def test_split_samples_probability_mapper(self):
skip_if_no_external('scipy')
nf = 10
ns = 100
nsubj = 5
nchunks = 5
data = np.random.normal(size=(ns, nf))
ds = AttrDataset(data,
sa=dict(sidx=np.arange(ns),
targets=np.arange(ns) % nchunks,
chunks=np.floor(np.arange(ns) * nchunks / ns),
subjects=np.arange(ns) /
(ns / nsubj / nchunks) % nsubj),
fa=dict(fidx=np.arange(nf)))
analyzer = OneWayAnova()
element_selector = FractionTailSelector(.4,
mode='select',
tail='upper')
common = True
m = SplitSamplesProbabilityMapper(analyzer,
'subjects',
probability_label='fprob',
select_common_features=common,
selector=element_selector)
m.train(ds)
y = m(ds)
z = m(ds.samples)
assert_array_equal(z, y.samples)
assert_equal(y.shape, (100, 4))
def test_compound_node(self):
data = np.asarray([[1, 2, 3, 4]], dtype=np.float_).T
ds = AttrDataset(data, sa=dict(targets=[0, 0, 1, 1]))
add = lambda x: lambda y: x + y
mul = lambda x: lambda y: x * y
add2 = FxNode(add(2))
mul3 = FxNode(mul(3))
assert_array_equal(add2(ds).samples, data + 2)
add2mul3 = ChainNode([add2, mul3])
assert_array_equal(add2mul3(ds), (data + 2) * 3)
add2_mul3v = CombinedNode([add2, mul3], 'v')
add2_mul3h = CombinedNode([add2, mul3], 'h')
assert_array_equal(
add2_mul3v(ds).samples, np.vstack((data + 2, data * 3)))
assert_array_equal(
add2_mul3h(ds).samples, np.hstack((data + 2, data * 3)))
def test_compound_learner(self):
data = np.asarray([[1, 2, 3, 4]], dtype=np.float_).T
ds = AttrDataset(data, sa=dict(targets=[0, 0, 1, 1]))
train = ds[ds.sa.targets == 0]
test = ds[ds.sa.targets == 1]
dtrain = train.samples
dtest = test.samples
sub = FxyLearner(lambda x: lambda y: x - y)
assert_false(sub.is_trained)
sub.train(train)
assert_array_equal(sub(test).samples, dtrain - dtest)
div = FxyLearner(lambda x: lambda y: x / y)
div.train(train)
assert_array_almost_equal(div(test).samples, dtrain / dtest)
div.untrain()
subdiv = ChainLearner((sub, div))
assert_false(subdiv.is_trained)
subdiv.train(train)
assert_true(subdiv.is_trained)
subdiv.untrain()
assert_raises(RuntimeError, subdiv, test)
subdiv.train(train)
assert_array_almost_equal(
subdiv(test).samples, dtrain / (dtrain - dtest))
sub_div = CombinedLearner((sub, div), 'v')
assert_true(sub_div.is_trained)
sub_div.untrain()
subdiv.train(train)
assert_true(sub_div.is_trained)
assert_array_almost_equal(
sub_div(test).samples, np.vstack((dtrain - dtest, dtrain / dtest)))
def load_dataset(dataset_file):
ds = AttrDataset.from_hdf5(dataset_file)
return ds
def load_dataset(dataset_file):
ds = AttrDataset.from_hdf5(dataset_file)
return ds