我相信有一种方法可以找到长度为n的O(n)无序数组中第k大的元素。也可能是期望O(n)之类的。我们该怎么做呢?


当前回答

这是一个Javascript实现。

如果您释放了不能修改数组的约束,则可以使用两个索引来标识“当前分区”(经典快速排序样式- http://www.nczonline.net/blog/2012/11/27/computer-science-in-javascript-quicksort/)来防止使用额外的内存。

function kthMax(a, k){
    var size = a.length;

    var pivot = a[ parseInt(Math.random()*size) ]; //Another choice could have been (size / 2) 

    //Create an array with all element lower than the pivot and an array with all element higher than the pivot
    var i, lowerArray = [], upperArray = [];
    for (i = 0; i  < size; i++){
        var current = a[i];

        if (current < pivot) {
            lowerArray.push(current);
        } else if (current > pivot) {
            upperArray.push(current);
        }
    }

    //Which one should I continue with?
    if(k <= upperArray.length) {
        //Upper
        return kthMax(upperArray, k);
    } else {
        var newK = k - (size - lowerArray.length);

        if (newK > 0) {
            ///Lower
            return kthMax(lowerArray, newK);
        } else {
            //None ... it's the current pivot!
            return pivot;
        }   
    }
}  

如果你想测试它的表现,你可以使用这个变量:

    function kthMax (a, k, logging) {
         var comparisonCount = 0; //Number of comparison that the algorithm uses
         var memoryCount = 0;     //Number of integers in memory that the algorithm uses
         var _log = logging;

         if(k < 0 || k >= a.length) {
            if (_log) console.log ("k is out of range"); 
            return false;
         }      

         function _kthmax(a, k){
             var size = a.length;
             var pivot = a[parseInt(Math.random()*size)];
             if(_log) console.log("Inputs:", a,  "size="+size, "k="+k, "pivot="+pivot);

             // This should never happen. Just a nice check in this exercise
             // if you are playing with the code to avoid never ending recursion            
             if(typeof pivot === "undefined") {
                 if (_log) console.log ("Ops..."); 
                 return false;
             }

             var i, lowerArray = [], upperArray = [];
             for (i = 0; i  < size; i++){
                 var current = a[i];
                 if (current < pivot) {
                     comparisonCount += 1;
                     memoryCount++;
                     lowerArray.push(current);
                 } else if (current > pivot) {
                     comparisonCount += 2;
                     memoryCount++;
                     upperArray.push(current);
                 }
             }
             if(_log) console.log("Pivoting:",lowerArray, "*"+pivot+"*", upperArray);

             if(k <= upperArray.length) {
                 comparisonCount += 1;
                 return _kthmax(upperArray, k);
             } else if (k > size - lowerArray.length) {
                 comparisonCount += 2;
                 return _kthmax(lowerArray, k - (size - lowerArray.length));
             } else {
                 comparisonCount += 2;
                 return pivot;
             }
     /* 
      * BTW, this is the logic for kthMin if we want to implement that... ;-)
      * 

             if(k <= lowerArray.length) {
                 return kthMin(lowerArray, k);
             } else if (k > size - upperArray.length) {
                 return kthMin(upperArray, k - (size - upperArray.length));
             } else 
                 return pivot;
     */            
         }

         var result = _kthmax(a, k);
         return {result: result, iterations: comparisonCount, memory: memoryCount};
     }

剩下的代码只是创建一些游乐场:

    function getRandomArray (n){
        var ar = [];
        for (var i = 0, l = n; i < l; i++) {
            ar.push(Math.round(Math.random() * l))
        }

        return ar;
    }

    //Create a random array of 50 numbers
    var ar = getRandomArray (50);   

现在给你做几次测试。 因为Math.random()每次都会产生不同的结果:

    kthMax(ar, 2, true);
    kthMax(ar, 2);
    kthMax(ar, 2);
    kthMax(ar, 2);
    kthMax(ar, 2);
    kthMax(ar, 2);
    kthMax(ar, 34, true);
    kthMax(ar, 34);
    kthMax(ar, 34);
    kthMax(ar, 34);
    kthMax(ar, 34);
    kthMax(ar, 34);

如果你测试它几次,你甚至可以看到经验的迭代次数,平均来说,O(n) ~=常数* n, k的值不会影响算法。

其他回答

中位数中位数算法的解释可以在这里找到n中第k大的整数: http://cs.indstate.edu/~spitla/presentation.pdf

c++中的实现如下:

#include <iostream>
#include <vector>
#include <algorithm>
using namespace std;

int findMedian(vector<int> vec){
//    Find median of a vector
    int median;
    size_t size = vec.size();
    median = vec[(size/2)];
    return median;
}

int findMedianOfMedians(vector<vector<int> > values){
    vector<int> medians;

    for (int i = 0; i < values.size(); i++) {
        int m = findMedian(values[i]);
        medians.push_back(m);
    }

    return findMedian(medians);
}

void selectionByMedianOfMedians(const vector<int> values, int k){
//    Divide the list into n/5 lists of 5 elements each
    vector<vector<int> > vec2D;

    int count = 0;
    while (count != values.size()) {
        int countRow = 0;
        vector<int> row;

        while ((countRow < 5) && (count < values.size())) {
            row.push_back(values[count]);
            count++;
            countRow++;
        }
        vec2D.push_back(row);
    }

    cout<<endl<<endl<<"Printing 2D vector : "<<endl;
    for (int i = 0; i < vec2D.size(); i++) {
        for (int j = 0; j < vec2D[i].size(); j++) {
            cout<<vec2D[i][j]<<" ";
        }
        cout<<endl;
    }
    cout<<endl;

//    Calculating a new pivot for making splits
    int m = findMedianOfMedians(vec2D);
    cout<<"Median of medians is : "<<m<<endl;

//    Partition the list into unique elements larger than 'm' (call this sublist L1) and
//    those smaller them 'm' (call this sublist L2)
    vector<int> L1, L2;

    for (int i = 0; i < vec2D.size(); i++) {
        for (int j = 0; j < vec2D[i].size(); j++) {
            if (vec2D[i][j] > m) {
                L1.push_back(vec2D[i][j]);
            }else if (vec2D[i][j] < m){
                L2.push_back(vec2D[i][j]);
            }
        }
    }

//    Checking the splits as per the new pivot 'm'
    cout<<endl<<"Printing L1 : "<<endl;
    for (int i = 0; i < L1.size(); i++) {
        cout<<L1[i]<<" ";
    }

    cout<<endl<<endl<<"Printing L2 : "<<endl;
    for (int i = 0; i < L2.size(); i++) {
        cout<<L2[i]<<" ";
    }

//    Recursive calls
    if ((k - 1) == L1.size()) {
        cout<<endl<<endl<<"Answer :"<<m;
    }else if (k <= L1.size()) {
        return selectionByMedianOfMedians(L1, k);
    }else if (k > (L1.size() + 1)){
        return selectionByMedianOfMedians(L2, k-((int)L1.size())-1);
    }

}

int main()
{
    int values[] = {2, 3, 5, 4, 1, 12, 11, 13, 16, 7, 8, 6, 10, 9, 17, 15, 19, 20, 18, 23, 21, 22, 25, 24, 14};

    vector<int> vec(values, values + 25);

    cout<<"The given array is : "<<endl;
    for (int i = 0; i < vec.size(); i++) {
        cout<<vec[i]<<" ";
    }

    selectionByMedianOfMedians(vec, 8);

    return 0;
}

这叫做求k阶统计量。有一个非常简单的随机算法(叫做quickselect),平均时间为O(n),最坏情况时间为O(n²),还有一个相当复杂的非随机算法(叫做introselect),最坏情况时间为O(n)。维基百科上有一些信息,但不是很好。

你需要的一切都在这些幻灯片里。只需提取O(n)最坏情况算法(introselect)的基本算法:

Select(A,n,i):
    Divide input into ⌈n/5⌉ groups of size 5.

    /* Partition on median-of-medians */
    medians = array of each group’s median.
    pivot = Select(medians, ⌈n/5⌉, ⌈n/10⌉)
    Left Array L and Right Array G = partition(A, pivot)

    /* Find ith element in L, pivot, or G */
    k = |L| + 1
    If i = k, return pivot
    If i < k, return Select(L, k-1, i)
    If i > k, return Select(G, n-k, i-k)

在Cormen等人的《算法介绍》一书中也有非常详细的描述。

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));
}

对于k非常小的值(即k << n),我们可以在~O(n)时间内完成。否则,如果k与n比较,我们得到O(nlogn)

这种方法怎么样

保持一个长度为k的缓冲区和一个tmp_max,得到tmp_max为O(k)并执行n次因此类似于O(kn)

是这样还是我漏掉了什么?

虽然它没有击败快速选择的平均情况和中值统计方法的最坏情况,但它非常容易理解和实现。