九、collection系统

先做个练习

练习一:元素分类
有如下值集合 [11,22,33,44,55,66,77,88,99,90...],将所有大于 66 的值保存至字典的第一个key中,将小于 66 的值保存至第二个key的值中。
即: {'k1': 大于66 , 'k2': 小于66}

 1 #!/usr/bin/env python
 2 # _*_ coding:utf-8 _*_
 3 '''
 4 将一个数字列表分割成字典,'k1'的值为小于66的值,'k2'的值为大于66的值
 5 '''
 6 li =  [11,22,33,44,55,66,77,88,99,90]
 7 dic = {}
 8 for ele in li:
 9     #先判断是否小于66
10     if ele < 66:
11         #判断是否有'k1'的键,如果有就追加
12         if 'k1' in dic.keys():
13             dic['k1'].append(ele)
14         else:
15             #创建只有一个元素的列表
16             dic['k1'] = [ele,]
17     else:
18         if 'k2' in dic.keys():
19             dic['k2'].append(ele);
20         else:
21             dic['k2'] = [ele,]
22 
23 print dic
24 
25 #打印出字典的键和值,值占4个字符,前面用’*‘填充,打印时要把数值转换成字符串形式
26 for k in dic.keys():
27     print k
28     if type(dic[k]) == list:
29         for i in dic[k]:
30             print str(i).rjust(4,'*')
dict_Category

练习二:将文件中读出的内容转换成字典

已知文件内容为

alex|123|1
eric|123|1
john|123|1

 转换成字典形式

dic = {
'alex':[123,1]
'eric':[123,1]
'john':[123,1]
}
 1 #!/usr/bin/env python
 2 # _*_ coding:utf-8 _*_
 3 
 4 '''
 5 想要得到的效果
 6 dic = {
 7     'alex':[123,1]
 8     'eric':[123,1]
 9     'john':[123,1]
10 }
11 '''
12 
13 #打开文件,读取文件内容,用的with as,这样可以保证最后文件会被关闭
14 with open('log.txt') as f:
15     #将文件读出来赋值给一个列表
16     line_list = f.readlines();
17 print line_list
18 dic = {}
19 #遍历列表,将每行再分割成列表
20 for line in line_list:
21     line = line.strip();
22     ele_list = line.split('|')
23     #把姓名做成字典的key,并把后面所有元素当做这个key的值,这里用的是[1:],取出除了0外,所有的值
24     dic[ele_list[0]] = ele_list[1:]
25     
26 #下面是遍历字典的两种方法,推荐使用第一种,因为在字典内容少的时候两种方法都可以
27 #但当字典内容多的时候,第二种方法的字典会先值转换成列表,会消耗时间和占用内存
28 #方法一
29 for k in dic.keys():
30     print k,dic[k]
31     
32 for ele in dic:
33     print ele,dic[ele];
34 
35 #方法二    
36 for k,v in dic.items():
37     print k,v
dict_file

 

1、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

1 >>> import collections
2 NameError: name 'Counter' is not defined
3 >>> c = collections.Counter('asdfasdfasdfasdf')
4 >>> c
5 Counter({'a': 4, 's': 4, 'd': 4, 'f': 4})
6 >>> 
  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         >>> c
 68         Counter({'a': 12, 'f': 10, 'd': 9, 's': 9, 'c': 3, 'g': 3, 'e': 1})
 69         >>> c['a']
 70         12
 71         >>> c['z']
 72         0
 73         #原生字典会抛异常
 74         >>> a = {1:2,3:4}
 75         >>> a[1]
 76         2
 77         >>> a[55]
 78         Traceback (most recent call last):
 79           File "<stdin>", line 1, in <module>
 80         KeyError: 55
 81         >>> 
 82         """
 83         'The count of elements not in the Counter is zero.'
 84         # Needed so that self[missing_item] does not raise KeyError
 85         return 0
 86 
 87     def most_common(self, n=None):
 88         """ 列出n个出现次数最多的元素 默认最从多到少排序的,所以看起来就像是截取了前几个元素
 89         >>> c = collections.Counter('asdfasdfasdfasdfaaaacccsdfefgasdfasdfgasdfasdgf')
 90         >>> c
 91         Counter({'a': 12, 'f': 10, 'd': 9, 's': 9, 'c': 3, 'g': 3, 'e': 1})
 92         >>> c.most_common(3)
 93         [('a', 12), ('f', 10), ('d', 9)]
 94         >>> 
 95         """
 96         '''List the n most common elements and their counts from the most
 97         common to the least.  If n is None, then list all element counts.
 98 
 99         >>> Counter('abcdeabcdabcaba').most_common(3)
100         [('a', 5), ('b', 4), ('c', 3)]
101 
102         '''
103         # Emulate Bag.sortedByCount from Smalltalk
104         if n is None:
105             return sorted(self.iteritems(), key=_itemgetter(1), reverse=True)
106         return _heapq.nlargest(n, self.iteritems(), key=_itemgetter(1))
107 
108     def elements(self):
109         """ 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 
110         >>> c = collections.Counter('aaaabbbcc')
111         >>> c
112         Counter({'a': 4, 'b': 3, 'c': 2})
113         #因为是迭代器,所以要用循环取出
114         >>> c.elements()
115         <itertools.chain object at 0x7fb491a27890>
116         >>> for ele in c.elements():print ele;
117         ... 
118         a
119         a
120         a
121         a
122         c
123         c
124         b
125         b
126         b
127         >>> 
128         """
129         '''Iterator over elements repeating each as many times as its count.
130 
131         >>> c = Counter('ABCABC')
132         >>> sorted(c.elements())
133         ['A', 'A', 'B', 'B', 'C', 'C']
134 
135         # Knuth's example for prime factors of 1836:  2**2 * 3**3 * 17**1
136         >>> prime_factors = Counter({2: 2, 3: 3, 17: 1})
137         >>> product = 1
138         >>> for factor in prime_factors.elements():     # loop over factors
139         ...     product *= factor                       # and multiply them
140         >>> product
141 
142         Note, if an element's count has been set to zero or is a negative
143         number, elements() will ignore it.
144 
145         '''
146         # Emulate Bag.do from Smalltalk and Multiset.begin from C++.
147         return _chain.from_iterable(_starmap(_repeat, self.iteritems()))
148 
149     # Override dict methods where necessary
150 
151     @classmethod
152     def fromkeys(cls, iterable, v=None):
153         # There is no equivalent method for counters because setting v=1
154         # means that no element can have a count greater than one.
155         raise NotImplementedError(
156             'Counter.fromkeys() is undefined.  Use Counter(iterable) instead.')
157 
158     def update(self, iterable=None, **kwds):
159         """ 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 
160         >>> c
161         Counter({'a': 4, 'b': 3, 'c': 2})
162         >>> c.update('a')
163         >>> c
164         Counter({'a': 5, 'b': 3, 'c': 2})
165         >>> d = collections.Counter('ccddee')
166         >>> c.update(d)
167         >>> c
168         Counter({'a': 5, 'c': 4, 'b': 3, 'e': 2, 'd': 2})
169         >>> 
170         """
171         '''Like dict.update() but add counts instead of replacing them.
172 
173         Source can be an iterable, a dictionary, or another Counter instance.
174 
175         >>> c = Counter('which')
176         >>> c.update('witch')           # add elements from another iterable
177         >>> d = Counter('watch')
178         >>> c.update(d)                 # add elements from another counter
179         >>> c['h']                      # four 'h' in which, witch, and watch
180 
181         '''
182         # The regular dict.update() operation makes no sense here because the
183         # replace behavior results in the some of original untouched counts
184         # being mixed-in with all of the other counts for a mismash that
185         # doesn't have a straight-forward interpretation in most counting
186         # contexts.  Instead, we implement straight-addition.  Both the inputs
187         # and outputs are allowed to contain zero and negative counts.
188 
189         if iterable is not None:
190             if isinstance(iterable, Mapping):
191                 if self:
192                     self_get = self.get
193                     for elem, count in iterable.iteritems():
194                         self[elem] = self_get(elem, 0) + count
195                 else:
196                     super(Counter, self).update(iterable) # fast path when counter is empty
197             else:
198                 self_get = self.get
199                 for elem in iterable:
200                     self[elem] = self_get(elem, 0) + 1
201         if kwds:
202             self.update(kwds)
203 
204     def subtract(self, iterable=None, **kwds):
205         """ 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 
206         >>> c = collections.Counter('aabbcc')
207         >>> c
208         Counter({'a': 2, 'c': 2, 'b': 2})
209         >>> c.subtract('a')
210         >>> c
211         Counter({'c': 2, 'b': 2, 'a': 1})
212         >>> 
213         """
214         '''Like dict.update() but subtracts counts instead of replacing them.
215         Counts can be reduced below zero.  Both the inputs and outputs are
216         allowed to contain zero and negative counts.
217 
218         Source can be an iterable, a dictionary, or another Counter instance.
219 
220         >>> c = Counter('which')
221         >>> c.subtract('witch')             # subtract elements from another iterable
222         >>> c.subtract(Counter('watch'))    # subtract elements from another counter
223         >>> c['h']                          # 2 in which, minus 1 in witch, minus 1 in watch
224         >>> c['w']                          # 1 in which, minus 1 in witch, minus 1 in watch
225         -1
226 
227         '''
228         if iterable is not None:
229             self_get = self.get
230             if isinstance(iterable, Mapping):
231                 for elem, count in iterable.items():
232                     self[elem] = self_get(elem, 0) - count
233             else:
234                 for elem in iterable:
235                     self[elem] = self_get(elem, 0) - 1
236         if kwds:
237             self.subtract(kwds)
238 
239     def copy(self):
240         """ 拷贝 """
241         'Return a shallow copy.'
242         return self.__class__(self)
243 
244     def __reduce__(self):
245         """ 返回一个元组(类型,元组) """
246         return self.__class__, (dict(self),)
247 
248     def __delitem__(self, elem):
249         """ 删除元素 """
250         'Like dict.__delitem__() but does not raise KeyError for missing values.'
251         if elem in self:
252             super(Counter, self).__delitem__(elem)
253 
254     def __repr__(self):
255         if not self:
256             return '%s()' % self.__class__.__name__
257         items = ', '.join(map('%r: %r'.__mod__, self.most_common()))
258         return '%s({%s})' % (self.__class__.__name__, items)
259 
260     # Multiset-style mathematical operations discussed in:
261     #       Knuth TAOCP Volume II section 4.6.3 exercise 19
262     #       and at http://en.wikipedia.org/wiki/Multiset
263     #
264     # Outputs guaranteed to only include positive counts.
265     #
266     # To strip negative and zero counts, add-in an empty counter:
267     #       c += Counter()
268 
269     def __add__(self, other):
270         '''Add counts from two counters.
271 
272         >>> Counter('abbb') + Counter('bcc')
273         Counter({'b': 4, 'c': 2, 'a': 1})
274 
275         '''
276         if not isinstance(other, Counter):
277             return NotImplemented
278         result = Counter()
279         for elem, count in self.items():
280             newcount = count + other[elem]
281             if newcount > 0:
282                 result[elem] = newcount
283         for elem, count in other.items():
284             if elem not in self and count > 0:
285                 result[elem] = count
286         return result
287 
288     def __sub__(self, other):
289         ''' Subtract count, but keep only results with positive counts.
290 
291         >>> Counter('abbbc') - Counter('bccd')
292         Counter({'b': 2, 'a': 1})
293 
294         '''
295         if not isinstance(other, Counter):
296             return NotImplemented
297         result = Counter()
298         for elem, count in self.items():
299             newcount = count - other[elem]
300             if newcount > 0:
301                 result[elem] = newcount
302         for elem, count in other.items():
303             if elem not in self and count < 0:
304                 result[elem] = 0 - count
305         return result
306 
307     def __or__(self, other):
308         '''Union is the maximum of value in either of the input counters.
309 
310         >>> Counter('abbb') | Counter('bcc')
311         Counter({'b': 3, 'c': 2, 'a': 1})
312 
313         '''
314         if not isinstance(other, Counter):
315             return NotImplemented
316         result = Counter()
317         for elem, count in self.items():
318             other_count = other[elem]
319             newcount = other_count if count < other_count else count
320             if newcount > 0:
321                 result[elem] = newcount
322         for elem, count in other.items():
323             if elem not in self and count > 0:
324                 result[elem] = count
325         return result
326 
327     def __and__(self, other):
328         ''' Intersection is the minimum of corresponding counts.
329 
330         >>> Counter('abbb') & Counter('bcc')
331         Counter({'b': 1})
332 
333         '''
334         if not isinstance(other, Counter):
335             return NotImplemented
336         result = Counter()
337         for elem, count in self.items():
338             other_count = other[elem]
339             newcount = count if count < other_count else other_count
340             if newcount > 0:
341                 result[elem] = newcount
342         return result
collections.Counter

