如何在整数列表中找到重复项并创建重复项的另一个列表?
当前回答
另一种解决方案如下所示，不使用任何集合库。
a = [1,2,3,5,4,6,4,21,4,6,3,32,5,2,23,5]
duplicates = []
for i in a:
if a.count(i) > 1 and i not in duplicates:
duplicates.append(i)
print(duplicates)
输出是[2,3,5,4,6]
其他回答
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)
一个非常简单的解决方案，但是复杂度是O(n*n)。
>>> xs = [1,2,3,4,4,5,5,6,1]
>>> set([x for x in xs if xs.count(x) > 1])
set([1, 4, 5])
不需要转换为列表，可能最简单的方法是如下所示。 在面试中，当他们要求不要使用集合时，这可能会很有用
a=[1,2,3,3,3]
dup=[]
for each in a:
if each not in dup:
dup.append(each)
print(dup)
======= else获取唯一值和重复值的2个单独列表
a=[1,2,3,3,3]
uniques=[]
dups=[]
for each in a:
if each not in uniques:
uniques.append(each)
else:
dups.append(each)
print("Unique values are below:")
print(uniques)
print("Duplicate values are below:")
print(dups)
你不需要计数，只需要该物品之前是否被看到过。把这个答案用在这个问题上:
def list_duplicates(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 )
a = [1,2,3,2,1,5,6,5,5,5]
list_duplicates(a) # yields [1, 2, 5]
以防速度很重要，这里有一些时间安排:
# file: test.py
import collections
def thg435(l):
return [x for x, y in collections.Counter(l).items() if y > 1]
def moooeeeep(l):
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 l if x in seen or seen_add(x) )
# turn the set into a list (as requested)
return list( seen_twice )
def RiteshKumar(l):
return list(set([x for x in l if l.count(x) > 1]))
def JohnLaRooy(L):
seen = set()
seen2 = set()
seen_add = seen.add
seen2_add = seen2.add
for item in L:
if item in seen:
seen2_add(item)
else:
seen_add(item)
return list(seen2)
l = [1,2,3,2,1,5,6,5,5,5]*100
以下是结果:(做得好@JohnLaRooy!)
$ python -mtimeit -s 'import test' 'test.JohnLaRooy(test.l)'
10000 loops, best of 3: 74.6 usec per loop
$ python -mtimeit -s 'import test' 'test.moooeeeep(test.l)'
10000 loops, best of 3: 91.3 usec per loop
$ python -mtimeit -s 'import test' 'test.thg435(test.l)'
1000 loops, best of 3: 266 usec per loop
$ python -mtimeit -s 'import test' 'test.RiteshKumar(test.l)'
100 loops, best of 3: 8.35 msec per loop
有趣的是，除了计时本身，当使用pypy时，排名也略有变化。最有趣的是，基于counter的方法极大地受益于pypy的优化，而我建议的方法缓存方法似乎几乎没有任何效果。
$ pypy -mtimeit -s 'import test' 'test.JohnLaRooy(test.l)'
100000 loops, best of 3: 17.8 usec per loop
$ pypy -mtimeit -s 'import test' 'test.thg435(test.l)'
10000 loops, best of 3: 23 usec per loop
$ pypy -mtimeit -s 'import test' 'test.moooeeeep(test.l)'
10000 loops, best of 3: 39.3 usec per loop
显然，这种效应与输入数据的“重复性”有关。我设置了l = [random.randrange(1000000) for I in xrange(10000)]，得到了这些结果:
$ pypy -mtimeit -s 'import test' 'test.moooeeeep(test.l)'
1000 loops, best of 3: 495 usec per loop
$ pypy -mtimeit -s 'import test' 'test.JohnLaRooy(test.l)'
1000 loops, best of 3: 499 usec per loop
$ pypy -mtimeit -s 'import test' 'test.thg435(test.l)'
1000 loops, best of 3: 1.68 msec per loop
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
