def test_exceptions(self):
dims = [
((1,), (2,)), # mismatched vector vector
((2, 1,), (2,)), # mismatched matrix vector
((2,), (1, 2)), # mismatched vector matrix
((1, 2), (3, 1)), # mismatched matrix matrix
((1,), ()), # vector scalar
((), (1)), # scalar vector
((1, 1), ()), # matrix scalar
((), (1, 1)), # scalar matrix
((2, 2, 1), (3, 1, 2)), # cannot broadcast
]
for dt, (dm1, dm2) in itertools.product(self.types, dims):
a = np.ones(dm1, dtype=dt)
b = np.ones(dm2, dtype=dt)
assert_raises(ValueError, self.matmul, a, b)
python类matmul()的实例源码
def test_shapes(self):
dims = [
((1, 1), (2, 1, 1)), # broadcast first argument
((2, 1, 1), (1, 1)), # broadcast second argument
((2, 1, 1), (2, 1, 1)), # matrix stack sizes match
]
for dt, (dm1, dm2) in itertools.product(self.types, dims):
a = np.ones(dm1, dtype=dt)
b = np.ones(dm2, dtype=dt)
res = self.matmul(a, b)
assert_(res.shape == (2, 1, 1))
# vector vector returns scalars.
for dt in self.types:
a = np.ones((2,), dtype=dt)
b = np.ones((2,), dtype=dt)
c = self.matmul(a, b)
assert_(np.array(c).shape == ())
def test_numpy_ufunc_override(self):
# 2016-01-29: NUMPY_UFUNC_DISABLED
return
class A(np.ndarray):
def __new__(cls, *args, **kwargs):
return np.array(*args, **kwargs).view(cls)
def __numpy_ufunc__(self, ufunc, method, pos, inputs, **kwargs):
return "A"
class B(np.ndarray):
def __new__(cls, *args, **kwargs):
return np.array(*args, **kwargs).view(cls)
def __numpy_ufunc__(self, ufunc, method, pos, inputs, **kwargs):
return NotImplemented
a = A([1, 2])
b = B([1, 2])
c = np.ones(2)
assert_equal(self.matmul(a, b), "A")
assert_equal(self.matmul(b, a), "A")
assert_raises(TypeError, self.matmul, b, c)
def test_matmul(self):
if not TEST_MATMUL:
pytest.skip("matmul is only tested in Python 3.5+")
D = {'shape': self.A.shape,
'matvec': lambda x: np.dot(self.A, x).reshape(self.A.shape[0]),
'rmatvec': lambda x: np.dot(self.A.T.conj(),
x).reshape(self.A.shape[1]),
'matmat': lambda x: np.dot(self.A, x)}
A = interface.LinearOperator(**D)
B = np.array([[1, 2, 3],
[4, 5, 6],
[7, 8, 9]])
b = B[0]
assert_equal(operator.matmul(A, b), A * b)
assert_equal(operator.matmul(A, B), A * B)
assert_raises(ValueError, operator.matmul, A, 2)
assert_raises(ValueError, operator.matmul, 2, A)
def test_exceptions(self):
dims = [
((1,), (2,)), # mismatched vector vector
((2, 1,), (2,)), # mismatched matrix vector
((2,), (1, 2)), # mismatched vector matrix
((1, 2), (3, 1)), # mismatched matrix matrix
((1,), ()), # vector scalar
((), (1)), # scalar vector
((1, 1), ()), # matrix scalar
((), (1, 1)), # scalar matrix
((2, 2, 1), (3, 1, 2)), # cannot broadcast
]
for dt, (dm1, dm2) in itertools.product(self.types, dims):
a = np.ones(dm1, dtype=dt)
b = np.ones(dm2, dtype=dt)
assert_raises(ValueError, self.matmul, a, b)
def test_shapes(self):
dims = [
((1, 1), (2, 1, 1)), # broadcast first argument
((2, 1, 1), (1, 1)), # broadcast second argument
((2, 1, 1), (2, 1, 1)), # matrix stack sizes match
]
for dt, (dm1, dm2) in itertools.product(self.types, dims):
a = np.ones(dm1, dtype=dt)
b = np.ones(dm2, dtype=dt)
res = self.matmul(a, b)
assert_(res.shape == (2, 1, 1))
