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
y = np.zeros((10, 3))
y[5:, 0] = 1
y[:, 1] = 1
y[:, 2] = 1
[[int(i >= 5), 2, 3] for i in range(10)]
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_equal(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_k_means_function():
# test calling the k_means function directly
# catch output
old_stdout = sys.stdout
sys.stdout = StringIO()
try:
cluster_centers, labels, inertia = k_means(X, n_clusters=n_clusters,
verbose=True)
finally:
sys.stdout = old_stdout
centers = cluster_centers
assert_equal(centers.shape, (n_clusters, n_features))
labels = labels
assert_equal(np.unique(labels).shape[0], n_clusters)
# check that the labels assignment are perfect (up to a permutation)
assert_equal(v_measure_score(true_labels, labels), 1.0)
assert_greater(inertia, 0.0)
# check warning when centers are passed
assert_warns(RuntimeWarning, k_means, X, n_clusters=n_clusters,
init=centers)
# to many clusters desired
assert_raises(ValueError, k_means, X, n_clusters=X.shape[0] + 1)
def test_check_symmetric():
arr_sym = np.array([[0, 1], [1, 2]])
arr_bad = np.ones(2)
arr_asym = np.array([[0, 2], [0, 2]])
test_arrays = {'dense': arr_asym,
'dok': sp.dok_matrix(arr_asym),
'csr': sp.csr_matrix(arr_asym),
'csc': sp.csc_matrix(arr_asym),
'coo': sp.coo_matrix(arr_asym),
'lil': sp.lil_matrix(arr_asym),
'bsr': sp.bsr_matrix(arr_asym)}
# check error for bad inputs
assert_raises(ValueError, check_symmetric, arr_bad)
# check that asymmetric arrays are properly symmetrized
for arr_format, arr in test_arrays.items():
# Check for warnings and errors
assert_warns(UserWarning, check_symmetric, arr)
assert_raises(ValueError, check_symmetric, arr, raise_exception=True)
output = check_symmetric(arr, raise_warning=False)
if sp.issparse(output):
assert_equal(output.format, arr_format)
assert_array_equal(output.toarray(), arr_sym)
else:
assert_array_equal(output, arr_sym)
def test_logistic_regression_path_convergence_fail():
rng = np.random.RandomState(0)
X = np.concatenate((rng.randn(100, 2) + [1, 1], rng.randn(100, 2)))
y = [1] * 100 + [-1] * 100
Cs = [1e3]
assert_warns(ConvergenceWarning, logistic_regression_path,
X, y, Cs=Cs, tol=0., max_iter=1, random_state=0, verbose=1)
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_k_means_function():
# test calling the k_means function directly
# catch output
old_stdout = sys.stdout
sys.stdout = StringIO()
try:
cluster_centers, labels, inertia = k_means(X, n_clusters=n_clusters,
sample_weight=None,
verbose=True)
finally:
sys.stdout = old_stdout
centers = cluster_centers
assert_equal(centers.shape, (n_clusters, n_features))
labels = labels
assert_equal(np.unique(labels).shape[0], n_clusters)
# check that the labels assignment are perfect (up to a permutation)
assert_equal(v_measure_score(true_labels, labels), 1.0)
assert_greater(inertia, 0.0)
# check warning when centers are passed
assert_warns(RuntimeWarning, k_means, X, n_clusters=n_clusters,
sample_weight=None, init=centers)
# to many clusters desired
assert_raises(ValueError, k_means, X, n_clusters=X.shape[0] + 1,
sample_weight=None)
# kmeans for algorithm='elkan' raises TypeError on sparse matrix
assert_raise_message(TypeError, "algorithm='elkan' not supported for "
"sparse input X", k_means, X=X_csr, n_clusters=2,
sample_weight=None, algorithm="elkan")
def test_logistic_regression_convergence_warnings():
"""Test that warnings are raised if model does not converge"""
X, y = make_classification(n_samples=20, n_features=20)
clf_lib = LogisticRegression(solver='liblinear', max_iter=2, verbose=1)
assert_warns(ConvergenceWarning, clf_lib.fit, X, y)
assert_equal(clf_lib.n_iter_, 2)
def test_lasso_lars_vs_lasso_cd_ill_conditioned2():
# Create an ill-conditioned situation in which the LARS has to go
# far in the path to converge, and check that LARS and coordinate
# descent give the same answers
# Note it used to be the case that Lars had to use the drop for good
# strategy for this but this is no longer the case with the
# equality_tolerance checks
X = [[1e20, 1e20, 0],
[-1e-32, 0, 0],
[1, 1, 1]]
y = [10, 10, 1]
alpha = .0001
def objective_function(coef):
return (1. / (2. * len(X)) * linalg.norm(y - np.dot(X, coef)) ** 2
+ alpha * linalg.norm(coef, 1))
lars = linear_model.LassoLars(alpha=alpha, normalize=False)
assert_warns(ConvergenceWarning, lars.fit, X, y)
lars_coef_ = lars.coef_
lars_obj = objective_function(lars_coef_)
coord_descent = linear_model.Lasso(alpha=alpha, tol=1e-4, normalize=False)
cd_coef_ = coord_descent.fit(X, y).coef_
cd_obj = objective_function(cd_coef_)
assert_less(lars_obj, cd_obj * (1. + 1e-8))
def test_grid_search_failing_classifier():
# GridSearchCV with on_error != 'raise'
# Ensures that a warning is raised and score reset where appropriate.
X, y = make_classification(n_samples=20, n_features=10, random_state=0)
clf = FailingClassifier()
# refit=False because we only want to check that errors caused by fits
# to individual folds will be caught and warnings raised instead. If
# refit was done, then an exception would be raised on refit and not
# caught by grid_search (expected behavior), and this would cause an
# error in this test.
gs = GridSearchCV(clf, [{'parameter': [0, 1, 2]}], scoring='accuracy',
refit=False, error_score=0.0)
assert_warns(FitFailedWarning, gs.fit, X, y)
# Ensure that grid scores were set to zero as required for those fits
# that are expected to fail.
assert all(np.all(this_point.cv_validation_scores == 0.0)
for this_point in gs.grid_scores_
if this_point.parameters['parameter'] ==
FailingClassifier.FAILING_PARAMETER)
gs = GridSearchCV(clf, [{'parameter': [0, 1, 2]}], scoring='accuracy',
refit=False, error_score=float('nan'))
assert_warns(FitFailedWarning, gs.fit, X, y)
assert all(np.all(np.isnan(this_point.cv_validation_scores))
for this_point in gs.grid_scores_
if this_point.parameters['parameter'] ==
FailingClassifier.FAILING_PARAMETER)
def test_oob_score_regression():
# Check that oob prediction is a good estimation of the generalization
# error.
rng = check_random_state(0)
X_train, X_test, y_train, y_test = train_test_split(boston.data,
boston.target,
random_state=rng)
clf = BaggingRegressor(base_estimator=DecisionTreeRegressor(),
n_estimators=50,
bootstrap=True,
oob_score=True,
random_state=rng).fit(X_train, y_train)
test_score = clf.score(X_test, y_test)
assert_less(abs(test_score - clf.oob_score_), 0.1)
# Test with few estimators
assert_warns(UserWarning,
BaggingRegressor(base_estimator=DecisionTreeRegressor(),
n_estimators=1,
bootstrap=True,
oob_score=True,
random_state=rng).fit,
X_train,
y_train)
def test_grid_search_failing_classifier():
