代码如下:
#encoding=utf-8 print '中国' #统计值 并按照次数排序 可以通过字典的值对key进行排序 #通过字典来实现 class hist(dict): def add(self,item,increment=1): self[item]=increment + self.get(item,0) def counts(self,reverse=False): aux=[(self[k],k) for k in self] aux.sort(cmp=None, key=None, reverse=False) if reverse: aux.reverse() return [k for v,k in aux] hist1=hist() hist1.add(3) hist1.add(3) hist1.add(1) print hist1.counts() #通过list来实现 class histlist(list): def __init__(self,n): list.__init__(self,n*[0]) def add(self,item,increment=1): self[item] += increment def counts(self,reverse=False): aux=[(v,k) for k,v in enumerate(self)] aux.sort(cmp=None, key=None, reverse=False) if reverse:aux.reverse() return [k for v,k in aux] hist1=histlist(4) hist1.add(3) hist1.add(3) hist1.add(1) print hist1 sentence = ''' Hello there this is a test. Hello there this was a test, but now it is not. ''' words = sentence.split( ) c = hist( ) for word in words: c.add(word) print "Ascending count:" print c.counts( ) print "Descending count:" print c.counts(reverse=True) from operator import itemgetter #itemgetter为获取当前维度的值 (key,val) val为维度一 排序当前维度的值 def dict_items_sorted_by_value(d, reverse=False): return sorted(d.iteritems( ), key=itemgetter(1), reverse=reverse) print dict_items_sorted_by_value(c)
打印结果如下:
中国
[1, 3]
[0, 1, 0, 2]
Ascending count:
['but', 'it', 'not.', 'now', 'test,', 'test.', 'was', 'Hello', 'a', 'is', 'there', 'this']
Descending count:
['this', 'there', 'is', 'a', 'Hello', 'was', 'test.', 'test,', 'now', 'not.', 'it', 'but']
[('not.', 1), ('it', 1), ('but', 1), ('test,', 1), ('now', 1), ('was', 1), ('test.', 1), ('a', 2), ('this', 2), ('is', 2), ('there', 2), ('Hello', 2)]