flatten a level one list
Robin Becker
robin at reportlab.com
Thu Jan 12 08:44:24 EST 2006
Peter Otten wrote:
> Tim Hochberg wrote:
>
>
>>Here's one more that's quite fast using Psyco, but only average without
>>it.
>
>
>
>>def flatten6():
>> n = min(len(xdata), len(ydata))
>> result = [None] * (2*n)
>> for i in xrange(n):
>> result[2*i] = xdata[i]
>> result[2*i+1] = ydata[i]
>
>
> I you require len(xdata) == len(ydata) there's an easy way to move the loop
> into C:
>
> def flatten7():
> n = len(xdata)
> assert len(ydata) == n
> result = [None] * (2*n)
> result[::2] = xdata
> result[1::2] = ydata
> return result
>
> $ python -m timeit 'from flatten import flatten6 as f' 'f()'
> 1000 loops, best of 3: 847 usec per loop
> $ python -m timeit 'from flatten import flatten7 as f' 'f()'
> 10000 loops, best of 3: 43.9 usec per loop
>
> Peter
That's the winner for my machine and it works in the case I need :)
The numbers are microseconds/call
I used 20 reps and n from 10 up to 1000.
no psyco
Name 10 20 100 200 500 1000
flatten1 111.383 189.298 745.709 1397.300 3499.579 6628.775
flatten2 142.923 209.496 907.182 1521.618 3565.397 7197.228
flatten3 176.224 314.342 1385.958 2733.560 6726.693 12879.067
flatten4 112.696 163.010 518.250 901.288 1979.749 3657.364
flatten5 78.334 110.768 386.949 711.794 1617.664 3255.749
flatten6 142.867 230.420 894.639 1767.012 4499.734 9017.906
flatten6a 163.093 263.330 1071.337 2084.287 5209.433 10383.610
flatten6b 180.582 275.761 1063.794 2074.705 5057.123 10043.567
flatten6c 167.898 253.664 974.202 1948.181 4821.339 9562.780
flatten6d 132.475 201.702 738.194 1406.659 3612.107 7242.038
flatten7 59.030 62.354 90.347 130.771 254.613 438.994
flatten8 88.978 173.737 1667.111 5674.297 28907.501 106330.749
flatten8a 107.388 225.951 2323.563 7088.136 34254.381 114538.384
psyco
Name 10 20 100 200 500 1000
flatten1 84.424 114.596 393.374 714.728 1809.448 3197.837
flatten2 102.387 136.302 507.243 942.494 2276.770 4451.990
flatten3 85.206 111.020 379.713 715.957 1607.104 3191.188
flatten4 102.667 144.599 509.255 856.450 1839.591 3425.128
flatten5 79.898 115.490 383.904 730.484 1739.411 3515.978
flatten6 54.560 61.293 183.012 332.109 837.146 1604.366
flatten6a 79.647 108.114 405.107 752.917 1873.674 3824.620
flatten6b 111.746 132.978 473.189 907.378 2217.600 4257.357
flatten6c 98.756 110.629 376.724 730.037 1772.963 3524.247
flatten6d 59.253 69.199 172.731 295.820 717.577 1402.720
flatten7 51.291 39.754 65.707 104.902 233.214 405.694
flatten8 87.050 166.837 1665.407 5410.576 28459.567 107847.422
flatten8a 122.753 251.457 2766.944 7931.204 36353.503 120773.674
###############################
from itertools import izip
import timeit
_R=100
def flatten1(x, y):
'''D Murman'''
return [i for pair in izip(x, y) for i in pair]
def flatten2(x, y):
'''D Murman'''
return [i for pair in zip(x, y) for i in pair]
def flatten3(x, y):
'''D Murman'''
res = []
for pair in izip(x, y):
for i in pair:
res.append(i)
return res
# New attempts:
from itertools import imap
def flatten4(x, y):
'''D Murman'''
l = []
list(imap(l.extend, izip(x, y)))
return l
from Tkinter import _flatten
def flatten5(x, y):
'''D Murman'''
return list(_flatten(zip(x, y)))
def flatten6(x,y):
'''Tim Hochberg'''
n = min(len(x), len(y))
result = [None] * (2*n)
for i in xrange(n):
result[2*i] = xdata[i]
result[2*i+1] = ydata[i]
return result
def flatten6a(x,y):
'''Robin Becker variant of 6'''
n = min(len(x), len(y))
result = [None] * (2*n)
for i in xrange(n):
result[2*i:2*i+2] = xdata[i],ydata[i]
return result
def flatten6b(x,y):
'''Robin Becker variant of 6'''
n = min(len(x), len(y))
result = [None] * (2*n)
for i,pair in enumerate(zip(xdata,ydata)):
result[2*i:2*i+2] = pair
return result
def flatten6c(x,y):
'''Robin Becker variant of 6'''
n = min(len(x), len(y))
result = [None] * (2*n)
for i,pair in enumerate(izip(xdata,ydata)):
result[2*i:2*i+2] = pair
return result
def flatten6d(x,y):
'''Robin Becker variant of 6'''
n = min(len(x), len(y))
result = [None] * (2*n)
j = 0
for i in xrange(n):
result[j] = xdata[i]
result[j+1] = ydata[i]
j+=2
return result
from operator import add as operator_add
def flatten8(x,y):
'''Paul Rubin'''
return reduce(operator_add,zip(x,y),())
def flatten8a(x,y):
'''Robin Becker variant of 8'''
return reduce(operator_add,(xy for xy in izip(x,y)),())
def flatten7(x,y):
'''Peter Otten special case equal lengths'''
n = len(x)
assert len(y) == n
result = [None] * (2*n)
result[::2] = x
result[1::2] = y
return result
funcs = [(n,v) for n,v in globals().items() if callable(v) and
n.startswith('flatten')]
funcs.sort()
def testthem():
res0 = funcs[0][1](xdata, ydata)
for name,func in funcs:
res = list(func(xdata, ydata))
if res!=res0:
print name,' fails', type(res0), type(res), res0[:5],res[:5],
res0[-5:],res[-5:]
def timethem(D,n):
for name,func in funcs:
t = timeit.Timer(name+"(xdata,ydata)",'from __main__ import
xdata,ydata,'+name)
D.setdefault(name,{})[n] = 1e7*t.timeit(_R)/float(_R)
if __name__=='__main__':
N = [10, 20, 100, 200, 500, 1000]
xdata = range(N[-1])
ydata = xdata[::-1]
testthem()
for p in 'no psyco','psyco':
D={}
if p=='psyco':
import psyco
psyco.full()
for n in N:
xdata = range(n)
ydata = xdata[::-1]
timethem(D,n)
print '\n',p
fmt = '%%%ds' % max(map(len,[x[0] for x in funcs]))
print (fmt + len(N)*' %9d') % (('Name',)+tuple(N))
fmt1 = fmt + len(N)*' %9.3f'
for name,func in funcs:
print fmt1 % tuple([name]+[D[name][n] for n in N])
print
###############################
--
Robin Becker
More information about the Python-list
mailing list