也可以传入列表或元组

1 >>> li = [11,22,33,44,11,22,22]
2 >>> c1 = collections.Counter(li)
3 >>> c1
4 Counter({22: 3, 11: 2, 33: 1, 44: 1})
5 >>> 

 2、有序字典(orderedDict)

orderedDict是对字典类型的补充,他记住了字典元素添加的顺序

有序字典和原生字典的使用完全一样

唯一的区别,orderedDict在内部做了一个排序,它其实是在内部维护一个列表,因为列表是有序的

  1 class OrderedDict(dict):
  2     'Dictionary that remembers insertion order'
  3     # An inherited dict maps keys to values.
  4     # The inherited dict provides __getitem__, __len__, __contains__, and get.
  5     # The remaining methods are order-aware.
  6     # Big-O running times for all methods are the same as regular dictionaries.
  7 
  8     # The internal self.__map dict maps keys to links in a doubly linked list.
  9     # The circular doubly linked list starts and ends with a sentinel element.
 10     # The sentinel element never gets deleted (this simplifies the algorithm).
 11     # Each link is stored as a list of length three:  [PREV, NEXT, KEY].
 12 
 13     def __init__(self, *args, **kwds):
 14         '''Initialize an ordered dictionary.  The signature is the same as
 15         regular dictionaries, but keyword arguments are not recommended because
 16         their insertion order is arbitrary.
 17 
 18         '''
 19         if len(args) > 1:
 20             raise TypeError('expected at most 1 arguments, got %d' % len(args))
 21         try:
 22             self.__root
 23         except AttributeError:
 24             self.__root = root = []                     # sentinel node
 25             root[:] = [root, root, None]
 26             self.__map = {}
 27         self.__update(*args, **kwds)
 28 
 29     def __setitem__(self, key, value, dict_setitem=dict.__setitem__):
 30         'od.__setitem__(i, y) <==> od[i]=y'
 31         # Setting a new item creates a new link at the end of the linked list,
 32         # and the inherited dictionary is updated with the new key/value pair.
 33         if key not in self:
 34             root = self.__root
 35             last = root[0]
 36             last[1] = root[0] = self.__map[key] = [last, root, key]
 37         return dict_setitem(self, key, value)
 38 
 39     def __delitem__(self, key, dict_delitem=dict.__delitem__):
 40         'od.__delitem__(y) <==> del od[y]'
 41         # Deleting an existing item uses self.__map to find the link which gets
 42         # removed by updating the links in the predecessor and successor nodes.
 43         dict_delitem(self, key)
 44         link_prev, link_next, _ = self.__map.pop(key)
 45         link_prev[1] = link_next                        # update link_prev[NEXT]
 46         link_next[0] = link_prev                        # update link_next[PREV]
 47 
 48     def __iter__(self):
 49         'od.__iter__() <==> iter(od)'
 50         # Traverse the linked list in order.
 51         root = self.__root
 52         curr = root[1]                                  # start at the first node
 53         while curr is not root:
 54             yield curr[2]                               # yield the curr[KEY]
 55             curr = curr[1]                              # move to next node
 56 
 57     def __reversed__(self):
 58         'od.__reversed__() <==> reversed(od)'
 59         # Traverse the linked list in reverse order.
 60         root = self.__root
 61         curr = root[0]                                  # start at the last node
 62         while curr is not root:
 63             yield curr[2]                               # yield the curr[KEY]
 64             curr = curr[0]                              # move to previous node
 65 
 66     def clear(self):
 67         'od.clear() -> None.  Remove all items from od.'
 68         root = self.__root
 69         root[:] = [root, root, None]
 70         self.__map.clear()
 71         dict.clear(self)
 72 
 73     # -- the following methods do not depend on the internal structure --
 74 
 75     def keys(self):
 76         'od.keys() -> list of keys in od'
 77         return list(self)
 78 
 79     def values(self):
 80         'od.values() -> list of values in od'
 81         return [self[key] for key in self]
 82 
 83     def items(self):
 84         'od.items() -> list of (key, value) pairs in od'
 85         return [(key, self[key]) for key in self]
 86 
 87     def iterkeys(self):
 88         'od.iterkeys() -> an iterator over the keys in od'
 89         return iter(self)
 90 
 91     def itervalues(self):
 92         'od.itervalues -> an iterator over the values in od'
 93         for k in self:
 94             yield self[k]
 95 
 96     def iteritems(self):
 97         'od.iteritems -> an iterator over the (key, value) pairs in od'
 98         for k in self:
 99             yield (k, self[k])
100 
101     update = MutableMapping.update
102 
103     __update = update # let subclasses override update without breaking __init__
104 
105     __marker = object()
106 
107     def pop(self, key, default=__marker):
108         '''od.pop(k[,d]) -> v, remove specified key and return the corresponding
109         value.  If key is not found, d is returned if given, otherwise KeyError
110         is raised.
111 
112         '''
113         if key in self:
114             result = self[key]
115             del self[key]
116             return result
117         if default is self.__marker:
118             raise KeyError(key)
119         return default
120 
121     def setdefault(self, key, default=None):
122         'od.setdefault(k[,d]) -> od.get(k,d), also set od[k]=d if k not in od'
123         if key in self:
124             return self[key]
125         self[key] = default
126         return default
127 
128     def popitem(self, last=True):
129         '''od.popitem() -> (k, v), return and remove a (key, value) pair.
130         Pairs are returned in LIFO order if last is true or FIFO order if false.
131 
132         '''
133         if not self:
134             raise KeyError('dictionary is empty')
135         key = next(reversed(self) if last else iter(self))
136         value = self.pop(key)
137         return key, value
138 
139     def __repr__(self, _repr_running={}):
140         'od.__repr__() <==> repr(od)'
141         call_key = id(self), _get_ident()
142         if call_key in _repr_running:
143             return '...'
144         _repr_running[call_key] = 1
145         try:
146             if not self:
147                 return '%s()' % (self.__class__.__name__,)
148             return '%s(%r)' % (self.__class__.__name__, self.items())
149         finally:
150             del _repr_running[call_key]
151 
152     def __reduce__(self):
153         'Return state information for pickling'
154         items = [[k, self[k]] for k in self]
155         inst_dict = vars(self).copy()
156         for k in vars(OrderedDict()):
157             inst_dict.pop(k, None)
158         if inst_dict:
159             return (self.__class__, (items,), inst_dict)
160         return self.__class__, (items,)
161 
162     def copy(self):
163         'od.copy() -> a shallow copy of od'
164         return self.__class__(self)
165 
166     @classmethod
167     def fromkeys(cls, iterable, value=None):
168         '''OD.fromkeys(S[, v]) -> New ordered dictionary with keys from S.
169         If not specified, the value defaults to None.
170 
171         '''
172         self = cls()
173         for key in iterable:
174             self[key] = value
175         return self
176 
177     def __eq__(self, other):
178         '''od.__eq__(y) <==> od==y.  Comparison to another OD is order-sensitive
179         while comparison to a regular mapping is order-insensitive.
180 
181         '''
182         if isinstance(other, OrderedDict):
183             return dict.__eq__(self, other) and all(_imap(_eq, self, other))
184         return dict.__eq__(self, other)
185 
186     def __ne__(self, other):
187         'od.__ne__(y) <==> od!=y'
188         return not self == other
189 
190     # -- the following methods support python 3.x style dictionary views --
191 
192     def viewkeys(self):
193         "od.viewkeys() -> a set-like object providing a view on od's keys"
194         return KeysView(self)
195 
196     def viewvalues(self):
197         "od.viewvalues() -> an object providing a view on od's values"
198         return ValuesView(self)
199 
200     def viewitems(self):
201         "od.viewitems() -> a set-like object providing a view on od's items"
202         return ItemsView(self)
203 
204 OrderedDict
orderedDict

3、默认字典(defaultdict)

学习需求:

'''
将一个数字列表分割成字典,'k1'的值为小于66的值,'k2'的值为大于66的值

li =  [11,22,33,44,55,66,77,88,99,90]
'''
 1 li =  [11,22,33,44,55,66,77,88,99,90]
 2 dic = {}
 3 for ele in li:
 4     if ele < 66:
 5         if 'k1' in dic.keys():
 6             dic['k1'].append(ele)
 7         else:
 8             #创建只有一个元素的列表
 9             dic['k1'] = [ele,]
10     else:
11         if 'k2' in dic.keys():
12             dic['k2'].append(ele);
13         else:
14             dic['k2'] = [ele,]
原生字典
1 from collections import Counter,defaultdict;
2 li = [11,22,33,44,55,66,77,88,99,90,87]
3 my_dic = defaultdict(list)
4 for ele in li:
5     if ele > 66:
6         my_dic['k2'].append(ele)
7     else:
8         my_dic['k1'].append(ele)
默认字典

defaultdict是对字典类型的补充,他默认给字典的值设置了一个类型,字典默认的是None,可以给字典设置一个默认类型,比如列表,元组等

 1 class defaultdict(dict):
 2     """
 3     defaultdict(default_factory[, ...]) --> dict with default factory
 4     
 5     The default factory is called without arguments to produce
 6     a new value when a key is not present, in __getitem__ only.
 7     A defaultdict compares equal to a dict with the same items.
 8     All remaining arguments are treated the same as if they were
 9     passed to the dict constructor, including keyword arguments.
10     """
11     def copy(self): # real signature unknown; restored from __doc__
12         """ D.copy() -> a shallow copy of D. """
13         pass
14 
15     def __copy__(self, *args, **kwargs): # real signature unknown
16         """ D.copy() -> a shallow copy of D. """
17         pass
18 
19     def __getattribute__(self, name): # real signature unknown; restored from __doc__
20         """ x.__getattribute__('name') <==> x.name """
21         pass
22 
23     def __init__(self, default_factory=None, **kwargs): # known case of _collections.defaultdict.__init__
24         """
25         defaultdict(default_factory[, ...]) --> dict with default factory
26         
27         The default factory is called without arguments to produce
28         a new value when a key is not present, in __getitem__ only.
29         A defaultdict compares equal to a dict with the same items.
30         All remaining arguments are treated the same as if they were
31         passed to the dict constructor, including keyword arguments.
32         
33         # (copied from class doc)
34         """
35         pass
36 
37     def __missing__(self, key): # real signature unknown; restored from __doc__
38         """
39         __missing__(key) # Called by __getitem__ for missing key; pseudo-code:
40           if self.default_factory is None: raise KeyError((key,))
41           self[key] = value = self.default_factory()
42           return value
43         """
44         pass
45 
46     def __reduce__(self, *args, **kwargs): # real signature unknown
47         """ Return state information for pickling. """
48         pass
49 
50     def __repr__(self): # real signature unknown; restored from __doc__
51         """ x.__repr__() <==> repr(x) """
52         pass
53 
54     default_factory = property(lambda self: object(), lambda self, v: None, lambda self: None)  # default
55     """Factory for default value called by __missing__()."""
56 
57 defaultdict
defaultdict

4、可命名元组(namedtuple)

