def test_remove_invariant_as_a_mapper():
from mvpa2.featsel.helpers import RangeElementSelector
from mvpa2.featsel.base import StaticFeatureSelection, SensitivityBasedFeatureSelection
from mvpa2.testing.datasets import datasets
from mvpa2.datasets.miscfx import remove_invariant_features
mapper = SensitivityBasedFeatureSelection(
lambda x: np.std(x, axis=0),
RangeElementSelector(lower=0, inclusive=False),
train_analyzer=False,
auto_train=True)
ds = datasets['uni2large'].copy()
ds.a['mapper'] = StaticFeatureSelection(np.arange(ds.nfeatures))
ds.fa['index'] = np.arange(ds.nfeatures)
ds.samples[:, [1, 8]] = 10
ds_out = mapper(ds)
# Validate that we are getting the same results as remove_invariant_features
ds_rifs = remove_invariant_features(ds)
assert_array_equal(ds_out.samples, ds_rifs.samples)
assert_array_equal(ds_out.fa.index, ds_rifs.fa.index)
assert_equal(ds_out.fa.index[1], 2)
assert_equal(ds_out.fa.index[8], 10)
def test_union_feature_selection(self):
# two methods: 5% highes F-scores, non-zero SMLR weights
fss = [SensitivityBasedFeatureSelection(
OneWayAnova(),
FractionTailSelector(0.05, mode='select', tail='upper')),
SensitivityBasedFeatureSelection(
SMLRWeights(SMLR(lm=1, implementation="C"),
postproc=sumofabs_sample()),
RangeElementSelector(mode='select'))]
fs = CombinedFeatureSelection(fss, method='union')
od_union = fs(self.dataset)
self.assertTrue(fs.method == 'union')
# check output dataset
self.assertTrue(od_union.nfeatures <= self.dataset.nfeatures)
# again for intersection
fs = CombinedFeatureSelection(fss, method='intersection')
od_intersect = fs(self.dataset)
assert_true(od_intersect.nfeatures < od_union.nfeatures)
def test_feature_selector(self):
"""Test feature selector"""
# remove 10% weekest
selector = FractionTailSelector(0.1)
data = np.array([3.5, 10, 7, 5, -0.4, 0, 0, 2, 10, 9])
# == rank [4, 5, 6, 7, 0, 3, 2, 9, 1, 8]
target10 = np.array([0, 1, 2, 3, 5, 6, 7, 8, 9])
target30 = np.array([0, 1, 2, 3, 7, 8, 9])
self.assertRaises(UnknownStateError, selector.ca.__getattribute__,
'ndiscarded')
self.assertTrue((selector(data) == target10).all())
selector.felements = 0.30 # discard 30%
self.assertTrue(selector.felements == 0.3)
self.assertTrue((selector(data) == target30).all())
self.assertTrue(selector.ca.ndiscarded == 3) # se 3 were discarded
selector = FixedNElementTailSelector(1)
# 0 1 2 3 4 5 6 7 8 9
data = np.array([3.5, 10, 7, 5, -0.4, 0, 0, 2, 10, 9])
self.assertTrue((selector(data) == target10).all())
selector.nelements = 3
self.assertTrue(selector.nelements == 3)
self.assertTrue((selector(data) == target30).all())
self.assertTrue(selector.ca.ndiscarded == 3)
# test range selector
# simple range 'above'
self.assertTrue((RangeElementSelector(lower=0)(data) == \
np.array([0,1,2,3,7,8,9])).all())
self.assertTrue((RangeElementSelector(lower=0,
inclusive=True)(data) == \
np.array([0,1,2,3,5,6,7,8,9])).all())
self.assertTrue((RangeElementSelector(lower=0, mode='discard',
inclusive=True)(data) == \
np.array([4])).all())
# simple range 'below'
self.assertTrue((RangeElementSelector(upper=2)(data) == \
np.array([4,5,6])).all())
self.assertTrue((RangeElementSelector(upper=2,
inclusive=True)(data) == \
np.array([4,5,6,7])).all())
self.assertTrue((RangeElementSelector(upper=2, mode='discard',
inclusive=True)(data) == \
np.array([0,1,2,3,8,9])).all())
# ranges
self.assertTrue((RangeElementSelector(lower=2, upper=9)(data) == \
np.array([0,2,3])).all())
self.assertTrue((RangeElementSelector(lower=2, upper=9,
inclusive=True)(data) == \
np.array([0,2,3,7,9])).all())
self.assertTrue((RangeElementSelector(
upper=2, lower=9, mode='discard',
inclusive=True)(data) == RangeElementSelector(
lower=2, upper=9, inclusive=False)(data)).all())
# non-0 elements -- should be equivalent to np.nonzero()[0]
self.assertTrue((RangeElementSelector()(data) == \
np.nonzero(data)[0]).all())
regrswh += [_lasso_lars_ic]
clfswh += [
RegressionAsClassifier(_lasso_lars_ic, descr='skl.LassoLarsIC_C()')
]
# kNN
clfswh += kNN(k=5, descr="kNN(k=5)")
clfswh += kNN(k=5, voting='majority', descr="kNN(k=5, voting='majority')")
clfswh += \
FeatureSelectionClassifier(
kNN(),
SensitivityBasedFeatureSelection(
SMLRWeights(SMLR(lm=1.0, implementation="C"),
postproc=maxofabs_sample()),
RangeElementSelector(mode='select')),
descr="kNN on SMLR(lm=1) non-0")
clfswh += \
FeatureSelectionClassifier(
kNN(),
SensitivityBasedFeatureSelection(
OneWayAnova(),
FractionTailSelector(0.05, mode='select', tail='upper')),
descr="kNN on 5%(ANOVA)")
clfswh += \
FeatureSelectionClassifier(
kNN(),
SensitivityBasedFeatureSelection(
OneWayAnova(),