# GridSearchCV with on_error != 'raise'
# Ensures that a warning is raised and score reset where appropriate.
X, y = make_classification(n_samples=20, n_features=10, random_state=0)
clf = FailingClassifier()
# refit=False because we only want to check that errors caused by fits
# to individual folds will be caught and warnings raised instead. If
# refit was done, then an exception would be raised on refit and not
# caught by grid_search (expected behavior), and this would cause an
# error in this test.
gs = GridSearchCV(clf, [{'parameter': [0, 1, 2]}], scoring='accuracy',
refit=False, error_score=0.0)
assert_warns(FitFailedWarning, gs.fit, X, y)
n_candidates = len(gs.cv_results_['params'])
# Ensure that grid scores were set to zero as required for those fits
# that are expected to fail.
get_cand_scores = lambda i: np.array(list(
gs.cv_results_['split%d_test_score' % s][i]
for s in range(gs.n_splits_)))
assert all((np.all(get_cand_scores(cand_i) == 0.0)
for cand_i in range(n_candidates)
if gs.cv_results_['param_parameter'][cand_i] ==
FailingClassifier.FAILING_PARAMETER))
gs = GridSearchCV(clf, [{'parameter': [0, 1, 2]}], scoring='accuracy',
refit=False, error_score=float('nan'))
assert_warns(FitFailedWarning, gs.fit, X, y)
n_candidates = len(gs.cv_results_['params'])
assert all(np.all(np.isnan(get_cand_scores(cand_i)))
for cand_i in range(n_candidates)
if gs.cv_results_['param_parameter'][cand_i] ==
FailingClassifier.FAILING_PARAMETER)
def test_ward_agglomeration():
"""
Check that we obtain the correct solution in a simplistic case
"""
rnd = np.random.RandomState(0)
mask = np.ones([10, 10], dtype=np.bool)
X = rnd.randn(50, 100)
connectivity = grid_to_graph(*mask.shape)
assert_warns(DeprecationWarning, WardAgglomeration)
with warnings.catch_warnings(record=True) as warning_list:
warnings.simplefilter("always", DeprecationWarning)
if hasattr(np, 'VisibleDeprecationWarning'):
# Let's not catch the numpy internal DeprecationWarnings
warnings.simplefilter('ignore', np.VisibleDeprecationWarning)
ward = WardAgglomeration(n_clusters=5, connectivity=connectivity)
ward.fit(X)
assert_equal(len(warning_list), 1)
agglo = FeatureAgglomeration(n_clusters=5, connectivity=connectivity)
agglo.fit(X)
assert_array_equal(agglo.labels_, ward.labels_)
assert_true(np.size(np.unique(agglo.labels_)) == 5)
X_red = agglo.transform(X)
assert_true(X_red.shape[1] == 5)
X_full = agglo.inverse_transform(X_red)
assert_true(np.unique(X_full[0]).size == 5)
assert_array_almost_equal(agglo.transform(X_full), X_red)
# Check that fitting with no samples raises a ValueError
assert_raises(ValueError, agglo.fit, X[:0])
def test_oob_score_classification():
# Check that oob prediction is a good estimation of the generalization
# error.
rng = check_random_state(0)
X_train, X_test, y_train, y_test = train_test_split(iris.data,
iris.target,
random_state=rng)
for base_estimator in [DecisionTreeClassifier(), SVC()]:
clf = BaggingClassifier(base_estimator=base_estimator,
n_estimators=100,
bootstrap=True,
oob_score=True,
random_state=rng).fit(X_train, y_train)
test_score = clf.score(X_test, y_test)
assert_less(abs(test_score - clf.oob_score_), 0.1)
# Test with few estimators
assert_warns(UserWarning,
BaggingClassifier(base_estimator=base_estimator,
n_estimators=1,
bootstrap=True,
oob_score=True,
random_state=rng).fit,
X_train,
y_train)
def test_check_array_accept_sparse_type_exception():
X = [[1, 2], [3, 4]]
X_csr = sp.csr_matrix(X)
invalid_type = SVR()
msg = ("A sparse matrix was passed, but dense data is required. "
"Use X.toarray() to convert to a dense numpy array.")
assert_raise_message(TypeError, msg,
check_array, X_csr, accept_sparse=False)
with pytest.warns(DeprecationWarning):
assert_raise_message(TypeError, msg,
check_array, X_csr, accept_sparse=None)
msg = ("Parameter 'accept_sparse' should be a string, "
"boolean or list of strings. You provided 'accept_sparse={}'.")
assert_raise_message(ValueError, msg.format(invalid_type),
check_array, X_csr, accept_sparse=invalid_type)
msg = ("When providing 'accept_sparse' as a tuple or list, "
"it must contain at least one string value.")
assert_raise_message(ValueError, msg.format([]),
check_array, X_csr, accept_sparse=[])
assert_raise_message(ValueError, msg.format(()),
check_array, X_csr, accept_sparse=())
assert_raise_message(TypeError, "SVR",
check_array, X_csr, accept_sparse=[invalid_type])
# Test deprecation of 'None'
assert_warns(DeprecationWarning, check_array, X, accept_sparse=None)
def test_check_dataframe_warns_on_dtype():
# Check that warn_on_dtype also works for DataFrames.
# https://github.com/scikit-learn/scikit-learn/issues/10948
pd = importorskip("pandas")
df = pd.DataFrame([[1, 2, 3], [4, 5, 6]], dtype=object)
assert_warns_message(DataConversionWarning,
"Data with input dtype object were all converted to "
"float64.",
check_array, df, dtype=np.float64, warn_on_dtype=True)
assert_warns(DataConversionWarning, check_array, df,
dtype='numeric', warn_on_dtype=True)
assert_no_warnings(check_array, df, dtype='object', warn_on_dtype=True)
# Also check that it raises a warning for mixed dtypes in a DataFrame.
df_mixed = pd.DataFrame([['1', 2, 3], ['4', 5, 6]])
assert_warns(DataConversionWarning, check_array, df_mixed,
dtype=np.float64, warn_on_dtype=True)
assert_warns(DataConversionWarning, check_array, df_mixed,
dtype='numeric', warn_on_dtype=True)
assert_warns(DataConversionWarning, check_array, df_mixed,
dtype=object, warn_on_dtype=True)
# Even with numerical dtypes, a conversion can be made because dtypes are
# uniformized throughout the array.
df_mixed_numeric = pd.DataFrame([[1., 2, 3], [4., 5, 6]])
assert_warns(DataConversionWarning, check_array, df_mixed_numeric,
dtype='numeric', warn_on_dtype=True)
assert_no_warnings(check_array, df_mixed_numeric.astype(int),
dtype='numeric', warn_on_dtype=True)
def test_grid_search_score_method():
X, y = make_classification(n_samples=100, n_classes=2, flip_y=.2,
random_state=0)
clf = LinearSVC(random_state=0)
grid = {'C': [.1]}
search_no_scoring = GridSearchCV(clf, grid, scoring=None).fit(X, y)
search_accuracy = GridSearchCV(clf, grid, scoring='accuracy').fit(X, y)
search_no_score_method_auc = GridSearchCV(LinearSVCNoScore(), grid,
scoring='roc_auc').fit(X, y)
search_auc = GridSearchCV(clf, grid, scoring='roc_auc').fit(X, y)
# Check warning only occurs in situation where behavior changed:
# estimator requires score method to compete with scoring parameter
score_no_scoring = assert_no_warnings(search_no_scoring.score, X, y)
score_accuracy = assert_warns(ChangedBehaviorWarning,
search_accuracy.score, X, y)
score_no_score_auc = assert_no_warnings(search_no_score_method_auc.score,
X, y)
score_auc = assert_warns(ChangedBehaviorWarning,
search_auc.score, X, y)
# ensure the test is sane
assert_true(score_auc < 1.0)
assert_true(score_accuracy < 1.0)
assert_not_equal(score_auc, score_accuracy)
assert_almost_equal(score_accuracy, score_no_scoring)
assert_almost_equal(score_auc, score_no_score_auc)
def test_convergence_fail():
d = load_linnerud()
X = d.data
Y = d.target
pls_bynipals = pls_.PLSCanonical(n_components=X.shape[1],
max_iter=2, tol=1e-10)
assert_warns(ConvergenceWarning, pls_bynipals.fit, X, Y)
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 test_prf_average_compat():
# Ensure warning if f1_score et al.'s average is implicit for multiclass
y_true = [1, 2, 3, 3]
y_pred = [1, 2, 3, 1]
y_true_bin = [0, 1, 1]
y_pred_bin = [0, 1, 0]
for metric in [precision_score, recall_score, f1_score,
partial(fbeta_score, beta=2)]:
score = assert_warns(DeprecationWarning, metric, y_true, y_pred)
score_weighted = assert_no_warnings(metric, y_true, y_pred,
average='weighted')
assert_equal(score, score_weighted,
'average does not act like "weighted" by default')
# check binary passes without warning
assert_no_warnings(metric, y_true_bin, y_pred_bin)
# but binary with pos_label=None should behave like multiclass
score = assert_warns(DeprecationWarning, metric,
y_true_bin, y_pred_bin, pos_label=None)
score_weighted = assert_no_warnings(metric, y_true_bin, y_pred_bin,
pos_label=None, average='weighted')
assert_equal(score, score_weighted,
'average does not act like "weighted" by default with '
'binary data and pos_label=None')
def test_sparse_randomized_pca_inverse():
"""Test that RandomizedPCA is inversible on sparse data"""
rng = np.random.RandomState(0)
n, p = 50, 3
X = rng.randn(n, p) # spherical data
X[:, 1] *= .00001 # make middle component relatively small
# no large means because the sparse version of randomized pca does not do
# centering to avoid breaking the sparsity
X = csr_matrix(X)