创建一个扩展tuple的类,Mytuple——类名

 1 #通过可命名元组创建一个类
 2 >>> Mytuple = collections.namedtuple('Mytuple',['x','y'])
 3 #通过这个类创建对象
 4 >>> new_tuple = Mytuple(1,2)
 5 >>> new_tuple
 6 Mytuple(x=1, y=2)
 7 #可以通过名称来调用
 8 >>> new_tuple.x
 9 1
10 >>> new_tuple.y
11 2
12 >>> old_tuple = ([1,2])       
13 >>> old_tuple
14 [1, 2]
15 >>> 
  1 class Mytuple(__builtin__.tuple)
  2  |  Mytuple(x, y)
  3  |  
  4  |  Method resolution order:
  5  |      Mytuple
  6  |      __builtin__.tuple
  7  |      __builtin__.object
  8  |  
  9  |  Methods defined here:
 10  |  
 11  |  __getnewargs__(self)
 12  |      Return self as a plain tuple.  Used by copy and pickle.
 13  |  
 14  |  __getstate__(self)
 15  |      Exclude the OrderedDict from pickling
 16  |  
 17  |  __repr__(self)
 18  |      Return a nicely formatted representation string
 19  |  
 20  |  _asdict(self)
 21  |      Return a new OrderedDict which maps field names to their values
 22  |  
 23  |  _replace(_self, **kwds)
 24  |      Return a new Mytuple object replacing specified fields with new values
 25  |  
 26  |  ----------------------------------------------------------------------
 27  |  Class methods defined here:
 28  |  
 29  |  _make(cls, iterable, new=<built-in method __new__ of type object>, len=<built-in function len>) from __builtin__.type
 30  |      Make a new Mytuple object from a sequence or iterable
 31  |  
 32  |  ----------------------------------------------------------------------
 33  |  Static methods defined here:
 34  |  
 35  |  __new__(_cls, x, y)
 36  |      Create new instance of Mytuple(x, y)
 37  |  
 38  |  ----------------------------------------------------------------------
 39  |  Data descriptors defined here:
 40  |  
 41  |  __dict__
 42  |      Return a new OrderedDict which maps field names to their values
 43  |  
 44  |  x
 45  |      Alias for field number 0
 46  |  
 47  |  y
 48  |      Alias for field number 1
 49  |  
 50  |  ----------------------------------------------------------------------
 51  |  Data and other attributes defined here:
 52  |  
 53  |  _fields = ('x', 'y')
 54  |  
 55  |  ----------------------------------------------------------------------
 56  |  Methods inherited from __builtin__.tuple:
 57  |  
 58  |  __add__(...)
 59  |      x.__add__(y) <==> x+y
 60  |  
 61  |  __contains__(...)
 62  |      x.__contains__(y) <==> y in x
 63  |  
 64  |  __eq__(...)
 65  |      x.__eq__(y) <==> x==y
 66  |  
 67  |  __ge__(...)
 68  |      x.__ge__(y) <==> x>=y
 69  |  
 70  |  __getattribute__(...)
 71  |      x.__getattribute__('name') <==> x.name
 72  |  
 73  |  __getitem__(...)
 74  |      x.__getitem__(y) <==> x[y]
 75  |  
 76  |  __getslice__(...)
 77  |      x.__getslice__(i, j) <==> x[i:j]
 78  |      
 79  |      Use of negative indices is not supported.
 80  |  
 81  |  __gt__(...)
 82  |      x.__gt__(y) <==> x>y
 83  |  
 84  |  __hash__(...)
 85  |      x.__hash__() <==> hash(x)
 86  |  
 87  |  __iter__(...)
 88  |      x.__iter__() <==> iter(x)
 89  |  
 90  |  __le__(...)
 91  |      x.__le__(y) <==> x<=y
 92  |  
 93  |  __len__(...)
 94  |      x.__len__() <==> len(x)
 95  |  
 96  |  __lt__(...)
 97  |      x.__lt__(y) <==> x<y
 98  |  
 99  |  __mul__(...)
100  |      x.__mul__(n) <==> x*n
101  |  
102  |  __ne__(...)
103  |      x.__ne__(y) <==> x!=y
104  |  
105  |  __rmul__(...)
106  |      x.__rmul__(n) <==> n*x
107  |  
108  |  __sizeof__(...)
109  |      T.__sizeof__() -- size of T in memory, in bytes
110  |  
111  |  count(...)
112  |      T.count(value) -> integer -- return number of occurrences of value
113  |  
114  |  index(...)
115  |      T.index(value, [start, [stop]]) -> integer -- return first index of value.
116  |      Raises ValueError if the value is not present.
Mytuple class

5、双向队列(deque)

