我有一组整数。我想用动态规划的方法求出这个集合的最长递增子序列。
当前回答
这可以用动态规划在O(n²)中解决。同样的Python代码是这样的:-
def LIS(numlist):
LS = [1]
for i in range(1, len(numlist)):
LS.append(1)
for j in range(0, i):
if numlist[i] > numlist[j] and LS[i]<=LS[j]:
LS[i] = 1 + LS[j]
print LS
return max(LS)
numlist = map(int, raw_input().split(' '))
print LIS(numlist)
输入:5 19 5 81 50 28 29 1 83 23
输出将是:[1,2,1,3,3,3,4,1,5,3] 5
输出列表的list_index是输入列表的list_index。输出列表中给定list_index的值表示该list_index的最长递增子序列长度。
其他回答
求最长递增子序列的O(NLog(N))方法 让我们维护一个数组,其中第i个元素是一个大小为i的子序列可以结束的最小的数字。
我故意避免进一步的细节,因为投票最多的答案已经解释了它,但这种技术最终导致使用set数据结构的整洁实现(至少在c++中)。
下面是c++中的实现(假设需要严格增加最长子序列的大小)
#include <bits/stdc++.h> // gcc supported header to include (almost) everything
using namespace std;
typedef long long ll;
int main()
{
ll n;
cin >> n;
ll arr[n];
set<ll> S;
for(ll i=0; i<n; i++)
{
cin >> arr[i];
auto it = S.lower_bound(arr[i]);
if(it != S.end())
S.erase(it);
S.insert(arr[i]);
}
cout << S.size() << endl; // Size of the set is the required answer
return 0;
}
Petar Minchev的解释帮助我理清了事情,但我很难解析所有内容,所以我做了一个带有过度描述性变量名和大量注释的Python实现。我做了一个简单的递归解,O(n²)解,和O(n log n)解。
我希望它能帮助理清算法!
递归解决方案
def recursive_solution(remaining_sequence, bigger_than=None):
"""Finds the longest increasing subsequence of remaining_sequence that is
bigger than bigger_than and returns it. This solution is O(2^n)."""
# Base case: nothing is remaining.
if len(remaining_sequence) == 0:
return remaining_sequence
# Recursive case 1: exclude the current element and process the remaining.
best_sequence = recursive_solution(remaining_sequence[1:], bigger_than)
# Recursive case 2: include the current element if it's big enough.
first = remaining_sequence[0]
if (first > bigger_than) or (bigger_than is None):
sequence_with = [first] + recursive_solution(remaining_sequence[1:], first)
# Choose whichever of case 1 and case 2 were longer.
if len(sequence_with) >= len(best_sequence):
best_sequence = sequence_with
return best_sequence
O(n²)动态规划解
def dynamic_programming_solution(sequence):
"""Finds the longest increasing subsequence in sequence using dynamic
programming. This solution is O(n^2)."""
longest_subsequence_ending_with = []
backreference_for_subsequence_ending_with = []
current_best_end = 0
for curr_elem in range(len(sequence)):
# It's always possible to have a subsequence of length 1.
longest_subsequence_ending_with.append(1)
# If a subsequence is length 1, it doesn't have a backreference.
backreference_for_subsequence_ending_with.append(None)
for prev_elem in range(curr_elem):
subsequence_length_through_prev = (longest_subsequence_ending_with[prev_elem] + 1)
# If the prev_elem is smaller than the current elem (so it's increasing)
# And if the longest subsequence from prev_elem would yield a better
# subsequence for curr_elem.
if ((sequence[prev_elem] < sequence[curr_elem]) and
(subsequence_length_through_prev >
longest_subsequence_ending_with[curr_elem])):
# Set the candidate best subsequence at curr_elem to go through prev.
longest_subsequence_ending_with[curr_elem] = (subsequence_length_through_prev)
backreference_for_subsequence_ending_with[curr_elem] = prev_elem
# If the new end is the best, update the best.
if (longest_subsequence_ending_with[curr_elem] >
longest_subsequence_ending_with[current_best_end]):
current_best_end = curr_elem
# Output the overall best by following the backreferences.
best_subsequence = []
current_backreference = current_best_end
while current_backreference is not None:
best_subsequence.append(sequence[current_backreference])
current_backreference = (backreference_for_subsequence_ending_with[current_backreference])
best_subsequence.reverse()
return best_subsequence
O(n log n)动态规划解
def find_smallest_elem_as_big_as(sequence, subsequence, elem):
"""Returns the index of the smallest element in subsequence as big as
sequence[elem]. sequence[elem] must not be larger than every element in
subsequence. The elements in subsequence are indices in sequence. Uses
binary search."""
