(d6)
Pmf({1: 0.16666666666666666,2: 0.16666666666666666,3: 0.16666666666666666,4: 0.16666666666666666,5: 0.16666666666666666,6: 0.16666666666666666})

d6_twice = d6 + d6
d6_twice.name = 'two dices'

for key,prob in d6_twice.items():
  print(key,prob)

import numpy as np
d6_thrice = np.sum([d6]*3)
d6_thrice.name = 'three dices'

for die in [d6,d6_twice,d6_thrice]:
  xs,ys = die.render()
  pyplot.plot(xs,ys,label=die.name,linewidth=3,alpha=0.5)

pyplot.xlabel('Total')
pyplot.ylabel('Probability')
pyplot.legend()
pyplot.show()

def make_die(num_sides):
  die = Pmf(range(1,num_sides+1))
  die.name = 'd%d' % num_sides
  die.normalize()
  return die


dice = [make_die(x) for x in [4,6,8,12,20]]
print(dice)

class Suite(Pmf):
  """Map from hypothesis to probability."""

  def bayesian_update(self,data):
    """Performs a Bayesian update.

    Note: called bayesian_update to avoid overriding dict.update

    data: result of a die roll
    """
    for hypo in self:
      like = self.likelihood(data,hypo)
      self[hypo] *= like

    self.normalize()

class DiceSuite(Suite):

  def likelihood(self,data,hypo):
    """Computes the likelihood of the data under the hypothesis.

    data: result of a die roll
    hypo: Die object
    """
    return hypo[data]

dice_suite = DiceSuite(dice)

dice_suite.bayesian_update(6)

for die,prob in sorted(dice_suite.items()):
  print die.name,prob

d4 0.0
d6 0.392156862745
d8 0.294117647059
d12 0.196078431373
d20 0.117647058824

dice_suite.bayesian_update(8)

for die,prob


d4 0.0
d6 0.0
d8 0.623268698061
d12 0.277008310249
d20 0.0997229916898