我注意到大多数解决方案的复杂度为O(n * n)，对于大型列表来说非常缓慢。所以我想分享一下我写的函数，它支持整数或字符串，在最好的情况下是O(n)。对于一个包含10万个元素的列表，最上面的解决方案需要超过30秒，而我的解决方案只需0.12秒

def get_duplicates(list1):
    '''Return all duplicates given a list. O(n) complexity for best case scenario.
    input: [1, 1, 1, 2, 3, 4, 4]
    output: [1, 1, 4]
    '''
    dic = {}
    for el in list1:
        try:
            dic[el] += 1
        except:
            dic[el] = 1
    dupes = []
    for key in dic.keys():
        for i in range(dic[key] - 1):
            dupes.append(key)
    return dupes


list1 = [1, 1, 1, 2, 3, 4, 4]
> print(get_duplicates(list1))
[1, 1, 4]

或者获得唯一的副本:

> print(list(set(get_duplicates(list1))))
[1, 4]

使用toolz时:

from toolz import frequencies, valfilter

a = [1,2,2,3,4,5,4]
>>> list(valfilter(lambda count: count > 1, frequencies(a)).keys())
[2,4] 

我在寻找相关的东西时遇到了这个问题-想知道为什么没有人提供基于生成器的解决方案?解决这个问题的方法是:

>>> print list(getDupes_9([1,2,3,2,1,5,6,5,5,5]))
[1, 2, 5]

我很关心可伸缩性，所以测试了几种方法，包括在小列表上工作得很好的naive项，但随着列表变大，可伸缩性很差(注意-使用timeit会更好，但这只是说明)。

我加入了@moooeeeep作为比较(它的速度非常快:如果输入列表是完全随机的，速度最快)和itertools方法，对于大多数排序的列表，它甚至更快……现在包括来自@ fireynx的熊猫方法-缓慢，但不是可怕的，而且简单。注意:在我的机器上，sort/tee/zip方法对于大型有序列表始终是最快的，moooeeeep对于洗牌列表是最快的，但您的情况可能会有所不同。

优势

非常快速简单的测试'任何'重复使用相同的代码

假设

重复项只应报告一次 重复的订单不需要保留 Duplicate可能位于列表中的任何位置

最快的解决方案，1m条目:

def getDupes(c):
        '''sort/tee/izip'''
        a, b = itertools.tee(sorted(c))
        next(b, None)
        r = None
        for k, g in itertools.izip(a, b):
            if k != g: continue
            if k != r:
                yield k
                r = k

方法测试

import itertools
import time
import random

def getDupes_1(c):
    '''naive'''
    for i in xrange(0, len(c)):
        if c[i] in c[:i]:
            yield c[i]

def getDupes_2(c):
    '''set len change'''
    s = set()
    for i in c:
        l = len(s)
        s.add(i)
        if len(s) == l:
            yield i

def getDupes_3(c):
    '''in dict'''
    d = {}
    for i in c:
        if i in d:
            if d[i]:
                yield i
                d[i] = False
        else:
            d[i] = True

def getDupes_4(c):
    '''in set'''
    s,r = set(),set()
    for i in c:
        if i not in s:
            s.add(i)
        elif i not in r:
            r.add(i)
            yield i

def getDupes_5(c):
    '''sort/adjacent'''
    c = sorted(c)
    r = None
    for i in xrange(1, len(c)):
        if c[i] == c[i - 1]:
            if c[i] != r:
                yield c[i]
                r = c[i]

def getDupes_6(c):
    '''sort/groupby'''
    def multiple(x):
        try:
            x.next()
            x.next()
            return True
        except:
            return False
    for k, g in itertools.ifilter(lambda x: multiple(x[1]), itertools.groupby(sorted(c))):
        yield k

def getDupes_7(c):
    '''sort/zip'''
    c = sorted(c)
    r = None
    for k, g in zip(c[:-1],c[1:]):
        if k == g:
            if k != r:
                yield k
                r = k

