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 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_less(abs(test_score - est.oob_score_), 0.1)
else:
assert_greater(test_score, est.oob_score_)
assert_greater(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_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_compute_sample_weight():
# Test (and demo) compute_sample_weight.
# Test with balanced classes
y = np.asarray([1, 1, 1, 2, 2, 2])
sample_weight = assert_warns(DeprecationWarning, compute_sample_weight,
"auto", y)
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
sample_weight = compute_sample_weight("balanced", y)
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
# Test with user-defined weights
sample_weight = compute_sample_weight({1: 2, 2: 1}, y)
assert_array_almost_equal(sample_weight, [2., 2., 2., 1., 1., 1.])
# Test with column vector of balanced classes
y = np.asarray([[1], [1], [1], [2], [2], [2]])
sample_weight = assert_warns(DeprecationWarning, compute_sample_weight,
"auto", y)
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
sample_weight = compute_sample_weight("balanced", y)
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
# Test with unbalanced classes
y = np.asarray([1, 1, 1, 2, 2, 2, 3])
sample_weight = assert_warns(DeprecationWarning, compute_sample_weight,
"auto", y)
expected_auto = np.asarray([.6, .6, .6, .6, .6, .6, 1.8])
assert_array_almost_equal(sample_weight, expected_auto)
sample_weight = compute_sample_weight("balanced", y)
expected_balanced = np.array(
[0.7777, 0.7777, 0.7777, 0.7777, 0.7777, 0.7777, 2.3333])
assert_array_almost_equal(sample_weight, expected_balanced, decimal=4)
# Test with `None` weights
sample_weight = compute_sample_weight(None, y)
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1., 1.])
# Test with multi-output of balanced classes
y = np.asarray([[1, 0], [1, 0], [1, 0], [2, 1], [2, 1], [2, 1]])
sample_weight = assert_warns(DeprecationWarning, compute_sample_weight,
"auto", y)
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
sample_weight = compute_sample_weight("balanced", y)
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
# Test with multi-output with user-defined weights
y = np.asarray([[1, 0], [1, 0], [1, 0], [2, 1], [2, 1], [2, 1]])
sample_weight = compute_sample_weight([{1: 2, 2: 1}, {0: 1, 1: 2}], y)
assert_array_almost_equal(sample_weight, [2., 2., 2., 2., 2., 2.])
# Test with multi-output of unbalanced classes
y = np.asarray([[1, 0], [1, 0], [1, 0], [2, 1], [2, 1], [2, 1], [3, -1]])
sample_weight = assert_warns(DeprecationWarning, compute_sample_weight,
"auto", y)
assert_array_almost_equal(sample_weight, expected_auto**2)
sample_weight = compute_sample_weight("balanced", y)
assert_array_almost_equal(sample_weight, expected_balanced**2, decimal=3)
def test_shape_y():
# Test with float class labels.
clf = GradientBoostingClassifier(n_estimators=100, random_state=1)
y_ = np.asarray(y, dtype=np.int32)
y_ = y_[:, np.newaxis]
# This will raise a DataConversionWarning that we want to
# "always" raise, elsewhere the warnings gets ignored in the
# later tests, and the tests that check for this warning fail
assert_warns(DataConversionWarning, clf.fit, X, y_)
assert_array_equal(clf.predict(T), true_result)
assert_equal(100, len(clf.estimators_))
def test_warn_wrong_warning(self):
def f():
warnings.warn("yo", DeprecationWarning)
failed = False
filters = sys.modules['warnings'].filters[:]
try:
try:
# Should raise an AssertionError
assert_warns(UserWarning, f)
failed = True
except AssertionError:
pass
finally:
sys.modules['warnings'].filters = filters
if failed:
raise AssertionError("wrong warning caught by assert_warn")
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 test_compute_class_weight():
# Test (and demo) compute_class_weight.
y = np.asarray([2, 2, 2, 3, 3, 4])
classes = np.unique(y)
cw = assert_warns(DeprecationWarning, compute_class_weight, "auto",
classes, y)
assert_almost_equal(cw.sum(), classes.shape)
assert_true(cw[0] < cw[1] < cw[2])
cw = compute_class_weight("balanced", classes, y)
# total effect of samples is preserved
class_counts = np.bincount(y)[2:]
assert_almost_equal(np.dot(cw, class_counts), y.shape[0])
assert_true(cw[0] < cw[1] < cw[2])
def test_compute_class_weight_auto_unordered():
# Test compute_class_weight when classes are unordered
classes = np.array([1, 0, 3])
y = np.asarray([1, 0, 0, 3, 3, 3])
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([1.636, 0.818, 0.545]), decimal=3)
cw = compute_class_weight("balanced", classes, y)
class_counts = np.bincount(y)[classes]
assert_almost_equal(np.dot(cw, class_counts), y.shape[0])
assert_array_almost_equal(cw, [2., 1., 2. / 3])
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='auto',
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)
def test_warn(self):
def f():
warnings.warn("yo")
