#!usr/bin/python
def frq(words):
    freq = {}
    for w in words:
            if w in freq:
                    freq[w] = freq.get(w)+1
            else:
                    freq[w] =1
    return freq

fp = open("poem","r")
list = fp.read()
fp.close()
input = list.split()
print input
d = frq(input)
print "frequency of input\n: "
print d
fp1 = open("output.txt","w+")
for k,v in d.items():
fp1.write(str(k)+':'+str(v)+"\n")
fp1.close()

在Python 2.7(或更新版本)中，可以使用集合。计数器:

>>> import collections
>>> a = [5, 1, 2, 2, 4, 3, 1, 2, 3, 1, 1, 5, 2]
>>> counter = collections.Counter(a)
>>> counter
Counter({1: 4, 2: 4, 5: 2, 3: 2, 4: 1})
>>> counter.values()
dict_values([2, 4, 4, 1, 2])
>>> counter.keys()
dict_keys([5, 1, 2, 4, 3])
>>> counter.most_common(3)
[(1, 4), (2, 4), (5, 2)]
>>> dict(counter)
{5: 2, 1: 4, 2: 4, 4: 1, 3: 2}
>>> # Get the counts in order matching the original specification,
>>> # by iterating over keys in sorted order
>>> [counter[x] for x in sorted(counter.keys())]
[4, 4, 2, 1, 2]

如果您使用的是Python 2.6或更老版本，可以在这里下载实现。

我使用计数器在1行代码中从文本文件单词生成一个frequency . dict

def _fileIndex(fh):
''' create a dict using Counter of a
flat list of words (re.findall(re.compile(r"[a-zA-Z]+"), lines)) in (lines in file->for lines in fh)
'''
return Counter(
    [wrd.lower() for wrdList in
     [words for words in
      [re.findall(re.compile(r'[a-zA-Z]+'), lines) for lines in fh]]
     for wrd in wrdList])

还有另一种不使用集合的算法解决方案:

def countFreq(A):
   n=len(A)
   count=[0]*n                     # Create a new list initialized with '0'
   for i in range(n):
      count[A[i]]+= 1              # increase occurrence for value A[i]
   return [x for x in count if x]  # return non-zero count

通过遍历列表并计算它们，手动计算出现的数量，使用collections.defaultdict跟踪到目前为止看到的内容:

from collections import defaultdict

appearances = defaultdict(int)

for curr in a:
    appearances[curr] += 1

对于您的第一个问题，迭代列表并使用字典跟踪元素的存在。

对于你的第二个问题，只需使用集合操作符。