两边都可以取,两边都可以插入,这就有一个线程安全的问题,谁先得到就会有一个线程锁,防止抢占资源

一个线程安全的双向队列

  1 class deque(object):
  2     """
  3     deque([iterable[, maxlen]]) --> deque object
  4     
  5     Build an ordered collection with optimized access from its endpoints.
  6     """
  7     def append(self, *args, **kwargs): # real signature unknown
  8         """ 追加元素到队列 
  9         >>> q = collections.deque()
 10         >>> q.append(1)
 11         >>> q.append(11)
 12         >>> q.append(111)
 13         >>> q.append(1111)
 14         >>> q
 15         deque([1, 11, 111, 1111])
 16         >>>
 17         """
 18         """ Add an element to the right side of the deque. """
 19         pass
 20 
 21     def appendleft(self, *args, **kwargs): # real signature unknown
 22         """ 加入元素到队列的左边
 23         >>> q
 24         deque([1, 11, 111])
 25         >>> q.appendleft(2)
 26         >>> q
 27         deque([2, 1, 11, 111])
 28         >>> 
 29         """
 30         """ Add an element to the left side of the deque. """
 31         pass
 32 
 33     def clear(self, *args, **kwargs): # real signature unknown
 34         """ 清除队列中所有元素
 35         >>> q
 36         deque([2, 2, 1, 11, 111])
 37         >>> q.clear()
 38         >>> q
 39         deque([])
 40         >>> 
 41         """
 42         """ Remove all elements from the deque. """
 43         pass
 44 
 45     def count(self, value): # real signature unknown; restored from __doc__
 46         """ 计算元素的个数
 47         >>> q
 48         deque([2, 1, 11, 111])
 49         >>> q.count(2)
 50         1
 51         >>> q.appendleft(2)
 52         >>> q.count(2)     
 53         2
 54         >>> q
 55         deque([2, 2, 1, 11, 111])
 56         >>> 
 57         """
 58         """ D.count(value) -> integer -- return number of occurrences of value """
 59         return 0
 60 
 61     def extend(self, *args, **kwargs): # real signature unknown
 62         """ 扩展队列从一个迭代器中
 63         >>> q
 64         deque([])
 65         >>> li = [11,22,33,44,55]
 66         >>> q.extend(li)
 67         >>> q
 68         deque([11, 22, 33, 44, 55])
 69         >>> 
 70         """
 71         """ Extend the right side of the deque with elements from the iterable """
 72         pass
 73 
 74     def extendleft(self, *args, **kwargs): # real signature unknown
 75         """ 从队列左边扩展元素
 76         >>> q
 77         deque([11, 22, 33, 44, 55])
 78         >>> lileft = (1,2,3,4,5)
 79         >>> q.extendleft(lileft)
 80         >>> q
 81         deque([5, 4, 3, 2, 1, 11, 22, 33, 44, 55])
 82         >>> 
 83         """
 84         """ Extend the left side of the deque with elements from the iterable """
 85         pass
 86 
 87     def pop(self, *args, **kwargs): # real signature unknown
 88         """移除队列最后一个元素并取得
 89         >>> q = collections.deque()
 90         >>> q.append(1)
 91         >>> q.append(11)
 92         >>> q.append(111)
 93         >>> q.append(1111)
 94         >>> q
 95         deque([1, 11, 111, 1111])
 96         >>> a = q.pop()
 97         >>> a
 98         1111
 99         >>> q
100         deque([1, 11, 111])
101         >>> 
102         """
103         """ Remove and return the rightmost element. """
104         pass
105 
106     def popleft(self, *args, **kwargs): # real signature unknown
107         """ 从队列左边移除一个元素并取得
108         >>> q
109         deque([5, 4, 3, 2, 1, 11, 22, 33, 44, 55])
110         >>> b = q.popleft()
111         >>> b
112         5
113         >>> 
114         """
115         """ Remove and return the leftmost element. """
116         pass
117 
118     def remove(self, value): # real signature unknown; restored from __doc__
119         """ 移除第一个被找到的值,如果没有,会抛出异常
120         >>> q
121         deque([4, 3, 2, 1, 11, 22, 33, 44, 55])
122         >>> q.remove(5)
123         Traceback (most recent call last):
124           File "<stdin>", line 1, in <module>
125         ValueError: deque.remove(x): x not in deque
126         >>> q.remove(4)
127         >>> q
128         deque([3, 2, 1, 11, 22, 33, 44, 55])
129         >>> 
130         """
131         """ D.remove(value) -- remove first occurrence of value. """
132         pass
133 
134     def reverse(self): # real signature unknown; restored from __doc__
135         """ 反转队列
136         >>> q
137         deque([3, 2, 1, 11, 22, 33, 44, 55])
138         >>> q.reverse()
139         >>> q
140         deque([55, 44, 33, 22, 11, 1, 2, 3])
141         >>> 
142         """
143         """ D.reverse() -- reverse *IN PLACE* """
144         pass
145 
146     def rotate(self, *args, **kwargs): # real signature unknown
147         """ 从右边移动值到左边,默认移动一个
148         >>> q
149         deque([55, 44, 33, 22, 11, 1, 2, 3])
150         >>> q.rotate()
151         >>> q
152         deque([3, 55, 44, 33, 22, 11, 1, 2])
153         >>> q.rotate(2)
154         >>> q
155         deque([1, 2, 3, 55, 44, 33, 22, 11])
156         >>> q.rotate(2)
157         >>> q
158         deque([22, 11, 1, 2, 3, 55, 44, 33])
159         >>> 
160         """
161         """ Rotate the deque n steps to the right (default n=1).  If n is negative, rotates left. """
162         pass
163 
164     def __copy__(self, *args, **kwargs): # real signature unknown
165         """ Return a shallow copy of a deque. """
166         pass
167 
168     def __delitem__(self, y): # real signature unknown; restored from __doc__
169         """ x.__delitem__(y) <==> del x[y] """
170         pass
171 
172     def __eq__(self, y): # real signature unknown; restored from __doc__
173         """ x.__eq__(y) <==> x==y """
174         pass
175 
176     def __getattribute__(self, name): # real signature unknown; restored from __doc__
177         """ x.__getattribute__('name') <==> x.name """
178         pass
179 
180     def __getitem__(self, y): # real signature unknown; restored from __doc__
181         """ x.__getitem__(y) <==> x[y] """
182         pass
183 
184     def __ge__(self, y): # real signature unknown; restored from __doc__
185         """ x.__ge__(y) <==> x>=y """
186         pass
187 
188     def __gt__(self, y): # real signature unknown; restored from __doc__
189         """ x.__gt__(y) <==> x>y """
190         pass
191 
192     def __iadd__(self, y): # real signature unknown; restored from __doc__
193         """ x.__iadd__(y) <==> x+=y """
194         pass
195 
196     def __init__(self, iterable=(), maxlen=None): # known case of _collections.deque.__init__
197         """
198         deque([iterable[, maxlen]]) --> deque object
199         
200         Build an ordered collection with optimized access from its endpoints.
201         # (copied from class doc)
202         """
203         pass
204 
205     def __iter__(self): # real signature unknown; restored from __doc__
206         """ x.__iter__() <==> iter(x) """
207         pass
208 
209     def __len__(self): # real signature unknown; restored from __doc__
210         """ x.__len__() <==> len(x) """
211         pass
212 
213     def __le__(self, y): # real signature unknown; restored from __doc__
214         """ x.__le__(y) <==> x<=y """
215         pass
216 
217     def __lt__(self, y): # real signature unknown; restored from __doc__
218         """ x.__lt__(y) <==> x<y """
219         pass
220 
221     @staticmethod # known case of __new__
222     def __new__(S, *more): # real signature unknown; restored from __doc__
223         """ T.__new__(S, ...) -> a new object with type S, a subtype of T """
224         pass
225 
226     def __ne__(self, y): # real signature unknown; restored from __doc__
227         """ x.__ne__(y) <==> x!=y """
228         pass
229 
230     def __reduce__(self, *args, **kwargs): # real signature unknown
231         """ Return state information for pickling. """
232         pass
233 
234     def __repr__(self): # real signature unknown; restored from __doc__
235         """ x.__repr__() <==> repr(x) """
236         pass
237 
238     def __reversed__(self): # real signature unknown; restored from __doc__
239         """ D.__reversed__() -- return a reverse iterator over the deque """
240         pass
241 
242     def __setitem__(self, i, y): # real signature unknown; restored from __doc__
243         """ x.__setitem__(i, y) <==> x[i]=y """
244         pass
245 
246     def __sizeof__(self): # real signature unknown; restored from __doc__
247         """ D.__sizeof__() -- size of D in memory, in bytes """
248         pass
249 
250     maxlen = property(lambda self: object(), lambda self, v: None, lambda self: None)  # default
251     """maximum size of a deque or None if unbounded"""
252 
253 
254     __hash__ = None
deque

6、单向队列(Queue.Queue)——先进先出(FIFO(First In First Out))

