您可以使用 Yan 的语法(len (x) > len (set (x))) ,但是不要使用 set (x) ,而是定义一个函数:
def f5(seq, idfun=None):
# order preserving
if idfun is None:
def idfun(x): return x
seen = {}
result = []
for item in seq:
marker = idfun(item)
# in old Python versions:
# if seen.has_key(marker)
# but in new ones:
if marker in seen: continue
seen[marker] = 1
result.append(item)
return result
>>> def allUnique(x):
... seen = set()
... return not any(i in seen or seen.add(i) for i in x)
...
>>> allUnique("ABCDEF")
True
>>> allUnique("ABACDEF")
False
如果 x 的元素不是散列的,那么你将不得不使用 seen的列表:
>>> def allUnique(x):
... seen = list()
... return not any(i in seen or seen.append(i) for i in x)
...
>>> allUnique([list("ABC"), list("DEF")])
True
>>> allUnique([list("ABC"), list("DEF"), list("ABC")])
False
import timeit
import numpy as np
def get_unique(mylist):
# sort the list and keep the index
sort = sorted((e,i) for i,e in enumerate(mylist))
# check for each element if it is similar to the previous or next one
isunique = [[sort[0][1],sort[0][0]!=sort[1][0]]] + \
[[s[1], (s[0]!=sort[i-1][0])and(s[0]!=sort[i+1][0])]
for [i,s] in enumerate (sort) if (i>0) and (i<len(sort)-1) ] +\
[[sort[-1][1],sort[-1][0]!=sort[-2][0]]]
# sort indices and booleans and return only the boolean
return [a[1] for a in sorted(isunique)]
def get_unique_using_count(mylist):
return [mylist.count(item)==1 for item in mylist]
mylist = list(np.random.randint(0,10,10))
%timeit for x in range(10): get_unique(mylist)
%timeit for x in range(10): get_unique_using_count(mylist)
mylist = list(np.random.randint(0,1000,1000))
%timeit for x in range(10): get_unique(mylist)
%timeit for x in range(10): get_unique_using_count(mylist)