# same check that we can find the original data from the transformed signal
# (since the data is almost of rank n_components)
pca = RandomizedPCA(n_components=2, random_state=0)
assert_warns(DeprecationWarning, pca.fit, X)
Y = pca.transform(X)
Y_inverse = pca.inverse_transform(Y)
assert_almost_equal(X.todense(), Y_inverse, decimal=2)
# same as above with whitening (approximate reconstruction)
pca = assert_warns(DeprecationWarning, RandomizedPCA(n_components=2,
whiten=True, random_state=0).fit, X)
Y = pca.transform(X)
Y_inverse = pca.inverse_transform(Y)
relative_max_delta = (np.abs(X.todense() - Y_inverse)
/ np.abs(X).mean()).max()
# XXX: this does not seam to work as expected:
assert_almost_equal(relative_max_delta, 0.91, decimal=2)
def test_warning_n_components_greater_than_n_features():
n_features = 20
data, _ = make_sparse_random_data(5, n_features, int(n_features / 4))
for RandomProjection in all_RandomProjection:
assert_warns(DataDimensionalityWarning,
RandomProjection(n_components=n_features + 1).fit, data)
def test_label_binarizer_multilabel():
lb = LabelBinarizer()
# test input as lists of tuples
inp = [(2, 3), (1,), (1, 2)]
indicator_mat = np.array([[0, 1, 1],
[1, 0, 0],
[1, 1, 0]])
got = assert_warns(DeprecationWarning, lb.fit_transform, inp)
assert_true(lb.multilabel_)
assert_array_equal(indicator_mat, got)
assert_equal(lb.inverse_transform(got), inp)
# test input as label indicator matrix
lb.fit(indicator_mat)
assert_array_equal(indicator_mat,
lb.inverse_transform(indicator_mat))
# regression test for the two-class multilabel case
lb = LabelBinarizer()
inp = [[1, 0], [0], [1], [0, 1]]
expected = np.array([[1, 1],
[1, 0],
[0, 1],
[1, 1]])
got = assert_warns(DeprecationWarning, lb.fit_transform, inp)
assert_true(lb.multilabel_)
assert_array_equal(expected, got)
assert_equal([set(x) for x in lb.inverse_transform(got)],
[set(x) for x in inp])
def test_unique_labels():
# Empty iterable
assert_raises(ValueError, unique_labels)
# Multiclass problem
assert_array_equal(unique_labels(xrange(10)), np.arange(10))
assert_array_equal(unique_labels(np.arange(10)), np.arange(10))
assert_array_equal(unique_labels([4, 0, 2]), np.array([0, 2, 4]))
# Multilabels
assert_array_equal(
assert_warns(DeprecationWarning, unique_labels, [(0, 1, 2), (0,), tuple(), (2, 1)]), np.arange(3)
)
assert_array_equal(assert_warns(DeprecationWarning, unique_labels, [[0, 1, 2], [0], list(), [2, 1]]), np.arange(3))
assert_array_equal(unique_labels(np.array([[0, 0, 1], [1, 0, 1], [0, 0, 0]])), np.arange(3))
assert_array_equal(unique_labels(np.array([[0, 0, 1], [0, 0, 0]])), np.arange(3))
# Several arrays passed
assert_array_equal(unique_labels([4, 0, 2], xrange(5)), np.arange(5))
assert_array_equal(unique_labels((0, 1, 2), (0,), (2, 1)), np.arange(3))
# Border line case with binary indicator matrix
assert_raises(ValueError, unique_labels, [4, 0, 2], np.ones((5, 5)))
assert_raises(ValueError, unique_labels, np.ones((5, 4)), np.ones((5, 5)))
assert_array_equal(unique_labels(np.ones((4, 5)), np.ones((5, 5))), np.arange(5))
# Some tests with strings input
assert_array_equal(unique_labels(["a", "b", "c"], ["d"]), ["a", "b", "c", "d"])
assert_array_equal(
assert_warns(DeprecationWarning, unique_labels, [["a", "b"], ["c"]], [["d"]]), ["a", "b", "c", "d"]
)
def test_compute_class_weight_auto_negative():
# Test compute_class_weight when labels are negative
# Test with balanced class labels.
classes = np.array([-2, -1, 0])
y = np.asarray([-1, -1, 0, 0, -2, -2])
cw = assert_warns(DeprecationWarning, compute_class_weight, "auto",
classes, y)
assert_almost_equal(cw.sum(), classes.shape)
assert_equal(len(cw), len(classes))
assert_array_almost_equal(cw, np.array([1., 1., 1.]))
cw = compute_class_weight("balanced", classes, y)
assert_equal(len(cw), len(classes))
assert_array_almost_equal(cw, np.array([1., 1., 1.]))
# Test with unbalanced class labels.
y = np.asarray([-1, 0, 0, -2, -2, -2])
cw = assert_warns(DeprecationWarning, compute_class_weight, "auto",
classes, y)
assert_almost_equal(cw.sum(), classes.shape)
assert_equal(len(cw), len(classes))
assert_array_almost_equal(cw, np.array([0.545, 1.636, 0.818]), decimal=3)
cw = compute_class_weight("balanced", classes, y)
assert_equal(len(cw), len(classes))
class_counts = np.bincount(y + 2)
assert_almost_equal(np.dot(cw, class_counts), y.shape[0])
assert_array_almost_equal(cw, [2. / 3, 2., 1.])
def test_oob_score_classification():
# Check that oob prediction is a good estimation of the generalization
# error.
X, y = make_imbalance(iris.data, iris.target, ratio={0: 20, 1: 25, 2: 50},
random_state=0)
X_train, X_test, y_train, y_test = train_test_split(X, y,
random_state=0)
for base_estimator in [DecisionTreeClassifier(), SVC()]:
clf = BalancedBaggingClassifier(
base_estimator=base_estimator,
n_estimators=100,
bootstrap=True,
oob_score=True,
random_state=0).fit(X_train, y_train)
test_score = clf.score(X_test, y_test)
assert abs(test_score - clf.oob_score_) < 0.1
# Test with few estimators
assert_warns(UserWarning,
BalancedBaggingClassifier(
base_estimator=base_estimator,
n_estimators=1,
bootstrap=True,
oob_score=True,
random_state=0).fit,
X_train,
y_train)
def test_timeout():
sp = svm.SVC(C=1, kernel=lambda x, y: x * y.T, probability=True,
random_state=0, max_iter=1)
with warnings.catch_warnings(record=True):
warnings.simplefilter("always")
assert_warns(ConvergenceWarning, sp.fit, X_sp, Y)
def test_label_binarizer():
lb = LabelBinarizer()
# one-class case defaults to negative label
inp = ["pos", "pos", "pos", "pos"]
expected = np.array([[0, 0, 0, 0]]).T
got = lb.fit_transform(inp)
assert_false(assert_warns(DeprecationWarning, getattr, lb, "multilabel_"))
assert_array_equal(lb.classes_, ["pos"])
assert_array_equal(expected, got)
assert_array_equal(lb.inverse_transform(got), inp)
# two-class case
inp = ["neg", "pos", "pos", "neg"]
expected = np.array([[0, 1, 1, 0]]).T
got = lb.fit_transform(inp)
assert_false(assert_warns(DeprecationWarning, getattr, lb, "multilabel_"))
assert_array_equal(lb.classes_, ["neg", "pos"])
assert_array_equal(expected, got)
to_invert = np.array([[1, 0], [0, 1], [0, 1], [1, 0]])
assert_array_equal(lb.inverse_transform(to_invert), inp)
# multi-class case
inp = ["spam", "ham", "eggs", "ham", "0"]
expected = np.array([[0, 0, 0, 1], [0, 0, 1, 0], [0, 1, 0, 0], [0, 0, 1, 0], [1, 0, 0, 0]])
got = lb.fit_transform(inp)
assert_array_equal(lb.classes_, ["0", "eggs", "ham", "spam"])
assert_false(assert_warns(DeprecationWarning, getattr, lb, "multilabel_"))
assert_array_equal(expected, got)
assert_array_equal(lb.inverse_transform(got), inp)
def test_lars_drop_for_good():
# Create an ill-conditioned situation in which the LARS has to go
# far in the path to converge, and check that LARS and coordinate
# descent give the same answers
X = [[1e20, 1e20, 0],
[-1e-32, 0, 0],
[1, 1, 1]]
y = [10, 10, 1]
alpha = .0001
def objective_function(coef):
return (1. / (2. * len(X)) * linalg.norm(y - np.dot(X, coef)) ** 2
+ alpha * linalg.norm(coef, 1))
lars = linear_model.LassoLars(alpha=alpha, normalize=False)
assert_warns(ConvergenceWarning, lars.fit, X, y)
lars_coef_ = lars.coef_
lars_obj = objective_function(lars_coef_)
coord_descent = linear_model.Lasso(alpha=alpha, tol=1e-10, normalize=False)
with ignore_warnings():
cd_coef_ = coord_descent.fit(X, y).coef_
cd_obj = objective_function(cd_coef_)
assert_less(lars_obj, cd_obj * (1. + 1e-8))
def test_ward_agglomeration():
"""
Check that we obtain the correct solution in a simplistic case
"""
rnd = np.random.RandomState(0)
mask = np.ones([10, 10], dtype=np.bool)
X = rnd.randn(50, 100)
connectivity = grid_to_graph(*mask.shape)
assert_warns(DeprecationWarning, WardAgglomeration)
with ignore_warnings():
ward = WardAgglomeration(n_clusters=5, connectivity=connectivity)
ward.fit(X)
agglo = FeatureAgglomeration(n_clusters=5, connectivity=connectivity)
agglo.fit(X)
assert_array_equal(agglo.labels_, ward.labels_)
assert_true(np.size(np.unique(agglo.labels_)) == 5)
X_red = agglo.transform(X)
assert_true(X_red.shape[1] == 5)
X_full = agglo.inverse_transform(X_red)
assert_true(np.unique(X_full[0]).size == 5)
assert_array_almost_equal(agglo.transform(X_full), X_red)
# Check that fitting with no samples raises a ValueError
assert_raises(ValueError, agglo.fit, X[:0])
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_roc_curve_toydata():
# Binary classification
y_true = [0, 1]
y_score = [0, 1]
tpr, fpr, _ = roc_curve(y_true, y_score)
roc_auc = roc_auc_score(y_true, y_score)
assert_array_almost_equal(tpr, [0, 0, 1])
assert_array_almost_equal(fpr, [0, 1, 1])
assert_almost_equal(roc_auc, 1.)
