还有一种算法，比快速选择算法性能更好。它叫做弗洛伊德-铆钉(FR)算法。

原文:https://doi.org/10.1145/360680.360694

下载版本:http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.309.7108&rep=rep1&type=pdf

维基百科文章https://en.wikipedia.org/wiki/Floyd%E2%80%93Rivest_algorithm

我尝试在c++中实现快速选择和FR算法。我还将它们与标准c++库实现std::nth_element(基本上是quickselect和heapselect的introselect混合)进行了比较。结果是快速选择和nth_element的平均运行，而FR算法的平均运行约。速度是它们的两倍。

我用于FR算法的示例代码:

template <typename T>
T FRselect(std::vector<T>& data, const size_t& n)
{
    if (n == 0)
        return *(std::min_element(data.begin(), data.end()));
    else if (n == data.size() - 1)
        return *(std::max_element(data.begin(), data.end()));
    else
        return _FRselect(data, 0, data.size() - 1, n);
}

template <typename T>
T _FRselect(std::vector<T>& data, const size_t& left, const size_t& right, const size_t& n)
{
    size_t leftIdx = left;
    size_t rightIdx = right;

    while (rightIdx > leftIdx)
    {
        if (rightIdx - leftIdx > 600)
        {
            size_t range = rightIdx - leftIdx + 1;
            long long i = n - (long long)leftIdx + 1;
            long long z = log(range);
            long long s = 0.5 * exp(2 * z / 3);
            long long sd = 0.5 * sqrt(z * s * (range - s) / range) * sgn(i - (long long)range / 2);

            size_t newLeft = fmax(leftIdx, n - i * s / range + sd);
            size_t newRight = fmin(rightIdx, n + (range - i) * s / range + sd);

            _FRselect(data, newLeft, newRight, n);
        }
        T t = data[n];
        size_t i = leftIdx;
        size_t j = rightIdx;
        // arrange pivot and right index
        std::swap(data[leftIdx], data[n]);
        if (data[rightIdx] > t)
            std::swap(data[rightIdx], data[leftIdx]);

        while (i < j)
        {
            std::swap(data[i], data[j]);
            ++i; --j;
            while (data[i] < t) ++i;
            while (data[j] > t) --j;
        }

        if (data[leftIdx] == t)
            std::swap(data[leftIdx], data[j]);
        else
        {
            ++j;
            std::swap(data[j], data[rightIdx]);
        }
        // adjust left and right towards the boundaries of the subset
        // containing the (k - left + 1)th smallest element
        if (j <= n)
            leftIdx = j + 1;
        if (n <= j)
            rightIdx = j - 1;
    }

    return data[leftIdx];
}

template <typename T>
int sgn(T val) {
    return (T(0) < val) - (val < T(0));
}

Python中性感的快速选择

def quickselect(arr, k):
    '''
     k = 1 returns first element in ascending order.
     can be easily modified to return first element in descending order
    '''

    r = random.randrange(0, len(arr))

    a1 = [i for i in arr if i < arr[r]] '''partition'''
    a2 = [i for i in arr if i > arr[r]]

    if k <= len(a1):
        return quickselect(a1, k)
    elif k > len(arr)-len(a2):
        return quickselect(a2, k - (len(arr) - len(a2)))
    else:
        return arr[r]

下面是eladv建议的算法的实现(我也把随机pivot的实现放在这里):

public class Median {

    public static void main(String[] s) {

        int[] test = {4,18,20,3,7,13,5,8,2,1,15,17,25,30,16};
        System.out.println(selectK(test,8));

        /*
        int n = 100000000;
        int[] test = new int[n];
        for(int i=0; i<test.length; i++)
            test[i] = (int)(Math.random()*test.length);

        long start = System.currentTimeMillis();
        random_selectK(test, test.length/2);
        long end = System.currentTimeMillis();
        System.out.println(end - start);
        */
    }

    public static int random_selectK(int[] a, int k) {
        if(a.length <= 1)
            return a[0];

        int r = (int)(Math.random() * a.length);
        int p = a[r];

        int small = 0, equal = 0, big = 0;
        for(int i=0; i<a.length; i++) {
            if(a[i] < p) small++;
            else if(a[i] == p) equal++;
            else if(a[i] > p) big++;
        }

        if(k <= small) {
            int[] temp = new int[small];
            for(int i=0, j=0; i<a.length; i++)
                if(a[i] < p)
                    temp[j++] = a[i];
            return random_selectK(temp, k);
        }

        else if (k <= small+equal)
            return p;

        else {
            int[] temp = new int[big];
            for(int i=0, j=0; i<a.length; i++)
                if(a[i] > p)
                    temp[j++] = a[i];
            return random_selectK(temp,k-small-equal);
        }
    }

    public static int selectK(int[] a, int k) {
        if(a.length <= 5) {
            Arrays.sort(a);
            return a[k-1];
        }

        int p = median_of_medians(a);

        int small = 0, equal = 0, big = 0;
        for(int i=0; i<a.length; i++) {
            if(a[i] < p) small++;
            else if(a[i] == p) equal++;
            else if(a[i] > p) big++;
        }

        if(k <= small) {
            int[] temp = new int[small];
            for(int i=0, j=0; i<a.length; i++)
                if(a[i] < p)
                    temp[j++] = a[i];
            return selectK(temp, k);
        }

        else if (k <= small+equal)
            return p;

        else {
            int[] temp = new int[big];
            for(int i=0, j=0; i<a.length; i++)
                if(a[i] > p)
                    temp[j++] = a[i];
            return selectK(temp,k-small-equal);
        }
    }

    private static int median_of_medians(int[] a) {
        int[] b = new int[a.length/5];
        int[] temp = new int[5];
        for(int i=0; i<b.length; i++) {
            for(int j=0; j<5; j++)
                temp[j] = a[5*i + j];
            Arrays.sort(temp);
            b[i] = temp[2];
        }

        return selectK(b, b.length/2 + 1);
    }
}

如果你想要一个真正的O(n)算法，而不是O(kn)或类似的算法，那么你应该使用快速选择(它基本上是快速排序，你会丢弃你不感兴趣的分区)。我的教授写了一篇很棒的文章，包括运行时分析:(参考)

