我在Python中有两个列表:
temp1 = ['One', 'Two', 'Three', 'Four']
temp2 = ['One', 'Two']
假设每个列表中的元素都是唯一的,我想用第一个列表中的项创建第三个列表,这些项不在第二个列表中:
temp3 = ['Three', 'Four']
有没有没有周期和检查的快速方法?
我在Python中有两个列表:
temp1 = ['One', 'Two', 'Three', 'Four']
temp2 = ['One', 'Two']
假设每个列表中的元素都是唯一的,我想用第一个列表中的项创建第三个列表,这些项不在第二个列表中:
temp3 = ['Three', 'Four']
有没有没有周期和检查的快速方法?
当前回答
下面是@arkolec的回答,下面是一个用于比较列表、元组和集的实用程序类:
from difflib import SequenceMatcher
class ListDiffer:
def __init__(self, left, right, strict:bool=False):
assert isinstance(left, (list, tuple, set)), "left must be list, tuple or set"
assert isinstance(right, (list, tuple, set)), "right must be list, tuple or set"
self.l = list(left) if isinstance(left, (tuple, set)) else left
self.r = list(right) if isinstance(left, (tuple, set)) else right
if strict:
assert isinstance(left, right.__class__), \
f'left type ({left.__class__.__name__}) must equal right type ({right.__class__.__name__})'
self.diffs = []
self.equal = []
for tag, i, j, k, l in SequenceMatcher(None, self.l, self.r).get_opcodes():
if tag in ['delete', 'replace', 'insert']:
self.diffs.append((tag, i, j, k, l))
elif tag == 'equal':
[self.equal.append(v) for v in left[i:j]]
def has_diffs(self):
return len(self.diffs) > 0
def only_left(self):
a = self.l[:]
[a.remove(v) for v in self.equal]
return a
def only_right(self):
a = self.r[:]
[a.remove(v) for v in self.equal]
return a
def __str__(self, verbose:bool=False):
iD = 0
sb = []
if verbose:
sb.append(f"left: {self.l}\n")
sb.append(f"right: {self.r}\n")
sb.append(f"diffs: ")
for tag, i, j, k, l in self.diffs:
s = f"({iD})"
if iD > 0: sb.append(' | ')
if tag in ('delete', 'replace'): s = f'{s} l:{self.l[i:j]}'
if tag in ('insert', 'replace'): s = f'{s} r:{self.r[k:l]}'
sb.append(s)
iD = iD + 1
if verbose:
sb.append(f"\nequal: {self.equal}")
return ''.join(sb)
def __repr__(self) -> str:
return "<ListDiffer> {}".format(self.__str__())
用法:
left = ['a','b','c']
right = ['aa','b','c','d']
# right = ('aa','b','c','d')
ld = ListDiffer(left, right, strict=True)
print(f'ld.has_diffs(): {ld.has_diffs()}')
print(f'ld: {ld}')
print(f'ld.only_left(): {ld.only_left()}')
print(f'ld.only_right(): {ld.only_right()}')
输出:
ld.has_diffs(): True
ld: (0) l:['a'] r:['aa'] | (1) r:['d']
ld.only_left(): ['a']
ld.only_right(): ['aa', 'd']
我不能说性能,但你可以使用ld.only_left()来获得你正在寻找的结果。
其他回答
如果要删除列表a中存在于列表b中的所有值。
def list_diff(a, b):
r = []
for i in a:
if i not in b:
r.append(i)
return r
list_diff([1、2、2],[1])
结果(2,2):
or
def list_diff(a, b):
return [x for x in a if x not in b]
如果你遇到TypeError: unhashable type: 'list',你需要将列表或集转换为元组。
set(map(tuple, list_of_lists1)).symmetric_difference(set(map(tuple, list_of_lists2)))
参见如何比较python中的列表/集列表?
你可以使用列表推导式:
temp3 = [item for item in temp1 if item not in temp2]
如果您想要更类似于变更集的东西……可以使用Counter
from collections import Counter
def diff(a, b):
""" more verbose than needs to be, for clarity """
ca, cb = Counter(a), Counter(b)
to_add = cb - ca
to_remove = ca - cb
changes = Counter(to_add)
changes.subtract(to_remove)
return changes
lista = ['one', 'three', 'four', 'four', 'one']
listb = ['one', 'two', 'three']
In [127]: diff(lista, listb)
Out[127]: Counter({'two': 1, 'one': -1, 'four': -2})
# in order to go from lista to list b, you need to add a "two", remove a "one", and remove two "four"s
In [128]: diff(listb, lista)
Out[128]: Counter({'four': 2, 'one': 1, 'two': -1})
# in order to go from listb to lista, you must add two "four"s, add a "one", and remove a "two"
我在这个游戏中有点晚了,但你可以做一个性能的比较,上面提到的一些代码和这个,两个最快的竞争者是,
list(set(x).symmetric_difference(set(y)))
list(set(x) ^ set(y))
我为我的初级编码水平道歉。
import time
import random
from itertools import filterfalse
# 1 - performance (time taken)
# 2 - correctness (answer - 1,4,5,6)
# set performance
performance = 1
numberoftests = 7
def answer(x,y,z):
if z == 0:
start = time.clock()
lists = (str(list(set(x)-set(y))+list(set(y)-set(y))))
times = ("1 = " + str(time.clock() - start))
return (lists,times)
elif z == 1:
start = time.clock()
lists = (str(list(set(x).symmetric_difference(set(y)))))
times = ("2 = " + str(time.clock() - start))
return (lists,times)
elif z == 2:
start = time.clock()
lists = (str(list(set(x) ^ set(y))))
times = ("3 = " + str(time.clock() - start))
return (lists,times)
elif z == 3:
start = time.clock()
lists = (filterfalse(set(y).__contains__, x))
times = ("4 = " + str(time.clock() - start))
return (lists,times)
elif z == 4:
start = time.clock()
lists = (tuple(set(x) - set(y)))
times = ("5 = " + str(time.clock() - start))
return (lists,times)
elif z == 5:
start = time.clock()
lists = ([tt for tt in x if tt not in y])
times = ("6 = " + str(time.clock() - start))
return (lists,times)
else:
start = time.clock()
Xarray = [iDa for iDa in x if iDa not in y]
Yarray = [iDb for iDb in y if iDb not in x]
lists = (str(Xarray + Yarray))
times = ("7 = " + str(time.clock() - start))
return (lists,times)
n = numberoftests
if performance == 2:
a = [1,2,3,4,5]
b = [3,2,6]
for c in range(0,n):
d = answer(a,b,c)
print(d[0])
elif performance == 1:
for tests in range(0,10):
print("Test Number" + str(tests + 1))
a = random.sample(range(1, 900000), 9999)
b = random.sample(range(1, 900000), 9999)
for c in range(0,n):
#if c not in (1,4,5,6):
d = answer(a,b,c)
print(d[1])