Я поэкспериментировал с вашим кодом и попытался, если бы средневзвешенное значение напрямую без использования np.average было бы быстрее, и похоже, что так оно и есть.На моей платформе это примерно на 40% быстрее.
import time as t
import numpy as np
def func(weights, x1, x2, x3, x4):
for x in (x2, x3, x4):
# Mask of the distance between the column '-6' of x1 versus arrays
# x2,x3,x4
msk = abs(x1[-6] - x[-6]) > 0.01
# If the distance in this array is larger than the maximum allowed,
# mask with the values taken from 'x1'.
x[:, msk] = x1[:, msk]
# Weighted average for all the arrays.
avrg_data = np.average(np.array([x1, x2, x3, x4]), weights=weights, axis=0)
return avrg_data
def faster_func(weights, x1, x2, x3, x4):
for x in (x2, x3, x4):
# Mask of the distance between the column '-6' of x1 versus arrays
# x2,x3,x4
msk = abs(x1[-6] - x[-6]) > 0.01
# If the distance in this array is larger than the maximum allowed,
# mask with the values taken from 'x1'.
x[:, msk] = x1[:, msk]
# Scale weights so they add up to 1, then add based on them
weights = weights / np.mean(weights) / 4
avrg_data = x1*weights[0] + x2*weights[1] + x3*weights[2] + x4*weights[3]
return avrg_data
# Random data with proper shape
x1, x2, x3, x4 = np.random.uniform(1., 10., (4, 10, 1000))
weights = np.random.uniform(0.01, .5, 4)
# Call many times and time it
for method in (func, faster_func):
s = t.time()
for _ in range(10000):
method(weights, x1, x2, x3, x4)
print(method, t.time() - s)
# Test that the results are still the same
result1 = func(weights, x1, x2, x3, x4)
result2 = faster_func(weights, x1, x2, x3, x4)
biggest_difference = np.max(abs(result1-result2))
print("Biggest difference between two methods was %.8f" % biggest_difference)