def m_svm():
if ARGV.one_vs:
svm_model = svm.svm_to_binary(svm.svm_raw())
else:
svm_model = multi.one_against_one(svm.svm_to_binary(svm.svm_raw()))
# return milk.defaultclassifier(mode='slow', multi_strategy='1-vs-1')
learner = milk.supervised.classifier.ctransforms(
# remove nans
supervised.normalise.chkfinite(),
# normalize to [-1,1]
supervised.normalise.interval_normalise(),
# feature selection
featureselection.featureselector(
featureselection.linear_independent_features),
# sda filter
featureselection.sda_filter(),
# same parameter range as 'medium'
supervised.gridsearch(
svm_model,
params = {
'C': 2.0 ** np.arange(-2, 4),
'kernel': [ svm.rbf_kernel(2.0 ** i) for i in xrange(-4, 4) ]
}
)
)
return learner
def test_rbf_kernel_call_many():
from milk.supervised.svm import rbf_kernel
np.random.seed(232)
X = np.random.random((32,16))
k = rbf_kernel(1.)
pre = k.preprocess(X)
qs = np.random.random((8,16))
mapped = np.array(list(map(pre, qs)))
manyed = pre.call_many(qs)
assert np.allclose(manyed, mapped)
def test_rbf_kernel_call_many():
from milk.supervised.svm import rbf_kernel
np.random.seed(232)
X = np.random.random((32, 16))
k = rbf_kernel(1.)
pre = k.preprocess(X)
qs = np.random.random((8, 16))
mapped = np.array(map(pre, qs))
manyed = pre.call_many(qs)
assert np.allclose(manyed, mapped)
def bench_milk(X, y, T, valid):
#
# .. milk ..
#
from milk.supervised import svm
start = datetime.now()
learner = svm.svm_raw(
kernel=svm.rbf_kernel(sigma=1./X.shape[1]), C=1.)
model = learner.train(X,y)
pred = np.sign(map(model.apply, T))
score = np.mean(pred == valid)
return score, datetime.now() - start
def test_nfoldcrossvalidation():
np.random.seed(22)
features = np.array(
[np.random.rand(8 + (i % 3), 12) * (i // 20) for i in range(40)],
dtype=object)
labels = np.zeros(40, int)
labels[20:] = 1
classifier = milk.supervised.grouped.voting_classifier(
milk.supervised.svm_simple(C=1., kernel=rbf_kernel(1. / 12)))
cmat, names = milk.nfoldcrossvalidation(features,
labels,
classifier=classifier)
assert cmat.shape == (2, 2)
assert sorted(names) == list(range(2))
def m_svm():
if ARGV.one_vs:
svm_model = svm.svm_to_binary(svm.svm_raw())
else:
svm_model = multi.one_against_one(svm.svm_to_binary(svm.svm_raw()))
# return milk.defaultclassifier(mode='slow', multi_strategy='1-vs-1')
learner = milk.supervised.classifier.ctransforms(
# remove nans
supervised.normalise.chkfinite(),
# normalize to [-1,1]
supervised.normalise.interval_normalise(),
# feature selection
featureselection.featureselector(
featureselection.linear_independent_features),
# sda filter
featureselection.sda_filter(),
# same parameter range as 'medium'
supervised.gridsearch(
svm_model,
params={
'C': 2.0**np.arange(-2, 4),
'kernel': [svm.rbf_kernel(2.0**i) for i in xrange(-4, 4)]
}))
return learner
def test_nfoldcrossvalidation():
np.random.seed(22)
features = np.array([np.random.rand(8+(i%3), 12)*(i//20) for i in xrange(40)], dtype=object)
labels = np.zeros(40, int)
labels[20:] = 1
classifier = milk.supervised.grouped.voting_classifier(milk.supervised.svm_simple(C=1., kernel=rbf_kernel(1./12)))
cmat, names = milk.nfoldcrossvalidation(features, labels, classifier=classifier)
assert cmat.shape == (2,2)
assert sorted(names) == range(2)