1.简介

numpy数组如何访问比较高效？使用numpy提供的方法，还是自定义方法？如果数组很大，毫无疑问使用numpy提供的方法最高效。本文研究了查找numpy最大值、最小值、四则运算、特定值查找等4种情况。

2.最大值和最小值

numpy提供了数组最大值和最小的方法，分别是max和min。数组是一维的，从1个元素一直到500个元素。数组是随机生成的，查找的次数为1000次。
代码如下：

#coding:utf8
import numpy as np
import timeit
import matplotlib.pyplot as plt

def my_max(H):
    r = -9223372036854775808 # int64 最小值
    for i in range(H.shape[0]):
        if H[i]>r:
            r = H[i]
    return r

def my_min(H):
    r = 9223372036854775807 # int64最大值
    for i in range(H.shape[0]):
        if H[i]<r:
            r = H[i]
    return r

def np_max(H):
    return np.max(H)

def np_min(H):
    return np.min(H)


if __name__ == '__main__':
    array = 300
    H = np.random.randint(100, 1000000, array)
    x = np.arange(1,array+1)
    npmin = []
    mymin = []
    npmax = []
    mymax = []
    times = 1000
    for i in range(1,array+1):
        K = H[0:i]
        npmin.append(timeit.timeit("np_min(K)", setup="from __main__ import np_min",number=times,globals=globals()))
        mymin.append(timeit.timeit("my_min(K)", setup="from __main__ import my_min", number=times, globals=globals()))
        npmax.append(timeit.timeit("np_max(K)", setup="from __main__ import np_min",number=times,globals=globals()))
        mymax.append(timeit.timeit("my_max(K)", setup="from __main__ import my_min", number=times, globals=globals()))

    plt.plot(x,npmin,color='red')
    plt.plot(x,mymin,color='green')
    plt.plot(x,npmax, color='blue')
    plt.plot(x,mymax, color='black')
    plt.show()

结论：
（1）numpy的方法o(1)的。并没有随着数组元素增多而线性增长
（2）自定义方法是o(n)的
（3）自定义的max方法比min方法要速度快一点点。估计是交换的次数少一些。

3.四则运算

四则运算包括numpy数组与常数的四则运算，以及numpy数组与同shape的numpy数组的四则运算。

3.1 numpy数组与常数的四则运算

与查找最大值、最小值类似，用numpy自带的方法进行四则运算效率更高。代码中的拷贝数组不是必须的，要看实际的实现情况。
代码中分别实现了加法和乘法的情形，因为减法和除法与加法和乘法在实现方法上是没有区别的。

#coding:utf8
import numpy as np
import timeit
import matplotlib.pyplot as plt

def my_add(K,value):
    H = np.array(K)
    for i in range(H.shape[0]):
        H[i] += value
    return H


def my_times(K,value):
    H = np.array(K)
    for i in range(H.shape[0]):
        H[i] *= value
    return H

def np_add(K,value):
    H = np.array(K)
    return H+value


def np_times(K,value):
    H = np.array(K)
    return H*value

if __name__ == '__main__':
    array = 300
    H = np.random.random(array)

    x = np.arange(1,array+1,dtype=np.uint16)
    times = 1000
    npadd=[]
    myadd=[]
    nptimes=[]
    mytimes=[]

    for i in range(1, array + 1):
        K = H[0:i]
        npadd.append(timeit.timeit("np_add(K,20.)", setup="from __main__ import np_add", number=times, globals=globals()))
        myadd.append(timeit.timeit("my_add(K,20.)", setup="from __main__ import my_add", number=times, globals=globals()))
        nptimes.append(timeit.timeit("np_times(K,20.)", setup="from __main__ import np_times",number=times,globals=globals()))
        mytimes.append(timeit.timeit("my_times(K,20.)", setup="from __main__ import my_times", number=times, globals=globals()))

    plt.plot(x,npadd,color='red')
    plt.plot(x,myadd,color='green')
    plt.plot(x,nptimes, color='blue')
    plt.plot(x,mytimes, color='black')
    plt.show()
    

3.2 数组与数组的四则运算

数组与数组和数组与常数的四则运算耗时是差别不大的。这是因为耗时主要体现在数组循环上，而不是在四则运算上。

# coding:utf8
import numpy as np
import timeit
import matplotlib.pyplot as plt


def my_add(K, value):
    H = np.array(K)
    for i in range(H.shape[0]):
        H[i] += value[i]
    return H


def my_times(K, value):
    H = np.array(K)
    for i in range(H.shape[0]):
        H[i] *= value[i]
    return H


def np_add(K, value):
    H = np.array(K)
    return H + value


def np_times(K, value):
    H = np.array(K)
    return H * value


if __name__ == '__main__':
    array = 300
    H = np.random.random(array)
    V = np.random.random(array)
    x = np.arange(1, array + 1, dtype=np.uint16)

    times = 1000
    npadd = []
    myadd = []
    nptimes = []
    mytimes = []

    for i in range(1, array + 1):
        K = H[0:i]
        W = V[0:i]
        npadd.append(
            timeit.timeit("np_add(K,W)", setup="from __main__ import np_add", number=times, globals=globals()))
        myadd.append(
            timeit.timeit("my_add(K,W)", setup="from __main__ import my_add", number=times, globals=globals()))
        nptimes.append(
            timeit.timeit("np_times(K,W)", setup="from __main__ import np_times", number=times, globals=globals()))
        mytimes.append(
            timeit.timeit("my_times(K,W)", setup="from __main__ import my_times", number=times, globals=globals()))

    plt.plot(x, npadd, color='red')
    plt.plot(x, myadd, color='green')
    plt.plot(x, nptimes, color='blue')
    plt.plot(x, mytimes, color='black')
    plt.show()

4. 特定值查找

特定值查找是在数组中找到指定的数值。

# coding:utf8
import numpy as np
import timeit
import matplotlib.pyplot as plt


def my_find(K, value):
    for i in range(K.shape[0]):
        if K[i] == value:
            return i
    return -1


def np_find(K, value):
    return np.where(K == value)[0]

if __name__ == '__main__':
    array = 300
    H = np.random.random(array)
    V = np.random.random(1)
    x = np.arange(1, array + 1, dtype=np.uint16)

    times = 1000
    npfind = []
    myfind = []

    for i in range(1, array + 1):
        K = H[0:i]
        npfind.append(
            timeit.timeit("np_find(K,V[0])", setup="from __main__ import np_find", number=times, globals=globals()))
        myfind.append(
            timeit.timeit("my_find(K,V[0])", setup="from __main__ import my_find", number=times, globals=globals()))

    plt.plot(x, npfind, color='red')
    plt.plot(x, myfind, color='blue')
    plt.show()