y_true = [0, 1]
y_score = [1, 0]
tpr, fpr, _ = roc_curve(y_true, y_score)
roc_auc = roc_auc_score(y_true, y_score)
assert_array_almost_equal(tpr, [0, 1, 1])
assert_array_almost_equal(fpr, [0, 0, 1])
assert_almost_equal(roc_auc, 0.)
y_true = [1, 0]
y_score = [1, 1]
tpr, fpr, _ = roc_curve(y_true, y_score)
roc_auc = roc_auc_score(y_true, y_score)
assert_array_almost_equal(tpr, [0, 1])
assert_array_almost_equal(fpr, [0, 1])
assert_almost_equal(roc_auc, 0.5)
y_true = [1, 0]
y_score = [1, 0]
tpr, fpr, _ = roc_curve(y_true, y_score)
roc_auc = roc_auc_score(y_true, y_score)
assert_array_almost_equal(tpr, [0, 0, 1])
assert_array_almost_equal(fpr, [0, 1, 1])
assert_almost_equal(roc_auc, 1.)
y_true = [1, 0]
y_score = [0.5, 0.5]
tpr, fpr, _ = roc_curve(y_true, y_score)
roc_auc = roc_auc_score(y_true, y_score)
assert_array_almost_equal(tpr, [0, 1])
assert_array_almost_equal(fpr, [0, 1])
assert_almost_equal(roc_auc, .5)
y_true = [0, 0]
y_score = [0.25, 0.75]
# assert UndefinedMetricWarning because of no positive sample in y_true
tpr, fpr, _ = assert_warns(UndefinedMetricWarning, roc_curve, y_true,
y_score)
assert_raises(ValueError, roc_auc_score, y_true, y_score)
assert_array_almost_equal(tpr, [0., 0.5, 1.])
assert_array_almost_equal(fpr, [np.nan, np.nan, np.nan])
y_true = [1, 1]
y_score = [0.25, 0.75]
# assert UndefinedMetricWarning because of no negative sample in y_true
tpr, fpr, _ = assert_warns(UndefinedMetricWarning, roc_curve, y_true,
y_score)
assert_raises(ValueError, roc_auc_score, y_true, y_score)
assert_array_almost_equal(tpr, [np.nan, np.nan, np.nan])
assert_array_almost_equal(fpr, [0., 0.5, 1.])
# Multi-label classification task
y_true = np.array([[0, 1], [0, 1]])
y_score = np.array([[0, 1], [0, 1]])
assert_raises(ValueError, roc_auc_score, y_true, y_score, average="macro")
assert_raises(ValueError,
roc_auc_score,
y_true,
y_score,
average="weighted")
assert_almost_equal(roc_auc_score(y_true, y_score, average="samples"), 1.)
assert_almost_equal(roc_auc_score(y_true, y_score, average="micro"), 1.)
y_true = np.array([[0, 1], [0, 1]])
y_score = np.array([[0, 1], [1, 0]])
assert_raises(ValueError, roc_auc_score, y_true, y_score, average="macro")
assert_raises(ValueError,
roc_auc_score,
y_true,
y_score,
average="weighted")
assert_almost_equal(roc_auc_score(y_true, y_score, average="samples"), 0.5)
assert_almost_equal(roc_auc_score(y_true, y_score, average="micro"), 0.5)
y_true = np.array([[1, 0], [0, 1]])
y_score = np.array([[0, 1], [1, 0]])
assert_almost_equal(roc_auc_score(y_true, y_score, average="macro"), 0)
assert_almost_equal(roc_auc_score(y_true, y_score, average="weighted"), 0)
assert_almost_equal(roc_auc_score(y_true, y_score, average="samples"), 0)
assert_almost_equal(roc_auc_score(y_true, y_score, average="micro"), 0)
y_true = np.array([[1, 0], [0, 1]])
y_score = np.array([[0.5, 0.5], [0.5, 0.5]])
assert_almost_equal(roc_auc_score(y_true, y_score, average="macro"), .5)
assert_almost_equal(roc_auc_score(y_true, y_score, average="weighted"), .5)
assert_almost_equal(roc_auc_score(y_true, y_score, average="samples"), .5)
assert_almost_equal(roc_auc_score(y_true, y_score, average="micro"), .5)
def test_minibatch_k_means_init_multiple_runs_with_explicit_centers():
mb_k_means = MiniBatchKMeans(init=centers.copy(),
n_clusters=n_clusters,
random_state=42,
n_init=10)
assert_warns(RuntimeWarning, mb_k_means.fit, X)
def test_check_estimator():
# tests that the estimator actually fails on "bad" estimators.
# not a complete test of all checks, which are very extensive.
# check that we have a set_params and can clone
msg = "it does not implement a 'get_params' methods"
assert_raises_regex(TypeError, msg, check_estimator, object)
assert_raises_regex(TypeError, msg, check_estimator, object())
# check that values returned by get_params match set_params
msg = "get_params result does not match what was passed to set_params"
assert_raises_regex(AssertionError, msg, check_estimator,
ModifiesValueInsteadOfRaisingError())
assert_warns(UserWarning, check_estimator, RaisesErrorInSetParams())
assert_raises_regex(AssertionError, msg, check_estimator,
ModifiesAnotherValue())
# check that we have a fit method
msg = "object has no attribute 'fit'"
assert_raises_regex(AttributeError, msg, check_estimator, BaseEstimator)
assert_raises_regex(AttributeError, msg, check_estimator, BaseEstimator())
# check that fit does input validation
msg = "TypeError not raised"
assert_raises_regex(AssertionError, msg, check_estimator,
BaseBadClassifier)
assert_raises_regex(AssertionError, msg, check_estimator,
BaseBadClassifier())
# check that sample_weights in fit accepts pandas.Series type
try:
from pandas import Series # noqa
msg = ("Estimator NoSampleWeightPandasSeriesType raises error if "
"'sample_weight' parameter is of type pandas.Series")
assert_raises_regex(ValueError, msg, check_estimator,
NoSampleWeightPandasSeriesType)
except ImportError:
pass
# check that predict does input validation (doesn't accept dicts in input)
msg = "Estimator doesn't check for NaN and inf in predict"
assert_raises_regex(AssertionError, msg, check_estimator, NoCheckinPredict)
assert_raises_regex(AssertionError, msg, check_estimator,
NoCheckinPredict())
# check that estimator state does not change
# at transform/predict/predict_proba time
msg = 'Estimator changes __dict__ during predict'
assert_raises_regex(AssertionError, msg, check_estimator, ChangesDict)
# check that `fit` only changes attribures that
# are private (start with an _ or end with a _).
msg = ('Estimator ChangesWrongAttribute should not change or mutate '
'the parameter wrong_attribute from 0 to 1 during fit.')
assert_raises_regex(AssertionError, msg, check_estimator,
ChangesWrongAttribute)
check_estimator(ChangesUnderscoreAttribute)
# check that `fit` doesn't add any public attribute
msg = (r'Estimator adds public attribute\(s\) during the fit method.'
