What is the most efficient way to deal with a loop on NumPy arrays?

The question is simple: here is my current algorithm. This is terribly slow because of the loops on the arrays. Is there a way to change it in order to avoid the loops and take advantage of the NumPy arrays types ?

import numpy as np

def loopingFunction(listOfVector1, listOfVector2):
    resultArray = []

    for vector1 in listOfVector1:
        result = 0

        for vector2 in listOfVector2:
            result += np.dot(vector1, vector2) * vector2[2]

        resultArray.append(result)

    return np.array(resultArray)

listOfVector1x = np.linspace(0,0.33,1000)
listOfVector1y = np.linspace(0.33,0.66,1000)
listOfVector1z = np.linspace(0.66,1,1000)

listOfVector1 = np.column_stack((listOfVector1x, listOfVector1y, listOfVector1z))

listOfVector2x = np.linspace(0.33,0.66,1000)
listOfVector2y = np.linspace(0.66,1,1000)
listOfVector2z = np.linspace(0, 0.33, 1000)

listOfVector2 = np.column_stack((listOfVector2x, listOfVector2y, listOfVector2z))

result = loopingFunction(listOfVector1, listOfVector2)

I am supposed to deal with really big arrays, that have way more than 1000 vectors in each. So if you have any advice, I’ll take it.

>Solution :

You can at least remove the two forloop to save alot of time, use matrix computation directly

import time

import numpy as np

def loopingFunction(listOfVector1, listOfVector2):
    resultArray = []

    for vector1 in listOfVector1:
        result = 0

        for vector2 in listOfVector2:
            result += np.dot(vector1, vector2) * vector2[2]

        resultArray.append(result)

    return np.array(resultArray)

def loopingFunction2(listOfVector1, listOfVector2):
    resultArray = np.sum(np.dot(listOfVector1, listOfVector2.T) * listOfVector2[:,2], axis=1)

    return resultArray

listOfVector1x = np.linspace(0,0.33,1000)
listOfVector1y = np.linspace(0.33,0.66,1000)
listOfVector1z = np.linspace(0.66,1,1000)

listOfVector1 = np.column_stack((listOfVector1x, listOfVector1y, listOfVector1z))

listOfVector2x = np.linspace(0.33,0.66,1000)
listOfVector2y = np.linspace(0.66,1,1000)
listOfVector2z = np.linspace(0, 0.33, 1000)

listOfVector2 = np.column_stack((listOfVector2x, listOfVector2y, listOfVector2z))
import time
t0 = time.time()
result = loopingFunction(listOfVector1, listOfVector2)
print('time old version',time.time() - t0)
t0 = time.time()
result2 = loopingFunction2(listOfVector1, listOfVector2)
print('time matrix computation version',time.time() - t0)
print('Are results are the same',np.allclose(result,result2))

Which gives

time old version 1.174513578414917
time matrix computation version 0.011968612670898438
Are results are the same True

Basically, the less loop the better.