基本数据类型补充：
set 是一个无序且不重复的元素集合
1 class set(object):
2 """
3 set() -> new empty set object
4 set(iterable) -> new set object
5
6 Build an unordered collection of unique elements.
7 """
8 def add(self, *args, **kwargs): # real signature unknown
9 """
10 Add an element to a set，添加元素
11
12 This has no effect if the element is already present.
13 """
14 pass
15
16 def clear(self, *args, **kwargs): # real signature unknown
17 """ Remove all elements from this set. 清除内容"""
18 pass
19
20 def copy(self, *args, **kwargs): # real signature unknown
21 """ Return a shallow copy of a set. 浅拷贝 """
22 pass
23
24 def difference(self, *args, **kwargs): # real signature unknown
25 """
26 Return the difference of two or more sets as a new set. A中存在，B中不存在
27
28 (i.e. all elements that are in this set but not the others.)
29 """
30 pass
31
32 def difference_update(self, *args, **kwargs): # real signature unknown
33 """ Remove all elements of another set from this set. 从当前集合中删除和B中相同的元素"""
34 pass
35
36 def discard(self, *args, **kwargs): # real signature unknown
37 """
38 Remove an element from a set if it is a member.
39
40 If the element is not a member, do nothing. 移除指定元素，不存在不保错
41 """
42 pass
43
44 def intersection(self, *args, **kwargs): # real signature unknown
45 """
46 Return the intersection of two sets as a new set. 交集
47
48 (i.e. all elements that are in both sets.)
49 """
50 pass
51
52 def intersection_update(self, *args, **kwargs): # real signature unknown
53 """ Update a set with the intersection of itself and another. 取交集并更更新到A中 """
54 pass
55
56 def isdisjoint(self, *args, **kwargs): # real signature unknown
57 """ Return True if two sets have a null intersection. 如果没有交集，返回True，否则返回False"""
58 pass
59
60 def issubset(self, *args, **kwargs): # real signature unknown
61 """ Report whether another set contains this set. 是否是子序列"""
62 pass
63
64 def issuperset(self, *args, **kwargs): # real signature unknown
65 """ Report whether this set contains another set. 是否是父序列"""
66 pass
67
68 def pop(self, *args, **kwargs): # real signature unknown
69 """
70 Remove and return an arbitrary set element.
71 Raises KeyError if the set is empty. 移除元素
72 """
73 pass
74
75 def remove(self, *args, **kwargs): # real signature unknown
76 """
77 Remove an element from a set; it must be a member.
78
79 If the element is not a member, raise a KeyError. 移除指定元素，不存在保错
80 """
81 pass
82
83 def symmetric_difference(self, *args, **kwargs): # real signature unknown
84 """
85 Return the symmetric difference of two sets as a new set. 对称差集
86
87 (i.e. all elements that are in exactly one of the sets.)
88 """
89 pass
90
91 def symmetric_difference_update(self, *args, **kwargs): # real signature unknown
92 """ Update a set with the symmetric difference of itself and another. 对称差集，并更新到a中 """
93 pass
94
95 def union(self, *args, **kwargs): # real signature unknown
96 """
97 Return the union of sets as a new set. 并集
98
99 (i.e. all elements that are in either set.)
100 """
101 pass
102
103 def update(self, *args, **kwargs): # real signature unknown
104 """ Update a set with the union of itself and others. 更新 """
105 pass
1：创建
1 s = set()
2 s = {11,22,33,55}
2：转换
1 li = [11,22,33,44]
2 tu = (11,22,33,44)
3 st = '123'
4 s = set(li)
3：intersection , intersection_update方法
a = {11,22,33,44}
b = {22,66,77,88}
ret = a.intersection(b)
print(ret)
intersection取得两个集合中的交集元素，并将这些元素以一个新的集合返回给一个变量接收
a = {11,22,33,44}
b = {22,66,77,88}
a.intersection_update(b)
print(a)
intersection_update取得两个集合的交集元素，并更新a集合
4：isdisjoint , issubset , issuperset方法
1 s = {11,22,33,44}
2 b = {11,22,77,55}
3 ret = s.isdisjoint(b)#有交集返回False，没有交集返回True
4 print(ret)
5 ## False
issubset判断是否为子集
a = {11,22,33,44}
b = {11,44}
ret = b.issubset(a)
print(ret)
##########################################
True
issuperset判断是否为父集
a = {11,22,33,44}
b = {11,44}
ret = a.issubset(b)
print(ret)
##########################################
False
5：discard , remove , pop
1 s = {11,22,33,44}