' Estimators are only allowed to add private attributes'
' either started with _ or ended'
' with _ but wrong_attribute added')
assert_raises_regex(AssertionError, msg, check_estimator,
SetsWrongAttribute)
# check for invariant method
name = NotInvariantPredict.__name__
method = 'predict'
msg = ("{method} of {name} is not invariant when applied "
"to a subset.").format(method=method, name=name)
assert_raises_regex(AssertionError, msg, check_estimator,
NotInvariantPredict)
# check for sparse matrix input handling
name = NoSparseClassifier.__name__
msg = "Estimator %s doesn't seem to fail gracefully on sparse data" % name
# the check for sparse input handling prints to the stdout,
# instead of raising an error, so as not to remove the original traceback.
# that means we need to jump through some hoops to catch it.
old_stdout = sys.stdout
string_buffer = StringIO()
sys.stdout = string_buffer
try:
check_estimator(NoSparseClassifier)
except:
pass
finally:
sys.stdout = old_stdout
assert_true(msg in string_buffer.getvalue())
# Large indices test on bad estimator
msg = ('Estimator LargeSparseNotSupportedClassifier doesn\'t seem to '
r'support \S{3}_64 matrix, and is not failing gracefully.*')
# only supported by scipy version more than 0.14.0
if LARGE_SPARSE_SUPPORTED:
assert_raises_regex(AssertionError, msg, check_estimator,
LargeSparseNotSupportedClassifier)
# non-regression test for estimators transforming to sparse data
check_estimator(SparseTransformer())
# doesn't error on actual estimator
check_estimator(AdaBoostClassifier)
check_estimator(AdaBoostClassifier())
check_estimator(MultiTaskElasticNet)
check_estimator(MultiTaskElasticNet())
def test_minibatch_init_with_large_k():
mb_k_means = MiniBatchKMeans(init='k-means++', init_size=10, n_clusters=20)
# Check that a warning is raised, as the number clusters is larger
# than the init_size
assert_warns(RuntimeWarning, mb_k_means.fit, X)
def test_data_format():
X = [1.3, 1.1, 0.9, 1.4, 1.5, 3.2]
clf = loop.LocalOutlierProbability(X, n_neighbors=3)
assert_warns(UserWarning, clf.fit)
def test_extent():
X = np.array([[1, 1], [1, 0]])
clf = loop.LocalOutlierProbability(X, n_neighbors=2, extent=4)
assert_warns(UserWarning, clf.fit)
def test_lasso_alpha_warning():
X = [[-1], [0], [1]]
Y = [-1, 0, 1] # just a straight line
clf = Lasso(alpha=0)
assert_warns(UserWarning, clf.fit, X, Y)
def test_f_classif_constant_feature():
# Test that f_classif warns if a feature is constant throughout.
X, y = make_classification(n_samples=10, n_features=5)
X[:, 0] = 2.0
assert_warns(UserWarning, f_classif, X, y)
def test_check_array_dtype_warning():
X_int_list = [[1, 2, 3], [4, 5, 6], [7, 8, 9]]
X_float64 = np.asarray(X_int_list, dtype=np.float64)
X_float32 = np.asarray(X_int_list, dtype=np.float32)
X_int64 = np.asarray(X_int_list, dtype=np.int64)
X_csr_float64 = sp.csr_matrix(X_float64)
X_csr_float32 = sp.csr_matrix(X_float32)
X_csc_float32 = sp.csc_matrix(X_float32)
X_csc_int32 = sp.csc_matrix(X_int64, dtype=np.int32)
y = [0, 0, 1]
integer_data = [X_int64, X_csc_int32]
float64_data = [X_float64, X_csr_float64]
float32_data = [X_float32, X_csr_float32, X_csc_float32]
for X in integer_data:
X_checked = assert_no_warnings(check_array, X, dtype=np.float64,
accept_sparse=True)
assert_equal(X_checked.dtype, np.float64)
X_checked = assert_warns(DataConversionWarning, check_array, X,
dtype=np.float64,
accept_sparse=True, warn_on_dtype=True)
assert_equal(X_checked.dtype, np.float64)
# Check that the warning message includes the name of the Estimator
X_checked = assert_warns_message(DataConversionWarning,
'SomeEstimator',
check_array, X,
dtype=[np.float64, np.float32],
accept_sparse=True,
warn_on_dtype=True,
estimator='SomeEstimator')
assert_equal(X_checked.dtype, np.float64)
X_checked, y_checked = assert_warns_message(
DataConversionWarning, 'KNeighborsClassifier',
check_X_y, X, y, dtype=np.float64, accept_sparse=True,
warn_on_dtype=True, estimator=KNeighborsClassifier())
assert_equal(X_checked.dtype, np.float64)
for X in float64_data:
X_checked = assert_no_warnings(check_array, X, dtype=np.float64,
accept_sparse=True, warn_on_dtype=True)
assert_equal(X_checked.dtype, np.float64)
X_checked = assert_no_warnings(check_array, X, dtype=np.float64,
accept_sparse=True, warn_on_dtype=False)
assert_equal(X_checked.dtype, np.float64)
for X in float32_data:
X_checked = assert_no_warnings(check_array, X,
dtype=[np.float64, np.float32],
accept_sparse=True)
assert_equal(X_checked.dtype, np.float32)
assert X_checked is X
X_checked = assert_no_warnings(check_array, X,
dtype=[np.float64, np.float32],
accept_sparse=['csr', 'dok'],
copy=True)
assert_equal(X_checked.dtype, np.float32)
assert X_checked is not X
X_checked = assert_no_warnings(check_array, X_csc_float32,
dtype=[np.float64, np.float32],
accept_sparse=['csr', 'dok'],
copy=False)
assert_equal(X_checked.dtype, np.float32)
assert X_checked is not X_csc_float32
assert_equal(X_checked.format, 'csr')
def test_alpha():
# Setting alpha=0 should not output nan results when p(x_i|y_j)=0 is a case
X = np.array([[1, 0], [1, 1]])
y = np.array([0, 1])
nb = BernoulliNB(alpha=0.)
assert_warns(UserWarning, nb.partial_fit, X, y, classes=[0, 1])
assert_warns(UserWarning, nb.fit, X, y)
prob = np.array([[1, 0], [0, 1]])
assert_array_almost_equal(nb.predict_proba(X), prob)
nb = MultinomialNB(alpha=0.)
assert_warns(UserWarning, nb.partial_fit, X, y, classes=[0, 1])
assert_warns(UserWarning, nb.fit, X, y)
prob = np.array([[2. / 3, 1. / 3], [0, 1]])
assert_array_almost_equal(nb.predict_proba(X), prob)
# Test sparse X
X = scipy.sparse.csr_matrix(X)
nb = BernoulliNB(alpha=0.)
assert_warns(UserWarning, nb.fit, X, y)
prob = np.array([[1, 0], [0, 1]])
assert_array_almost_equal(nb.predict_proba(X), prob)
nb = MultinomialNB(alpha=0.)
assert_warns(UserWarning, nb.fit, X, y)
prob = np.array([[2. / 3, 1. / 3], [0, 1]])
assert_array_almost_equal(nb.predict_proba(X), prob)
# Test for alpha < 0
X = np.array([[1, 0], [1, 1]])
y = np.array([0, 1])
expected_msg = ('Smoothing parameter alpha = -1.0e-01. '
'alpha should be > 0.')
