David Cournapeau wrote:
Hi,
When trying to speed up some matplotlib routines with the matplotlib
dev team, I noticed that numpy.clip is pretty slow: clip(data, m, M) is
slower than a direct numpy implementation (that is data[data<m] = m;
data[data>M] = M; return data.copy()). My understanding is that the code
does the same thing, right ?
Below, a small script which shows the difference (twice slower for a
8000x256 array on my workstation):
I think there was a bug in your clip2_bench that was making it
artificially fast. Attached is a script that I think gives a more fair
comparison, in which clip1 and clip2 are nearly identical, and includes
a third version using putmask which is faster than either of the others:
15 function calls in 6.450 CPU seconds
Ordered by: cumulative time
ncalls tottime percall cumtime percall filename:lineno(function)
1 0.004 0.004 6.450 6.450 cliptest.py:10(bench_clip)
1 2.302 2.302 2.302 2.302 cliptest.py:19(clip2_bench)
1 0.013 0.013 2.280 2.280 cliptest.py:15(clip1_bench)
10 2.267 0.227 2.267 0.227
/usr/local/lib/python2.4/site-packages/numpy/core/fromnumeric.py:357(clip)
1 1.498 1.498 1.498 1.498 cliptest.py:25(clip3_bench)
1 0.366 0.366 0.366 0.366
cliptest.py:6(generate_data_2d)
0 0.000 0.000 profile:0(profiler)
Eric
import numpy as N
#==========================
# To benchmark imshow alone
#==========================
def generate_data_2d(fr, nwin, hop, len):
nframes = 1.0 * fr / hop * len
return N.random.randn(nframes, nwin)
def bench_clip():
m = -1.
M = 1.
# 2 minutes (120 sec) of sounds @ 8 kHz with 256 samples with 50 %
overlap
data = generate_data_2d(8000, 256, 128, 120)
def clip1_bench(data, niter):
for i in range(niter):
blop = N.clip(data, m, M)
def clip2_bench(data, niter):
for i in range(niter):
data[data<m] = m
data[data<M] = M
blop = data.copy()
clip1_bench(data, 10)
clip2_bench(data, 10)
if __name__ == '__main__':
# test clip
import hotshot, hotshot.stats
profile_file = 'clip.prof'
prof = hotshot.Profile(profile_file, lineevents=1)
prof.runcall(bench_clip)
p = hotshot.stats.load(profile_file)
print p.sort_stats('cumulative').print_stats(20)
prof.close()
cheers,
David
_______________________________________________
Numpy-discussion mailing list
[email protected]
http://projects.scipy.org/mailman/listinfo/numpy-discussion
import numpy as N
#==========================
# To benchmark imshow alone
#==========================
def generate_data_2d(fr, nwin, hop, len):
nframes = 1.0 * fr / hop * len
return N.random.randn(nframes, nwin)
def bench_clip():
m = -1.
M = 1.
data = generate_data_2d(8000, 256, 128, 120)
def clip1_bench(data, niter):
for i in range(niter):
blop = N.clip(data, m, M)
def clip2_bench(data, niter):
for i in range(niter):
d = data.copy()
d[d<m] = m
d[d>M] = M
def clip3_bench(data, niter):
for i in range(niter):
d = data.copy()
N.putmask(d, d<m, m)
N.putmask(d, d>M, M)
clip1_bench(data, 10)
clip2_bench(data, 10)
clip3_bench(data, 10)
if __name__ == '__main__':
# test clip
import hotshot, hotshot.stats
profile_file = 'clip.prof'
prof = hotshot.Profile(profile_file, lineevents=1)
prof.runcall(bench_clip)
p = hotshot.stats.load(profile_file)
print p.sort_stats('cumulative').print_stats(30)
prof.close()
_______________________________________________
Numpy-discussion mailing list
[email protected]
http://projects.scipy.org/mailman/listinfo/numpy-discussion