2 s.remove(11)
3 print(s)
4 s.discard(22)
5 print(s)
6 s.pop()
7 print(s)
三者都能达到移除元素的效果，区别在于remove移除集合中不存在的元素时会报错，discard移除不存在的元素是不会报错，pop无法精确控制移除哪个元素，按其自身的规则随机移除元素，返回被移除的元素，可以使用变量接收其返回值
6：symmetric_difference取差集
1 s = {11,22,33,44}
2 b = {11,22,77,55}
3 r1 = s.difference(b)
4 r2 = b.difference(s)
5 print(r1)
6 print(r2)
7 ret = s.symmetric_difference(b)
8 print(ret)
9 ## set([33, 44])
10 ## set([77, 55])
11 ## set([33, 44, 77, 55])
symmetric_difference返回两个集合中不是交集的元素
上面的代码中，将symmetric_difference换成symmetric_difference_update则表示将两个集合中不是交集的部分赋值给s
7：union , update方法
1 s = {11,22,33,44}
2 b = {11,22,77,55}
3 ret = s.union(b)
4 print(ret)
5 ## set([33, 11, 44, 77, 22, 55])
union方法合并两个集合
1 s = {11,22,33,44}
2 b = {11,22,77,55}
3 s.update(b)
4 print(s)
5 ## set([33, 11, 44, 77, 22, 55])
update方法更新s集合，将b集合中的元素添加到s集合中！update方法也可以传递一个列表，如：update([23,45,67])
练习题：有下面两个字典
要求：
1）两个字典中有相同键的，则将new_dict中的值更新到old_dict对应键的值
2）old_dict中存在的键且new_dict中没有的键，在old_dict中删除，并把new_dict中的键值更新到old_dict中
3）最后输出old_dict
1 # 数据库中原有
2 old_dict = {
3 "#1":{ 'hostname':'c1', 'cpu_count': 2, 'mem_capicity': 80 },
4 "#2":{ 'hostname':'c1', 'cpu_count': 2, 'mem_capicity': 80 },
5 "#3":{ 'hostname':'c1', 'cpu_count': 2, 'mem_capicity': 80 }
6 }
7
8 # cmdb 新汇报的数据
9 new_dict = {
10 "#1":{ 'hostname':'c1', 'cpu_count': 2, 'mem_capicity': 800 },
11 "#3":{ 'hostname':'c1', 'cpu_count': 2, 'mem_capicity': 80 },
12 "#4":{ 'hostname':'c2', 'cpu_count': 2, 'mem_capicity': 80 }
13 }
old_keys = set(old_dict.keys())
new_keys = set(new_dict.keys())
#需要更新元素的键
update_keys = old_keys.intersection(new_keys)
print(update_keys)
#需要删除元素的键
del_keys = old_keys.difference(new_keys)
#需要添加元素的键
add_keys = new_keys.difference(old_keys)
print(del_keys)
print(add_keys)
update_keys = list(update_keys)
for i in update_keys :
old_dict[i] = new_dict[i]
del_keys = list(del_keys)
for j in del_keys :
del old_dict[j]
for k in list(add_keys) :
old_dict[k] = new_dict[k]
print(old_dict)
########################################
{'#3': {'hostname': 'c1', 'cpu_count': 2, 'mem_capicity': 80}, '#1': {'hostname': 'c1', 'cpu_count': 2, 'mem_capicity': 800}, '#4': {'hostname': 'c2', 'cpu_count': 2, 'mem_capicity': 80}}
collections系列
一、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})
1 ######################################################################## 2 ### Counter 3 ######################################################################## 4 5 class Counter(dict): 6 '''Dict subclass for counting hashable items. Sometimes called a bag 7 or multiset. Elements are stored as dictionary keys and their counts 8 are stored as dictionary values. 9 10 >>> c = Counter('abcdeabcdabcaba') # count elements from a string 11 12 >>> c.most_common(3) # three most common elements 13 [('a', 5), ('b', 4), ('c', 3)] 14 >>> sorted(c) # list all unique elements 15 ['a', 'b', 'c', 'd', 'e'] 16 >>> ''.join(sorted(c.elements())) # list elements with repetitions 17 'aaaaabbbbcccdde' 18 >>> sum(c.values()) # total of all counts 19 20 >>> c['a'] # count of letter 'a' 21 >>> for elem in 'shazam': # update counts from an iterable 22 ... c[elem] += 1 # by adding 1 to each element's count 23 >>> c['a'] # now there are seven 'a' 24 >>> del c['b'] # remove all 'b' 25 >>> c['b'] # now there are zero 'b' 26 27 >>> d = Counter('simsalabim') # make another counter 28 >>> c.update(d) # add in the second counter 29 >>> c['a'] # now there are nine 'a' 30 31 >>> c.clear() # empty the counter 32 >>> c 33 Counter() 34 35 Note: If a count is set to zero or reduced to zero, it will remain 36 in the counter until the entry is deleted or the counter is cleared: 37 38 >>> c = Counter('aaabbc') 39 >>> c['b'] -= 2 # reduce the count of 'b' by two 40 >>> c.most_common() # 'b' is still in, but its count is zero 41 [('a', 3), ('c', 1), ('b', 0)] 42 43 ''' 44 # References: 45 # http://en.wikipedia.org/wiki/Multiset 46 # http://www.gnu.org/software/smalltalk/manual-base/html_node/Bag.html 47 # http://www.demo2s.com/Tutorial/Cpp/0380__set-multiset/Catalog0380__set-multiset.htm 48 # http://code.activestate.com/recipes/259174/ 49 # Knuth, TAOCP Vol. II section 4.6.3 50 51 def __init__(self, iterable=None, **kwds): 52 '''Create a new, empty Counter object. And if given, count elements 53 from an input iterable. Or, initialize the count from another mapping 54 of elements to their counts. 