import numpy as np
def get_median(xs):
        mid = len(xs) // 2  # Take the mid of the list
        if len(xs) % 2 == 1: # check if the len of list is odd
            return sorted(xs)[mid] #if true then mid will be median after sorting
        else:
            #return 0.5 * sum(sorted(xs)[mid - 1:mid + 1])
            return 0.5 * np.sum(sorted(xs)[mid - 1:mid + 1]) #if false take the avg of mid
print(get_median([7, 7, 3, 1, 4, 5]))
print(get_median([1,2,3, 4,5]))

(适用于python-2.x):

def median(lst):
    n = len(lst)
    s = sorted(lst)
    return (s[n//2-1]/2.0+s[n//2]/2.0, s[n//2])[n % 2] if n else None

>>> median([-5, -5, -3, -4, 0, -1])
-3.5

numpy.median ():

>>> from numpy import median
>>> median([1, -4, -1, -1, 1, -3])
-1.0

python 3。X，使用statistics.median:

>>> from statistics import median
>>> median([5, 2, 3, 8, 9, -2])
4.0

我在“中位数的中位数”算法的Python实现中发布了我的解决方案，这比使用sort()稍微快一点。我的解决方案每列使用15个数字，速度~5N比每列使用5个数字的速度~10N快。最佳速度是~4N，但我可能是错的。

根据Tom在评论中的要求，我在这里添加了我的代码，以供参考。我认为速度的关键部分是每列使用15个数字，而不是5个。

#!/bin/pypy
#
# TH @stackoverflow, 2016-01-20, linear time "median of medians" algorithm
#
import sys, random


items_per_column = 15


def find_i_th_smallest( A, i ):
    t = len(A)
    if(t <= items_per_column):
        # if A is a small list with less than items_per_column items, then:
        #
        # 1. do sort on A
        # 2. find i-th smallest item of A
        #
        return sorted(A)[i]
    else:
        # 1. partition A into columns of k items each. k is odd, say 5.
        # 2. find the median of every column
        # 3. put all medians in a new list, say, B
        #
        B = [ find_i_th_smallest(k, (len(k) - 1)/2) for k in [A[j:(j + items_per_column)] for j in range(0,len(A),items_per_column)]]

        # 4. find M, the median of B
        #
        M = find_i_th_smallest(B, (len(B) - 1)/2)


        # 5. split A into 3 parts by M, { < M }, { == M }, and { > M }
        # 6. find which above set has A's i-th smallest, recursively.
        #
        P1 = [ j for j in A if j < M ]
        if(i < len(P1)):
            return find_i_th_smallest( P1, i)
        P3 = [ j for j in A if j > M ]
        L3 = len(P3)
        if(i < (t - L3)):
            return M
        return find_i_th_smallest( P3, i - (t - L3))


# How many numbers should be randomly generated for testing?
#
number_of_numbers = int(sys.argv[1])


# create a list of random positive integers
#
L = [ random.randint(0, number_of_numbers) for i in range(0, number_of_numbers) ]


# Show the original list
#
# print L


# This is for validation
#
# print sorted(L)[int((len(L) - 1)/2)]


# This is the result of the "median of medians" function.
# Its result should be the same as the above.
#
print find_i_th_smallest( L, (len(L) - 1) / 2)

简单地说，创建一个中值函数，参数为数字列表，并调用该函数。

def median(l):
    l = sorted(l)
    lent = len(l)
    if (lent % 2) == 0:
        m = int(lent / 2)
        result = l[m]
    else:
        m = int(float(lent / 2) - 0.5)
        result = l[m]
    return result

我所做的是:

def median(a):
    a = sorted(a)
    if len(a) / 2 != int:
        return a[len(a) / 2]
    else:
        return (a[len(a) / 2] + a[(len(a) / 2) - 1]) / 2

解释:基本上，如果列表中的项目数量是奇数，则返回中间的数字，否则，如果你是偶数列表的一半，python会自动舍入较大的数字，这样我们就知道在它之前的数字会少一个(因为我们对它进行了排序)，我们可以将默认的较大数字和小于它的数字相加，然后除以2得到中位数。

更普遍的中位数(和百分位数)方法是:

def get_percentile(data, percentile):
    # Get the number of observations
    cnt=len(data)
    # Sort the list
    data=sorted(data)
    # Determine the split point
    i=(cnt-1)*percentile
    # Find the `floor` of the split point
    diff=i-int(i)
    # Return the weighted average of the value above and below the split point
    return data[int(i)]*(1-diff)+data[int(i)+1]*(diff)

# Data
data=[1,2,3,4,5]
# For the median
print(get_percentile(data=data, percentile=.50))
# > 3
print(get_percentile(data=data, percentile=.75))
# > 4

# Note the weighted average difference when an int is not returned by the percentile
print(get_percentile(data=data, percentile=.51))
# > 3.04