low = 0
high = len(subsequence) - 1
while high > low:
mid = (high + low) / 2
# If the current element is not as big as elem, throw out the low half of
# sequence.
if sequence[subsequence[mid]] < sequence[elem]:
low = mid + 1
# If the current element is as big as elem, throw out everything bigger, but
# keep the current element.
else:
high = mid
return high
def optimized_dynamic_programming_solution(sequence):
"""Finds the longest increasing subsequence in sequence using dynamic
programming and binary search (per
http://en.wikipedia.org/wiki/Longest_increasing_subsequence). This solution
is O(n log n)."""
# Both of these lists hold the indices of elements in sequence and not the
# elements themselves.
# This list will always be sorted.
smallest_end_to_subsequence_of_length = []
# This array goes along with sequence (not
# smallest_end_to_subsequence_of_length). Following the corresponding element
# in this array repeatedly will generate the desired subsequence.
parent = [None for _ in sequence]
for elem in range(len(sequence)):
# We're iterating through sequence in order, so if elem is bigger than the
# end of longest current subsequence, we have a new longest increasing
# subsequence.
if (len(smallest_end_to_subsequence_of_length) == 0 or
sequence[elem] > sequence[smallest_end_to_subsequence_of_length[-1]]):
# If we are adding the first element, it has no parent. Otherwise, we
# need to update the parent to be the previous biggest element.
if len(smallest_end_to_subsequence_of_length) > 0:
parent[elem] = smallest_end_to_subsequence_of_length[-1]
smallest_end_to_subsequence_of_length.append(elem)
else:
# If we can't make a longer subsequence, we might be able to make a
# subsequence of equal size to one of our earlier subsequences with a
# smaller ending number (which makes it easier to find a later number that
# is increasing).
# Thus, we look for the smallest element in
# smallest_end_to_subsequence_of_length that is at least as big as elem
# and replace it with elem.
# This preserves correctness because if there is a subsequence of length n
# that ends with a number smaller than elem, we could add elem on to the
# end of that subsequence to get a subsequence of length n+1.
location_to_replace = find_smallest_elem_as_big_as(sequence, smallest_end_to_subsequence_of_length, elem)
smallest_end_to_subsequence_of_length[location_to_replace] = elem
# If we're replacing the first element, we don't need to update its parent
# because a subsequence of length 1 has no parent. Otherwise, its parent
# is the subsequence one shorter, which we just added onto.
if location_to_replace != 0:
parent[elem] = (smallest_end_to_subsequence_of_length[location_to_replace - 1])