b_nb = BernoulliNB(alpha=-0.1)
m_nb = MultinomialNB(alpha=-0.1)
assert_raise_message(ValueError, expected_msg, b_nb.fit, X, y)
assert_raise_message(ValueError, expected_msg, m_nb.fit, X, y)
b_nb = BernoulliNB(alpha=-0.1)
m_nb = MultinomialNB(alpha=-0.1)
assert_raise_message(ValueError,
expected_msg,
b_nb.partial_fit,
X,
y,
classes=[0, 1])
assert_raise_message(ValueError,
expected_msg,
m_nb.partial_fit,
X,
y,
classes=[0, 1])
def test_ledoit_wolf():
# Tests LedoitWolf module on a simple dataset.
# test shrinkage coeff on a simple data set
X_centered = X - X.mean(axis=0)
lw = LedoitWolf(assume_centered=True)
lw.fit(X_centered)
shrinkage_ = lw.shrinkage_
score_ = lw.score(X_centered)
assert_almost_equal(
ledoit_wolf_shrinkage(X_centered, assume_centered=True), shrinkage_)
assert_almost_equal(
ledoit_wolf_shrinkage(X_centered, assume_centered=True, block_size=6),
shrinkage_)
# compare shrunk covariance obtained from data and from MLE estimate
lw_cov_from_mle, lw_shinkrage_from_mle = ledoit_wolf(X_centered,
assume_centered=True)
assert_array_almost_equal(lw_cov_from_mle, lw.covariance_, 4)
assert_almost_equal(lw_shinkrage_from_mle, lw.shrinkage_)
# compare estimates given by LW and ShrunkCovariance
scov = ShrunkCovariance(shrinkage=lw.shrinkage_, assume_centered=True)
scov.fit(X_centered)
assert_array_almost_equal(scov.covariance_, lw.covariance_, 4)
# test with n_features = 1
X_1d = X[:, 0].reshape((-1, 1))
lw = LedoitWolf(assume_centered=True)
lw.fit(X_1d)
lw_cov_from_mle, lw_shinkrage_from_mle = ledoit_wolf(X_1d,
assume_centered=True)
assert_array_almost_equal(lw_cov_from_mle, lw.covariance_, 4)
assert_almost_equal(lw_shinkrage_from_mle, lw.shrinkage_)
assert_array_almost_equal((X_1d**2).sum() / n_samples, lw.covariance_, 4)
# test shrinkage coeff on a simple data set (without saving precision)
lw = LedoitWolf(store_precision=False, assume_centered=True)
lw.fit(X_centered)
assert_almost_equal(lw.score(X_centered), score_, 4)
assert (lw.precision_ is None)
# Same tests without assuming centered data
# test shrinkage coeff on a simple data set
lw = LedoitWolf()
lw.fit(X)
assert_almost_equal(lw.shrinkage_, shrinkage_, 4)
assert_almost_equal(lw.shrinkage_, ledoit_wolf_shrinkage(X))
assert_almost_equal(lw.shrinkage_, ledoit_wolf(X)[1])
assert_almost_equal(lw.score(X), score_, 4)
# compare shrunk covariance obtained from data and from MLE estimate
lw_cov_from_mle, lw_shinkrage_from_mle = ledoit_wolf(X)
assert_array_almost_equal(lw_cov_from_mle, lw.covariance_, 4)
assert_almost_equal(lw_shinkrage_from_mle, lw.shrinkage_)
# compare estimates given by LW and ShrunkCovariance
scov = ShrunkCovariance(shrinkage=lw.shrinkage_)
scov.fit(X)
assert_array_almost_equal(scov.covariance_, lw.covariance_, 4)
# test with n_features = 1
X_1d = X[:, 0].reshape((-1, 1))
lw = LedoitWolf()
lw.fit(X_1d)
lw_cov_from_mle, lw_shinkrage_from_mle = ledoit_wolf(X_1d)
assert_array_almost_equal(lw_cov_from_mle, lw.covariance_, 4)
assert_almost_equal(lw_shinkrage_from_mle, lw.shrinkage_)
assert_array_almost_equal(empirical_covariance(X_1d), lw.covariance_, 4)
# test with one sample
# FIXME I don't know what this test does
X_1sample = np.arange(5)
lw = LedoitWolf()
assert_warns(UserWarning, lw.fit, X_1sample)
assert_array_almost_equal(lw.covariance_,
np.zeros(shape=(5, 5), dtype=np.float64))
# test shrinkage coeff on a simple data set (without saving precision)
lw = LedoitWolf(store_precision=False)
lw.fit(X)
assert_almost_equal(lw.score(X), score_, 4)
assert (lw.precision_ is None)
def test_oas():
# Tests OAS module on a simple dataset.
# test shrinkage coeff on a simple data set
X_centered = X - X.mean(axis=0)
oa = OAS(assume_centered=True)
oa.fit(X_centered)
shrinkage_ = oa.shrinkage_
score_ = oa.score(X_centered)
# compare shrunk covariance obtained from data and from MLE estimate
oa_cov_from_mle, oa_shinkrage_from_mle = oas(X_centered,
assume_centered=True)
assert_array_almost_equal(oa_cov_from_mle, oa.covariance_, 4)
assert_almost_equal(oa_shinkrage_from_mle, oa.shrinkage_)
# compare estimates given by OAS and ShrunkCovariance
scov = ShrunkCovariance(shrinkage=oa.shrinkage_, assume_centered=True)
scov.fit(X_centered)
assert_array_almost_equal(scov.covariance_, oa.covariance_, 4)
# test with n_features = 1
X_1d = X[:, 0].reshape((-1, 1))
oa = OAS(assume_centered=True)
oa.fit(X_1d)
oa_cov_from_mle, oa_shinkrage_from_mle = oas(X_1d, assume_centered=True)
assert_array_almost_equal(oa_cov_from_mle, oa.covariance_, 4)
assert_almost_equal(oa_shinkrage_from_mle, oa.shrinkage_)
assert_array_almost_equal((X_1d**2).sum() / n_samples, oa.covariance_, 4)
# test shrinkage coeff on a simple data set (without saving precision)
oa = OAS(store_precision=False, assume_centered=True)
oa.fit(X_centered)
assert_almost_equal(oa.score(X_centered), score_, 4)
assert (oa.precision_ is None)
# Same tests without assuming centered data--------------------------------
# test shrinkage coeff on a simple data set
oa = OAS()
oa.fit(X)
assert_almost_equal(oa.shrinkage_, shrinkage_, 4)
assert_almost_equal(oa.score(X), score_, 4)
# compare shrunk covariance obtained from data and from MLE estimate
oa_cov_from_mle, oa_shinkrage_from_mle = oas(X)
assert_array_almost_equal(oa_cov_from_mle, oa.covariance_, 4)
assert_almost_equal(oa_shinkrage_from_mle, oa.shrinkage_)
# compare estimates given by OAS and ShrunkCovariance
scov = ShrunkCovariance(shrinkage=oa.shrinkage_)
scov.fit(X)
assert_array_almost_equal(scov.covariance_, oa.covariance_, 4)
# test with n_features = 1
X_1d = X[:, 0].reshape((-1, 1))
oa = OAS()
oa.fit(X_1d)
oa_cov_from_mle, oa_shinkrage_from_mle = oas(X_1d)
assert_array_almost_equal(oa_cov_from_mle, oa.covariance_, 4)
assert_almost_equal(oa_shinkrage_from_mle, oa.shrinkage_)
assert_array_almost_equal(empirical_covariance(X_1d), oa.covariance_, 4)
# test with one sample
# FIXME I don't know what this test does
X_1sample = np.arange(5)
oa = OAS()
assert_warns(UserWarning, oa.fit, X_1sample)
assert_array_almost_equal(oa.covariance_,
np.zeros(shape=(5, 5), dtype=np.float64))
# test shrinkage coeff on a simple data set (without saving precision)
oa = OAS(store_precision=False)
oa.fit(X)
assert_almost_equal(oa.score(X), score_, 4)
assert (oa.precision_ is None)
def test_ignore_warning():
# This check that ignore_warning decorateur and context manager are working
# as expected
def _warning_function():
warnings.warn("deprecation warning", DeprecationWarning)
def _multiple_warning_function():
warnings.warn("deprecation warning", DeprecationWarning)
warnings.warn("deprecation warning")
# Check the function directly
assert_no_warnings(ignore_warnings(_warning_function))
assert_no_warnings(
ignore_warnings(_warning_function, category=DeprecationWarning))
assert_warns(DeprecationWarning,
ignore_warnings(_warning_function, category=UserWarning))
assert_warns(
UserWarning,
ignore_warnings(_multiple_warning_function,
category=DeprecationWarning))
assert_warns(
DeprecationWarning,
ignore_warnings(_multiple_warning_function, category=UserWarning))
assert_no_warnings(
ignore_warnings(_warning_function,
category=(DeprecationWarning, UserWarning)))
