您可以使用iteration_utilities.duplicates：
>>> from iteration_utilities import duplicates
>>> list(duplicates([1,1,2,1,2,3,4,2]))
[1, 1, 2, 2]
或者，如果您只希望每个重复项之一，可以将其与iteration_utilities.unique_everseen：
>>> from iteration_utilities import unique_everseen
>>> list(unique_everseen(duplicates([1,1,2,1,2,3,4,2])))
[1, 2]
它还可以处理不可散列的元素（但是以性能为代价）：
>>> list(duplicates([[1], [2], [1], [3], [1]]))
[[1], [1]]
>>> list(unique_everseen(duplicates([[1], [2], [1], [3], [1]])))
[[1]]
这是这里仅有的其他几种方法可以处理的。
基准测试
我做了一个快速基准测试，其中包含这里提到的大多数（但不是全部）方法。
第一个基准测试仅包含一小部分列表长度，因为某些方法具有 O(n**2)行为。
在曲线图中，y轴表示时间，因此值越低越好。它还绘制了对数-对数，因此可以更好地可视化各种值：
除去这些O(n**2)方法，我做了另一个基准测试，列表中最多有500万个元素：
如您所见 iteration_utilities.duplicates方法比其他任何方法甚至链式方法都快unique_everseen(duplicates(...))都快也比其他方法快或同样快。
这里要注意的另一件有趣的事情是，对于小名单，熊猫方法非常慢，但可以轻松竞争更长的名单。
但是，由于这些基准测试表明大多数方法的性能大致相同，因此使用哪种方法都无关紧要（除了具有O(n**2)运行时的三种方法外）。
from iteration_utilities import duplicates, unique_everseen
from collections import Counter
import pandas as pd
import itertools
def georg_counter(it):
return [item for item, count in Counter(it).items() if count > 1]
def georg_set(it):
seen = set()
uniq = []
for x in it:
if x not in seen:
uniq.append(x)
seen.add(x)
def georg_set2(it):
seen = set()
return [x for x in it if x not in seen and not seen.add(x)]
def georg_set3(it):
seen = {}
dupes = []
for x in it:
if x not in seen:
seen[x] = 1
else:
if seen[x] == 1:
dupes.append(x)
seen[x] += 1
def RiteshKumar_count(l):
return set([x for x in l if l.count(x) > 1])
def moooeeeep(seq):
seen = set()
seen_add = seen.add
# adds all elements it doesn't know yet to seen and all other to seen_twice
seen_twice = set( x for x in seq if x in seen or seen_add(x) )
# turn the set into a list (as requested)
return list( seen_twice )
def F1Rumors_implementation(c):
a, b = itertools.tee(sorted(c))
next(b, None)
r = None
for k, g in zip(a, b):
if k != g: continue
if k != r:
yield k
r = k
def F1Rumors(c):
return list(F1Rumors_implementation(c))
def Edward(a):
d = {}
for elem in a:
if elem in d:
d[elem] += 1
else:
d[elem] = 1
return [x for x, y in d.items() if y > 1]
def wordsmith(a):
return pd.Series(a)[pd.Series(a).duplicated()].values
def NikhilPrabhu(li):
li = li.copy()
for x in set(li):
li.remove(x)
return list(set(li))
def firelynx(a):
vc = pd.Series(a).value_counts()
return vc[vc > 1].index.tolist()
def HenryDev(myList):
newList = set()
for i in myList:
if myList.count(i) >= 2:
newList.add(i)
return list(newList)
def yota(number_lst):
seen_set = set()
duplicate_set = set(x for x in number_lst if x in seen_set or seen_set.add(x))
return seen_set - duplicate_set
def IgorVishnevskiy(l):
s=set(l)
d=[]
for x in l:
if x in s:
s.remove(x)
else:
d.append(x)
return d
def it_duplicates(l):
return list(duplicates(l))
def it_unique_duplicates(l):
return list(unique_everseen(duplicates(l)))
基准1
from simple_benchmark import benchmark
import random
funcs = [
georg_counter, georg_set, georg_set2, georg_set3, RiteshKumar_count, moooeeeep,
F1Rumors, Edward, wordsmith, NikhilPrabhu, firelynx,
HenryDev, yota, IgorVishnevskiy, it_duplicates, it_unique_duplicates
]
args = {2**i: [random.randint(0, 2**(i-1)) for _ in range(2**i)] for i in range(2, 12)}
b = benchmark(funcs, args, 'list size')
b.plot()
基准2
funcs = [
georg_counter, georg_set, georg_set2, georg_set3, moooeeeep,
F1Rumors, Edward, wordsmith, firelynx,
yota, IgorVishnevskiy, it_duplicates, it_unique_duplicates
]
args = {2**i: [random.randint(0, 2**(i-1)) for _ in range(2**i)] for i in range(2, 20)}
b = benchmark(funcs, args, 'list size')
b.plot()
免责声明
1这来自我编写的第三方库iteration_utilities。