return 3
# Test that assert_warns is not impacted by externally set
# filters and is reset internally.
# This is because `clean_warning_registry()` is called internally by
# assert_warns and clears all previous filters.
warnings.simplefilter("ignore", UserWarning)
assert_equal(assert_warns(UserWarning, f), 3)
# Test that the warning registry is empty after assert_warns
assert_equal(sys.modules['warnings'].filters, [])
assert_raises(AssertionError, assert_no_warnings, f)
assert_equal(assert_no_warnings(lambda x: x, 1), 1)
def check_importances(name, criterion, X, y):
ForestEstimator = FOREST_ESTIMATORS[name]
est = ForestEstimator(n_estimators=20, criterion=criterion, random_state=0)
est.fit(X, y)
importances = est.feature_importances_
n_important = np.sum(importances > 0.1)
assert_equal(importances.shape[0], 10)
assert_equal(n_important, 3)
# XXX: Remove this test in 0.19 after transform support to estimators
# is removed.
X_new = assert_warns(DeprecationWarning,
est.transform,
X,
threshold="mean")
assert_less(0 < X_new.shape[1], X.shape[1])
# Check with parallel
importances = est.feature_importances_
est.set_params(n_jobs=2)
importances_parrallel = est.feature_importances_
assert_array_almost_equal(importances, importances_parrallel)
# Check with sample weights
sample_weight = check_random_state(0).randint(1, 10, len(X))
est = ForestEstimator(n_estimators=20, random_state=0, criterion=criterion)
est.fit(X, y, sample_weight=sample_weight)
importances = est.feature_importances_
assert_true(np.all(importances >= 0.0))
for scale in [0.5, 10, 100]:
est = ForestEstimator(n_estimators=20,
random_state=0,
criterion=criterion)
est.fit(X, y, sample_weight=scale * sample_weight)
importances_bis = est.feature_importances_
assert_less(np.abs(importances - importances_bis).mean(), 0.001)
def test_feature_importances():
X = np.array(boston.data, dtype=np.float32)
y = np.array(boston.target, dtype=np.float32)
for presort in True, False:
clf = GradientBoostingRegressor(n_estimators=100,
max_depth=5,
min_samples_split=2,
random_state=1,
presort=presort)
clf.fit(X, y)
assert_true(hasattr(clf, 'feature_importances_'))
# XXX: Remove this test in 0.19 after transform support to estimators
# is removed.
X_new = assert_warns(DeprecationWarning,
clf.transform,
X,
threshold="mean")
assert_less(X_new.shape[1], X.shape[1])
feature_mask = (clf.feature_importances_ >
clf.feature_importances_.mean())
assert_array_almost_equal(X_new, X[:, feature_mask])
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_true(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_false(X_checked is 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_false(X_checked is X_csc_float32)
assert_equal(X_checked.format, 'csr')
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_compute_sample_weight_with_subsample():
# Test compute_sample_weight with subsamples specified.
# Test with balanced classes and all samples present
y = np.asarray([1, 1, 1, 2, 2, 2])
sample_weight = assert_warns(DeprecationWarning, compute_sample_weight,
"auto", y)
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
sample_weight = compute_sample_weight("balanced", y, range(6))
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
# Test with column vector of balanced classes and all samples present
y = np.asarray([[1], [1], [1], [2], [2], [2]])
sample_weight = assert_warns(DeprecationWarning, compute_sample_weight,
"auto", y)
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
sample_weight = compute_sample_weight("balanced", y, range(6))
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
# Test with a subsample
y = np.asarray([1, 1, 1, 2, 2, 2])
sample_weight = assert_warns(DeprecationWarning, compute_sample_weight,
"auto", y, range(4))
assert_array_almost_equal(sample_weight, [.5, .5, .5, 1.5, 1.5, 1.5])
sample_weight = compute_sample_weight("balanced", y, range(4))
assert_array_almost_equal(sample_weight,
[2. / 3, 2. / 3, 2. / 3, 2., 2., 2.])
