There are two sorted arrays nums1 and nums2 of size m and n respectively.
Find the median of the two sorted arrays. The overall run time complexity should be O(log (m+n)).
Example 1:
nums1 = [1, 3]
nums2 = [2]
The median is 2.0
Example 2:
nums1 = [1, 2]
nums2 = [3, 4]
The median is (2 + 3)/2 = 2.5
#include <iostream>
#include <vector>
#include <algorithm>
using namespace std;
double findMedianSortedArrays(vector<int>& nums1, vector<int>& nums2)
{
int m = nums1.size();
int n = nums2.size();
vector<int> a;
int i = 0;
a.resize(m+n);
copy(nums1.begin(),nums1.end(),a.begin());
vector<int>::iterator it = a.begin();
while(i < m)
{
++i;
++it;
}
copy(nums2.begin(),nums2.end(),it);
sort(a.begin(),a.end());
double median = double ( (m+n)%2 ? a[(n+m)>>1] : (a[(n+m)>>1]+a[(m+n-1)>>1])/2.0 );
return median;
}
int main()
{
int arr[] = {};
int arr1[] = {2,3};
vector<int> nums1;
vector<int> nums2;
for(int i = 0; i < sizeof(arr)/sizeof(arr[0]); ++i)
nums1.push_back(arr[i]);
for(int i = 0; i < sizeof(arr1)/sizeof(arr1[0]); ++i)
nums2.push_back(arr1[i]);
cout<<findMedianSortedArrays(nums1,nums2)<<endl;
return 0;
}
该方法居然也通过测试,但是其复杂度最坏情况为O(nlogn),这说明leetcode只对算法的正确性有要求,时间要求其实不严格。
改进方法:
该方法的核心是将原问题转变成一个寻找第k小数的问题(假设两个原序列升序排列),这样中位数实际上是第(m+n)/2小的数。所以只要解决了第k小数的问题,原问题也得以解决。
首先假设数组A和B的元素个数都大于k/2,我们比较A[k/2-1]和B[k/2-1]两个元素,这两个元素分别表示A的第k/2小的元素和B的第k/2小的元素。这两个元素比较共有三种情况:>、<和=。如果A[k/2-1]
double findKth(int a[], int m, int b[], int n, int k)
{
//always assume that m is equal or smaller than n
if (m > n)
return findKth(b, n, a, m, k);
if (m == 0)
return b[k - 1];
if (k == 1)
return min(a[0], b[0]);
//divide k into two parts
int pa = min(k / 2, m), pb = k - pa;
if (a[pa - 1] < b[pb - 1])
return findKth(a + pa, m - pa, b, n, k - pa);
else if (a[pa - 1] > b[pb - 1])
return findKth(a, m, b + pb, n - pb, k - pb);
else
return a[pa - 1];
}
class Solution
{
public:
double findMedianSortedArrays(int A[], int m, int B[], int n)
{
int total = m + n;
if (total & 0x1)
return findKth(A, m, B, n, total / 2 + 1);
else
return (findKth(A, m, B, n, total / 2)
+ findKth(A, m, B, n, total / 2 + 1)) / 2;
}
};
我们可以看出,代码非常简洁,而且效率也很高。在最好情况下,每次都有k一半的元素被删除,所以算法复杂度为logk,由于求中位数时k为(m+n)/2,所以算法复杂度为log(m+n)。