1 collections系列
方法如下
1 class Counter(dict): 2 '''Dict subclass for counting hashable items. Sometimes called a bag 3 or multiset. Elements are stored as dictionary keys and their counts 4 are stored as dictionary values. 5 6 >>> c = Counter('abcdeabcdabcaba') # count elements from a string 7 8 >>> c.most_common(3) # three most common elements 9 [('a', 5), ('b', 4), ('c', 3)] 10 >>> sorted(c) # list all unique elements 11 ['a', 'b', 'c', 'd', 'e'] 12 >>> ''.join(sorted(c.elements())) # list elements with repetitions 13 'aaaaabbbbcccdde' 14 >>> sum(c.values()) # total of all counts 15 15 16 17 >>> c['a'] # count of letter 'a' 18 5 19 >>> for elem in 'shazam': # update counts from an iterable 20 ... c[elem] += 1 # by adding 1 to each element's count 21 >>> c['a'] # now there are seven 'a' 22 7 23 >>> del c['b'] # remove all 'b' 24 >>> c['b'] # now there are zero 'b' 25 0 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 9 31 32 >>> c.clear() # empty the counter 33 >>> c 34 Counter() 35 36 Note: If a count is set to zero or reduced to zero, it will remain 37 in the counter until the entry is deleted or the counter is cleared: 38 39 >>> c = Counter('aaabbc') 40 >>> c['b'] -= 2 # reduce the count of 'b' by two 41 >>> c.most_common() # 'b' is still in, but its count is zero 42 [('a', 3), ('c', 1), ('b', 0)] 43 44 ''' 45 # References: 46 # http://en.wikipedia.org/wiki/Multiset 47 # http://www.gnu.org/software/smalltalk/manual-base/html_node/Bag.html 48 # http://www.demo2s.com/Tutorial/Cpp/0380__set-multiset/Catalog0380__set-multiset.htm 49 # http://code.activestate.com/recipes/259174/ 50 # Knuth, TAOCP Vol. II section 4.6.3 51 52 def __init__(*args, **kwds): 53 '''Create a new, empty Counter object. And if given, count elements 54 from an input iterable. Or, initialize the count from another mapping 55 of elements to their counts. 56 57 >>> c = Counter() # a new, empty counter 58 >>> c = Counter('gallahad') # a new counter from an iterable 59 >>> c = Counter({'a': 4, 'b': 2}) # a new counter from a mapping 60 >>> c = Counter(a=4, b=2) # a new counter from keyword args 61 62 ''' 63 if not args: 64 raise TypeError("descriptor '__init__' of 'Counter' object " 65 "needs an argument") 66 self = args[0] 67 args = args[1:] 68 if len(args) > 1: 69 raise TypeError('expected at most 1 arguments, got %d' % len(args)) 70 super(Counter, self).__init__() 71 self.update(*args, **kwds) 72 73 def __missing__(self, key): 74 'The count of elements not in the Counter is zero.' 75 # Needed so that self[missing_item] does not raise KeyError 76 return 0 77 78 def most_common(self, n=None): 79 '''List the n most common elements and their counts from the most 80 common to the least. If n is None, then list all element counts. 81 82 >>> Counter('abcdeabcdabcaba').most_common(3) 83 [('a', 5), ('b', 4), ('c', 3)] 84 85 ''' 86 # Emulate Bag.sortedByCount from Smalltalk 87 if n is None: 88 return sorted(self.iteritems(), key=_itemgetter(1), reverse=True) 89 return _heapq.nlargest(n, self.iteritems(), key=_itemgetter(1)) 90 91 def elements(self): 92 '''Iterator over elements repeating each as many times as its count. 93 94 >>> c = Counter('ABCABC') 95 >>> sorted(c.elements()) 96 ['A', 'A', 'B', 'B', 'C', 'C'] 97 98 # Knuth's example for prime factors of 1836: 2**2 * 3**3 * 17**1 99 >>> prime_factors = Counter({2: 2, 3: 3, 17: 1}) 100 >>> product = 1 101 >>> for factor in prime_factors.elements(): # loop over factors 102 ... product *= factor # and multiply them 103 >>> product 104 1836 105 106 Note, if an element's count has been set to zero or is a negative 107 number, elements() will ignore it. 108 109 ''' 110 # Emulate Bag.do from Smalltalk and Multiset.begin from C++. 