我试图从一个numpy数组中的源坐标计算欧几里得距离和方向。
这是我能想到的,但是对于大型阵列来说,速度相对较慢。基于源坐标的欧几里得距离和方向在很大程度上依赖于每个像元的索引。这就是为什么我要遍历每一行和每一列。我研究了scipy cdist,pdist和np linalg。
import numpy as np
from math import atan, degrees, sqrt
from timeit import default_timer
def euclidean_from_source(input_array, y_index, x_index):
# copy arrays
distance = np.empty_like(input_array, dtype=float)
direction = np.empty_like(input_array, dtype=int)
# loop each row
for i, row in enumerate(X):
# loop each cell
for c, cell in enumerate(row):
# get b
b = x_index - i
# get a
a = y_index - c
hypotenuse = sqrt(a * a + b * b) * 10
distance[i][c] = hypotenuse
direction[i][c] = get_angle(a, b)
return [distance, direction]
def calibrate_angle(a, b, angle):
if b > 0 and a > 0:
angle+=90
elif b < 0 and a < 0:
angle+=270
elif b > 0 > a:
angle+=270
elif a > 0 > b:
angle+=90
return angle
def get_angle(a, b):
# get angle
if b == 0 and a == 0:
angle = 0
elif b == 0 and a >= 0:
angle = 90
elif b == 0 and a < 0:
angle = 270
elif a == 0 and b >= 0:
angle = 180
elif a == 0 and b < 0:
angle = 360
else:
theta = atan(b / a)
angle = degrees(theta)
return calibrate_angle(a, b, angle)
if __name__ == "__main__":
dimension_1 = 5
dimension_2 = 5
X = np.random.rand(dimension_1, dimension_2)
y_index = int(dimension_1/2)
x_index = int(dimension_2/2)
start = default_timer()
distance, direction = euclidean_from_source(X, y_index, x_index)
print('Total Seconds {{'.format(default_timer() - start))
print(distance)
print(direction)
更新 我能够使用广播功能以所需的速度完成我所需要的一切。但是我仍在弄清楚如何在整个矩阵中将角度校准为0、360(在这种情况下,取模将无效)。
import numpy as np
from math import atan, degrees, sqrt
from timeit import default_timer
def euclidean_from_source_update(input_array, y_index, x_index):
size = input_array.shape
center = (y_index, x_index)
x = np.arange(size[0])
y = np.arange(size[1])
# use broadcasting to get euclidean distance from source point
distance = np.multiply(np.sqrt((x - center[0]) ** 2 + (y[:, None] - center[1]) ** 2), 10)
# use broadcasting to get euclidean direction from source point
direction = np.rad2deg(np.arctan2((x - center[0]) , (y[:, None] - center[1])))
return [distance, direction]
def euclidean_from_source(input_array, y_index, x_index):
# copy arrays
distance = np.empty_like(input_array, dtype=float)
direction = np.empty_like(input_array, dtype=int)
# loop each row
for i, row in enumerate(X):
# loop each cell
for c, cell in enumerate(row):
# get b
b = x_index - i
# get a
a = y_index - c
hypotenuse = sqrt(a * a + b * b) * 10
distance[i][c] = hypotenuse
direction[i][c] = get_angle(a, b)
return [distance, direction]
def calibrate_angle(a, b, angle):
if b > 0 and a > 0:
angle+=90
elif b < 0 and a < 0:
angle+=270
elif b > 0 > a:
angle+=270
elif a > 0 > b:
angle+=90
return angle
def get_angle(a, b):
# get angle
if b == 0 and a == 0:
angle = 0
elif b == 0 and a >= 0:
angle = 90
elif b == 0 and a < 0:
angle = 270
elif a == 0 and b >= 0:
angle = 180
elif a == 0 and b < 0:
angle = 360
else:
theta = atan(b / a)
angle = degrees(theta)
return calibrate_angle(a, b, angle)
if __name__ == "__main__":
dimension_1 = 5
dimension_2 = 5
X = np.random.rand(dimension_1, dimension_2)
y_index = int(dimension_1/2)
x_index = int(dimension_2/2)
start = default_timer()
distance, direction = euclidean_from_source(X, y_index, x_index)
print('Total Seconds {}'.format(default_timer() - start))
start = default_timer()
distance2, direction2 = euclidean_from_source_update(X, y_index, x_index)
print('Total Seconds {}'.format(default_timer() - start))
print(distance)
print(distance2)
print(direction)
print(direction2)
更新2 感谢大家的反馈,在测试方法之后,这两种方法是最快的,并且产生了我需要的结果。我仍然愿意接受你们能想到的任何优化。
def get_euclidean_direction(input_array, y_index, x_index):
rdist = np.arange(input_array.shape[0]).reshape(-1, 1) - x_index
cdist = np.arange(input_array.shape[1]).reshape(1, -1) - y_index
direction = np.mod(np.degrees(np.arctan2(rdist, cdist)), 270)
direction[y_index:, :x_index]+= -90
direction[y_index:, x_index:]+= 270
direction[y_index][x_index] = 0
return direction
def get_euclidean_distance(input_array, y_index, x_index):
size = input_array.shape
center = (y_index, x_index)
x = np.arange(size[0])
y = np.arange(size[1])
return np.multiply(np.sqrt((x - center[0]) ** 2 + (y[:, None] - center[1]) ** 2), 10)
答案 0 :(得分:2)
此操作非常容易矢量化。一方面,a
和b
根本不需要以2D计算,因为它们仅取决于数组中的一个方向。可以使用np.hypot
计算距离。广播会将形状转换为正确的2D形式。
您的角度函数几乎完全等同于将np.degrees
应用于np.arctan2
。
不清楚为什么用x
标记行,而用y
标记行,而不是用标准的方式标记行,但是只要保持一致,就可以了。
这是向量化版本:
def euclidean_from_source(input_array, c, r):
rdist = np.arange(input_array.shape[0]).reshape(-1, 1) - r
# Broadcasting doesn't require this second reshape
cdist = np.arange(input_array.shape[1]).reshape(1, -1) - c
distance = np.hypot(rdist, cdist) * 10
direction = np.degrees(np.arctan2(rdist, cdist))
return distance, direction
我将把它留给读者练习,以确定是否需要任何其他处理来微调角度,如果需要,以矢量化的方式实现。
答案 1 :(得分:1)
通过数组或元组传递想要度量的cordrints可能会更容易。另外,尽管可能需要更多的内存,但我认为使用np.indices
可能会更快一些(因为它允许np.einsum
发挥其神奇作用)。
def euclidean_from_source(input_array, coord):
grid = np.indices(input_array.shape)
grid -= np.asarray(coord)[:, None, None]
distance = np.einsum('ijk, ijk -> jk', grid, grid) ** .5
direction = np.degrees(np.arctan2(grid[0], grid[1]))
return distance, direction
该方法还可以扩展到n-d(尽管显然角度计算会有些棘手