def test_fastica_convergence_fail():
# Test the FastICA algorithm on very simple data
# (see test_non_square_fastica).
# Ensure a ConvergenceWarning raised if the tolerance is sufficiently low.
rng = np.random.RandomState(0)
n_samples = 1000
# Generate two sources:
t = np.linspace(0, 100, n_samples)
s1 = np.sin(t)
s2 = np.ceil(np.sin(np.pi * t))
s = np.c_[s1, s2].T
center_and_norm(s)
s1, s2 = s
# Mixing matrix
mixing = rng.randn(6, 2)
m = np.dot(mixing, s)
# Do fastICA with tolerance 0. to ensure failing convergence
ica = FastICA(algorithm="parallel",
n_components=2,
random_state=rng,
max_iter=2,
tol=0.)
assert_warns(ConvergenceWarning, ica.fit, m.T)
def test_ovr_always_present():
# Test that ovr works with classes that are always present or absent.
# Note: tests is the case where _ConstantPredictor is utilised
X = np.ones((10, 2))
X[:5, :] = 0
# Build an indicator matrix where two features are always on.
# As list of lists, it would be: [[int(i >= 5), 2, 3] for i in range(10)]
y = np.zeros((10, 3))
y[5:, 0] = 1
y[:, 1] = 1
y[:, 2] = 1
ovr = OneVsRestClassifier(LogisticRegression())
assert_warns(UserWarning, ovr.fit, X, y)
y_pred = ovr.predict(X)
assert_array_equal(np.array(y_pred), np.array(y))
y_pred = ovr.decision_function(X)
assert np.unique(y_pred[:, -2:]) == 1
y_pred = ovr.predict_proba(X)
assert_array_equal(y_pred[:, -1], np.ones(X.shape[0]))
# y has a constantly absent label
y = np.zeros((10, 2))
y[5:, 0] = 1 # variable label
ovr = OneVsRestClassifier(LogisticRegression())
assert_warns(UserWarning, ovr.fit, X, y)
y_pred = ovr.predict_proba(X)
assert_array_equal(y_pred[:, -1], np.zeros(X.shape[0]))
def test_fastica_nowhiten():
m = [[0, 1], [1, 0]]
# test for issue #697
ica = FastICA(n_components=1, whiten=False, random_state=0)
assert_warns(UserWarning, ica.fit, m)
assert hasattr(ica, 'mixing_')
def test_identical_regressors():
newX = X.copy()
newX[:, 1] = newX[:, 0]
gamma = np.zeros(n_features)
gamma[0] = gamma[1] = 1.
newy = np.dot(newX, gamma)
assert_warns(RuntimeWarning, orthogonal_mp, newX, newy, 2)
def check_oob_score(name, X, y, n_estimators=20):
# Check that oob prediction is a good estimation of the generalization
# error.
# Proper behavior
est = FOREST_ESTIMATORS[name](oob_score=True,
random_state=0,
n_estimators=n_estimators,
bootstrap=True)
n_samples = X.shape[0]
est.fit(X[:n_samples // 2, :], y[:n_samples // 2])
test_score = est.score(X[n_samples // 2:, :], y[n_samples // 2:])
if name in FOREST_CLASSIFIERS:
assert abs(test_score - est.oob_score_) < 0.1
else:
assert test_score > est.oob_score_
assert est.oob_score_ > .8
# Check warning if not enough estimators
with np.errstate(divide="ignore", invalid="ignore"):
est = FOREST_ESTIMATORS[name](oob_score=True,
random_state=0,
n_estimators=1,
bootstrap=True)
assert_warns(UserWarning, est.fit, X, y)
def test_enet_coordinate_descent(klass, n_classes, kwargs):
"""Test that a warning is issued if model does not converge"""
clf = klass(max_iter=2, **kwargs)
n_samples = 5
n_features = 2
X = np.ones((n_samples, n_features)) * 1e50
y = np.ones((n_samples, n_classes))
if klass == Lasso:
y = y.ravel()
assert_warns(ConvergenceWarning, clf.fit, X, y)
def test_ridge_regression_convergence_fail():
rng = np.random.RandomState(0)
y = rng.randn(5)
X = rng.randn(5, 10)
assert_warns(ConvergenceWarning,
ridge_regression,
X,
y,
alpha=1.0,
solver="sparse_cg",
tol=0.,
max_iter=None,
verbose=1)
def test_lda_priors():
# Test priors (negative priors)
priors = np.array([0.5, -0.5])
clf = LinearDiscriminantAnalysis(priors=priors)
msg = "priors must be non-negative"
assert_raise_message(ValueError, msg, clf.fit, X, y)
# Test that priors passed as a list are correctly handled (run to see if
# failure)
clf = LinearDiscriminantAnalysis(priors=[0.5, 0.5])
clf.fit(X, y)
# Test that priors always sum to 1
priors = np.array([0.5, 0.6])
prior_norm = np.array([0.45, 0.55])
clf = LinearDiscriminantAnalysis(priors=priors)
assert_warns(UserWarning, clf.fit, X, y)
assert_array_almost_equal(clf.priors_, prior_norm, 2)
def test_covariance():