def getDupes_8(c):
    '''sort/izip'''
    c = sorted(c)
    r = None
    for k, g in itertools.izip(c[:-1],c[1:]):
        if k == g:
            if k != r:
                yield k
                r = k

def getDupes_9(c):
    '''sort/tee/izip'''
    a, b = itertools.tee(sorted(c))
    next(b, None)
    r = None
    for k, g in itertools.izip(a, b):
        if k != g: continue
        if k != r:
            yield k
            r = k

def getDupes_a(l):
    '''moooeeeep'''
    seen = set()
    seen_add = seen.add
    # adds all elements it doesn't know yet to seen and all other to seen_twice
    for x in l:
        if x in seen or seen_add(x):
            yield x

def getDupes_b(x):
    '''iter*/sorted'''
    x = sorted(x)
    def _matches():
        for k,g in itertools.izip(x[:-1],x[1:]):
            if k == g:
                yield k
    for k, n in itertools.groupby(_matches()):
        yield k

def getDupes_c(a):
    '''pandas'''
    import pandas as pd
    vc = pd.Series(a).value_counts()
    i = vc[vc > 1].index
    for _ in i:
        yield _

def hasDupes(fn,c):
    try:
        if fn(c).next(): return True    # Found a dupe
    except StopIteration:
        pass
    return False

def getDupes(fn,c):
    return list(fn(c))

STABLE = True
if STABLE:
    print 'Finding FIRST then ALL duplicates, single dupe of "nth" placed element in 1m element array'
else:
    print 'Finding FIRST then ALL duplicates, single dupe of "n" included in randomised 1m element array'
for location in (50,250000,500000,750000,999999):
    for test in (getDupes_2, getDupes_3, getDupes_4, getDupes_5, getDupes_6,
                 getDupes_8, getDupes_9, getDupes_a, getDupes_b, getDupes_c):
        print 'Test %-15s:%10d - '%(test.__doc__ or test.__name__,location),
        deltas = []
        for FIRST in (True,False):
            for i in xrange(0, 5):
                c = range(0,1000000)
                if STABLE:
                    c[0] = location
                else:
                    c.append(location)
                    random.shuffle(c)
                start = time.time()
                if FIRST:
                    print '.' if location == test(c).next() else '!',
                else:
                    print '.' if [location] == list(test(c)) else '!',
                deltas.append(time.time()-start)
            print ' -- %0.3f  '%(sum(deltas)/len(deltas)),
        print
    print

“all dupes”测试的结果是一致的，在这个数组中找到“first”重复，然后是“all”重复:

Finding FIRST then ALL duplicates, single dupe of "nth" placed element in 1m element array
Test set len change :    500000 -  . . . . .  -- 0.264   . . . . .  -- 0.402  
Test in dict        :    500000 -  . . . . .  -- 0.163   . . . . .  -- 0.250  
Test in set         :    500000 -  . . . . .  -- 0.163   . . . . .  -- 0.249  
Test sort/adjacent  :    500000 -  . . . . .  -- 0.159   . . . . .  -- 0.229  
Test sort/groupby   :    500000 -  . . . . .  -- 0.860   . . . . .  -- 1.286  
Test sort/izip      :    500000 -  . . . . .  -- 0.165   . . . . .  -- 0.229  
Test sort/tee/izip  :    500000 -  . . . . .  -- 0.145   . . . . .  -- 0.206  *
Test moooeeeep      :    500000 -  . . . . .  -- 0.149   . . . . .  -- 0.232  
Test iter*/sorted   :    500000 -  . . . . .  -- 0.160   . . . . .  -- 0.221  
Test pandas         :    500000 -  . . . . .  -- 0.493   . . . . .  -- 0.499  

当列表首先被打乱时，排序的代价就变得明显了——效率显著下降，@moooeeeep方法占主导地位，set和dict方法类似，但性能较差:

