def test_iris(self, basis):
X, y = load_iris(return_X_y=True)
scml = SCML_Supervised(basis=basis, n_basis=85, k_genuine=7, k_impostor=5,
random_state=42)
scml.fit(X, y)
csep = class_separation(scml.transform(X), y)
assert csep < 0.24
def test_big_n_features(self):
X, y = make_classification(n_samples=100, n_classes=3, n_features=60,
n_informative=60, n_redundant=0, n_repeated=0,
random_state=42)
X = StandardScaler().fit_transform(X)
scml = SCML_Supervised(random_state=42)
scml.fit(X, y)
csep = class_separation(scml.transform(X), y)
assert csep < 0.7
def test_int_inputs_supervised(self, name):
value = 1.0
d = {name: value}
scml = SCML_Supervised(**d)
X = np.array([[0, 0], [1, 1], [3, 3], [4, 4]])
y = np.array([1, 1, 0, 0])
msg = ("%s should be an integer, instead it is of type"
" %s" % (name, type(value)))
with pytest.raises(ValueError) as raised_error:
scml.fit(X, y)
assert msg == raised_error.value.args[0]
def test_small_n_basis_lda(self):
X = np.array([[0, 0], [1, 1], [2, 2], [3, 3]])
y = np.array([0, 0, 1, 1])
n_class = 2
scml = SCML_Supervised(n_basis=n_class-1)
msg = ("The number of basis is less than the number of classes, which may"
" lead to poor discriminative performance.")
with pytest.warns(UserWarning) as raised_warning:
scml.fit(X, y)
assert msg == raised_warning[0].message.args[0]
def test_lda_toy(self):
expected_n_basis = 7
model = SCML_Supervised(n_basis=expected_n_basis)
X = np.array([[0, 0], [1, 1], [2, 2], [3, 3]])
y = np.array([0, 0, 1, 1])
basis, n_basis = model._generate_bases_LDA(X, y)
# All points are along the same line, so the only possible basis will be
# the vector along that line normalized. In this case it is possible to
# obtain it with positive or negative orientations.
expected_basis = np.ones((expected_n_basis, 2)) / np.sqrt(2)
assert n_basis == expected_n_basis
np.testing.assert_allclose(np.abs(basis), expected_basis)
def test_triplet_diffs_toy(self):
expected_n_basis = 10
model = SCML_Supervised(n_basis=expected_n_basis)
X = np.array([[0, 0], [1, 1], [2, 2], [3, 3]])
triplets = np.array([[0, 1, 2], [0, 1, 3], [1, 0, 2], [1, 0, 3],
[2, 3, 1], [2, 3, 0], [3, 2, 1], [3, 2, 0]])
basis, n_basis = model._generate_bases_dist_diff(triplets, X)
# All points are along the same line, so the only possible basis will be
# the vector along that line normalized.
expected_basis = np.ones((expected_n_basis, 2)) / np.sqrt(2)
assert n_basis == expected_n_basis
np.testing.assert_allclose(basis, expected_basis)
def test_iris(self, basis):
"""
SCML applied to Iris dataset should give better results when
computing class separation.
"""
X, y = load_iris(return_X_y=True)
before = class_separation(X, y)
scml = SCML_Supervised(basis=basis, n_basis=85, k_genuine=7, k_impostor=5,
random_state=42)
scml.fit(X, y)
after = class_separation(scml.transform(X), y)
assert before > after + 0.03 # It's better by a margin of 0.03
def test_lda(self, n_samples, n_features, n_classes):
X, y = make_classification(n_samples=n_samples, n_classes=n_classes,
n_features=n_features, n_informative=n_features,
n_redundant=0, n_repeated=0)
X = StandardScaler().fit_transform(X)
model = SCML_Supervised()
basis, n_basis = model._generate_bases_LDA(X, y)
num_eig = min(n_classes - 1, n_features)
expected_n_basis = min(20 * n_features, n_samples * 2 * num_eig - 1)
assert n_basis == expected_n_basis
assert basis.shape == (expected_n_basis, n_features)
def test_big_n_basis_lda(self):
X = np.array([[0, 0], [1, 1], [3, 3]])
y = np.array([1, 2, 3])
n_class = 3
num_eig = min(n_class - 1, X.shape[1])
n_basis = X.shape[0] * 2 * num_eig
scml = SCML_Supervised(n_basis=n_basis)
msg = ("Not enough samples to generate %d LDA bases, n_basis"
"should be smaller than %d" % (n_basis, n_basis))
with pytest.raises(ValueError) as raised_error:
scml.fit(X, y)
assert msg == raised_error.value.args[0]
def test_triplet_diffs(self, n_samples, n_features, n_classes):
X, y = make_classification(n_samples=n_samples, n_classes=n_classes,
n_features=n_features, n_informative=n_features,
n_redundant=0, n_repeated=0)
X = StandardScaler().fit_transform(X)
model = SCML_Supervised()
constraints = Constraints(y)
triplets = constraints.generate_knntriplets(X, model.k_genuine,
model.k_impostor)
basis, n_basis = model._generate_bases_dist_diff(triplets, X)
expected_n_basis = n_features * 80
assert n_basis == expected_n_basis
assert basis.shape == (expected_n_basis, n_features)
def test_lda(self, n_samples, n_features, n_classes):
"""
Test that when n_basis=None, the correct n_basis is generated,
for SCML_Supervised and different values of n_samples, n_features
and n_classes.