# Check the decorator
@ignore_warnings
def decorator_no_warning():
_warning_function()
_multiple_warning_function()
@ignore_warnings(category=(DeprecationWarning, UserWarning))
def decorator_no_warning_multiple():
_multiple_warning_function()
@ignore_warnings(category=DeprecationWarning)
def decorator_no_deprecation_warning():
_warning_function()
@ignore_warnings(category=UserWarning)
def decorator_no_user_warning():
_warning_function()
@ignore_warnings(category=DeprecationWarning)
def decorator_no_deprecation_multiple_warning():
_multiple_warning_function()
@ignore_warnings(category=UserWarning)
def decorator_no_user_multiple_warning():
_multiple_warning_function()
assert_no_warnings(decorator_no_warning)
assert_no_warnings(decorator_no_warning_multiple)
assert_no_warnings(decorator_no_deprecation_warning)
assert_warns(DeprecationWarning, decorator_no_user_warning)
assert_warns(UserWarning, decorator_no_deprecation_multiple_warning)
assert_warns(DeprecationWarning, decorator_no_user_multiple_warning)
# Check the context manager
def context_manager_no_warning():
with ignore_warnings():
_warning_function()
def context_manager_no_warning_multiple():
with ignore_warnings(category=(DeprecationWarning, UserWarning)):
_multiple_warning_function()
def context_manager_no_deprecation_warning():
with ignore_warnings(category=DeprecationWarning):
_warning_function()
def context_manager_no_user_warning():
with ignore_warnings(category=UserWarning):
_warning_function()
def context_manager_no_deprecation_multiple_warning():
with ignore_warnings(category=DeprecationWarning):
_multiple_warning_function()
def context_manager_no_user_multiple_warning():
with ignore_warnings(category=UserWarning):
_multiple_warning_function()
assert_no_warnings(context_manager_no_warning)
assert_no_warnings(context_manager_no_warning_multiple)
assert_no_warnings(context_manager_no_deprecation_warning)
assert_warns(DeprecationWarning, context_manager_no_user_warning)
assert_warns(UserWarning, context_manager_no_deprecation_multiple_warning)
assert_warns(DeprecationWarning, context_manager_no_user_multiple_warning)
def test_acmes_clip_samples():
opt = ACMESOptimizer(n_train_max=20001)
assert_warns(UserWarning, opt.init, 1)
assert_equal(opt.n_train_max, 20000)
tree_builder, X.T, np.ones((4, 4)))
def test_unstructured_linkage_tree():
"""
Check that we obtain the correct solution for unstructured linkage trees.
"""
rnd = np.random.RandomState(0)
X = rnd.randn(50, 100)
<<<<<<< HEAD
=======
for this_X in (X, X[0]):
# With specified a number of clusters just for the sake of
# raising a warning and testing the warning code
children, n_nodes, n_leaves, parent = assert_warns(UserWarning,
ward_tree,
this_X.T,
n_clusters=10)
n_nodes = 2 * X.shape[1] - 1
assert_equal(len(children) + n_leaves, n_nodes)
>>>>>>> remote
for tree_builder in _TREE_BUILDERS.values():
for this_X in (X, X[0]):
with warnings.catch_warnings(record=True) as warning_list:
warnings.simplefilter("always", UserWarning)
warnings.simplefilter("ignore", DeprecationWarning)
# With specified a number of clusters just for the sake of
# raising a warning and testing the warning code
children, n_nodes, n_leaves, parent = tree_builder(
this_X.T, n_clusters=10)
def test_label_binarizer_errors():
"""Check that invalid arguments yield ValueError"""
one_class = np.array([0, 0, 0, 0])
lb = LabelBinarizer().fit(one_class)
assert_false(assert_warns(DeprecationWarning, getattr, lb, "multilabel_"))
multi_label = [(2, 3), (0, ), (0, 2)]
assert_raises(ValueError, lb.transform, multi_label)
lb = LabelBinarizer()
assert_raises(ValueError, lb.transform, [])
assert_raises(ValueError, lb.inverse_transform, [])
y = np.array([[0, 1, 0], [1, 1, 1]])
classes = np.arange(3)
assert_raises(ValueError,
label_binarize,
y,
classes,
multilabel=True,
neg_label=2,
pos_label=1)
assert_raises(ValueError,
label_binarize,
y,
classes,
multilabel=True,
neg_label=2,
pos_label=2)
assert_raises(ValueError, LabelBinarizer, neg_label=2, pos_label=1)
assert_raises(ValueError, LabelBinarizer, neg_label=2, pos_label=2)
assert_raises(ValueError,
LabelBinarizer,
neg_label=1,
pos_label=2,
sparse_output=True)
# Fail on y_type
assert_raises(ValueError,
_inverse_binarize_thresholding,
y=csr_matrix([[1, 2], [2, 1]]),
output_type="foo",
classes=[1, 2],
threshold=0)
# Fail on the number of classes
assert_raises(ValueError,
_inverse_binarize_thresholding,
y=csr_matrix([[1, 2], [2, 1]]),
output_type="foo",
classes=[1, 2, 3],
threshold=0)
# Fail on the dimension of 'binary'
assert_raises(ValueError,
_inverse_binarize_thresholding,
y=np.array([[1, 2, 3], [2, 1, 3]]),
output_type="binary",
classes=[1, 2, 3],
threshold=0)
# Fail on multioutput data
assert_raises(ValueError, LabelBinarizer().fit, np.array([[1, 3], [2, 1]]))
assert_raises(ValueError, label_binarize, np.array([[1, 3], [2, 1]]),
[1, 2, 3])
def test_extent() -> None:
X = np.array([[1, 1], [1, 0]])
clf = loop.LocalOutlierProbability(X, n_neighbors=2, extent=4,
use_numba=NUMBA)
assert_warns(UserWarning, clf.fit)
def test_metric_params_interface():
assert_warns(SyntaxWarning, neighbors.KNeighborsClassifier,
metric_params={'p': 3})
def test_check_array_dtype_warning():
X_int_list = [[1, 2, 3], [4, 5, 6], [7, 8, 9]]
X_float64 = np.asarray(X_int_list, dtype=np.float64)
X_float32 = np.asarray(X_int_list, dtype=np.float32)
X_int64 = np.asarray(X_int_list, dtype=np.int64)
X_csr_float64 = sp.csr_matrix(X_float64)
X_csr_float32 = sp.csr_matrix(X_float32)
X_csc_float32 = sp.csc_matrix(X_float32)
X_csc_int32 = sp.csc_matrix(X_int64, dtype=np.int32)
y = [0, 0, 1]
integer_data = [X_int64, X_csc_int32]
float64_data = [X_float64, X_csr_float64]
float32_data = [X_float32, X_csr_float32, X_csc_float32]
for X in integer_data:
X_checked = assert_no_warnings(check_array,
X,
dtype=np.float64,
accept_sparse=True)
assert X_checked.dtype == np.float64
X_checked = assert_warns(DataConversionWarning,
check_array,
X,
dtype=np.float64,
accept_sparse=True,
warn_on_dtype=True)
assert X_checked.dtype == np.float64
# Check that the warning message includes the name of the Estimator
X_checked = assert_warns_message(DataConversionWarning,
'SomeEstimator',
check_array,
X,
dtype=[np.float64, np.float32],
accept_sparse=True,
warn_on_dtype=True,
estimator='SomeEstimator')
assert X_checked.dtype == np.float64
X_checked, y_checked = assert_warns_message(
DataConversionWarning,
'KNeighborsClassifier',
check_X_y,
X,
y,
dtype=np.float64,
accept_sparse=True,
warn_on_dtype=True,
estimator=KNeighborsClassifier())
assert X_checked.dtype == np.float64
for X in float64_data:
with pytest.warns(None) as record:
warnings.simplefilter("ignore", DeprecationWarning) # 0.23
X_checked = check_array(X,
dtype=np.float64,
accept_sparse=True,
warn_on_dtype=True)
assert X_checked.dtype == np.float64
X_checked = check_array(X,
dtype=np.float64,
accept_sparse=True,
warn_on_dtype=False)
assert X_checked.dtype == np.float64
assert len(record) == 0
for X in float32_data:
X_checked = assert_no_warnings(check_array,
X,
dtype=[np.float64, np.float32],
accept_sparse=True)
assert X_checked.dtype == np.float32
assert X_checked is X