55 56 >>> c = Counter() # a new, empty counter 57 >>> c = Counter('gallahad') # a new counter from an iterable 58 >>> c = Counter({'a': 4, 'b': 2}) # a new counter from a mapping 59 >>> c = Counter(a=4, b=2) # a new counter from keyword args 60 61 ''' 62 super(Counter, self).__init__() 63 self.update(iterable, **kwds) 64 65 def __missing__(self, key): 66 """ 对于不存在的元素，返回计数器为0 """ 67 'The count of elements not in the Counter is zero.' 68 # Needed so that self[missing_item] does not raise KeyError 69 return 0 70 71 def most_common(self, n=None): 72 """ 数量大于等n的所有元素和计数器 """ 73 '''List the n most common elements and their counts from the most 74 common to the least. If n is None, then list all element counts. 75 76 >>> Counter('abcdeabcdabcaba').most_common(3) 77 [('a', 5), ('b', 4), ('c', 3)] 78 79 ''' 80 # Emulate Bag.sortedByCount from Smalltalk 81 if n is None: 82 return sorted(self.iteritems(), key=_itemgetter(1), reverse=True) 83 return _heapq.nlargest(n, self.iteritems(), key=_itemgetter(1)) 84 85 def elements(self): 86 """ 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 """ 87 '''Iterator over elements repeating each as many times as its count. 88 89 >>> c = Counter('ABCABC') 90 >>> sorted(c.elements()) 91 ['A', 'A', 'B', 'B', 'C', 'C'] 92 93 # Knuth's example for prime factors of 1836: 2**2 * 3**3 * 17**1 94 >>> prime_factors = Counter({2: 2, 3: 3, 17: 1}) 95 >>> product = 1 96 >>> for factor in prime_factors.elements(): # loop over factors 97 ... product *= factor # and multiply them 98 >>> product 99 100 Note, if an element's count has been set to zero or is a negative 101 number, elements() will ignore it. 102 103 ''' 104 # Emulate Bag.do from Smalltalk and Multiset.begin from C++. 105 return _chain.from_iterable(_starmap(_repeat, self.iteritems())) 106 107 # Override dict methods where necessary 108 109 @classmethod 110 def fromkeys(cls, iterable, v=None): 111 # There is no equivalent method for counters because setting v=1 112 # means that no element can have a count greater than one. 113 raise NotImplementedError( 114 'Counter.fromkeys() is undefined. Use Counter(iterable) instead.') 115 116 def update(self, iterable=None, **kwds): 117 """ 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 """ 118 '''Like dict.update() but add counts instead of replacing them. 119 120 Source can be an iterable, a dictionary, or another Counter instance. 121 122 >>> c = Counter('which') 123 >>> c.update('witch') # add elements from another iterable 124 >>> d = Counter('watch') 125 >>> c.update(d) # add elements from another counter 126 >>> c['h'] # four 'h' in which, witch, and watch 127 128 ''' 129 # The regular dict.update() operation makes no sense here because the 130 # replace behavior results in the some of original untouched counts 131 # being mixed-in with all of the other counts for a mismash that 132 # doesn't have a straight-forward interpretation in most counting 133 # contexts. Instead, we implement straight-addition. Both the inputs 134 # and outputs are allowed to contain zero and negative counts. 135 136 if iterable is not None: 137 if isinstance(iterable, Mapping): 138 if self: 139 self_get = self.get 140 for elem, count in iterable.iteritems(): 141 self[elem] = self_get(elem, 0) + count 142 else: 143 super(Counter, self).update(iterable) # fast path when counter is empty 144 else: 145 self_get = self.get 146 for elem in iterable: 147 self[elem] = self_get(elem, 0) + 1 148 if kwds: 149 self.update(kwds) 150 151 def subtract(self, iterable=None, **kwds): 152 """ 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 """ 153 '''Like dict.update() but subtracts counts instead of replacing them. 154 Counts can be reduced below zero. Both the inputs and outputs are 155 allowed to contain zero and negative counts. 