111 return _chain.from_iterable(_starmap(_repeat, self.iteritems())) 112 113 # Override dict methods where necessary 114 115 @classmethod 116 def fromkeys(cls, iterable, v=None): 117 # There is no equivalent method for counters because setting v=1 118 # means that no element can have a count greater than one. 119 raise NotImplementedError( 120 'Counter.fromkeys() is undefined. Use Counter(iterable) instead.') 121 122 def update(*args, **kwds): 123 '''Like dict.update() but add counts instead of replacing them. 124 125 Source can be an iterable, a dictionary, or another Counter instance. 126 127 >>> c = Counter('which') 128 >>> c.update('witch') # add elements from another iterable 129 >>> d = Counter('watch') 130 >>> c.update(d) # add elements from another counter 131 >>> c['h'] # four 'h' in which, witch, and watch 132 4 133 134 ''' 135 # The regular dict.update() operation makes no sense here because the 136 # replace behavior results in the some of original untouched counts 137 # being mixed-in with all of the other counts for a mismash that 138 # doesn't have a straight-forward interpretation in most counting 139 # contexts. Instead, we implement straight-addition. Both the inputs 140 # and outputs are allowed to contain zero and negative counts. 141 142 if not args: 143 raise TypeError("descriptor 'update' of 'Counter' object " 144 "needs an argument") 145 self = args[0] 146 args = args[1:] 147 if len(args) > 1: 148 raise TypeError('expected at most 1 arguments, got %d' % len(args)) 149 iterable = args[0] if args else None 150 if iterable is not None: 151 if isinstance(iterable, Mapping): 152 if self: 153 self_get = self.get 154 for elem, count in iterable.iteritems(): 155 self[elem] = self_get(elem, 0) + count 156 else: 157 super(Counter, self).update(iterable) # fast path when counter is empty 158 else: 159 self_get = self.get 160 for elem in iterable: 161 self[elem] = self_get(elem, 0) + 1 162 if kwds: 163 self.update(kwds) 164 165 def subtract(*args, **kwds): 166 '''Like dict.update() but subtracts counts instead of replacing them. 167 Counts can be reduced below zero. Both the inputs and outputs are 168 allowed to contain zero and negative counts. 169 170 Source can be an iterable, a dictionary, or another Counter instance. 171 172 >>> c = Counter('which') 173 >>> c.subtract('witch') # subtract elements from another iterable 174 >>> c.subtract(Counter('watch')) # subtract elements from another counter 175 >>> c['h'] # 2 in which, minus 1 in witch, minus 1 in watch 176 0 177 >>> c['w'] # 1 in which, minus 1 in witch, minus 1 in watch 178 -1 179 180 ''' 181 if not args: 182 raise TypeError("descriptor 'subtract' of 'Counter' object " 183 "needs an argument") 184 self = args[0] 185 args = args[1:] 186 if len(args) > 1: 187 raise TypeError('expected at most 1 arguments, got %d' % len(args)) 188 iterable = args[0] if args else None 189 if iterable is not None: 190 self_get = self.get 191 if isinstance(iterable, Mapping): 192 for elem, count in iterable.items(): 193 self[elem] = self_get(elem, 0) - count 194 else: 195 for elem in iterable: 196 self[elem] = self_get(elem, 0) - 1 197 if kwds: 198 self.subtract(kwds) 199 200 def copy(self): 201 'Return a shallow copy.' 202 return self.__class__(self) 203 204 def __reduce__(self): 205 return self.