def bench_pymvpa():
#
# .. PyMVPA ..
#
from mvpa.mappers.mdp_adaptor import PCAMapper as MVPA_PCA
from mvpa.datasets import dataset_wizard
start = datetime.now()
clf = MVPA_PCA(output_dim=n_components)
data = dataset_wizard(samples=X)
clf.train(data)
return datetime.now() - start
def bench_pymvpa(X, y, T, valid):
#
# .. PyMVPA ..
#
from mvpa.mappers.mdp_adaptor import PCAMapper
from mvpa.datasets import dataset_wizard
start = datetime.now()
clf = PCAMapper(output_dim=n_components)
data = dataset_wizard(samples=X)
clf.train(data)
delta = datetime.now() - start
ev = explained_variance(X, clf.proj.T).sum()
return ev, delta
def bench_pymvpa(X, y, T, valid):
#
# .. PyMVPA ..
#
from mvpa.mappers.mdp_adaptor import PCAMapper
from mvpa.datasets import dataset_wizard
start = datetime.now()
clf = PCAMapper(output_dim=n_components)
data = dataset_wizard(samples=X)
clf.train(data)
delta = datetime.now() - start
ev = explained_variance(X, clf.proj.T).sum()
return ev, delta
def test_pcamapper():
# data: 40 sample feature line in 20d space (40x20; samples x features)
ndlin = Dataset(np.concatenate([np.arange(40)
for i in range(20)]).reshape(20,-1).T)
pm = PCAMapper()
# train PCA
assert_raises(mdp.NodeException, pm.train, ndlin)
ndlin.samples = ndlin.samples.astype('float')
ndlin_noise = ndlin.copy()
ndlin_noise.samples += np.random.random(size=ndlin.samples.shape)
# we have no variance for more than one PCA component, hence just one
# actual non-zero eigenvalue
assert_raises(mdp.NodeException, pm.train, ndlin)
pm.train(ndlin_noise)
assert_equal(pm.proj.shape, (20, 20))
# now project data into PCA space
p = pm.forward(ndlin.samples)
assert_equal(p.shape, (40, 20))
# check that the mapped data can be fully recovered by 'reverse()'
assert_array_almost_equal(pm.reverse(p), ndlin)
def test_pcamapper():
# data: 40 sample feature line in 20d space (40x20; samples x features)
ndlin = Dataset(
np.concatenate([np.arange(40) for i in range(20)]).reshape(20, -1).T)
pm = PCAMapper()
# train PCA
assert_raises(mdp.NodeException, pm.train, ndlin)
ndlin.samples = ndlin.samples.astype('float')
ndlin_noise = ndlin.copy()
ndlin_noise.samples += np.random.random(size=ndlin.samples.shape)
# we have no variance for more than one PCA component, hence just one
# actual non-zero eigenvalue
assert_raises(mdp.NodeException, pm.train, ndlin)
pm.train(ndlin_noise)
assert_equal(pm.proj.shape, (20, 20))
# now project data into PCA space
p = pm.forward(ndlin.samples)
assert_equal(p.shape, (40, 20))
# check that the mapped data can be fully recovered by 'reverse()'
assert_array_almost_equal(pm.reverse(p), ndlin)
from mvpa.mappers.svd import SVDMapper
from mvpa.mappers.mdp_adaptor import ICAMapper, PCAMapper
from mvpa import cfg
center = [10, 20]
axis_range = 7
##REF: Name was automagically refactored
def plot_proj_dir(p):
pl.plot([0, p[0, 0]], [0, p[0, 1]], linewidth=3, hold=True, color='y')
pl.plot([0, p[1, 0]], [0, p[1, 1]], linewidth=3, hold=True, color='k')
mappers = {
'PCA': PCAMapper(),
'SVD': SVDMapper(),
'ICA': ICAMapper(alg='CuBICA'),
}
datasets = [
noisy_2d_fx(100, lambda x: x, [lambda x: x], center, noise_std=0.5),
noisy_2d_fx(50,
lambda x: x, [lambda x: x, lambda x: -x],
center,
noise_std=0.5),
noisy_2d_fx(50,
lambda x: x, [lambda x: x, lambda x: 0],
center,
noise_std=0.5),
]