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

下面是一个随机化快速选择的c++实现。这个想法是随机选择一个主元。为了实现随机分区,我们使用一个随机函数rand()来生成l和r之间的索引,将随机生成索引处的元素与最后一个元素交换,最后调用以最后一个元素为枢轴的标准分区过程。

#include<iostream>
#include<climits>
#include<cstdlib>
using namespace std;

int randomPartition(int arr[], int l, int r);

// This function returns k'th smallest element in arr[l..r] using
// QuickSort based method.  ASSUMPTION: ALL ELEMENTS IN ARR[] ARE DISTINCT
int kthSmallest(int arr[], int l, int r, int k)
{
    // If k is smaller than number of elements in array
    if (k > 0 && k <= r - l + 1)
    {
        // Partition the array around a random element and
        // get position of pivot element in sorted array
        int pos = randomPartition(arr, l, r);

        // If position is same as k
        if (pos-l == k-1)
            return arr[pos];
        if (pos-l > k-1)  // If position is more, recur for left subarray
            return kthSmallest(arr, l, pos-1, k);

        // Else recur for right subarray
        return kthSmallest(arr, pos+1, r, k-pos+l-1);
    }

    // If k is more than number of elements in array
    return INT_MAX;
}

void swap(int *a, int *b)
{
    int temp = *a;
    *a = *b;
    *b = temp;
}

// Standard partition process of QuickSort().  It considers the last
// element as pivot and moves all smaller element to left of it and
// greater elements to right. This function is used by randomPartition()
int partition(int arr[], int l, int r)
{
    int x = arr[r], i = l;
    for (int j = l; j <= r - 1; j++)
    {
        if (arr[j] <= x) //arr[i] is bigger than arr[j] so swap them
        {
            swap(&arr[i], &arr[j]);
            i++;
        }
    }
    swap(&arr[i], &arr[r]); // swap the pivot
    return i;
}

// Picks a random pivot element between l and r and partitions
// arr[l..r] around the randomly picked element using partition()
int randomPartition(int arr[], int l, int r)
{
    int n = r-l+1;
    int pivot = rand() % n;
    swap(&arr[l + pivot], &arr[r]);
    return partition(arr, l, r);
}

// Driver program to test above methods
int main()
{
    int arr[] = {12, 3, 5, 7, 4, 19, 26};
    int n = sizeof(arr)/sizeof(arr[0]), k = 3;
    cout << "K'th smallest element is " << kthSmallest(arr, 0, n-1, k);
    return 0;
}

上述解的最坏情况时间复杂度仍为O(n2)。在最坏的情况下,随机函数可能总是选择一个角元素。上述随机化QuickSelect的期望时间复杂度为Θ(n)

其他回答

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。

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;
    }
}

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。

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)

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。