def test_cache_speedup(self):
skip_if_no_external('shogun', ver_dep='shogun:rev', min_version=4455)
ck = sgSVM(kernel=CachedKernel(kernel=RbfSGKernel(sigma=2)), C=1)
sk = sgSVM(kernel=RbfSGKernel(sigma=2), C=1)
cv_c = CrossValidation(ck, NFoldPartitioner())
cv_s = CrossValidation(sk, NFoldPartitioner())
#data = datasets['uni4large']
P = 5000
data = normal_feature_dataset(snr=2,
perlabel=200,
nchunks=10,
means=np.random.randn(2, P),
nfeatures=P)
t0 = time()
ck.params.kernel.compute(data)
cachetime = time() - t0
t0 = time()
cached_err = cv_c(data)
ccv_time = time() - t0
t0 = time()
norm_err = cv_s(data)
ncv_time = time() - t0
assert_almost_equal(np.asanyarray(cached_err), np.asanyarray(norm_err))
ok_(cachetime < ncv_time)
ok_(ccv_time < ncv_time)
#print 'Regular CV time: %s seconds'%ncv_time
#print 'Caching time: %s seconds'%cachetime
#print 'Cached CV time: %s seconds'%ccv_time
speedup = ncv_time / (ccv_time + cachetime)
#print 'Speedup factor: %s'%speedup
# Speedup ideally should be 10, though it's not purely linear
self.failIf(speedup < 2, 'Problem caching data - too slow!')
bad_classifiers.append('gnpp')
for impl in sg.SVM._KNOWN_IMPLEMENTATIONS:
# Uncomment the ones to disable
if impl in bad_classifiers:
continue
clfswh += [
sg.SVM(descr="sg.LinSVM(C=def)/%s" % impl, svm_impl=impl),
sg.SVM(C=-10.0,
descr="sg.LinSVM(C=10*def)/%s" % impl,
svm_impl=impl),
sg.SVM(C=1.0, descr="sg.LinSVM(C=1)/%s" % impl, svm_impl=impl),
]
if not impl in ['svmocas']: # inherently linear only
clfswh += [
sg.SVM(kernel=RbfSGKernel(),
descr="sg.RbfSVM()/%s" % impl,
svm_impl=impl),
# sg.SVM(kernel=RbfSGKernel(),
# descr="sg.RbfSVM(gamma=0.1)/%s"
# % impl, svm_impl=impl, gamma=0.1),
# sg.SVM(descr="sg.SigmoidSVM()/%s"
# % impl, svm_impl=impl, kernel=SigmoidSGKernel(),),
]
_optional_regressions = []
if externals.exists(
'shogun.krr') and externals.versions['shogun'] >= '0.9':
_optional_regressions += ['krr']
for impl in ['libsvr'] + _optional_regressions: # \
# XXX svrlight sucks in SG -- dont' have time to figure it out