我想“剪切”一个 numpy 数组。我不确定我是否正确使用了“剪切”一词；通过剪切，我的意思是：
将第一列移动 0 位
将第二列
移动 1 位 将第三列移动 2 位
等...
所以这个数组：
array([[11, 12, 13],
[17, 18, 19],
[35, 36, 37]])
会变成这个数组：
array([[11, 36, 19],
[17, 12, 37],
[35, 18, 13]])
或类似这个数组的东西：
array([[11, 0, 0],
[17, 12, 0],
[35, 18, 13]])
取决于我们如何处理边缘。我对边缘行为不太讲究。
这是我对执行此操作的功能的尝试：
import numpy
def shear(a, strength=1, shift_axis=0, increase_axis=1, edges='clip'):
strength = int(strength)
shift_axis = int(shift_axis)
increase_axis = int(increase_axis)
if shift_axis == increase_axis:
raise UserWarning("Shear can't shift in the direction it increases")
temp = numpy.zeros(a.shape, dtype=int)
indices = []
for d, num in enumerate(a.shape):
coords = numpy.arange(num)
shape = [1] * len(a.shape)
shape[d] = num
coords = coords.reshape(shape) + temp
indices.append(coords)
indices[shift_axis] -= strength * indices[increase_axis]
if edges == 'clip':
indices[shift_axis][indices[shift_axis] < 0] = -1
indices[shift_axis][indices[shift_axis] >= a.shape[shift_axis]] = -1
res = a[indices]
res[indices[shift_axis] == -1] = 0
elif edges == 'roll':
indices[shift_axis] %= a.shape[shift_axis]
res = a[indices]
return res
if __name__ == '__main__':
a = numpy.random.random((3,4))
print a
print shear(a)
它似乎工作。如果没有请告诉我！
它也显得笨重和不雅。我是否忽略了执行此操作的内置 numpy/scipy 函数？在 numpy 中是否有更清洁/更好/更有效的方法来做到这一点？我在重新发明轮子吗？
编辑：
如果这适用于 N 维数组，而不仅仅是二维情况，则加分。
这个函数将位于循环的中心，我将在我们的数据处理中重复多次，所以我怀疑它实际上值得优化。
第二次编辑：我终于做了一些基准测试。看起来 numpy.roll 是要走的路，尽管有循环。谢谢，tom10 和 Sven Marnach！
基准代码：（在 Windows 上运行，我认为不要在 Linux 上使用 time.clock）
import time, numpy
def shear_1(a, strength=1, shift_axis=0, increase_axis=1, edges='roll'):
strength = int(strength)
shift_axis = int(shift_axis)
increase_axis = int(increase_axis)
if shift_axis == increase_axis:
raise UserWarning("Shear can't shift in the direction it increases")
temp = numpy.zeros(a.shape, dtype=int)
indices = []
for d, num in enumerate(a.shape):
coords = numpy.arange(num)
shape = [1] * len(a.shape)
shape[d] = num
coords = coords.reshape(shape) + temp
indices.append(coords)
indices[shift_axis] -= strength * indices[increase_axis]
if edges == 'clip':
indices[shift_axis][indices[shift_axis] < 0] = -1
indices[shift_axis][indices[shift_axis] >= a.shape[shift_axis]] = -1
res = a[indices]
res[indices[shift_axis] == -1] = 0
elif edges == 'roll':
indices[shift_axis] %= a.shape[shift_axis]
res = a[indices]
return res
def shear_2(a, strength=1, shift_axis=0, increase_axis=1, edges='roll'):
indices = numpy.indices(a.shape)
indices[shift_axis] -= strength * indices[increase_axis]
indices[shift_axis] %= a.shape[shift_axis]
res = a[tuple(indices)]
if edges == 'clip':
res[indices[shift_axis] < 0] = 0
res[indices[shift_axis] >= a.shape[shift_axis]] = 0
return res
def shear_3(a, strength=1, shift_axis=0, increase_axis=1):
if shift_axis > increase_axis:
shift_axis -= 1
res = numpy.empty_like(a)
index = numpy.index_exp[:] * increase_axis
roll = numpy.roll
for i in range(0, a.shape[increase_axis]):
index_i = index + (i,)
res[index_i] = roll(a[index_i], i * strength, shift_axis)
return res
numpy.random.seed(0)
for a in (
numpy.random.random((3, 3, 3, 3)),
numpy.random.random((50, 50, 50, 50)),
numpy.random.random((300, 300, 10, 10)),
):
print 'Array dimensions:', a.shape
for sa, ia in ((0, 1), (1, 0), (2, 3), (0, 3)):
print 'Shift axis:', sa
print 'Increase axis:', ia
ref = shear_1(a, shift_axis=sa, increase_axis=ia)
for shear, label in ((shear_1, '1'), (shear_2, '2'), (shear_3, '3')):
start = time.clock()
b = shear(a, shift_axis=sa, increase_axis=ia)
end = time.clock()
print label + ': %0.6f seconds'%(end-start)
if (b - ref).max() > 1e-9:
print "Something's wrong."
print