# vector vector returns scalars.
for dt in self.types:
a = np.ones((2,), dtype=dt)
b = np.ones((2,), dtype=dt)
c = self.matmul(a, b)
assert_(np.array(c).shape == ())
def test_numpy_ufunc_override(self):
# 2016-01-29: NUMPY_UFUNC_DISABLED
return
class A(np.ndarray):
def __new__(cls, *args, **kwargs):
return np.array(*args, **kwargs).view(cls)
def __numpy_ufunc__(self, ufunc, method, pos, inputs, **kwargs):
return "A"
class B(np.ndarray):
def __new__(cls, *args, **kwargs):
return np.array(*args, **kwargs).view(cls)
def __numpy_ufunc__(self, ufunc, method, pos, inputs, **kwargs):
return NotImplemented
a = A([1, 2])
b = B([1, 2])
c = np.ones(2)
assert_equal(self.matmul(a, b), "A")
assert_equal(self.matmul(b, a), "A")
assert_raises(TypeError, self.matmul, b, c)
test_multiarray.py 文件源码
项目：PyDataLondon29-EmbarrassinglyParallelDAWithAWSLambda
作者: SignalMedia
项目源码
文件源码
阅读 21
收藏 0
点赞 0
评论 0
def test_exceptions(self):
dims = [
((1,), (2,)), # mismatched vector vector
((2, 1,), (2,)), # mismatched matrix vector
((2,), (1, 2)), # mismatched vector matrix
((1, 2), (3, 1)), # mismatched matrix matrix
((1,), ()), # vector scalar
((), (1)), # scalar vector
((1, 1), ()), # matrix scalar
((), (1, 1)), # scalar matrix
((2, 2, 1), (3, 1, 2)), # cannot broadcast
]
for dt, (dm1, dm2) in itertools.product(self.types, dims):
a = np.ones(dm1, dtype=dt)
b = np.ones(dm2, dtype=dt)
assert_raises(ValueError, self.matmul, a, b)
test_multiarray.py 文件源码
项目：PyDataLondon29-EmbarrassinglyParallelDAWithAWSLambda
作者: SignalMedia
项目源码
文件源码
阅读 21
收藏 0
点赞 0
评论 0
def test_shapes(self):
dims = [
((1, 1), (2, 1, 1)), # broadcast first argument
((2, 1, 1), (1, 1)), # broadcast second argument
((2, 1, 1), (2, 1, 1)), # matrix stack sizes match
]
for dt, (dm1, dm2) in itertools.product(self.types, dims):
a = np.ones(dm1, dtype=dt)
b = np.ones(dm2, dtype=dt)
res = self.matmul(a, b)
assert_(res.shape == (2, 1, 1))
# vector vector returns scalars.
for dt in self.types:
a = np.ones((2,), dtype=dt)
b = np.ones((2,), dtype=dt)
c = self.matmul(a, b)
assert_(np.array(c).shape == ())
test_multiarray.py 文件源码
项目：PyDataLondon29-EmbarrassinglyParallelDAWithAWSLambda
作者: SignalMedia
项目源码
文件源码
阅读 22
收藏 0
点赞 0
评论 0
def test_numpy_ufunc_override(self):
# Temporarily disable __numpy_ufunc__ for 1.10; see gh-5844
return
class A(np.ndarray):
def __new__(cls, *args, **kwargs):
return np.array(*args, **kwargs).view(cls)
def __numpy_ufunc__(self, ufunc, method, pos, inputs, **kwargs):
return "A"
class B(np.ndarray):
def __new__(cls, *args, **kwargs):
return np.array(*args, **kwargs).view(cls)
def __numpy_ufunc__(self, ufunc, method, pos, inputs, **kwargs):
return NotImplemented
a = A([1, 2])
b = B([1, 2])
c = np.ones(2)
assert_equal(self.matmul(a, b), "A")
assert_equal(self.matmul(b, a), "A")
assert_raises(TypeError, self.matmul, b, c)
def test_exceptions(self):
dims = [
((1,), (2,)), # mismatched vector vector
((2, 1,), (2,)), # mismatched matrix vector
((2,), (1, 2)), # mismatched vector matrix
((1, 2), (3, 1)), # mismatched matrix matrix
((1,), ()), # vector scalar
((), (1)), # scalar vector
((1, 1), ()), # matrix scalar
((), (1, 1)), # scalar matrix
((2, 2, 1), (3, 1, 2)), # cannot broadcast
]
for dt, (dm1, dm2) in itertools.product(self.types, dims):
a = np.ones(dm1, dtype=dt)
b = np.ones(dm2, dtype=dt)
assert_raises(ValueError, self.matmul, a, b)
def test_shapes(self):
dims = [
((1, 1), (2, 1, 1)), # broadcast first argument
((2, 1, 1), (1, 1)), # broadcast second argument
((2, 1, 1), (2, 1, 1)), # matrix stack sizes match
]
for dt, (dm1, dm2) in itertools.product(self.types, dims):
a = np.ones(dm1, dtype=dt)
b = np.ones(dm2, dtype=dt)
res = self.matmul(a, b)
assert_(res.shape == (2, 1, 1))
