I have two lists in Python:
temp1 = ['One', 'Two', 'Three', 'Four']
temp2 = ['One', 'Two']
I want to create a third list with items from the first list which aren't in the second list:
temp3 = ['Three', 'Four']
Are there any fast ways without cycles and checking?
Here are a few simple, order-preserving ways of diffing two lists of strings.
Code
An unusual approach using pathlib:
import pathlib
temp1 = ["One", "Two", "Three", "Four"]
temp2 = ["One", "Two"]
p = pathlib.Path(*temp1)
r = p.relative_to(*temp2)
list(r.parts)
# ['Three', 'Four']
This assumes both lists contain strings with equivalent beginnings. See the docs for more details. Note, it is not particularly fast compared to set operations.
A straight-forward implementation using itertools.zip_longest:
import itertools as it
[x for x, y in it.zip_longest(temp1, temp2) if x != y]
# ['Three', 'Four']
Here is a modified version of @SuperNova's answer
def get_diff(a: list, b: list) -> list:
return list(set(a) ^ set(b))
I am little too late in the game for this but you can do a comparison of performance of some of the above mentioned code with this, two of the fastest contenders are,
list(set(x).symmetric_difference(set(y)))
list(set(x) ^ set(y))
I apologize for the elementary level of coding.
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])
I prefer to use converting to sets and then using the "difference()" function. The full code is :
temp1 = ['One', 'Two', 'Three', 'Four' ]
temp2 = ['One', 'Two']
set1 = set(temp1)
set2 = set(temp2)
set3 = set1.difference(set2)
temp3 = list(set3)
print(temp3)
Output:
>>>print(temp3)
['Three', 'Four']
It's the easiest to undersand, and morover in future if you work with large data, converting it to sets will remove duplicates if duplicates are not required. Hope it helps ;-)
Let's say we have two lists
list1 = [1, 3, 5, 7, 9]
list2 = [1, 2, 3, 4, 5]
we can see from the above two lists that items 1, 3, 5 exist in list2 and items 7, 9 do not. On the other hand, items 1, 3, 5 exist in list1 and items 2, 4 do not.
What is the best solution to return a new list containing items 7, 9 and 2, 4?
All answers above find the solution, now whats the most optimal?
def difference(list1, list2):
new_list = []
for i in list1:
if i not in list2:
new_list.append(i)
for j in list2:
if j not in list1:
new_list.append(j)
return new_list
versus
def sym_diff(list1, list2):
return list(set(list1).symmetric_difference(set(list2)))
Using timeit we can see the results
t1 = timeit.Timer("difference(list1, list2)", "from __main__ import difference,
list1, list2")
t2 = timeit.Timer("sym_diff(list1, list2)", "from __main__ import sym_diff,
list1, list2")
print('Using two for loops', t1.timeit(number=100000), 'Milliseconds')
print('Using two for loops', t2.timeit(number=100000), 'Milliseconds')
returns
[7, 9, 2, 4]
Using two for loops 0.11572412995155901 Milliseconds
Using symmetric_difference 0.11285737506113946 Milliseconds
Process finished with exit code 0
If you should remove all values from list a, which are present in list b.
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])
Result: [2,2]
or
def list_diff(a, b):
return [x for x in a if x not in b]
I know this question got great answers already but I wish to add the following method using numpy.
temp1 = ['One', 'Two', 'Three', 'Four']
temp2 = ['One', 'Two']
list(np.setdiff1d(temp1,temp2))
['Four', 'Three'] #Output
Here is an simple way to distinguish two lists (whatever the contents are), you can get the result as shown below :
>>> from sets import Set
>>>
>>> l1 = ['xvda', False, 'xvdbb', 12, 'xvdbc']
>>> l2 = ['xvda', 'xvdbb', 'xvdbc', 'xvdbd', None]
>>>
>>> Set(l1).symmetric_difference(Set(l2))
Set([False, 'xvdbd', None, 12])
Hope this will helpful.
You can cycle through the first list and, for every item that isn't in the second list but is in the first list, add it to the third list. E.g:
temp3 = []
for i in temp1:
if i not in temp2:
temp3.append(i)
print(temp3)
def diffList(list1, list2): # returns the difference between two lists.
if len(list1) > len(list2):
return (list(set(list1) - set(list2)))
else:
return (list(set(list2) - set(list1)))
e.g. if list1 = [10, 15, 20, 25, 30, 35, 40] and list2 = [25, 40, 35] then the returned list will be output = [10, 20, 30, 15]
Following on @arkolec's answer, here is a utility class for comparing lists, tuples and sets:
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__())
Usage:
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()}')
Output:
ld.has_diffs(): True
ld: (0) l:['a'] r:['aa'] | (1) r:['d']
ld.only_left(): ['a']
ld.only_right(): ['aa', 'd']
I cannot speak to performance but you could use ld.only_left() to get the result you are looking for.