def check_dtype_object(name, Estimator):
# check that estimators treat dtype object as numeric if possible
rng = np.random.RandomState(0)
X = rng.rand(40, 10).astype(object)
y = (X[:, 0] * 4).astype(np.int)
y = multioutput_estimator_convert_y_2d(name, y)
with warnings.catch_warnings():
estimator = Estimator()
set_fast_parameters(estimator)
estimator.fit(X, y)
if hasattr(estimator, "predict"):
estimator.predict(X)
if hasattr(estimator, "transform"):
estimator.transform(X)
try:
estimator.fit(X, y.astype(object))
except Exception as e:
if "Unknown label type" not in str(e):
raise
X[0, 0] = {'foo': 'bar'}
assert_raise_message(TypeError, "string or a number", estimator.fit, X, y)
def test_assert_raise_message():
def _raise_ValueError(message):
raise ValueError(message)
assert_raise_message(ValueError, "test", _raise_ValueError, "test")
assert_raises(AssertionError, assert_raise_message, ValueError,
"something else", _raise_ValueError, "test")
assert_raises(ValueError, assert_raise_message, TypeError,
"something else", _raise_ValueError, "test")
def test_assert_raise_message():
def _raise_ValueError(message):
raise ValueError(message)
assert_raise_message(ValueError, "test",
_raise_ValueError, "test")
assert_raises(AssertionError,
assert_raise_message, ValueError, "something else",
_raise_ValueError, "test")
assert_raises(ValueError,
assert_raise_message, TypeError, "something else",
_raise_ValueError, "test")
def check_estimators_empty_data_messages(name, Estimator):
e = Estimator()
set_fast_parameters(e)
set_random_state(e, 1)
X_zero_samples = np.empty(0).reshape(0, 3)
# The precise message can change depending on whether X or y is
# validated first. Let us test the type of exception only:
assert_raises(ValueError, e.fit, X_zero_samples, [])
X_zero_features = np.empty(0).reshape(3, 0)
# the following y should be accepted by both classifiers and regressors
# and ignored by unsupervised models
y = multioutput_estimator_convert_y_2d(name, np.array([1, 0, 1]))
msg = "0 feature(s) (shape=(3, 0)) while a minimum of 1 is required."
assert_raise_message(ValueError, msg, e.fit, X_zero_features, y)
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 = 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)
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 = 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)