# vector vector returns scalars.
for dt in self.types:
a = np.ones((2,), dtype=dt)
b = np.ones((2,), dtype=dt)
c = self.matmul(a, b)
assert_(np.array(c).shape == ())
def test_numpy_ufunc_override(self):
# Temporarily disable __numpy_ufunc__ for 1.10; see gh-5844
return
class A(np.ndarray):
def __new__(cls, *args, **kwargs):
return np.array(*args, **kwargs).view(cls)
def __numpy_ufunc__(self, ufunc, method, pos, inputs, **kwargs):
return "A"
class B(np.ndarray):
def __new__(cls, *args, **kwargs):
return np.array(*args, **kwargs).view(cls)
def __numpy_ufunc__(self, ufunc, method, pos, inputs, **kwargs):
return NotImplemented
a = A([1, 2])
b = B([1, 2])
c = np.ones(2)
assert_equal(self.matmul(a, b), "A")
assert_equal(self.matmul(b, a), "A")
assert_raises(TypeError, self.matmul, b, c)
def test_exceptions(self):
dims = [
((1,), (2,)), # mismatched vector vector
((2, 1,), (2,)), # mismatched matrix vector
((2,), (1, 2)), # mismatched vector matrix
((1, 2), (3, 1)), # mismatched matrix matrix
((1,), ()), # vector scalar
((), (1)), # scalar vector
((1, 1), ()), # matrix scalar
((), (1, 1)), # scalar matrix
((2, 2, 1), (3, 1, 2)), # cannot broadcast
]
for dt, (dm1, dm2) in itertools.product(self.types, dims):
a = np.ones(dm1, dtype=dt)
b = np.ones(dm2, dtype=dt)
assert_raises(ValueError, self.matmul, a, b)
def test_shapes(self):
dims = [
((1, 1), (2, 1, 1)), # broadcast first argument
((2, 1, 1), (1, 1)), # broadcast second argument
((2, 1, 1), (2, 1, 1)), # matrix stack sizes match
]
for dt, (dm1, dm2) in itertools.product(self.types, dims):
a = np.ones(dm1, dtype=dt)
b = np.ones(dm2, dtype=dt)
res = self.matmul(a, b)
assert_(res.shape == (2, 1, 1))
# vector vector returns scalars.
for dt in self.types:
a = np.ones((2,), dtype=dt)
b = np.ones((2,), dtype=dt)
c = self.matmul(a, b)
assert_(np.array(c).shape == ())
def test_numpy_ufunc_override(self):
# 2016-01-29: NUMPY_UFUNC_DISABLED
return
class A(np.ndarray):
def __new__(cls, *args, **kwargs):
return np.array(*args, **kwargs).view(cls)
def __numpy_ufunc__(self, ufunc, method, pos, inputs, **kwargs):
return "A"
class B(np.ndarray):
def __new__(cls, *args, **kwargs):
return np.array(*args, **kwargs).view(cls)
def __numpy_ufunc__(self, ufunc, method, pos, inputs, **kwargs):
return NotImplemented
a = A([1, 2])
b = B([1, 2])
c = np.ones(2)
assert_equal(self.matmul(a, b), "A")
assert_equal(self.matmul(b, a), "A")
assert_raises(TypeError, self.matmul, b, c)
def test_exceptions(self):
dims = [
((1,), (2,)), # mismatched vector vector
((2, 1,), (2,)), # mismatched matrix vector
((2,), (1, 2)), # mismatched vector matrix
((1, 2), (3, 1)), # mismatched matrix matrix
((1,), ()), # vector scalar
((), (1)), # scalar vector
((1, 1), ()), # matrix scalar
((), (1, 1)), # scalar matrix
((2, 2, 1), (3, 1, 2)), # cannot broadcast
]
for dt, (dm1, dm2) in itertools.product(self.types, dims):
a = np.ones(dm1, dtype=dt)
b = np.ones(dm2, dtype=dt)
assert_raises(ValueError, self.matmul, a, b)
def test_shapes(self):
dims = [
((1, 1), (2, 1, 1)), # broadcast first argument
((2, 1, 1), (1, 1)), # broadcast second argument
((2, 1, 1), (2, 1, 1)), # matrix stack sizes match
]
for dt, (dm1, dm2) in itertools.product(self.types, dims):
a = np.ones(dm1, dtype=dt)
b = np.ones(dm2, dtype=dt)
res = self.matmul(a, b)
assert_(res.shape == (2, 1, 1))
