计算词频

>>> from collections import Counter
>>> c = Counter()
>>> for ch in ‘programming‘:
...     c[ch] = c[ch] + 1
...
>>> c
Counter({‘g‘: 2, ‘m‘: 2, ‘r‘: 2, ‘a‘: 1, ‘i‘: 1, ‘o‘: 1, ‘n‘: 1, ‘p‘: 1})

class Counter(dict):
    def __getitem__(self,key):
        if key not in self:
            return 0
        else:
            return super(Counter,self).__getitem__(key)

c=Counter()
for ch in ‘programmingA‘:
    c[ch]=c[ch]+1
for key in sorted(c.keys()):
    print ‘{} : {}‘.format(key,c[key])

data=[‘a‘,‘box‘,‘tea‘,‘apple‘,‘banana‘,‘banner‘,‘a test!‘,‘Zoo‘,‘Z‘]
t={}
for e in data:
    t.setdefault(e[0].upper(),[]).append(e)
else:
    print t

-------------------------------------
得到{‘A‘: [‘a‘, ‘apple‘, ‘a test!‘], ‘Z‘: [‘Zoo‘, ‘Z‘], ‘B‘: [‘box‘, ‘banana‘, ‘banner‘], ‘T‘: [‘tea‘]}

data=‘programmingA‘
t={}
for e in data:
    t.setdefault(e,[]).append(e)
else:
    print {key:len(value) for key,value  in t.items()} 
-------------------------------------------------------
{‘a‘: 1, ‘A‘: 1, ‘g‘: 2, ‘i‘: 1, ‘m‘: 2, ‘o‘: 1, ‘n‘: 1, ‘p‘: 1, ‘r‘: 2}