156 157 Source can be an iterable, a dictionary, or another Counter instance. 158 159 >>> c = Counter('which') 160 >>> c.subtract('witch') # subtract elements from another iterable 161 >>> c.subtract(Counter('watch')) # subtract elements from another counter 162 >>> c['h'] # 2 in which, minus 1 in witch, minus 1 in watch 163 >>> c['w'] # 1 in which, minus 1 in witch, minus 1 in watch 164 -1 165 166 ''' 167 if iterable is not None: 168 self_get = self.get 169 if isinstance(iterable, Mapping): 170 for elem, count in iterable.items(): 171 self[elem] = self_get(elem, 0) - count 172 else: 173 for elem in iterable: 174 self[elem] = self_get(elem, 0) - 1 175 if kwds: 176 self.subtract(kwds) 177 178 def copy(self): 179 """ 拷贝 """ 180 'Return a shallow copy.' 181 return self.__class__(self) 182 183 def __reduce__(self): 184 """ 返回一个元组（类型，元组） """ 185 return self.__class__, (dict(self),) 186 187 def __delitem__(self, elem): 188 """ 删除元素 """ 189 'Like dict.__delitem__() but does not raise KeyError for missing values.' 190 if elem in self: 191 super(Counter, self).__delitem__(elem) 192 193 def __repr__(self): 194 if not self: 195 return '%s()' % self.__class__.__name__ 196 items = ', '.join(map('%r: %r'.__mod__, self.most_common())) 197 return '%s({%s})' % (self.__class__.__name__, items) 198 199 # Multiset-style mathematical operations discussed in: 200 # Knuth TAOCP Volume II section 4.6.3 exercise 19 201 # and at http://en.wikipedia.org/wiki/Multiset 202 # 203 # Outputs guaranteed to only include positive counts. 204 # 205 # To strip negative and zero counts, add-in an empty counter: 206 # c += Counter() 207 208 def __add__(self, other): 209 '''Add counts from two counters. 210 211 >>> Counter('abbb') + Counter('bcc') 212 Counter({'b': 4, 'c': 2, 'a': 1}) 213 214 ''' 215 if not isinstance(other, Counter): 216 return NotImplemented 217 result = Counter() 218 for elem, count in self.items(): 219 newcount = count + other[elem] 220 if newcount > 0: 221 result[elem] = newcount 222 for elem, count in other.items(): 223 if elem not in self and count > 0: 224 result[elem] = count 225 return result 226 227 def __sub__(self, other): 228 ''' Subtract count, but keep only results with positive counts. 229 230 >>> Counter('abbbc') - Counter('bccd') 231 Counter({'b': 2, 'a': 1}) 232 233 ''' 234 if not isinstance(other, Counter): 235 return NotImplemented 236 result = Counter() 237 for elem, count in self.items(): 238 newcount = count - other[elem] 239 if newcount > 0: 240 result[elem] = newcount 241 for elem, count in other.items(): 242 if elem not in self and count < 0: 243 result[elem] = 0 - count 244 return result 245 246 def __or__(self, other): 247 '''Union is the maximum of value in either of the input counters. 248 249 >>> Counter('abbb') | Counter('bcc') 250 Counter({'b': 3, 'c': 2, 'a': 1}) 251 252 ''' 253 if not isinstance(other, Counter): 254 return NotImplemented 255 result = Counter() 256 for elem, count in self.items(): 257 other_count = other[elem] 258 newcount = other_count if count < other_count else count 259 if newcount > 0: 260 result[elem] = newcount 261 for elem, count in other.items(): 262 if elem not in self and count > 0: 263 result[elem] = count 264 return result 265 266 def __and__(self, other): 267 ''' Intersection is the minimum of corresponding counts. 268 269 >>> Counter('abbb') & Counter('bcc') 270 Counter({'b': 1}) 271 272 ''' 273 if not isinstance(other, Counter): 274 return NotImplemented 275 result = Counter() 276 for elem, count in self.items(): 277 other_count = other[elem] 278 newcount = count if count < other_count else other_count 279 if newcount > 0: 280 result[elem] = newcount 281 return result 282 283 Counter