def test_hashes_are_different_between_c_and_fortran_contiguous_arrays():
# We want to be sure that the c-contiguous and f-contiguous versions of the
# same array produce 2 different hashes.
rng = np.random.RandomState(0)
arr_c = rng.random_sample((10, 10))
arr_f = np.asfortranarray(arr_c)
assert hash(arr_c) != hash(arr_f)
def test_hashes_are_different_between_c_and_fortran_contiguous_arrays():
# We want to be sure that the c-contiguous and f-contiguous versions of the
# same array produce 2 different hashes.
rng = np.random.RandomState(0)
arr_c = rng.random_sample((10, 10))
arr_f = np.asfortranarray(arr_c)
assert hash(arr_c) != hash(arr_f)
def test_hash_numpy_noncontiguous():
a = np.asarray(np.arange(6000).reshape((1000, 2, 3)), order='F')[:, :1, :]
b = np.ascontiguousarray(a)
nose.tools.assert_not_equal(hash(a), hash(b))
c = np.asfortranarray(a)
nose.tools.assert_not_equal(hash(a), hash(c))
def test_hash_numpy_noncontiguous():
a = np.asarray(np.arange(6000).reshape((1000, 2, 3)), order='F')[:, :1, :]
b = np.ascontiguousarray(a)
assert hash(a) != hash(b)
c = np.asfortranarray(a)
assert hash(a) != hash(c)
def create_objects_to_hash():
rng = np.random.RandomState(42)
# Being explicit about dtypes in order to avoid
# architecture-related differences. Also using 'f4' rather than
# 'f8' for float arrays because 'f8' arrays generated by
# rng.random.randn don't seem to be bit-identical on 32bit and
# 64bit machines.
to_hash_list = [
rng.randint(-1000, high=1000, size=50).astype('<i8'),
tuple(rng.randn(3).astype('<f4') for _ in range(5)),
[rng.randn(3).astype('<f4') for _ in range(5)],
{
-3333:
rng.randn(3, 5).astype('<f4'),
0: [
rng.randint(10, size=20).astype('<i8'),
rng.randn(10).astype('<f4')
]
},
# Non regression cases for
# https://github.com/joblib/joblib/issues/308
np.arange(100, dtype='<i8').reshape((10, 10)),
# Fortran contiguous array
np.asfortranarray(np.arange(100, dtype='<i8').reshape((10, 10))),
# Non contiguous array
np.arange(100, dtype='<i8').reshape((10, 10))[:, :2],
]
return to_hash_list
def test_hashes_stay_the_same_with_numpy_objects():
# We want to make sure that hashes don't change with joblib
# version. For end users, that would mean that they have to
# regenerate their cache from scratch, which potentially means
# lengthy recomputations.
rng = np.random.RandomState(42)
# Being explicit about dtypes in order to avoid
# architecture-related differences. Also using 'f4' rather than
# 'f8' for float arrays because 'f8' arrays generated by
# rng.random.randn don't seem to be bit-identical on 32bit and
# 64bit machines.
to_hash_list = [
rng.randint(-1000, high=1000, size=50).astype('<i8'),
tuple(rng.randn(3).astype('<f4') for _ in range(5)),
[rng.randn(3).astype('<f4') for _ in range(5)],
{
-3333:
rng.randn(3, 5).astype('<f4'),
0: [
rng.randint(10, size=20).astype('<i8'),
rng.randn(10).astype('<f4')
]