X_checked = assert_no_warnings(check_array,
X,
dtype=[np.float64, np.float32],
accept_sparse=['csr', 'dok'],
copy=True)
assert X_checked.dtype == np.float32
assert X_checked is not X
X_checked = assert_no_warnings(check_array,
X_csc_float32,
dtype=[np.float64, np.float32],
accept_sparse=['csr', 'dok'],
copy=False)
assert X_checked.dtype == np.float32
assert X_checked is not X_csc_float32
assert X_checked.format == 'csr'
def test_timeout():
sp = svm.SVC(C=1, kernel=lambda x, y: x * y.T, probability=True,
random_state=0, max_iter=1)
assert_warns(ConvergenceWarning, sp.fit, X_sp, Y)
def test_metric_params_interface():
assert_warns(DeprecationWarning, neighbors.KNeighborsClassifier,
metric='wminkowski', w=np.ones(10))
assert_warns(SyntaxWarning, neighbors.KNeighborsClassifier,
metric_params={'p': 3})
def test_nearmiss_deprecation():
nm = NearMiss(ver3_samp_ngh=3, version=3)
assert_warns(DeprecationWarning, nm.fit_sample, X, Y)
def check_target_type(name, Estimator):
X = np.random.random((20, 2))
y = np.linspace(0, 1, 20)
estimator = Estimator()
set_random_state(estimator)
assert_warns(UserWarning, estimator.fit, X, y)
def check_multiclass_warning(name, Estimator):
X = np.random.random((20, 2))
y = np.array([0] * 3 + [1] * 2 + [2] * 15)
estimator = Estimator()
set_random_state(estimator)
assert_warns(UserWarning, estimator.fit, X, y)
def test_oob_score():
"""Test if oob_score is deprecated. """
clf = GradientBoostingClassifier(n_estimators=100, random_state=1,
subsample=0.5)
clf.fit(X, y)
assert_warns(DeprecationWarning, hasattr, clf, 'oob_score_')
def test_multilabel_representation_invariance():
# Generate some data
n_classes = 4
n_samples = 50
# using sequence of sequences is deprecated, but still tested
make_ml = ignore_warnings(make_multilabel_classification)
_, y1 = make_ml(n_features=1,
n_classes=n_classes,
random_state=0,
n_samples=n_samples)
_, y2 = make_ml(n_features=1,
n_classes=n_classes,
random_state=1,
n_samples=n_samples)
# Be sure to have at least one empty label
y1 += ([], )
y2 += ([], )
# NOTE: The "sorted" trick is necessary to shuffle labels, because it
# allows to return the shuffled tuple.
rng = check_random_state(42)
shuffled = lambda x: sorted(x, key=lambda *args: rng.rand())
y1_shuffle = [shuffled(x) for x in y1]
y2_shuffle = [shuffled(x) for x in y2]
# Let's have redundant labels
y1_redundant = [x * rng.randint(1, 4) for x in y1]
y2_redundant = [x * rng.randint(1, 4) for x in y2]
# Binary indicator matrix format
lb = MultiLabelBinarizer().fit([range(n_classes)])
y1_binary_indicator = lb.transform(y1)
y2_binary_indicator = lb.transform(y2)
y1_shuffle_binary_indicator = lb.transform(y1_shuffle)
y2_shuffle_binary_indicator = lb.transform(y2_shuffle)
for name in MULTILABELS_METRICS:
metric = ALL_METRICS[name]
# XXX cruel hack to work with partial functions
if isinstance(metric, partial):
metric.__module__ = 'tmp'
metric.__name__ = name
# Check warning for sequence of sequences
measure = assert_warns(DeprecationWarning, metric, y1, y2)
metric = ignore_warnings(metric)
# Check representation invariance
assert_almost_equal(metric(y1_binary_indicator, y2_binary_indicator),
measure,
err_msg="%s failed representation invariance "
"between list of list of labels "
"format and dense binary indicator "
"format." % name)
with ignore_warnings(): # sequence of sequences is deprecated
# Check invariance with redundant labels with list of labels
assert_almost_equal(
metric(y1, y2_redundant),
measure,
err_msg="%s failed rendundant label invariance" % name)
assert_almost_equal(
metric(y1_redundant, y2_redundant),
measure,
err_msg="%s failed rendundant label invariance" % name)
assert_almost_equal(
metric(y1_redundant, y2),
measure,
err_msg="%s failed rendundant label invariance" % name)
# Check shuffling invariance with list of labels
assert_almost_equal(metric(y1_shuffle, y2_shuffle),
measure,
err_msg="%s failed shuffling invariance "
"with list of list of labels format." % name)
# Check shuffling invariance with dense binary indicator matrix
assert_almost_equal(metric(y1_shuffle_binary_indicator,
y2_shuffle_binary_indicator),
measure,
err_msg="%s failed shuffling invariance "
" with dense binary indicator format." % name)
with ignore_warnings(): # sequence of sequences is deprecated
# Check raises error with mix input representation
assert_raises(ValueError, metric, y1, y2_binary_indicator)
assert_raises(ValueError, metric, y1_binary_indicator, y2)
def test_timeout():
a = svm.SVC(kernel=lambda x, y: np.dot(x, y.T),
probability=True,
random_state=0,
max_iter=1)
assert_warns(ConvergenceWarning, a.fit, X, Y)
def test_factor_analysis():
"""Test FactorAnalysis ability to recover the data covariance structure
"""
rng = np.random.RandomState(0)
n_samples, n_features, n_components = 20, 5, 3
# Some random settings for the generative model
W = rng.randn(n_components, n_features)
# latent variable of dim 3, 20 of it
h = rng.randn(n_samples, n_components)
# using gamma to model different noise variance
# per component
noise = rng.gamma(1, size=n_features) * rng.randn(n_samples, n_features)
# generate observations
# wlog, mean is 0
X = np.dot(h, W) + noise
assert_raises(ValueError, FactorAnalysis, svd_method='foo')
fa_fail = FactorAnalysis()
fa_fail.svd_method = 'foo'
assert_raises(ValueError, fa_fail.fit, X)
fas = []
for method in ['randomized', 'lapack']:
fa = FactorAnalysis(n_components=n_components, svd_method=method)
fa.fit(X)
fas.append(fa)
X_t = fa.transform(X)
assert_equal(X_t.shape, (n_samples, n_components))
assert_almost_equal(fa.loglike_[-1], fa.score_samples(X).sum())
assert_almost_equal(fa.score_samples(X).mean(), fa.score(X))
diff = np.all(np.diff(fa.loglike_))
assert_greater(diff, 0., 'Log likelihood dif not increase')
# Sample Covariance
scov = np.cov(X, rowvar=0., bias=1.)
# Model Covariance
mcov = fa.get_covariance()
diff = np.sum(np.abs(scov - mcov)) / W.size
assert_less(diff, 0.1, "Mean absolute difference is %f" % diff)
fa = FactorAnalysis(n_components=n_components,
noise_variance_init=np.ones(n_features))
assert_raises(ValueError, fa.fit, X[:, :2])
f = lambda x, y: np.abs(getattr(x, y)) # sign will not be equal
fa1, fa2 = fas
for attr in ['loglike_', 'components_', 'noise_variance_']:
assert_almost_equal(f(fa1, attr), f(fa2, attr))
fa1.max_iter = 1
fa1.verbose = True
assert_warns(ConvergenceWarning, fa1.fit, X)
# Test get_covariance and get_precision with n_components == n_features
# with n_components < n_features and with n_components == 0
for n_components in [0, 2, X.shape[1]]:
fa.n_components = n_components
fa.fit(X)
cov = fa.get_covariance()
precision = fa.get_precision()
assert_array_almost_equal(np.dot(cov, precision),
np.eye(X.shape[1]), 12)
def test_linear_svc_convergence_warnings():
# Test that warnings are raised if model does not converge
lsvc = svm.LinearSVC(max_iter=2, verbose=1)
assert_warns(ConvergenceWarning, lsvc.fit, X, Y)
assert_equal(lsvc.n_iter_, 2)
def test_lda_n_topics_deprecation():
n_components, X = _build_sparse_mtx()
lda = LatentDirichletAllocation(n_topics=10, learning_method='batch')
assert_warns(DeprecationWarning, lda.fit, X)
