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_notanarray():
with pytest.warns(DeprecationWarning, match="removed in version 0.24"):
NotAnArray([1, 2])
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=False
X_array = check_array([0, 1, 2], ensure_2d=False)
assert_equal(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)
# 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 = np.arange(8).reshape(2, 2, 2)
assert_raises(ValueError, check_array, X_ndim)
check_array(X_ndim, allow_nd=True) # doesn't 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 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(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 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 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, 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 isinstance(result, np.ndarray)
# 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, np.array(X_str, dtype='U'), np.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, np.array(X_bytes, dtype='V1')]:
with pytest.warns(FutureWarning, match=expected_warn_regex):
check_array(X, dtype="numeric")
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()