},
# Non regression cases for https://github.com/joblib/joblib/issues/308.
# Generated with joblib 0.9.4.
np.arange(100, dtype='<i8').reshape((10, 10)),
# Fortran contiguous array
np.asfortranarray(np.arange(100, dtype='<i8').reshape((10, 10))),
# Non contiguous array
np.arange(100, dtype='<i8').reshape((10, 10))[:, :2],
]
# These expected results have been generated with joblib 0.9.0
expected_dict = {
'py2': [
'80f2387e7752abbda2658aafed49e086',
'0d700f7f25ea670fd305e4cd93b0e8cd',
'83a2bdf843e79e4b3e26521db73088b9',
'63e0efd43c0a9ad92a07e8ce04338dd3',
'03fef702946b602c852b8b4e60929914',
'07074691e90d7098a85956367045c81e',
'd264cf79f353aa7bbfa8349e3df72d8f'
],
'py3': [
'10a6afc379ca2708acfbaef0ab676eab',
'988a7114f337f381393025911ebc823b',
'c6809f4b97e35f2fa0ee8d653cbd025c',
'b3ad17348e32728a7eb9cda1e7ede438',
'927b3e6b0b6a037e8e035bda134e0b05',
'108f6ee98e7db19ea2006ffd208f4bf1',
'bd48ccaaff28e16e6badee81041b7180'
]
}
py_version_str = 'py3' if PY3_OR_LATER else 'py2'
expected_list = expected_dict[py_version_str]
for to_hash, expected in zip(to_hash_list, expected_list):
assert hash(to_hash) == expected
def test_hash_numpy_noncontiguous():
a = np.asarray(np.arange(6000).reshape((1000, 2, 3)),
order='F')[:, :1, :]
b = np.ascontiguousarray(a)
assert hash(a) != hash(b)
c = np.asfortranarray(a)
assert hash(a) != hash(c)
def test_hash_numpy_noncontiguous():
a = np.asarray(np.arange(6000).reshape((1000, 2, 3)),
order='F')[:, :1, :]
b = np.ascontiguousarray(a)
nose.tools.assert_not_equal(hash(a), hash(b))
c = np.asfortranarray(a)
nose.tools.assert_not_equal(hash(a), hash(c))
def test_hashes_stay_the_same_with_numpy_objects():
# We want to make sure that hashes don't change with joblib
# version. For end users, that would mean that they have to
# regenerate their cache from scratch, which potentially means
# lengthy recomputations.
rng = np.random.RandomState(42)
# Being explicit about dtypes in order to avoid
# architecture-related differences. Also using 'f4' rather than
# 'f8' for float arrays because 'f8' arrays generated by
# rng.random.randn don't seem to be bit-identical on 32bit and
# 64bit machines.
to_hash_list = [
rng.randint(-1000, high=1000, size=50).astype('<i8'),
tuple(rng.randn(3).astype('<f4') for _ in range(5)),
[rng.randn(3).astype('<f4') for _ in range(5)],
{
-3333: rng.randn(3, 5).astype('<f4'),
0: [
rng.randint(10, size=20).astype('<i8'),
rng.randn(10).astype('<f4')
]
},
# Non regression cases for https://github.com/joblib/joblib/issues/308.
# Generated with joblib 0.9.4.
np.arange(100, dtype='<i8').reshape((10, 10)),
# Fortran contiguous array
np.asfortranarray(np.arange(100, dtype='<i8').reshape((10, 10))),
# Non contiguous array
np.arange(100, dtype='<i8').reshape((10, 10))[:, :2],
]
# These expected results have been generated with joblib 0.9.0
expected_dict = {'py2': ['80f2387e7752abbda2658aafed49e086',
'0d700f7f25ea670fd305e4cd93b0e8cd',
'83a2bdf843e79e4b3e26521db73088b9',
'63e0efd43c0a9ad92a07e8ce04338dd3',
'03fef702946b602c852b8b4e60929914',
'07074691e90d7098a85956367045c81e',
'd264cf79f353aa7bbfa8349e3df72d8f'],
'py3': ['10a6afc379ca2708acfbaef0ab676eab',
'988a7114f337f381393025911ebc823b',
'c6809f4b97e35f2fa0ee8d653cbd025c',
'b3ad17348e32728a7eb9cda1e7ede438',
'927b3e6b0b6a037e8e035bda134e0b05',
'108f6ee98e7db19ea2006ffd208f4bf1',
'bd48ccaaff28e16e6badee81041b7180']}
py_version_str = 'py3' if PY3_OR_LATER else 'py2'
expected_list = expected_dict[py_version_str]
for to_hash, expected in zip(to_hash_list, expected_list):