队列:先进先出 FIFO

栈:先进后出 弹夹

 1 #创建一个最多十个内容的队列
 2 >>> q = Queue.Queue(10)
 3 >>> q
 4 <Queue.Queue instance at 0x7f82028390e0>
 5 #给队列放值,用put
 6 >>> q.put(1)
 7 >>> q.put(2)
 8 >>> q.put(3) 
 9 #取值用get,get取值是阻塞的
10 >>> q.get()
11 1
12 >>> q.get()
13 2
14 >>> q.get()
15 3
16 #当取完后,再取就会阻塞住,直到队列中有值才继续
17 >>> q.get()  
  1 class Queue:
  2     """Create a queue object with a given maximum size.
  3 
  4     If maxsize is <= 0, the queue size is infinite.
  5     """
  6     def __init__(self, maxsize=0):
  7         self.maxsize = maxsize
  8         self._init(maxsize)
  9         # mutex must be held whenever the queue is mutating.  All methods
 10         # that acquire mutex must release it before returning.  mutex
 11         # is shared between the three conditions, so acquiring and
 12         # releasing the conditions also acquires and releases mutex.
 13         self.mutex = _threading.Lock()
 14         # Notify not_empty whenever an item is added to the queue; a
 15         # thread waiting to get is notified then.
 16         self.not_empty = _threading.Condition(self.mutex)
 17         # Notify not_full whenever an item is removed from the queue;
 18         # a thread waiting to put is notified then.
 19         self.not_full = _threading.Condition(self.mutex)
 20         # Notify all_tasks_done whenever the number of unfinished tasks
 21         # drops to zero; thread waiting to join() is notified to resume
 22         self.all_tasks_done = _threading.Condition(self.mutex)
 23         self.unfinished_tasks = 0
 24 
 25     def task_done(self):
 26         """Indicate that a formerly enqueued task is complete.
 27 
 28         Used by Queue consumer threads.  For each get() used to fetch a task,
 29         a subsequent call to task_done() tells the queue that the processing
 30         on the task is complete.
 31 
 32         If a join() is currently blocking, it will resume when all items
 33         have been processed (meaning that a task_done() call was received
 34         for every item that had been put() into the queue).
 35 
 36         Raises a ValueError if called more times than there were items
 37         placed in the queue.
 38         """
 39         self.all_tasks_done.acquire()
 40         try:
 41             unfinished = self.unfinished_tasks - 1
 42             if unfinished <= 0:
 43                 if unfinished < 0:
 44                     raise ValueError('task_done() called too many times')
 45                 self.all_tasks_done.notify_all()
 46             self.unfinished_tasks = unfinished
 47         finally:
 48             self.all_tasks_done.release()
 49 
 50     def join(self):
 51         """Blocks until all items in the Queue have been gotten and processed.
 52 
 53         The count of unfinished tasks goes up whenever an item is added to the
 54         queue. The count goes down whenever a consumer thread calls task_done()
 55         to indicate the item was retrieved and all work on it is complete.
 56 
 57         When the count of unfinished tasks drops to zero, join() unblocks.
 58         """
 59         self.all_tasks_done.acquire()
 60         try:
 61             while self.unfinished_tasks:
 62                 self.all_tasks_done.wait()
 63         finally:
 64             self.all_tasks_done.release()
 65 
 66     def qsize(self):
 67         """Return the approximate size of the queue (not reliable!)."""
 68         self.mutex.acquire()
 69         n = self._qsize()
 70         self.mutex.release()
 71         return n
 72 
 73     def empty(self):
 74         """Return True if the queue is empty, False otherwise (not reliable!)."""
 75         self.mutex.acquire()
 76         n = not self._qsize()
 77         self.mutex.release()
 78         return n
 79 
 80     def full(self):
 81         """Return True if the queue is full, False otherwise (not reliable!)."""
 82         self.mutex.acquire()
 83         n = 0 < self.maxsize == self._qsize()
 84         self.mutex.release()
 85         return n
 86 
 87     def put(self, item, block=True, timeout=None):
 88         """Put an item into the queue.
 89 
 90         If optional args 'block' is true and 'timeout' is None (the default),
 91         block if necessary until a free slot is available. If 'timeout' is
 92         a non-negative number, it blocks at most 'timeout' seconds and raises
 93         the Full exception if no free slot was available within that time.
 94         Otherwise ('block' is false), put an item on the queue if a free slot
 95         is immediately available, else raise the Full exception ('timeout'
 96         is ignored in that case).
 97         """
 98         self.not_full.acquire()
 99         try:
100             if self.maxsize > 0:
101                 if not block:
102                     if self._qsize() == self.maxsize:
103                         raise Full
104                 elif timeout is None:
105                     while self._qsize() == self.maxsize:
106                         self.not_full.wait()
107                 elif timeout < 0:
108                     raise ValueError("'timeout' must be a non-negative number")
109                 else:
110                     endtime = _time() + timeout
111                     while self._qsize() == self.maxsize:
112                         remaining = endtime - _time()
113                         if remaining <= 0.0:
114                             raise Full
115                         self.not_full.wait(remaining)
116             self._put(item)
117             self.unfinished_tasks += 1
118             self.not_empty.notify()
119         finally:
120             self.not_full.release()
121 
122     def put_nowait(self, item):
123         """Put an item into the queue without blocking.
124 
125         Only enqueue the item if a free slot is immediately available.
126         Otherwise raise the Full exception.
127         """
128         return self.put(item, False)
129 
130     def get(self, block=True, timeout=None):
131         """Remove and return an item from the queue.
132 
133         If optional args 'block' is true and 'timeout' is None (the default),
134         block if necessary until an item is available. If 'timeout' is
135         a non-negative number, it blocks at most 'timeout' seconds and raises
136         the Empty exception if no item was available within that time.
137         Otherwise ('block' is false), return an item if one is immediately
138         available, else raise the Empty exception ('timeout' is ignored
139         in that case).
140         """
141         self.not_empty.acquire()
142         try:
143             if not block:
144                 if not self._qsize():
145                     raise Empty
146             elif timeout is None:
147                 while not self._qsize():
148                     self.not_empty.wait()
149             elif timeout < 0:
150                 raise ValueError("'timeout' must be a non-negative number")
151             else:
152                 endtime = _time() + timeout
153                 while not self._qsize():
154                     remaining = endtime - _time()
155                     if remaining <= 0.0:
156                         raise Empty
157                     self.not_empty.wait(remaining)
158             item = self._get()
159             self.not_full.notify()
160             return item
161         finally:
162             self.not_empty.release()
163 
164     def get_nowait(self):
165         """Remove and return an item from the queue without blocking.
166 
167         Only get an item if one is immediately available. Otherwise
168         raise the Empty exception.
169         """
170         return self.get(False)
171 
172     # Override these methods to implement other queue organizations
173     # (e.g. stack or priority queue).
174     # These will only be called with appropriate locks held
175 
176     # Initialize the queue representation
177     def _init(self, maxsize):
178         self.queue = deque()
179 
180     def _qsize(self, len=len):
181         return len(self.queue)
182 
183     # Put a new item in the queue
184     def _put(self, item):
185         self.queue.append(item)
186 
187     # Get an item from the queue
188     def _get(self):
189         return self.queue.popleft()
Queue.Queue

双向队列和单向队列的区别

双向队列是两边都可以插入数据和读取数据,单向队列只能从一边取和插
双向队列是在collections模块中,单向队列是在Queue模块中
都是线程安全的

会通过help方法找到collections,大致知道计算器、有序字典、默认字典、可命名元组和双向队列

迭代器和生成器

 一、迭代器

对于python列表的for循环,他的内部原理:查看下一个元素是否存在,如果存在,则取出,如果不存在,则报异常StopIteration。(python内部对异常已处理)

1 >>> c
2 Counter({'d': 4, 's': 4, 'a': 2, 'c': 2, 'b': 2, 'e': 2, 'f': 2, 'g': 1})
3 >>> c.elements()
4 <itertools.chain object at 0x7f4424b59890>
5 >>> 

迭代器的内容要用循环取出来

 1 class listiterator(object)
 2  |  Methods defined here:
 3  |  
 4  |  __getattribute__(...)
 5  |      x.__getattribute__('name') <==> x.name
 6  |  
 7  |  __iter__(...)
 8  |      x.__iter__() <==> iter(x)
 9  |  
10  |  __length_hint__(...)
11  |      Private method returning an estimate of len(list(it)).
12  |  
13  |  next(...)
14  |      x.next() -> the next value, or raise StopIteration
listiterator

二、生成器

range不是生成器 xrange是生成器

redlines不是生成器 xreadlines是生成器

1 >>> print range(10)
2 [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
3 >>> print xrange(10)
4 xrange(10)
5 >>>

xrange(10)创建时只是一个对象,只有在循环或使用时才会在内存中开辟空间
生成器内部基于yield创建,即:对于生成器只有使用时才创建,从而避免内存浪费

练习:有如下列表:
    [13, 22, 6, 99, 11]
利用列表的下标进行循环

>>> li
[13, 22, 6, 99, 11]
>>> i = 0
>>> while i < len(li):
...   print li[i]
...   i += 1
... 
13
22
6
99
11
练习:有如下列表:
    [13, 22, 6, 99, 11]
 
请按照一下规则计算:
13 和 22 比较,将大的值放在右侧,即:[13, 22, 6, 99, 11]
22 和 6 比较,将大的值放在右侧,即:[13, 6, 22, 99, 11]
22 和 99 比较,将大的值放在右侧,即:[13, 6, 22, 99, 11]
99 和 42 比较,将大的值放在右侧,即:[13, 6, 22, 11, 99,]
 
13 和 6 比较,将大的值放在右侧,即:[6, 13, 22, 11, 99,]
...
 1 #!/usr/bin/env python
 2 # _*_ coding:utf-8 _*_
 3 li = [12, 33, 6, 99, 11]
 4 '''
 5 方法一:第一种方法是固定一个数a与后面的数b相比,如果a大于b,就把a\b对调,再用a和下面的一个数比,全部比完后会得到一个最小的数放在最左面,然后用第二个数继续往下比,以此类推就得到了从小到大的排序
 6 '''
 7 for i in range(len(li) - 1):
 8     for j in range(i+1,len(li)):
 9         if li[i] > li[j]:
10             temp = li[i];
11             li[i] = li[j]
12             li[j] = temp
13 
14 print li
15 
16 '''
17 方法二:两个相邻的数比较,如果左边的数比右边的大,就调换位置,一个循环后会把最大的数放在最右边,以此类推,所有数字都循环完后会得到从小到大的排序
18 '''
19 for x in range(len(li)):
20     for i in range(len(li)-1):
21         if li[i] > li[i+1]:
22             t = li[i];
23             li[i] = li[i+1];
24             li[i+1] = t
25 print li;
冒泡排序