# Tests Covariance module on a simple dataset.
# test covariance fit from data
cov = EmpiricalCovariance()
cov.fit(X)
emp_cov = empirical_covariance(X)
assert_array_almost_equal(emp_cov, cov.covariance_, 4)
assert_almost_equal(cov.error_norm(emp_cov), 0)
assert_almost_equal(cov.error_norm(emp_cov, norm='spectral'), 0)
assert_almost_equal(cov.error_norm(emp_cov, norm='frobenius'), 0)
assert_almost_equal(cov.error_norm(emp_cov, scaling=False), 0)
assert_almost_equal(cov.error_norm(emp_cov, squared=False), 0)
with pytest.raises(NotImplementedError):
cov.error_norm(emp_cov, norm='foo')
# Mahalanobis distances computation test
mahal_dist = cov.mahalanobis(X)
assert np.amin(mahal_dist) > 0
# test with n_features = 1
X_1d = X[:, 0].reshape((-1, 1))
cov = EmpiricalCovariance()
cov.fit(X_1d)
assert_array_almost_equal(empirical_covariance(X_1d), cov.covariance_, 4)
assert_almost_equal(cov.error_norm(empirical_covariance(X_1d)), 0)
assert_almost_equal(
cov.error_norm(empirical_covariance(X_1d), norm='spectral'), 0)
# test with one sample
# Create X with 1 sample and 5 features
X_1sample = np.arange(5).reshape(1, 5)
cov = EmpiricalCovariance()
assert_warns(UserWarning, cov.fit, X_1sample)
assert_array_almost_equal(cov.covariance_,
np.zeros(shape=(5, 5), dtype=np.float64))
# test integer type
X_integer = np.asarray([[0, 1], [1, 0]])
result = np.asarray([[0.25, -0.25], [-0.25, 0.25]])
assert_array_almost_equal(empirical_covariance(X_integer), result)
# test centered case
cov = EmpiricalCovariance(assume_centered=True)
cov.fit(X)
assert_array_equal(cov.location_, np.zeros(X.shape[1]))
def test_unreachable_accuracy():
assert_array_almost_equal(orthogonal_mp(X, y, tol=0),
orthogonal_mp(X, y, n_nonzero_coefs=n_features))
assert_array_almost_equal(
assert_warns(RuntimeWarning,
orthogonal_mp,
X,
y,
tol=0,
precompute=True),
orthogonal_mp(X, y, precompute=True, n_nonzero_coefs=n_features))
def check_warm_start_equal_n_estimators(name):
# Test if warm start with equal n_estimators does nothing and returns the
# same forest and raises a warning.
X, y = hastie_X, hastie_y
ForestEstimator = FOREST_ESTIMATORS[name]
clf = ForestEstimator(n_estimators=5,
max_depth=3,
warm_start=True,
random_state=1)
clf.fit(X, y)
clf_2 = ForestEstimator(n_estimators=5,
max_depth=3,
warm_start=True,
random_state=1)
clf_2.fit(X, y)
# Now clf_2 equals clf.
clf_2.set_params(random_state=2)
assert_warns(UserWarning, clf_2.fit, X, y)
# If we had fit the trees again we would have got a different forest as we
# changed the random state.
assert_array_equal(clf.apply(X), clf_2.apply(X))
def check_class_weight_errors(name):
# Test if class_weight raises errors and warnings when expected.
ForestClassifier = FOREST_CLASSIFIERS[name]
_y = np.vstack((y, np.array(y) * 2)).T
# Invalid preset string
clf = ForestClassifier(class_weight='the larch', random_state=0)
assert_raises(ValueError, clf.fit, X, y)
assert_raises(ValueError, clf.fit, X, _y)
# Warning warm_start with preset
clf = ForestClassifier(class_weight='balanced',
warm_start=True,
random_state=0)
assert_warns(UserWarning, clf.fit, X, y)
assert_warns(UserWarning, clf.fit, X, _y)
# Not a list or preset for multi-output
clf = ForestClassifier(class_weight=1, random_state=0)
assert_raises(ValueError, clf.fit, X, _y)
# Incorrect length list for multi-output
clf = ForestClassifier(class_weight=[{-1: 0.5, 1: 1.}], random_state=0)
assert_raises(ValueError, clf.fit, X, _y)