yield assert_equal, hash(to_hash), expected
def test_non_contiguous_array_pickling(tmpdir):
filename = tmpdir.join('test.pkl').strpath
for array in [ # Array that triggers a contiguousness issue with nditer,
# see https://github.com/joblib/joblib/pull/352 and see
# https://github.com/joblib/joblib/pull/353
np.asfortranarray([[1, 2], [3, 4]])[1:],
# Non contiguous array with works fine with nditer
np.ones((10, 50, 20), order='F')[:, :1, :]]:
assert not array.flags.c_contiguous
assert not array.flags.f_contiguous
numpy_pickle.dump(array, filename)
array_reloaded = numpy_pickle.load(filename)
np.testing.assert_array_equal(array_reloaded, array)
def test_non_contiguous_array_pickling():
filename = env['filename'] + str(random.randint(0, 1000))
for array in [ # Array that triggers a contiguousness issue with nditer,
# see https://github.com/joblib/joblib/pull/352 and see
# https://github.com/joblib/joblib/pull/353
np.asfortranarray([[1, 2], [3, 4]])[1:],
# Non contiguous array with works fine with nditer
np.ones((10, 50, 20), order='F')[:, :1, :]]:
assert not array.flags.c_contiguous
assert not array.flags.f_contiguous
numpy_pickle.dump(array, filename)
array_reloaded = numpy_pickle.load(filename)
np.testing.assert_array_equal(array_reloaded, array)
os.remove(filename)
def test_non_contiguous_array_pickling():
filename = env['filename'] + str(random.randint(0, 1000))
for array in [ # Array that triggers a contiguousness issue with nditer,
# see https://github.com/joblib/joblib/pull/352 and see
# https://github.com/joblib/joblib/pull/353
np.asfortranarray([[1, 2], [3, 4]])[1:],
# Non contiguous array with works fine with nditer
np.ones((10, 50, 20), order='F')[:, :1, :]
]:
nose.tools.assert_false(array.flags.c_contiguous)
nose.tools.assert_false(array.flags.f_contiguous)
numpy_pickle.dump(array, filename)
array_reloaded = numpy_pickle.load(filename)
np.testing.assert_array_equal(array_reloaded, array)
os.remove(filename)
def test_hashes_stay_the_same_with_numpy_objects():
# We want to make sure that hashes don't change with joblib
# version. For end users, that would mean that they have to
# regenerate their cache from scratch, which potentially means
# lengthy recomputations.
rng = np.random.RandomState(42)
# Being explicit about dtypes in order to avoid
# architecture-related differences. Also using 'f4' rather than
# 'f8' for float arrays because 'f8' arrays generated by
# rng.random.randn don't seem to be bit-identical on 32bit and
# 64bit machines.
to_hash_list = [
rng.randint(-1000, high=1000, size=50).astype('<i8'),
tuple(rng.randn(3).astype('<f4') for _ in range(5)),
[rng.randn(3).astype('<f4') for _ in range(5)],
{
-3333: rng.randn(3, 5).astype('<f4'),
0: [
rng.randint(10, size=20).astype('<i8'),
rng.randn(10).astype('<f4')
]
},
# Non regression cases for https://github.com/joblib/joblib/issues/308.
# Generated with joblib 0.9.4.
np.arange(100, dtype='<i8').reshape((10, 10)),
# Fortran contiguous array
np.asfortranarray(np.arange(100, dtype='<i8').reshape((10, 10))),
# Non contiguous array
np.arange(100, dtype='<i8').reshape((10, 10))[:, :2],
]
# These expected results have been generated with joblib 0.9.0
expected_hashes = [
'10a6afc379ca2708acfbaef0ab676eab',
'988a7114f337f381393025911ebc823b',
'c6809f4b97e35f2fa0ee8d653cbd025c',
'b3ad17348e32728a7eb9cda1e7ede438',
'927b3e6b0b6a037e8e035bda134e0b05',
'108f6ee98e7db19ea2006ffd208f4bf1',
'bd48ccaaff28e16e6badee81041b7180'
]
for to_hash, expected in zip(to_hash_list, expected_hashes):
assert hash(to_hash) == expected
