def shape_from_elems(*elems):
if len(elems) == 0:
return 1,
return np.broadcast(*[np.ones(elem.shape) for elem in elems]).shape
python类broadcast()的实例源码
def Softmax(x):
# TODO make this numerically stable by shifting by max?
exp = Exp(x)
if len(x.shape) == 1: # workaround because numpy einsum can't broadcast? https://github.com/numpy/numpy/issues/9984
return exp / Einsum("i->", exp)
elif len(x.shape) == 2:
return exp / Einsum("bi,o->bo", exp, np.array([1]))
elif len(x.shape) == 3:
return exp / Einsum("abi,o->abo", exp, np.array([1]))
elif len(x.shape) == 4:
return exp / Einsum("abci,o->abco", exp, np.array([1]))
else:
raise ValueError("5D tensors not yet supported")
def test_broadcast_in_args(self):
# gh-5881
arrs = [np.empty((6, 7)), np.empty((5, 6, 1)), np.empty((7,)),
np.empty((5, 1, 7))]
mits = [np.broadcast(*arrs),
np.broadcast(np.broadcast(*arrs[:2]), np.broadcast(*arrs[2:])),
np.broadcast(arrs[0], np.broadcast(*arrs[1:-1]), arrs[-1])]
for mit in mits:
assert_equal(mit.shape, (5, 6, 7))
assert_equal(mit.nd, 3)
assert_equal(mit.numiter, 4)
for a, ia in zip(arrs, mit.iters):
assert_(a is ia.base)
def test_number_of_arguments(self):
arr = np.empty((5,))
for j in range(35):
arrs = [arr] * j
if j < 2 or j > 32:
assert_raises(ValueError, np.broadcast, *arrs)
else:
mit = np.broadcast(*arrs)
assert_equal(mit.numiter, j)
def test_boolean_assignment_value_mismatch(self):
# A boolean assignment should fail when the shape of the values
# cannot be broadcast to the subscription. (see also gh-3458)
a = np.arange(4)
def f(a, v):
a[a > -1] = v
assert_raises(ValueError, f, a, [])
assert_raises(ValueError, f, a, [1, 2, 3])
assert_raises(ValueError, f, a[:1], [1, 2, 3])
def setUp(self):
self.a = np.arange(np.prod([3, 1, 5, 6])).reshape(3, 1, 5, 6)
self.b = np.empty((3, 0, 5, 6))
self.complex_indices = ['skip', Ellipsis,
0,
# Boolean indices, up to 3-d for some special cases of eating up
# dimensions, also need to test all False
np.array(False),
np.array([True, False, False]),
np.array([[True, False], [False, True]]),
np.array([[[False, False], [False, False]]]),
# Some slices:
slice(-5, 5, 2),
slice(1, 1, 100),
slice(4, -1, -2),
slice(None, None, -3),
# Some Fancy indexes:
np.empty((0, 1, 1), dtype=np.intp), # empty and can be broadcast
np.array([0, 1, -2]),
np.array([[2], [0], [1]]),
np.array([[0, -1], [0, 1]], dtype=np.dtype('intp').newbyteorder()),
np.array([2, -1], dtype=np.int8),
np.zeros([1]*31, dtype=int), # trigger too large array.
np.array([0., 1.])] # invalid datatype
# Some simpler indices that still cover a bit more
self.simple_indices = [Ellipsis, None, -1, [1], np.array([True]), 'skip']
# Very simple ones to fill the rest:
self.fill_indices = [slice(None, None), 0]
def _compare_index_result(self, arr, index, mimic_get, no_copy):
"""Compare mimicked result to indexing result.
"""
arr = arr.copy()
indexed_arr = arr[index]
assert_array_equal(indexed_arr, mimic_get)
# Check if we got a view, unless its a 0-sized or 0-d array.
# (then its not a view, and that does not matter)
if indexed_arr.size != 0 and indexed_arr.ndim != 0:
assert_(np.may_share_memory(indexed_arr, arr) == no_copy)
# Check reference count of the original array
if no_copy:
# refcount increases by one:
assert_equal(sys.getrefcount(arr), 3)
else:
assert_equal(sys.getrefcount(arr), 2)
# Test non-broadcast setitem:
b = arr.copy()
b[index] = mimic_get + 1000
if b.size == 0:
return # nothing to compare here...
if no_copy and indexed_arr.ndim != 0:
# change indexed_arr in-place to manipulate original:
indexed_arr += 1000
assert_array_equal(arr, b)
return
# Use the fact that the array is originally an arange:
arr.flat[indexed_arr.ravel()] += 1000
assert_array_equal(arr, b)
def broadcast_to(array, shape, subok=False):
"""Broadcast an array to a new shape.