函数

函数分为内置函数、自定义函数、导入函数。函数就是按功能划分的代码块

一、内置函数

内置函数就是python为用户提供的快捷方法

 先看几个常用的

help()函数可以得到方法的一些帮助

 1 >>> help(list)
 2 Help on class list in module __builtin__:
 3 
 4 class list(object)
 5  |  list() -> new empty list
 6  |  list(iterable) -> new list initialized from iterable's items
 7  |  
 8  |  Methods defined here:
 9  |  
10  |  __add__(...)
11  |      x.__add__(y) <==> x+y
12  |  
13  |  __contains__(...)
14  |      x.__contains__(y) <==> y in x
15  |  
16  |  __delitem__(...)
17  |      x.__delitem__(y) <==> del x[y]
18  |  
19  |  __delslice__(...)
20  |      x.__delslice__(i, j) <==> del x[i:j]
21  |      
22  |      Use of negative indices is not supported.
help(list)

dir()可以把一个类的方法全部打印出来

1 >>> dir(list)
2 ['__add__', '__class__', '__contains__', '__delattr__', '__delitem__', '__delslice__', '__doc__', '__eq__', '__format__', '__ge__', '__getattribute__', '__getitem__', '__getslice__', '__gt__', '__hash__', '__iadd__', '__imul__', '__init__', '__iter__', '__le__', '__len__', '__lt__', '__mul__', '__ne__', '__new__', '__reduce__', '__reduce_ex__', '__repr__', '__reversed__', '__rmul__', '__setattr__', '__setitem__', '__setslice__', '__sizeof__', '__str__', '__subclasshook__', 'append', 'count', 'extend', 'index', 'insert', 'pop', 'remove', 'reverse', 'sort']
3 >>> 
dir(list)

vars()可以显示出所有的变量

1 >>> vars()
2 {'a': xrange(10), 'c': Counter({'d': 4, 's': 4, 'a': 2, 'c': 2, 'b': 2, 'e': 2, 'f': 2, 'g': 1}), '__builtins__': <module '__builtin__' (built-in)>, '__package__': None, 'i': 1, 'collections': <module 'collections' from '/usr/lib/python2.7/collections.pyc'>, 'tab': <module 'tab' from '/usr/lib/python2.7/dist-packages/tab.pyc'>, '__name__': '__main__', 'li': [13, 22, 6, 99, 11], '__doc__': None}
3 >>> 
vars()

type()查看变量的类型

>>> type(li)
<type 'list'>
>>> 

abc()取绝对值

>>> abs(-9)
9
>>> abs(0)
0
>>> abs(33)
33
>>> 

divmod()输入两个数字,得到一个元组(商、余数)

>>> divmod(10,3)
(3, 1)
>>> divmod(10,2)
(5, 0)
>>> 

 ord()输入一个字符,返回ASCII

>>> ord('a')
97
>>> 

 chr()输入ASCII,返回字符

>>> chr(100)
'd'
>>>

 cmp()比较两个数大小,大于返回1,小于返回-1,等于返回0

>>> cmp(20,2)
1
>>> cmp(20,20)
0
>>> cmp(20,21)
-1
>>> 

 eval()可以计算一个字符串的值

>>> eval('200/4+4')
54
>>> 

 format()格式化输出字符串

>>> a = 'I am a {0},hello {1}'
>>> print a.format('techer','world')
I am a techer,hello world
>>> 

 hex(x)转换成十六进制

>>> hex(255)
'0xff'
>>> 

 id()返回对象的内存地址

>>> a = 20
>>> id(a)
22802320
>>> 

 input()输入内容

 1 #input接收到的是输入的是什么就是什么类型,比如输入22,那么a类型就是数值类型
 2 >>> a = input()
 3 22
 4 >>> type(a)
 5 <type 'int'>
 6 #输入一个hello,接收到的就是一个变量名,根据下面的异常提示也可以知道
 7 >>> a = input()
 8 hello
 9 Traceback (most recent call last):
10   File "<stdin>", line 1, in <module>
11   File "<string>", line 1, in <module>
12 NameError: name 'hello' is not defined
13 #如果想得到一个字符串,输入的时候要加引号
14 >>> a = input()
15 'hello'
16 >>> type(a)
17 <type 'str'>
18 >>> 
input

int()输入一个数字,转换成整型,字符串不能是小数形式的

>>> a = '22'
>>> type(a)
<type 'str'>
>>> b = int(a)
>>> type(b)
<type 'int'>
>>> b
22
>>> 

 len()计算长度

>>> li 
[13, 22, 6, 99, 11]
>>> len(li)
5
>>> s = 'hello world'
>>> len(s)
11
>>> 

 max()找出最大值

>>> a = 22
>>> b = 33
>>> c = 21
>>> max(a,b,c)
33
>>> 

 min()找出最小值

>>> a,b,c
(22, 33, 21)
>>> min(a,b,c)
21
>>> t = (11,111,1111)
>>> min(t)
11
>>> 

 oct()转换成八进制

>>> a = 100
>>> oct(a)
'0144'
>>> 

 pow()求幂

>>> pow(2,2)   
4
>>> pow(2,10)  
1024
>>> 

 range()生成一个连续的数字序列

>>> range(5)
[0, 1, 2, 3, 4]
>>> range(2,8)
[2, 3, 4, 5, 6, 7]
>>> 

 raw_input()接收终端输入的内容

>>> a = raw_input()
hello
>>> a
'hello'
>>> a = raw_input()
33
>>> a
'33'
>>> 

 reload(module)重新导入模块

如果一个模块已经导入,修改过这个模块后需要重新导入,就需要用reload重新导入

sum()计算一个数字序列的和

>>> sum([1,2,3])
6
>>> 

 all()如果里面有空值,就返回False

>>> a = [1,2,3,'']
>>> all(a)
False
>>> a = [1,2,3,'a']
>>> all(a)         
True
>>> 

 any()只要有一个是真就是真

>>> a = []
>>> any(a)
False
>>> a = [1,2,'']
>>> any(a)      
True
>>> 

 enumerate()循环序列,前面加一个序号,默认从0开始,可以指定起始值

>>> a = [11,22,33,44,55]
>>> for k,v in enumerate(a,1):
...   print k,v
... 
1 11
2 22
3 33
4 44
5 55
>>> 

 二、自定义函数

一、在学习函数之前,一直遵循:面向过程编程,即:根据业务逻辑从上到下实现功能,其往往用一长段代码来实现指定功能,开发过程中最常见的操作就是粘贴复制,也就是将之前实现的代码块复制到现需要功能处。

while True:
    if cpu利用率 > 90%:
        #发送邮件提醒
        连接邮箱服务器
        发送邮件
        关闭连接
  
    if 硬盘使用空间 > 90%:
        #发送邮件提醒
        连接邮箱服务器
        发送邮件
        关闭连接
  
    if 内存占用 > 80%:
        #发送邮件提醒
        连接邮箱服务器
        发送邮件
        关闭连接

 如上述代码,if条件语句下的内容可以被提取出来公用,如下:

def 发送邮件(内容)
    #发送邮件提醒
    连接邮箱服务器
    发送邮件
    关闭连接
  
while True:
  
    if cpu利用率 > 90%:
        发送邮件('CPU报警')
  
    if 硬盘使用空间 > 90%:
        发送邮件('硬盘报警')
  
    if 内存占用 > 80%:

 对于上述的两种实现方式,第二次必然比第一次的重用性和可读性要好,其实这就是函数式编程和面向过程编程的区别:

  • 函数式:将某功能代码封装到函数中,日后便无需重复编写,仅调用函数即可
  • 面向对象:对函数进行分类和封装,让开始“更快更好更强……”

函数式编程最重要的是增强代码的重用性和可读性

二、函数的定义和使用

def 函数名(参数):
     
    ...
    函数体
    ...

 函数的定义主要有如下要点:

  • def:表示函数的关键字
  • 函数名:函数的名称,日后根据函数名调用函数
  • 函数体:函数中进行一系列的逻辑计算,如:发送邮件、计算出 [11,22,38,888,2]中的最大数等...
  • 参数:为函数体提供数据
  • 返回值:当函数执行完毕后,可以给调用者返回数据。

以上要点中,比较重要有参数和返回值:

1、返回值

函数是一个功能块,该功能到底执行成功与否,需要通过返回值来告知调用者。

def 发送短信():
     
    发送短信的代码...
 
    if 发送成功:
        return True
    else:
        return False
 
 
while True:
     
    # 每次执行发送短信函数,都会将返回值自动赋值给result
    # 之后,可以根据result来写日志,或重发等操作
 
    result = 发送短信()
    if result == False:
        记录日志,短信发送失败...