Finding FIRST then ALL duplicates, single dupe of "n" included in randomised 1m element array
Test set len change :    500000 -  . . . . .  -- 0.321   . . . . .  -- 0.473  
Test in dict        :    500000 -  . . . . .  -- 0.285   . . . . .  -- 0.360  
Test in set         :    500000 -  . . . . .  -- 0.309   . . . . .  -- 0.365  
Test sort/adjacent  :    500000 -  . . . . .  -- 0.756   . . . . .  -- 0.823  
Test sort/groupby   :    500000 -  . . . . .  -- 1.459   . . . . .  -- 1.896  
Test sort/izip      :    500000 -  . . . . .  -- 0.786   . . . . .  -- 0.845  
Test sort/tee/izip  :    500000 -  . . . . .  -- 0.743   . . . . .  -- 0.804  
Test moooeeeep      :    500000 -  . . . . .  -- 0.234   . . . . .  -- 0.311  *
Test iter*/sorted   :    500000 -  . . . . .  -- 0.776   . . . . .  -- 0.840  
Test pandas         :    500000 -  . . . . .  -- 0.539   . . . . .  -- 0.540  

为了实现这个问题，我们可以使用多种不同的方法来解决它，这两种是常见的解决方案，但在实际场景中实现它们时，我们还必须考虑时间复杂性。

import random
import time

dupl_list = [random.randint(1,1000) for x in range(500)]
print("List with duplicate integers")
print (dupl_list)


#Method 1 
print("******************Method 1 *************")

def Repeat_num(x):
    _size = len(x)
    repeated = []
    for i in range(_size):
        # print(i)
        k = i + 1
        for j in range(k, _size):
            # print(j)
            if x[i] == x[j] and x[i] not in repeated:
                repeated.append(x[i])
    return repeated

start = time.time()
print(Repeat_num(dupl_list))
end = time.time()
print("The time of execution of above program is :",(end-start) * 10**3, "ms")

print("***************Method 2****************")

#method 2 - using count()
def repeast_count(dup_list):
  new = []
  for a in dup_list:
      # print(a)
      # checking the occurrence of elements
      n = dup_list.count(a)
      # if the occurrence is more than
      # one we add it to the output list
      if n > 1:
          if new.count(a) == 0:  # condition to check
              new.append(a)
  return new


start = time.time()
print(repeast_count(dupl_list))
end = time.time()
print("The time of execution of above program is :",(end-start) * 10**3, "ms")

# #输出示例:

List with duplicate integers
[5, 45, 28, 81, 32, 98, 8, 83, 47, 95, 41, 49, 4, 1, 85, 26, 38, 82, 54, 11]
******************Method 1 *************
[]
The time of execution of above program is : 1.1069774627685547 ms
***************Method 2****************
[]
The time of execution of above program is : 0.1881122589111328 ms

对于一般的理解，方法1是好的，但是对于真正的实现，我更喜欢方法2，因为它比方法1花费的时间更少。

list2 = [1, 2, 3, 4, 1, 2, 3]
lset = set()
[(lset.add(item), list2.append(item))
 for item in list2 if item not in lset]
print list(lset)

下面是一个快速生成器，它使用dict将每个元素存储为一个带有布尔值的键，用于检查是否已经产生了重复项。

对于所有元素都是可哈希类型的列表:

def gen_dupes(array):
    unique = {}
    for value in array:
        if value in unique and unique[value]:
            unique[value] = False
            yield value
        else:
            unique[value] = True

array = [1, 2, 2, 3, 4, 1, 5, 2, 6, 6]
print(list(gen_dupes(array)))
# => [2, 1, 6]

对于可能包含列表的列表:

def gen_dupes(array):
    unique = {}
    for value in array:
        is_list = False
        if type(value) is list:
            value = tuple(value)
            is_list = True

        if value in unique and unique[value]:
            unique[value] = False
            if is_list:
                value = list(value)

            yield value
        else:
            unique[value] = True

array = [1, 2, 2, [1, 2], 3, 4, [1, 2], 5, 2, 6, 6]
print(list(gen_dupes(array)))
# => [2, [1, 2], 6]