# vector vector returns scalars.
for dt in self.types:
a = np.ones((2,), dtype=dt)
b = np.ones((2,), dtype=dt)
c = self.matmul(a, b)
assert_(np.array(c).shape == ())
def test_numpy_ufunc_override(self):
# 2016-01-29: NUMPY_UFUNC_DISABLED
return
class A(np.ndarray):
def __new__(cls, *args, **kwargs):
return np.array(*args, **kwargs).view(cls)
def __numpy_ufunc__(self, ufunc, method, pos, inputs, **kwargs):
return "A"
class B(np.ndarray):
def __new__(cls, *args, **kwargs):
return np.array(*args, **kwargs).view(cls)
def __numpy_ufunc__(self, ufunc, method, pos, inputs, **kwargs):
return NotImplemented
a = A([1, 2])
b = B([1, 2])
c = np.ones(2)
assert_equal(self.matmul(a, b), "A")
assert_equal(self.matmul(b, a), "A")
assert_raises(TypeError, self.matmul, b, c)
def test_exceptions(self):
dims = [
((1,), (2,)), # mismatched vector vector
((2, 1,), (2,)), # mismatched matrix vector
((2,), (1, 2)), # mismatched vector matrix
((1, 2), (3, 1)), # mismatched matrix matrix
((1,), ()), # vector scalar
((), (1)), # scalar vector
((1, 1), ()), # matrix scalar
((), (1, 1)), # scalar matrix
((2, 2, 1), (3, 1, 2)), # cannot broadcast
]
for dt, (dm1, dm2) in itertools.product(self.types, dims):
a = np.ones(dm1, dtype=dt)
b = np.ones(dm2, dtype=dt)
assert_raises(ValueError, self.matmul, a, b)
def test_shapes(self):
dims = [
((1, 1), (2, 1, 1)), # broadcast first argument
((2, 1, 1), (1, 1)), # broadcast second argument
((2, 1, 1), (2, 1, 1)), # matrix stack sizes match
]
for dt, (dm1, dm2) in itertools.product(self.types, dims):
a = np.ones(dm1, dtype=dt)
b = np.ones(dm2, dtype=dt)
res = self.matmul(a, b)
assert_(res.shape == (2, 1, 1))
# vector vector returns scalars.
for dt in self.types:
a = np.ones((2,), dtype=dt)
b = np.ones((2,), dtype=dt)
c = self.matmul(a, b)
assert_(np.array(c).shape == ())
def test_numpy_ufunc_override(self):
# 2016-01-29: NUMPY_UFUNC_DISABLED
return
class A(np.ndarray):
def __new__(cls, *args, **kwargs):
return np.array(*args, **kwargs).view(cls)
def __numpy_ufunc__(self, ufunc, method, pos, inputs, **kwargs):
return "A"
class B(np.ndarray):
def __new__(cls, *args, **kwargs):
return np.array(*args, **kwargs).view(cls)
def __numpy_ufunc__(self, ufunc, method, pos, inputs, **kwargs):
return NotImplemented
a = A([1, 2])
b = B([1, 2])
c = np.ones(2)
assert_equal(self.matmul(a, b), "A")
assert_equal(self.matmul(b, a), "A")
assert_raises(TypeError, self.matmul, b, c)
def test_result_types(self):
mat = np.ones((1,1))
vec = np.ones((1,))
for dt in self.types:
m = mat.astype(dt)
v = vec.astype(dt)
for arg in [(m, v), (v, m), (m, m)]:
res = self.matmul(*arg)
assert_(res.dtype == dt)
# vector vector returns scalars
res = self.matmul(v, v)
assert_(type(res) is np.dtype(dt).type)
def test_vector_vector_values(self):
vec = np.array([1, 2])
tgt = 5
for dt in self.types[1:]:
v1 = vec.astype(dt)
res = self.matmul(v1, v1)
assert_equal(res, tgt)
# boolean type
vec = np.array([True, True], dtype='?')