# Test with a bootstrap subsample
y = np.asarray([1, 1, 1, 2, 2, 2])
sample_weight = assert_warns(DeprecationWarning, compute_sample_weight,
"auto", y, [0, 1, 1, 2, 2, 3])
expected_auto = np.asarray(
[1 / 3., 1 / 3., 1 / 3., 5 / 3., 5 / 3., 5 / 3.])
assert_array_almost_equal(sample_weight, expected_auto)
sample_weight = compute_sample_weight("balanced", y, [0, 1, 1, 2, 2, 3])
expected_balanced = np.asarray([0.6, 0.6, 0.6, 3., 3., 3.])
assert_array_almost_equal(sample_weight, expected_balanced)
# Test with a bootstrap subsample for multi-output
y = np.asarray([[1, 0], [1, 0], [1, 0], [2, 1], [2, 1], [2, 1]])
sample_weight = assert_warns(DeprecationWarning, compute_sample_weight,
"auto", y, [0, 1, 1, 2, 2, 3])
assert_array_almost_equal(sample_weight, expected_auto**2)
sample_weight = compute_sample_weight("balanced", y, [0, 1, 1, 2, 2, 3])
assert_array_almost_equal(sample_weight, expected_balanced**2)
# Test with a missing class
y = np.asarray([1, 1, 1, 2, 2, 2, 3])
sample_weight = assert_warns(DeprecationWarning, compute_sample_weight,
"auto", y, range(6))
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1., 0.])
sample_weight = compute_sample_weight("balanced", y, range(6))
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1., 0.])
# Test with a missing class for multi-output
y = np.asarray([[1, 0], [1, 0], [1, 0], [2, 1], [2, 1], [2, 1], [2, 2]])
sample_weight = assert_warns(DeprecationWarning, compute_sample_weight,
"auto", y, range(6))
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1., 0.])
sample_weight = compute_sample_weight("balanced", y, range(6))
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1., 0.])
def test_check_array():
# accept_sparse == None
# raise error on sparse inputs
X = [[1, 2], [3, 4]]
X_csr = sp.csr_matrix(X)
assert_raises(TypeError, check_array, X_csr)
# ensure_2d
assert_warns(DeprecationWarning, check_array, [0, 1, 2])
X_array = check_array([0, 1, 2])
assert_equal(X_array.ndim, 2)
X_array = check_array([0, 1, 2], ensure_2d=False)
assert_equal(X_array.ndim, 1)
# don't allow ndim > 3
X_ndim = np.arange(8).reshape(2, 2, 2)
assert_raises(ValueError, check_array, X_ndim)
check_array(X_ndim, allow_nd=True) # doesn't raise
# force_all_finite
X_inf = np.arange(4).reshape(2, 2).astype(np.float)
X_inf[0, 0] = np.inf
assert_raises(ValueError, check_array, X_inf)
check_array(X_inf, force_all_finite=False) # no raise
# nan check
X_nan = np.arange(4).reshape(2, 2).astype(np.float)
X_nan[0, 0] = np.nan
assert_raises(ValueError, check_array, X_nan)
check_array(X_inf, force_all_finite=False) # no raise
# dtype and order enforcement.
X_C = np.arange(4).reshape(2, 2).copy("C")
X_F = X_C.copy("F")
X_int = X_C.astype(np.int)
X_float = X_C.astype(np.float)
Xs = [X_C, X_F, X_int, X_float]
dtypes = [np.int32, np.int, np.float, np.float32, None, np.bool, object]
orders = ['C', 'F', None]
copys = [True, False]
for X, dtype, order, copy in product(Xs, dtypes, orders, copys):
X_checked = check_array(X, dtype=dtype, order=order, copy=copy)
if dtype is not None:
assert_equal(X_checked.dtype, dtype)
else:
assert_equal(X_checked.dtype, X.dtype)
if order == 'C':
assert_true(X_checked.flags['C_CONTIGUOUS'])
assert_false(X_checked.flags['F_CONTIGUOUS'])
elif order == 'F':
assert_true(X_checked.flags['F_CONTIGUOUS'])
assert_false(X_checked.flags['C_CONTIGUOUS'])
if copy:
assert_false(X is X_checked)
else:
# doesn't copy if it was already good
if (X.dtype == X_checked.dtype and X_checked.flags['C_CONTIGUOUS']
== X.flags['C_CONTIGUOUS']
and X_checked.flags['F_CONTIGUOUS']
== X.flags['F_CONTIGUOUS']):
assert_true(X is X_checked)
# allowed sparse != None
X_csc = sp.csc_matrix(X_C)
X_coo = X_csc.tocoo()
X_dok = X_csc.todok()
X_int = X_csc.astype(np.int)
X_float = X_csc.astype(np.float)
Xs = [X_csc, X_coo, X_dok, X_int, X_float]
accept_sparses = [['csr', 'coo'], ['coo', 'dok']]
for X, dtype, accept_sparse, copy in product(Xs, dtypes, accept_sparses,
copys):
with warnings.catch_warnings(record=True) as w:
X_checked = check_array(X,
dtype=dtype,
accept_sparse=accept_sparse,
copy=copy)
if (dtype is object or sp.isspmatrix_dok(X)) and len(w):
message = str(w[0].message)
messages = [
"object dtype is not supported by sparse matrices",
"Can't check dok sparse matrix for nan or inf."
