你可以在O(n)个时间和常数空间中找到第k个最小的元素。如果我们认为数组只用于整数。

方法是对数组值的范围进行二分搜索。如果min_value和max_value都在整数范围内，我们可以对该范围进行二分搜索。 我们可以写一个比较器函数，它会告诉我们是否有任何值是第k个最小值或小于第k个最小值或大于第k个最小值。 进行二分搜索，直到找到第k小的数

这是它的代码

类解决方案:

def _iskthsmallest(self, A, val, k):
    less_count, equal_count = 0, 0
    for i in range(len(A)):
        if A[i] == val: equal_count += 1
        if A[i] < val: less_count += 1

    if less_count >= k: return 1
    if less_count + equal_count < k: return -1
    return 0

def kthsmallest_binary(self, A, min_val, max_val, k):
    if min_val == max_val:
        return min_val
    mid = (min_val + max_val)/2
    iskthsmallest = self._iskthsmallest(A, mid, k)
    if iskthsmallest == 0: return mid
    if iskthsmallest > 0: return self.kthsmallest_binary(A, min_val, mid, k)
    return self.kthsmallest_binary(A, mid+1, max_val, k)

# @param A : tuple of integers
# @param B : integer
# @return an integer
def kthsmallest(self, A, k):
    if not A: return 0
    if k > len(A): return 0
    min_val, max_val = min(A), max(A)
    return self.kthsmallest_binary(A, min_val, max_val, k)

还有Wirth的选择算法，它的实现比QuickSelect简单。Wirth的选择算法比QuickSelect慢，但经过一些改进，它变得更快。

更详细地说。使用Vladimir Zabrodsky的MODIFIND优化和3中位数的枢轴选择，并注意算法划分部分的最后步骤，我提出了以下算法(想象一下，命名为“LefSelect”):

#define F_SWAP(a,b) { float temp=(a);(a)=(b);(b)=temp; }

# Note: The code needs more than 2 elements to work
float lefselect(float a[], const int n, const int k) {
    int l=0, m = n-1, i=l, j=m;
    float x;

    while (l<m) {
        if( a[k] < a[i] ) F_SWAP(a[i],a[k]);
        if( a[j] < a[i] ) F_SWAP(a[i],a[j]);
        if( a[j] < a[k] ) F_SWAP(a[k],a[j]);

        x=a[k];
        while (j>k & i<k) {
            do i++; while (a[i]<x);
            do j--; while (a[j]>x);

            F_SWAP(a[i],a[j]);
        }
        i++; j--;

        if (j<k) {
            while (a[i]<x) i++;
            l=i; j=m;
        }
        if (k<i) {
            while (x<a[j]) j--;
            m=j; i=l;
        }
    }
    return a[k];
}

在我这里做的基准测试中，LefSelect比QuickSelect快20-30%。

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;
    }
}

首先，我们可以从未排序的数组中构建一个BST，它需要O(n)时间，从BST中我们可以找到O(log(n))中第k个最小的元素，它的总计数为O(n)。

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]