__class__, (dict(self),) 206 207 def __delitem__(self, elem): 208 'Like dict.__delitem__() but does not raise KeyError for missing values.' 209 if elem in self: 210 super(Counter, self).__delitem__(elem) 211 212 def __repr__(self): 213 if not self: 214 return '%s()' % self.__class__.__name__ 215 items = ', '.join(map('%r: %r'.__mod__, self.most_common())) 216 return '%s({%s})' % (self.__class__.__name__, items) 217 218 # Multiset-style mathematical operations discussed in: 219 # Knuth TAOCP Volume II section 4.6.3 exercise 19 220 # and at http://en.wikipedia.org/wiki/Multiset 221 # 222 # Outputs guaranteed to only include positive counts. 223 # 224 # To strip negative and zero counts, add-in an empty counter: 225 # c += Counter() 226 227 def __add__(self, other): 228 '''Add counts from two counters. 229 230 >>> Counter('abbb') + Counter('bcc') 231 Counter({'b': 4, 'c': 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] = count 244 return result 245 246 def __sub__(self, other): 247 ''' Subtract count, but keep only results with positive counts. 248 249 >>> Counter('abbbc') - Counter('bccd') 250 Counter({'b': 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 newcount = count - other[elem] 258 if newcount > 0: 259 result[elem] = newcount 260 for elem, count in other.items(): 261 if elem not in self and count < 0: 262 result[elem] = 0 - count 263 return result 264 265 def __or__(self, other): 266 '''Union is the maximum of value in either of the input counters. 267 268 >>> Counter('abbb') | Counter('bcc') 269 Counter({'b': 3, 'c': 2, 'a': 1}) 270 271 ''' 272 if not isinstance(other, Counter): 273 return NotImplemented 274 result = Counter() 275 for elem, count in self.items(): 276 other_count = other[elem] 277 newcount = other_count if count < other_count else count 278 if newcount > 0: 279 result[elem] = newcount 280 for elem, count in other.items(): 281 if elem not in self and count > 0: 282 result[elem] = count 283 return result 284 285 def __and__(self, other): 286 ''' Intersection is the minimum of corresponding counts. 287 288 >>> Counter('abbb') & Counter('bcc') 289 Counter({'b': 1}) 290 291 ''' 292 if not isinstance(other, Counter): 293 return NotImplemented 294 result = Counter() 295 for elem, count in self.items(): 296 other_count = other[elem] 297 newcount = count if count < other_count else other_count 298 if newcount > 0: 299 result[elem] = newcount 300 return result 301 302 303 if __name__ == '__main__': 304 # verify that instances can be pickled 305 from cPickle import loads, dumps 306 Point = namedtuple('Point', 'x, y', True) 307 p = Point(x=10, y=20) 308 assert p == loads(dumps(p)) 309 310 # test and demonstrate ability to override methods 311 class Point(namedtuple('Point', 'x y')): 312 __slots__ = () 313 @property 314 def hypot(self): 315 return (self.x ** 2 + self.y ** 2) ** 0.5 316 def __str__(self): 317 return 'Point: x=%6.3f y=%6.3f hypot=%6.3f' % (self.x, self.y, self.hypot) 318 319 for p in Point(3, 4), Point(14, 5/7.): 320 print p 321 322 class Point(namedtuple('Point', 'x y')): 323 'Point class with optimized _make() and _replace() without error-checking' 324 __slots__ = () 325 _make = classmethod(tuple.__new__) 326 def _replace(self, _map=map, **kwds): 327 return self._make(_map(kwds.get, ('x', 'y'), self)) 328 329 print Point(11, 22)._replace(x=100) 330 331 Point3D = namedtuple('Point3D', Point._fields + ('z',)) 332 print Point3D.__doc__ 333 334 import doctest 335 TestResults = namedtuple('TestResults', 'failed attempted') 336 print TestResults(*doctest.testmod())