Parameters
----------
array : array_like
The array to broadcast.
shape : tuple
The shape of the desired array.
subok : bool, optional
If True, then sub-classes will be passed-through, otherwise
the returned array will be forced to be a base-class array (default).
Returns
-------
broadcast : array
A readonly view on the original array with the given shape. It is
typically not contiguous. Furthermore, more than one element of a
broadcasted array may refer to a single memory location.
Raises
------
ValueError
If the array is not compatible with the new shape according to NumPy's
broadcasting rules.
Notes
-----
.. versionadded:: 1.10.0
Examples
--------
>>> x = np.array([1, 2, 3])
>>> np.broadcast_to(x, (3, 3))
array([[1, 2, 3],
[1, 2, 3],
[1, 2, 3]])
"""
return _broadcast_to(array, shape, subok=subok, readonly=True)
def test_broadcast_in_args(self):
# gh-5881
arrs = [np.empty((6, 7)), np.empty((5, 6, 1)), np.empty((7,)),
np.empty((5, 1, 7))]
mits = [np.broadcast(*arrs),
np.broadcast(np.broadcast(*arrs[:2]), np.broadcast(*arrs[2:])),
np.broadcast(arrs[0], np.broadcast(*arrs[1:-1]), arrs[-1])]
for mit in mits:
assert_equal(mit.shape, (5, 6, 7))
assert_equal(mit.nd, 3)
assert_equal(mit.numiter, 4)
for a, ia in zip(arrs, mit.iters):
assert_(a is ia.base)
def test_broadcast_single_arg(self):
# gh-6899
arrs = [np.empty((5, 6, 7))]
mit = np.broadcast(*arrs)
assert_equal(mit.shape, (5, 6, 7))
assert_equal(mit.nd, 3)
assert_equal(mit.numiter, 1)
assert_(arrs[0] is mit.iters[0].base)
def test_number_of_arguments(self):
arr = np.empty((5,))
for j in range(35):
arrs = [arr] * j
if j < 1 or j > 32:
assert_raises(ValueError, np.broadcast, *arrs)
else:
mit = np.broadcast(*arrs)
assert_equal(mit.numiter, j)
def test_boolean_assignment_value_mismatch(self):
# A boolean assignment should fail when the shape of the values
# cannot be broadcast to the subscription. (see also gh-3458)
a = np.arange(4)
def f(a, v):
a[a > -1] = v
assert_raises(ValueError, f, a, [])
assert_raises(ValueError, f, a, [1, 2, 3])
assert_raises(ValueError, f, a[:1], [1, 2, 3])
def setUp(self):
self.a = np.arange(np.prod([3, 1, 5, 6])).reshape(3, 1, 5, 6)
self.b = np.empty((3, 0, 5, 6))
self.complex_indices = ['skip', Ellipsis,
0,
# Boolean indices, up to 3-d for some special cases of eating up
# dimensions, also need to test all False
np.array(False),
np.array([True, False, False]),
np.array([[True, False], [False, True]]),
np.array([[[False, False], [False, False]]]),
# Some slices:
slice(-5, 5, 2),
slice(1, 1, 100),
slice(4, -1, -2),
slice(None, None, -3),
# Some Fancy indexes:
np.empty((0, 1, 1), dtype=np.intp), # empty and can be broadcast
np.array([0, 1, -2]),
np.array([[2], [0], [1]]),
np.array([[0, -1], [0, 1]], dtype=np.dtype('intp').newbyteorder()),
np.array([2, -1], dtype=np.int8),
np.zeros([1]*31, dtype=int), # trigger too large array.
np.array([0., 1.])] # invalid datatype
# Some simpler indices that still cover a bit more
self.simple_indices = [Ellipsis, None, -1, [1], np.array([True]), 'skip']
# Very simple ones to fill the rest:
self.fill_indices = [slice(None, None), 0]
def broadcast_to(array, shape, subok=False):
"""Broadcast an array to a new shape.
Parameters
----------
array : array_like
The array to broadcast.
shape : tuple
The shape of the desired array.
subok : bool, optional
If True, then sub-classes will be passed-through, otherwise
the returned array will be forced to be a base-class array (default).
Returns
-------
broadcast : array
A readonly view on the original array with the given shape. It is
typically not contiguous. Furthermore, more than one element of a
broadcasted array may refer to a single memory location.
