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])

def frequencyDistribution(data):
    return {i: data.count(i) for i in data}   

print frequencyDistribution([1,2,3,4])

...

 {1: 1, 2: 1, 3: 1, 4: 1}   # originalNumber: count

我将简单地以以下方式使用scipy.stats.itemfreq:

from scipy.stats import itemfreq

a = [1,1,1,1,2,2,2,2,3,3,4,5,5]

freq = itemfreq(a)

a = freq[:,0]
b = freq[:,1]

您可以在这里查看文档:http://docs.scipy.org/doc/scipy-0.16.0/reference/generated/scipy.stats.itemfreq.html

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

我找到了另一种方法，使用集合。

#ar is the list of elements
#convert ar to set to get unique elements
sock_set = set(ar)

#create dictionary of frequency of socks
sock_dict = {}

for sock in sock_set:
    sock_dict[sock] = ar.count(sock)

from collections import Counter
a=["E","D","C","G","B","A","B","F","D","D","C","A","G","A","C","B","F","C","B"]

counter=Counter(a)

kk=[list(counter.keys()),list(counter.values())]

pd.DataFrame(np.array(kk).T, columns=['Letter','Count'])