QuickSelect算法可以快速找到包含n个元素的无序数组中的第k个最小元素。这是一个随机算法，所以我们计算最坏情况下的预期运行时间。

这是算法。

QuickSelect(A, k)
  let r be chosen uniformly at random in the range 1 to length(A)
  let pivot = A[r]
  let A1, A2 be new arrays
  # split into a pile A1 of small elements and A2 of big elements
  for i = 1 to n
    if A[i] < pivot then
      append A[i] to A1
    else if A[i] > pivot then
      append A[i] to A2
    else
      # do nothing
  end for
  if k <= length(A1):
    # it's in the pile of small elements
    return QuickSelect(A1, k)
  else if k > length(A) - length(A2)
    # it's in the pile of big elements
    return QuickSelect(A2, k - (length(A) - length(A2))
  else
    # it's equal to the pivot
    return pivot

这个算法的运行时间是多少?如果对手为我们抛硬币，我们可能会发现主元总是最大的元素，k总是1，给出的运行时间为

T(n) = Theta(n) + T(n-1) = Theta(n2)

但如果选择确实是随机的，则预期运行时间由

T(n) <= Theta(n) + (1/n) ∑i=1 to nT(max(i, n-i-1))

我们做了一个不完全合理的假设递归总是落在A1或A2中较大的那个。

让我们猜测对于某个a T(n) <= an，然后我们得到

T(n) 
 <= cn + (1/n) ∑i=1 to nT(max(i-1, n-i))
 = cn + (1/n) ∑i=1 to floor(n/2) T(n-i) + (1/n) ∑i=floor(n/2)+1 to n T(i)
 <= cn + 2 (1/n) ∑i=floor(n/2) to n T(i)
 <= cn + 2 (1/n) ∑i=floor(n/2) to n ai

现在我们要用加号右边这个可怕的和来吸收左边的cn。如果我们将其限定为2(1/n)∑i=n/2到n an，我们大致得到2(1/n)(n/2)an = an。但是这个太大了，没有多余的空间来挤进一个cn。让我们用等差级数公式展开和:

∑i=floor(n/2) to n i  
 = ∑i=1 to n i - ∑i=1 to floor(n/2) i  
 = n(n+1)/2 - floor(n/2)(floor(n/2)+1)/2  
 <= n2/2 - (n/4)2/2  
 = (15/32)n2

我们利用n“足够大”的优势，用更干净(更小)的n/4替换丑陋的地板(n/2)因子。现在我们可以继续

cn + 2 (1/n) ∑i=floor(n/2) to n ai,
 <= cn + (2a/n) (15/32) n2
 = n (c + (15/16)a)
 <= an

提供了> 16c。

得到T(n) = O(n)显然是(n)所以我们得到T(n) = (n)

Haskell的解决方案:

kthElem index list = sort list !! index

withShape ~[]     []     = []
withShape ~(x:xs) (y:ys) = x : withShape xs ys

sort []     = []
sort (x:xs) = (sort ls `withShape` ls) ++ [x] ++ (sort rs `withShape` rs)
  where
   ls = filter (<  x)
   rs = filter (>= x)

这通过使用withShape方法来实现中值解的中值，从而发现分区的大小，而无需实际计算分区大小。

虽然不是很确定O(n)复杂度，但肯定在O(n)和nLog(n)之间。也肯定更接近于O(n)而不是nLog(n)函数是用Java编写的

public int quickSelect(ArrayList<Integer>list, int nthSmallest){
    //Choose random number in range of 0 to array length
    Random random =  new Random();
    //This will give random number which is not greater than length - 1
    int pivotIndex = random.nextInt(list.size() - 1); 

    int pivot = list.get(pivotIndex);

    ArrayList<Integer> smallerNumberList = new ArrayList<Integer>();
    ArrayList<Integer> greaterNumberList = new ArrayList<Integer>();

    //Split list into two. 
    //Value smaller than pivot should go to smallerNumberList
    //Value greater than pivot should go to greaterNumberList
    //Do nothing for value which is equal to pivot
    for(int i=0; i<list.size(); i++){
        if(list.get(i)<pivot){
            smallerNumberList.add(list.get(i));
        }
        else if(list.get(i)>pivot){
            greaterNumberList.add(list.get(i));
        }
        else{
            //Do nothing
        }
    }

    //If smallerNumberList size is greater than nthSmallest value, nthSmallest number must be in this list 
    if(nthSmallest < smallerNumberList.size()){
        return quickSelect(smallerNumberList, nthSmallest);
    }
    //If nthSmallest is greater than [ list.size() - greaterNumberList.size() ], nthSmallest number must be in this list
    //The step is bit tricky. If confusing, please see the above loop once again for clarification.
    else if(nthSmallest > (list.size() - greaterNumberList.size())){
        //nthSmallest will have to be changed here. [ list.size() - greaterNumberList.size() ] elements are already in 
        //smallerNumberList
        nthSmallest = nthSmallest - (list.size() - greaterNumberList.size());
        return quickSelect(greaterNumberList,nthSmallest);
    }
    else{
        return pivot;
    }
}