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_ordering():
# Check that ordering is enforced correctly by validation utilities.
# We need to check each validation utility, because a 'copy' without
# 'order=K' will kill the ordering.
X = np.ones((10, 5))
for A in X, X.T:
for copy in (True, False):
B = check_array(A, order="C", copy=copy)
assert_true(B.flags["C_CONTIGUOUS"])
B = check_array(A, order="F", copy=copy)
assert_true(B.flags["F_CONTIGUOUS"])
if copy:
assert_false(A is B)
X = sp.csr_matrix(X)
X.data = X.data[::-1]
assert_false(X.data.flags["C_CONTIGUOUS"])
for copy in (True, False):
Y = check_array(X, accept_sparse="csr", copy=copy, order="C")
assert_true(Y.data.flags["C_CONTIGUOUS"])
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_ordering():
# Check that ordering is enforced correctly by validation utilities.
# We need to check each validation utility, because a 'copy' without
# 'order=K' will kill the ordering.
X = np.ones((10, 5))
for A in X, X.T:
for copy in (True, False):
B = check_array(A, order='C', copy=copy)
assert_true(B.flags['C_CONTIGUOUS'])
B = check_array(A, order='F', copy=copy)
assert_true(B.flags['F_CONTIGUOUS'])
if copy:
assert_false(A is B)
X = sp.csr_matrix(X)
X.data = X.data[::-1]
assert_false(X.data.flags['C_CONTIGUOUS'])
for copy in (True, False):
Y = check_array(X, accept_sparse='csr', copy=copy, order='C')
assert_true(Y.data.flags['C_CONTIGUOUS'])
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
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():
# 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
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))