"""
X, y = make_classification(n_samples=n_samples, n_classes=n_classes,
n_features=n_features, n_informative=n_features,
n_redundant=0, n_repeated=0)
X = StandardScaler().fit_transform(X)
msg = "As no value for `n_basis` was selected, "
with pytest.warns(UserWarning) as raised_warning:
model = SCML_Supervised(n_basis=None) # Explicit n_basis=None
basis, n_basis = model._generate_bases_LDA(X, y)
assert msg in str(raised_warning[0].message)
num_eig = min(n_classes - 1, n_features)
expected_n_basis = min(20 * n_features, n_samples * 2 * num_eig - 1)
assert n_basis == expected_n_basis
assert basis.shape == (expected_n_basis, n_features)
def test_triplet_diffs(self, n_samples, n_features, n_classes):
"""
Test that the correct value of n_basis is being generated with
different triplet constraints.
"""
X, y = make_classification(n_samples=n_samples, n_classes=n_classes,
n_features=n_features, n_informative=n_features,
n_redundant=0, n_repeated=0)
X = StandardScaler().fit_transform(X)
model = SCML_Supervised(n_basis=None) # Explicit n_basis=None
constraints = Constraints(y)
triplets = constraints.generate_knntriplets(X, model.k_genuine,
model.k_impostor)
msg = "As no value for `n_basis` was selected, "
with pytest.warns(UserWarning) as raised_warning:
basis, n_basis = model._generate_bases_dist_diff(triplets, X)
assert msg in str(raised_warning[0].message)
expected_n_basis = n_features * 80
assert n_basis == expected_n_basis
assert basis.shape == (expected_n_basis, n_features)
def test_scml(self):
msg = "As no value for `n_basis` was selected, "
with pytest.warns(UserWarning) as raised_warning:
check_estimator(SCML_Supervised())
assert msg in str(raised_warning[0].message)
(SDML(prior='identity', balance_param=1e-5), build_pairs)
]
ids_pairs_learners = list(
map(lambda x: x.__class__.__name__,
[learner for (learner, _) in pairs_learners]))
classifiers = [(Covariance(), build_classification),
(LFDA(), build_classification), (LMNN(), build_classification),
(NCA(), build_classification), (RCA(), build_classification),
(ITML_Supervised(max_iter=5), build_classification),
(LSML_Supervised(), build_classification),
(MMC_Supervised(max_iter=5), build_classification),
(RCA_Supervised(num_chunks=5), build_classification),
(SDML_Supervised(prior='identity',
balance_param=1e-5), build_classification),
(SCML_Supervised(), build_classification)]
ids_classifiers = list(
map(lambda x: x.__class__.__name__,
[learner for (learner, _) in classifiers]))
regressors = [(MLKR(init='pca'), build_regression)]
ids_regressors = list(
map(lambda x: x.__class__.__name__,
[learner for (learner, _) in regressors]))
WeaklySupervisedClasses = (_PairsClassifierMixin, _TripletsClassifierMixin,
_QuadrupletsClassifierMixin)
tuples_learners = pairs_learners + triplets_learners + quadruplets_learners
ids_tuples_learners = ids_pairs_learners + ids_triplets_learners \
+ ids_quadruplets_learners
def test_scml(self):
check_estimator(SCML_Supervised())