]
assert_true(message in messages)
else:
assert_equal(len(w), 0)
if dtype is not None:
assert_equal(X_checked.dtype, dtype)
else:
assert_equal(X_checked.dtype, X.dtype)
if X.format in accept_sparse:
# no change if allowed
assert_equal(X.format, X_checked.format)
else:
# got converted
assert_equal(X_checked.format, accept_sparse[0])
if copy:
assert_false(X is X_checked)
else:
# doesn't copy if it was already good
if (X.dtype == X_checked.dtype and X.format == X_checked.format):
assert_true(X is X_checked)
# other input formats
# convert lists to arrays
X_dense = check_array([[1, 2], [3, 4]])
assert_true(isinstance(X_dense, np.ndarray))
# raise on too deep lists
assert_raises(ValueError, check_array, X_ndim.tolist())
check_array(X_ndim.tolist(), allow_nd=True) # doesn't raise
# convert weird stuff to arrays
X_no_array = NotAnArray(X_dense)
result = check_array(X_no_array)
assert_true(isinstance(result, np.ndarray))
def test_check_array_min_samples_and_features_messages():
# empty list is considered 2D by default:
msg = "0 feature(s) (shape=(1, 0)) while a minimum of 1 is required."
assert_raise_message(ValueError, msg, check_array, [[]])
# If considered a 1D collection when ensure_2d=False, then the minimum
# number of samples will break:
msg = "0 sample(s) (shape=(0,)) while a minimum of 1 is required."
assert_raise_message(ValueError, msg, check_array, [], ensure_2d=False)
# Invalid edge case when checking the default minimum sample of a scalar
msg = "Singleton array array(42) cannot be considered a valid collection."
assert_raise_message(TypeError, msg, check_array, 42, ensure_2d=False)
# But this works if the input data is forced to look like a 2 array with
# one sample and one feature:
X_checked = assert_warns(DeprecationWarning,
check_array, [42],
ensure_2d=True)
assert_array_equal(np.array([[42]]), X_checked)
# Simulate a model that would need at least 2 samples to be well defined
X = np.ones((1, 10))
y = np.ones(1)
msg = "1 sample(s) (shape=(1, 10)) while a minimum of 2 is required."
assert_raise_message(ValueError,
msg,
check_X_y,
X,
y,
ensure_min_samples=2)
# The same message is raised if the data has 2 dimensions even if this is
# not mandatory
assert_raise_message(ValueError,
msg,
check_X_y,
X,
y,
ensure_min_samples=2,
ensure_2d=False)
# Simulate a model that would require at least 3 features (e.g. SelectKBest
# with k=3)
X = np.ones((10, 2))
y = np.ones(2)
msg = "2 feature(s) (shape=(10, 2)) while a minimum of 3 is required."
assert_raise_message(ValueError,
msg,
check_X_y,
X,
y,
ensure_min_features=3)
# Only the feature check is enabled whenever the number of dimensions is 2
# even if allow_nd is enabled:
assert_raise_message(ValueError,
msg,
check_X_y,
X,
y,
ensure_min_features=3,
allow_nd=True)
# Simulate a case where a pipeline stage as trimmed all the features of a
# 2D dataset.
X = np.empty(0).reshape(10, 0)
y = np.ones(10)
msg = "0 feature(s) (shape=(10, 0)) while a minimum of 1 is required."
assert_raise_message(ValueError, msg, check_X_y, X, y)
# nd-data is not checked for any minimum number of features by default:
X = np.ones((10, 0, 28, 28))
y = np.ones(10)
X_checked, y_checked = check_X_y(X, y, allow_nd=True)
assert_array_equal(X, X_checked)
assert_array_equal(y, y_checked)