 2、参数

函数中有三种不同的参数

  • 普通参数
  • 默认参数
  • 动态参数
1 # ######### 定义函数 ######### 
2 
3 # name 叫做函数func的形式参数,简称:形参
4 def func(name):
5     print name
6 
7 # ######### 执行函数 ######### 
8 #  'wangwei' 叫做函数func的实际参数,简称:实参
9 func('wangwei')
普通参数
 1 def func(name, age = 18):
 2     
 3     print "%s:%s" %(name,age)
 4 
 5 # 指定参数
 6 func('wupeiqi', 19)
 7 # 使用默认参数
 8 func('alex')
 9 
10 注:默认参数需要放在参数列表最后
默认参数
动态参数一
 1 def func(**kwargs):
 2 
 3     print args
 4 
 5 
 6 # 执行方式一
 7 func(name='wupeiqi',age=18)
 8 
 9 # 执行方式二
10 li = {'name':'wupeiqi', age:18, 'gender':'male'}
11 func(**li)
12 #传入字典时前面要加两个星
动态参数二
1 def func(*args, **kwargs):
2 
3     print args
4     print kwargs
动态参数三
 1 >>> def func(*args,**kwargs):
 2 ...   print args
 3 ...   print kwargs
 4 ... 
 5 >>> func(11,22,33)
 6 (11, 22, 33)
 7 {}
 8 >>> func(k1=123,k2=321)
 9 ()
10 {'k2': 321, 'k1': 123}
11 >>> func(1,2,3,4,k1=123,k2=321)
12 (1, 2, 3, 4)
13 {'k2': 321, 'k1': 123}
14 >>> func([1,2,3],k1=123,k2=321)
15 ([1, 2, 3],)
16 {'k2': 321, 'k1': 123}
17 >>> 
动态函数补充

文件操作

操作文件时,一般需要经历如下步骤:

  • 打开文件
  • 操作文件

一、打开文件

文件句柄 = file('文件路径','模式')

 注:python中打开文件有两种方式,即:open(...)和file(...),本质上前者在内部会调用后者来进行文件操作,推荐使用open

打开文件时,需要指定文件路径和以何种方式打开文件,打开后,即可获取该文件句柄,日后通过此文件句柄对该文件操作。

打开文件的模式有:

  • r,只读模式(默认)
  • w,只写模式。——不可读,不存在则创建,存在则删除内容。
  • a,追加模式。——可读,不存在则创建,存在则只追加内容。

“+”表示可以同时读写某个文件。“+”只有在r+有意思,w+和a+和w、a的效果是一样的

  • r+,可读写文件——可读,可写,可追加
  • w+,写读
  • a+,同a

“U”表示在读取时,可以将\r \n \r\n自动转换成\n(与r或r+模式同时使用)

  • rU
  • r+U

“b”表示处理二进制文件(如:FTP发送上传ISO去镜像文件,linux可忽略,windows处理二进制文件时需标注)

  • rb
  • wb
  • ab

二、操作文件

  1 class file(object):
  2   
  3     def close(self): # real signature unknown; restored from __doc__
  4         #关闭文件
  5         """
  6         close() -> None or (perhaps) an integer.  Close the file.
  7          
  8         Sets data attribute .closed to True.  A closed file cannot be used for
  9         further I/O operations.  close() may be called more than once without
 10         error.  Some kinds of file objects (for example, opened by popen())
 11         may return an exit status upon closing.
 12         """
 13  
 14     def fileno(self): # real signature unknown; restored from __doc__
 15         #文件描述符  
 16          """
 17         fileno() -> integer "file descriptor".
 18          
 19         This is needed for lower-level file interfaces, such os.read().
 20         """
 21         return 0    
 22  
 23     def flush(self): # real signature unknown; restored from __doc__
 24         #刷新文件内部缓冲区
 25         """ flush() -> None.  Flush the internal I/O buffer. """
 26         pass
 27  
 28  
 29     def isatty(self): # real signature unknown; restored from __doc__
 30         #判断文件是否是同意tty设备
 31         """ isatty() -> true or false.  True if the file is connected to a tty device. """
 32         return False
 33  
 34  
 35     def next(self): # real signature unknown; restored from __doc__
 36         #获取下一行数据,不存在,则报错
 37         """ x.next() -> the next value, or raise StopIteration """
 38         pass
 39  
 40     def read(self, size=None): # real signature unknown; restored from __doc__
 41         #读取指定字节数据
 42         """
 43         read([size]) -> read at most size bytes, returned as a string.
 44          
 45         If the size argument is negative or omitted, read until EOF is reached.
 46         Notice that when in non-blocking mode, less data than what was requested
 47         may be returned, even if no size parameter was given.
 48         """
 49         pass
 50  
 51     def readinto(self): # real signature unknown; restored from __doc__
 52         #读取到缓冲区,不要用,将被遗弃
 53         """ readinto() -> Undocumented.  Don't use this; it may go away. """
 54         pass
 55  
 56     def readline(self, size=None): # real signature unknown; restored from __doc__
 57         #仅读取一行数据
 58         """
 59         readline([size]) -> next line from the file, as a string.
 60          
 61         Retain newline.  A non-negative size argument limits the maximum
 62         number of bytes to return (an incomplete line may be returned then).
 63         Return an empty string at EOF.
 64         """
 65         pass
 66  
 67     def readlines(self, size=None): # real signature unknown; restored from __doc__
 68         #读取所有数据,并根据换行保存值列表
 69         """
 70         readlines([size]) -> list of strings, each a line from the file.
 71          
 72         Call readline() repeatedly and return a list of the lines so read.
 73         The optional size argument, if given, is an approximate bound on the
 74         total number of bytes in the lines returned.
 75         """
 76         return []
 77  
 78     def seek(self, offset, whence=None): # real signature unknown; restored from __doc__
 79         #指定文件中指针位置
 80         """
 81         seek(offset[, whence]) -> None.  Move to new file position.
 82          
 83         Argument offset is a byte count.  Optional argument whence defaults to
 84         0 (offset from start of file, offset should be >= 0); other values are 1
 85         (move relative to current position, positive or negative), and 2 (move
 86         relative to end of file, usually negative, although many platforms allow
 87         seeking beyond the end of a file).  If the file is opened in text mode,
 88         only offsets returned by tell() are legal.  Use of other offsets causes
 89         undefined behavior.
 90         Note that not all file objects are seekable.
 91         """
 92         pass
 93  
 94     def tell(self): # real signature unknown; restored from __doc__
 95         #获取当前指针位置
 96         """ tell() -> current file position, an integer (may be a long integer). """
 97         pass
 98  
 99     def truncate(self, size=None): # real signature unknown; restored from __doc__
100         #截断数据,仅保留指定之前数据
101         """
102         truncate([size]) -> None.  Truncate the file to at most size bytes.
103          
104         Size defaults to the current file position, as returned by tell().
105         """
106         pass
107  
108     def write(self, p_str): # real signature unknown; restored from __doc__
109         #写内容
110         """
111         write(str) -> None.  Write string str to file.
112          
113         Note that due to buffering, flush() or close() may be needed before
114         the file on disk reflects the data written.
115         """
116         pass
117  
118     def writelines(self, sequence_of_strings): # real signature unknown; restored from __doc__
119         #将一个字符串列表写入文件
120         """
121         writelines(sequence_of_strings) -> None.  Write the strings to the file.
122          
123         Note that newlines are not added.  The sequence can be any iterable object
124         producing strings. This is equivalent to calling write() for each string.
125         """
126         pass
127  
128     def xreadlines(self): # real signature unknown; restored from __doc__
129         #可用于逐行读取文件,非全部
130         """
131         将弃用,可以用下面的方法
132         for line in f:          
133           print line.strip();
134         """
135         """
136         xreadlines() -> returns self.
137          
138         For backward compatibility. File objects now include the performance
139         optimizations previously implemented in the xreadlines module.
140         """
141         pass
file

 三、with

为了避免打开文件后忘记关闭,可以通过管理上下文,即:

with open('log','r') as f:
  ......

 如此方式,当with代码块执行完毕时,内部会自动关闭并释放文件资源。

在python2.7后,with又支持同时对多个文件的上下文进行管理,即:

with open('log1') as obj1,open('log2') as obj2:
    pass

 

posted on 2016-01-03 14:53  牧羊伯爵  阅读(270)  评论(0编辑  收藏  举报