Raises
------
ValueError
If the array is not compatible with the new shape according to NumPy's
broadcasting rules.
Notes
-----
.. versionadded:: 1.10.0
Examples
--------
>>> x = np.array([1, 2, 3])
>>> np.broadcast_to(x, (3, 3))
array([[1, 2, 3],
[1, 2, 3],
[1, 2, 3]])
"""
return _broadcast_to(array, shape, subok=subok, readonly=True)
def test_broadcast_in_args(self):
# gh-5881
arrs = [np.empty((6, 7)), np.empty((5, 6, 1)), np.empty((7,)),
np.empty((5, 1, 7))]
mits = [np.broadcast(*arrs),
np.broadcast(np.broadcast(*arrs[:2]), np.broadcast(*arrs[2:])),
np.broadcast(arrs[0], np.broadcast(*arrs[1:-1]), arrs[-1])]
for mit in mits:
assert_equal(mit.shape, (5, 6, 7))
assert_equal(mit.ndim, 3)
assert_equal(mit.nd, 3)
assert_equal(mit.numiter, 4)
for a, ia in zip(arrs, mit.iters):
assert_(a is ia.base)
def test_broadcast_single_arg(self):
# gh-6899
arrs = [np.empty((5, 6, 7))]
mit = np.broadcast(*arrs)
assert_equal(mit.shape, (5, 6, 7))
assert_equal(mit.ndim, 3)
assert_equal(mit.nd, 3)
assert_equal(mit.numiter, 1)
assert_(arrs[0] is mit.iters[0].base)
def test_number_of_arguments(self):
arr = np.empty((5,))
for j in range(35):
arrs = [arr] * j
if j < 1 or j > 32:
assert_raises(ValueError, np.broadcast, *arrs)
else:
mit = np.broadcast(*arrs)
assert_equal(mit.numiter, j)
def test_boolean_assignment_value_mismatch(self):
# A boolean assignment should fail when the shape of the values
# cannot be broadcast to the subscription. (see also gh-3458)
a = np.arange(4)
def f(a, v):
a[a > -1] = v
assert_raises(ValueError, f, a, [])
assert_raises(ValueError, f, a, [1, 2, 3])
assert_raises(ValueError, f, a[:1], [1, 2, 3])
def setUp(self):
self.a = np.arange(np.prod([3, 1, 5, 6])).reshape(3, 1, 5, 6)
self.b = np.empty((3, 0, 5, 6))
self.complex_indices = ['skip', Ellipsis,
0,
# Boolean indices, up to 3-d for some special cases of eating up
# dimensions, also need to test all False
np.array(False),
np.array([True, False, False]),
np.array([[True, False], [False, True]]),
np.array([[[False, False], [False, False]]]),
# Some slices:
slice(-5, 5, 2),
slice(1, 1, 100),
slice(4, -1, -2),
slice(None, None, -3),
# Some Fancy indexes:
np.empty((0, 1, 1), dtype=np.intp), # empty and can be broadcast
np.array([0, 1, -2]),
np.array([[2], [0], [1]]),
np.array([[0, -1], [0, 1]], dtype=np.dtype('intp').newbyteorder()),
np.array([2, -1], dtype=np.int8),
np.zeros([1]*31, dtype=int), # trigger too large array.
np.array([0., 1.])] # invalid datatype
# Some simpler indices that still cover a bit more
self.simple_indices = [Ellipsis, None, -1, [1], np.array([True]),
'skip']
# Very simple ones to fill the rest:
self.fill_indices = [slice(None, None), 0]
def broadcast_to(array, shape, subok=False):
"""Broadcast an array to a new shape.
Parameters
----------
array : array_like
The array to broadcast.
shape : tuple
The shape of the desired array.
subok : bool, optional
If True, then sub-classes will be passed-through, otherwise
the returned array will be forced to be a base-class array (default).
Returns
-------
broadcast : array
A readonly view on the original array with the given shape. It is
typically not contiguous. Furthermore, more than one element of a
broadcasted array may refer to a single memory location.
Raises
------
ValueError
If the array is not compatible with the new shape according to NumPy's
broadcasting rules.
Notes
-----
.. versionadded:: 1.10.0
Examples
--------
>>> x = np.array([1, 2, 3])
>>> np.broadcast_to(x, (3, 3))
array([[1, 2, 3],
[1, 2, 3],
[1, 2, 3]])
"""
return _broadcast_to(array, shape, subok=subok, readonly=True)
