def test_check_array_accept_sparse_type_exception():
X = [[1, 2], [3, 4]]
X_csr = sp.csr_matrix(X)
msg = ("A sparse tensor was passed, but dense data is required. "
"Use X.todense() to convert to a dense tensor.")
assert_raise_message(TypeError,
msg,
check_array,
X_csr,
accept_sparse=False)
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=())
with pytest.raises(ValueError):
check_array(X_csr, accept_sparse=object)
def test_check_array_pandas_dtype_object_conversion():
# test that data-frame like objects with dtype object
# get converted
X = mt.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]], dtype=mt.object)
X_df = MockDataFrame(X)
assert check_array(X_df).dtype.kind == "f"
assert check_array(X_df, ensure_2d=False).dtype.kind == "f"
# smoke-test against dataframes with column named "dtype"
X_df.dtype = "Hans"
assert check_array(X_df, ensure_2d=False).dtype.kind == "f"
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 = mt.ones((10, 5))
for A in X, X.T:
for copy in (True, False):
B = check_array(A, order='C', copy=copy)
assert B.flags['C_CONTIGUOUS'] is True
B = check_array(A, order='F', copy=copy)
assert B.flags['F_CONTIGUOUS'] is True
if copy:
assert A is not B
def test_check_array_accept_sparse_no_exception():
X = [[1, 2], [3, 4]]
X_csr = sp.csr_matrix(X)
array = check_array(X_csr, accept_sparse=True)
assert isinstance(array, Tensor)
assert array.issparse() is True
def test_check_array_accept_sparse_no_exception(self):
X = [[1, 2], [3, 4]]
X_csr = sp.csr_matrix(X)
array = check_array(X_csr, accept_sparse=True)
self.assertIsInstance(array, Tensor)
self.assertTrue(array.issparse())
def test_check_array(setup):
# accept_sparse == False
# raise error on sparse inputs
X = [[1, 2], [3, 4]]
X_csr = sp.csr_matrix(X)
with pytest.raises(TypeError):
check_array(X_csr)
X_csr = mt.tensor(sp.csr_matrix(X))
with pytest.raises(TypeError):
check_array(X_csr)
# ensure_2d=False
X_array = check_array([0, 1, 2], ensure_2d=False)
assert X_array.ndim == 1
# ensure_2d=True with 1d array
assert_raise_message(ValueError,
'Expected 2D array, got 1D array instead',
check_array, [0, 1, 2],
ensure_2d=True)
assert_raise_message(ValueError,
'Expected 2D array, got 1D array instead',
check_array,
mt.tensor([0, 1, 2]),
ensure_2d=True)
# ensure_2d=True with scalar array
assert_raise_message(ValueError,
'Expected 2D array, got scalar array instead',
check_array,
10,
ensure_2d=True)
# don't allow ndim > 3
X_ndim = mt.arange(8).reshape(2, 2, 2)
with pytest.raises(ValueError):
check_array(X_ndim)
check_array(X_ndim, allow_nd=True) # doesn't raise
# dtype and order enforcement.
X_C = mt.arange(4).reshape(2, 2).copy("C")
X_F = X_C.copy("F")
X_int = X_C.astype(mt.int)
X_float = X_C.astype(mt.float)
Xs = [X_C, X_F, X_int, X_float]
dtypes = [mt.int32, mt.int, mt.float, mt.float32, None, mt.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,
force_all_finite=False)
if dtype is not None:
assert X_checked.dtype == dtype
else:
assert X_checked.dtype == X.dtype
if order == 'C':
assert X_checked.flags['C_CONTIGUOUS']
assert not X_checked.flags['F_CONTIGUOUS']
elif order == 'F':
assert X_checked.flags['F_CONTIGUOUS']
assert not X_checked.flags['C_CONTIGUOUS']
if copy:
assert X is not 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 X is X_checked
# other input formats
# convert lists to arrays
X_dense = check_array([[1, 2], [3, 4]])
assert isinstance(X_dense, Tensor)
# raise on too deep lists
with pytest.raises(ValueError):
check_array(X_ndim.to_numpy().tolist())
check_array(X_ndim.to_numpy().tolist(), allow_nd=True) # doesn't raise
# convert weird stuff to arrays
X_no_array = NotAnArray(X_dense.to_numpy())
result = check_array(X_no_array)
assert isinstance(result, Tensor)
# deprecation warning if string-like array with dtype="numeric"
expected_warn_regex = r"converted to decimal numbers if dtype='numeric'"
X_str = [['11', '12'], ['13', 'xx']]
for X in [X_str, mt.array(X_str, dtype='U'), mt.array(X_str, dtype='S')]:
with pytest.warns(FutureWarning, match=expected_warn_regex):