res = self.matmul(vec, vec)
assert_equal(res, True)
def test_vector_matrix_values(self):
vec = np.array([1, 2])
mat1 = np.array([[1, 2], [3, 4]])
mat2 = np.stack([mat1]*2, axis=0)
tgt1 = np.array([7, 10])
tgt2 = np.stack([tgt1]*2, axis=0)
for dt in self.types[1:]:
v = vec.astype(dt)
m1 = mat1.astype(dt)
m2 = mat2.astype(dt)
res = self.matmul(v, m1)
assert_equal(res, tgt1)
res = self.matmul(v, m2)
assert_equal(res, tgt2)
# boolean type
vec = np.array([True, False])
mat1 = np.array([[True, False], [False, True]])
mat2 = np.stack([mat1]*2, axis=0)
tgt1 = np.array([True, False])
tgt2 = np.stack([tgt1]*2, axis=0)
res = self.matmul(vec, mat1)
assert_equal(res, tgt1)
res = self.matmul(vec, mat2)
assert_equal(res, tgt2)
def test_out_arg(self):
a = np.ones((2, 2), dtype=np.float)
b = np.ones((2, 2), dtype=np.float)
tgt = np.full((2,2), 2, dtype=np.float)
# test as positional argument
msg = "out positional argument"
out = np.zeros((2, 2), dtype=np.float)
self.matmul(a, b, out)
assert_array_equal(out, tgt, err_msg=msg)
# test as keyword argument
msg = "out keyword argument"
out = np.zeros((2, 2), dtype=np.float)
self.matmul(a, b, out=out)
assert_array_equal(out, tgt, err_msg=msg)
# test out with not allowed type cast (safe casting)
# einsum and cblas raise different error types, so
# use Exception.
msg = "out argument with illegal cast"
out = np.zeros((2, 2), dtype=np.int32)
assert_raises(Exception, self.matmul, a, b, out=out)
# skip following tests for now, cblas does not allow non-contiguous
# outputs and consistency with dot would require same type,
# dimensions, subtype, and c_contiguous.
# test out with allowed type cast
# msg = "out argument with allowed cast"
# out = np.zeros((2, 2), dtype=np.complex128)
# self.matmul(a, b, out=out)
# assert_array_equal(out, tgt, err_msg=msg)
# test out non-contiguous
# msg = "out argument with non-contiguous layout"
# c = np.zeros((2, 2, 2), dtype=np.float)
# self.matmul(a, b, out=c[..., 0])
# assert_array_equal(c, tgt, err_msg=msg)
def test_array_priority_override(self):
class A(object):
__array_priority__ = 1000
def __matmul__(self, other):
return "A"
def __rmatmul__(self, other):
return "A"
a = A()
b = np.ones(2)
assert_equal(self.matmul(a, b), "A")
assert_equal(self.matmul(b, a), "A")
def test_matmul_inplace():
# It would be nice to support in-place matmul eventually, but for now
# we don't have a working implementation, so better just to error out
# and nudge people to writing "a = a @ b".
a = np.eye(3)
b = np.eye(3)
assert_raises(TypeError, a.__imatmul__, b)
import operator
assert_raises(TypeError, operator.imatmul, a, b)
# we avoid writing the token `exec` so as not to crash python 2's
# parser
exec_ = getattr(builtins, "exec")
assert_raises(TypeError, exec_, "a @= b", globals(), locals())
def test_operator_matmul(self, xp, dtype1, dtype2):
x1 = testing.shaped_arange(self.shape_pair[0], xp, dtype1)
x2 = testing.shaped_arange(self.shape_pair[1], xp, dtype2)
return operator.matmul(x1, x2)
def test_cupy_matmul(self, xp, dtype1, dtype2):
x1 = testing.shaped_arange(self.shape_pair[0], xp, dtype1)
x2 = testing.shaped_arange(self.shape_pair[1], xp, dtype2)
return xp.matmul(x1, x2)
