我为一组数字定义了一个中值函数

def median(numbers):
    return (sorted(numbers)[int(round((len(numbers) - 1) / 2.0))] + sorted(numbers)[int(round((len(numbers) - 1) // 2.0))]) / 2.0

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

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

函数值:

def median(d):
    d=np.sort(d)
    n2=int(len(d)/2)
    r=n2%2
    if (r==0):
        med=d[n2] 
    else:
        med=(d[n2] + d[n2+1]) / 2
    return med

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。

def median(array):
    if len(array) < 1:
        return(None)
    if len(array) % 2 == 0:
        median = (array[len(array)//2-1: len(array)//2+1])
        return sum(median) / len(median)
    else:
        return(array[len(array)//2])