check_array(X, dtype="numeric")
# deprecation warning if byte-like array with dtype="numeric"
X_bytes = [[b'a', b'b'], [b'c', b'd']]
for X in [X_bytes, mt.array(X_bytes, dtype='V1')]:
with pytest.warns(FutureWarning, match=expected_warn_regex):
check_array(X, dtype="numeric")
# test finite
X = [[1.0, np.nan], [2.0, 3.0]]
with pytest.raises(ValueError):
_ = check_array(X).execute()
def test_check_array_from_dataframe():
X = md.DataFrame({'a': [1.0, 2.0, 3.0]})
assert check_array(X).dtype.kind == 'f'
def test_check_array(self):
# accept_sparse == False
# raise error on sparse inputs
X = [[1, 2], [3, 4]]
X_csr = sp.csr_matrix(X)
with self.assertRaises(TypeError):
check_array(X_csr)
X_csr = mt.tensor(sp.csr_matrix(X))
with self.assertRaises(TypeError):
check_array(X_csr)
# ensure_2d=False
X_array = check_array([0, 1, 2], ensure_2d=False)
self.assertEqual(X_array.ndim, 1)
# ensure_2d=True with 1d array
assert_raise_message(ValueError,
'Expected 2D array, got 1D array instead',
check_array, [0, 1, 2],
ensure_2d=True)
assert_raise_message(ValueError,
'Expected 2D array, got 1D array instead',
check_array,
mt.tensor([0, 1, 2]),
ensure_2d=True)
# ensure_2d=True with scalar array
assert_raise_message(ValueError,
'Expected 2D array, got scalar array instead',
check_array,
10,
ensure_2d=True)
# don't allow ndim > 3
X_ndim = mt.arange(8).reshape(2, 2, 2)
with self.assertRaises(ValueError):
check_array(X_ndim)
check_array(X_ndim, allow_nd=True) # doesn't raise
# dtype and order enforcement.
X_C = mt.arange(4).reshape(2, 2).copy("C")
X_F = X_C.copy("F")
X_int = X_C.astype(mt.int)
X_float = X_C.astype(mt.float)
Xs = [X_C, X_F, X_int, X_float]
dtypes = [
mt.int32, mt.int, mt.float, mt.float32, None, mt.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:
self.assertEqual(X_checked.dtype, dtype)
else:
self.assertEqual(X_checked.dtype, X.dtype)
if order == 'C':
assert X_checked.flags['C_CONTIGUOUS']
assert not X_checked.flags['F_CONTIGUOUS']
elif order == 'F':
assert X_checked.flags['F_CONTIGUOUS']
assert not X_checked.flags['C_CONTIGUOUS']
if copy:
assert X is not 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 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(mt.int)
# X_float = X_csc.astype(mt.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 message in messages
# else:
# self.assertEqual(len(w), 0)
# if dtype is not None:
# self.assertEqual(X_checked.dtype, dtype)
# else:
# self.assertEqual(X_checked.dtype, X.dtype)
# if X.format in accept_sparse:
# # no change if allowed
# self.assertEqual(X.format, X_checked.format)
# else:
# # got converted
# self.assertEqual(X_checked.format, accept_sparse[0])
# if copy:
# assert X is not X_checked
# else:
# # doesn't copy if it was already good
# if X.dtype == X_checked.dtype and X.format == X_checked.format:
# assert X is X_checked
# other input formats
# convert lists to arrays
X_dense = check_array([[1, 2], [3, 4]])
assert isinstance(X_dense, Tensor)
# raise on too deep lists
with self.assertRaises(ValueError):
check_array(X_ndim.execute().tolist())
check_array(X_ndim.execute().tolist(), allow_nd=True) # doesn't raise
# convert weird stuff to arrays
X_no_array = NotAnArray(X_dense.execute())
result = check_array(X_no_array)
assert isinstance(result, Tensor)
# deprecation warning if string-like array with dtype="numeric"
expected_warn_regex = r"converted to decimal numbers if dtype='numeric'"
X_str = [['11', '12'], ['13', 'xx']]
for X in [
X_str,
mt.array(X_str, dtype='U'),
mt.array(X_str, dtype='S')
]:
with pytest.warns(FutureWarning, match=expected_warn_regex):
check_array(X, dtype="numeric")
# deprecation warning if byte-like array with dtype="numeric"
X_bytes = [[b'a', b'b'], [b'c', b'd']]
for X in [X_bytes, mt.array(X_bytes, dtype='V1')]:
with pytest.warns(FutureWarning, match=expected_warn_regex):
check_array(X, dtype="numeric")
def test_check_array_from_dataframe(self):
X = md.DataFrame({'a': [1.0, 2.0, 3.0]})
self.assertEqual(check_array(X).dtype.kind, 'f')
