Created
April 14, 2014 14:13
-
-
Save morenopc/10651856 to your computer and use it in GitHub Desktop.
Python, compute list difference
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def diff(a, b): | |
b = set(b) | |
return [aa for aa in a if aa not in b] | |
def set_diff(a, b): | |
return list(set(a) - set(b)) | |
diff_lamb_hension = lambda l1,l2: [x for x in l1 if x not in l2] | |
diff_lamb_filter = lambda l1,l2: filter(lambda x: x not in l2, l1) | |
from difflib import SequenceMatcher | |
def squeezer(a, b): | |
squeeze = SequenceMatcher(None, a, b) | |
return reduce(lambda p,q: p+q, map( | |
lambda t: squeeze.a[t[1]:t[2]], | |
filter(lambda x:x[0]!='equal', | |
squeeze.get_opcodes()))) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Small | |
a = range(10) | |
b = range(10/2) | |
timeit[diff(a, b)] | |
100000 loops, best of 3: 1.97 µs per loop | |
timeit[set_diff(a, b)] | |
100000 loops, best of 3: 2.71 µs per loop | |
timeit[diff_lamb_hension(a, b)] | |
100000 loops, best of 3: 2.1 µs per loop | |
timeit[diff_lamb_filter(a, b)] | |
100000 loops, best of 3: 3.58 µs per loop | |
timeit[squeezer(a, b)] | |
10000 loops, best of 3: 36 µs per loop | |
# Medium | |
a = range(10**4) | |
b = range(10**4/2) | |
timeit[diff(a, b)] | |
1000 loops, best of 3: 1.17 ms per loop | |
timeit[set_diff(a, b)] | |
1000 loops, best of 3: 1.27 ms per loop | |
timeit[diff_lamb_hension(a, b)] | |
1 loops, best of 3: 736 ms per loop | |
timeit[diff_lamb_filter(a, b)] | |
1 loops, best of 3: 732 ms per loop | |
timeit[squeezer(a, b)] | |
100 loops, best of 3: 12.8 ms per loop | |
# Big | |
a = xrange(10**7) | |
b = xrange(10**7/2) | |
timeit[diff(a, b)] | |
1 loops, best of 3: 1.74 s per loop | |
timeit[set_diff(a, b)] | |
1 loops, best of 3: 2.57 s per loop | |
timeit[diff_lamb_filter(a, b)] | |
# too long to wait for | |
timeit[diff_lamb_filter(a, b)] | |
# too long to wait for | |
timeit[diff_lamb_filter(a, b)] | |
# TypeError: sequence index must be integer, not 'slice' |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment