如果您需要关于列表分布的额外信息，百分位数方法可能会很有用。中位数对应于列表的第50个百分位数:

import numpy as np
a = np.array([1,2,3,4,5,6,7,8,9])
median_value = np.percentile(a, 50) # return 50th percentile
print median_value 

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

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)

如果需要更快的平均情况运行时间，可以尝试快速选择算法。Quickselect具有平均(和最佳)情况性能O(n)，尽管在糟糕的一天它可能会以O(n²)结束。

下面是一个随机选择枢轴的实现:

import random

def select_nth(n, items):
    pivot = random.choice(items)

    lesser = [item for item in items if item < pivot]
    if len(lesser) > n:
        return select_nth(n, lesser)
    n -= len(lesser)

    numequal = items.count(pivot)
    if numequal > n:
        return pivot
    n -= numequal

    greater = [item for item in items if item > pivot]
    return select_nth(n, greater)

你可以简单地把它变成一个方法来寻找中位数:

def median(items):
    if len(items) % 2:
        return select_nth(len(items)//2, items)

    else:
        left  = select_nth((len(items)-1) // 2, items)
        right = select_nth((len(items)+1) // 2, items)

        return (left + right) / 2

这是非常未优化的，但即使是一个优化的版本也不太可能超过Tim Sort (CPython的内置排序)，因为它真的很快。我以前试过，但失败了。

下面是不使用中值函数就能找到中值的乏味方法:

def median(*arg):
    order(arg)
    numArg = len(arg)
    half = int(numArg/2)
    if numArg/2 ==half:
        print((arg[half-1]+arg[half])/2)
    else:
        print(int(arg[half]))

def order(tup):
    ordered = [tup[i] for i in range(len(tup))]
    test(ordered)
    while(test(ordered)):
        test(ordered)
    print(ordered)


def test(ordered):
    whileloop = 0 
    for i in range(len(ordered)-1):
        print(i)
        if (ordered[i]>ordered[i+1]):
            print(str(ordered[i]) + ' is greater than ' + str(ordered[i+1]))
            original = ordered[i+1]
            ordered[i+1]=ordered[i]
            ordered[i]=original
            whileloop = 1 #run the loop again if you had to switch values
    return whileloop

我在浮点值列表中遇到了一些问题。我最终使用了来自python3统计数据的代码片段。中位数和工作完美的浮动值没有导入。源

def calculateMedian(list):
    data = sorted(list)
    n = len(data)
    if n == 0:
        return None
    if n % 2 == 1:
        return data[n // 2]
    else:
        i = n // 2
        return (data[i - 1] + data[i]) / 2