# Generate the longest increasing subsequence by backtracking through parent.
curr_parent = smallest_end_to_subsequence_of_length[-1]
longest_increasing_subsequence = []
while curr_parent is not None:
longest_increasing_subsequence.append(sequence[curr_parent])
curr_parent = parent[curr_parent]
longest_increasing_subsequence.reverse()
return longest_increasing_subsequence
好的,我先描述最简单的解也就是O(N²)N是集合的大小。还有一个O(N log N)解,我也会讲到。在高效算法一节中可以找到。
我假设数组的下标从0到N - 1。因此,让我们定义DP[i]为LIS(最长递增子序列)的长度,它结束于索引为i的元素。为了计算DP[i],我们查看所有索引j < i,并检查DP[j] + 1 > DP[i]和array[j] < array[i](我们希望它是递增的)。如果这是真的,我们可以更新DP[i]的当前最优值。要找到数组的全局最优值,您可以从DP[0…]N - 1]。
int maxLength = 1, bestEnd = 0;
DP[0] = 1;
prev[0] = -1;
for (int i = 1; i < N; i++)
{
DP[i] = 1;
prev[i] = -1;
for (int j = i - 1; j >= 0; j--)
if (DP[j] + 1 > DP[i] && array[j] < array[i])
{
DP[i] = DP[j] + 1;
prev[i] = j;
}
if (DP[i] > maxLength)
{
bestEnd = i;
maxLength = DP[i];
}
}
我使用数组prev是为了以后能够找到实际的序列,而不仅仅是它的长度。只需在循环中使用prev[bestEnd]从bestEnd递归返回。-1值是停止的标志。
好了,现在来看更有效的O(nlog N)解:
设S[pos]定义为长度为pos的递增序列结束的最小整数。现在遍历输入集的每个整数X,并执行以下操作:
如果X >是S中的最后一个元素,那么将X附加到S的末尾,这本质上意味着我们已经找到了一个新的最大的LIS。 否则,找到S中最小的元素,即>= X,并将其改为X。 因为S在任何时候都是排序的,所以可以使用log(N)的二分搜索来找到元素。
总运行时间- N个整数,并对每个整数进行二进制搜索- N * log(N) = O(N log N)
现在我们来做一个真实的例子:
整数的集合: 2 6 3 4 1 2 9 5 8
步骤:
0. S = {} - Initialize S to the empty set
1. S = {2} - New largest LIS
2. S = {2, 6} - New largest LIS
3. S = {2, 3} - Changed 6 to 3
4. S = {2, 3, 4} - New largest LIS
5. S = {1, 3, 4} - Changed 2 to 1
6. S = {1, 2, 4} - Changed 3 to 2
7. S = {1, 2, 4, 9} - New largest LIS
8. S = {1, 2, 4, 5} - Changed 9 to 5
9. S = {1, 2, 4, 5, 8} - New largest LIS
所以LIS的长度是5 (S的大小)。
为了重建实际的LIS,我们将再次使用父数组。 设parent[i]是LIS中索引为i的元素的前身,该元素以索引为i的元素结束。
为了使事情更简单,我们可以在数组S中保留不是实际的整数,而是它们在集合中的下标(位置)。我们不保留{1,2,4,5,8},而是保留{4,5,3,7,8}。
即输入[4]= 1,输入[5]= 2,输入[3]= 4,输入[7]= 5,输入[8]= 8。
如果我们正确地更新父数组,实际的LIS是:
input[S[lastElementOfS]],
input[parent[S[lastElementOfS]]],
input[parent[parent[S[lastElementOfS]]]],
........................................
现在重要的是,我们如何更新父数组?有两种选择:
如果X >是S中的最后一个元素,那么parent[indexX] = indexLastElement。这意味着最新元素的父元素是最后一个元素。我们只是在S的末尾加上X。 否则,找到S中最小元素的索引>= than X,并将其更改为X。这里parent[indexX] = S[index - 1]。
最长递增子序列(Java)
import java.util.*;
class ChainHighestValue implements Comparable<ChainHighestValue>{
int highestValue;
int chainLength;
ChainHighestValue(int highestValue,int chainLength) {
this.highestValue = highestValue;
this.chainLength = chainLength;
}
@Override
public int compareTo(ChainHighestValue o) {
return this.chainLength-o.chainLength;
}
}
public class LongestIncreasingSubsequenceLinkedList {
private static LinkedList<Integer> LongestSubsequent(int arr[], int size){
ArrayList<LinkedList<Integer>> seqList=new ArrayList<>();
ArrayList<ChainHighestValue> valuePairs=new ArrayList<>();
for(int i=0;i<size;i++){
int currValue=arr[i];
if(valuePairs.size()==0){
LinkedList<Integer> aList=new LinkedList<>();
aList.add(arr[i]);
seqList.add(aList);
valuePairs.add(new ChainHighestValue(arr[i],1));
}else{
try{
ChainHighestValue heighestIndex=valuePairs.stream().filter(e->e.highestValue<currValue).max(ChainHighestValue::compareTo).get();
int index=valuePairs.indexOf(heighestIndex);
seqList.get(index).add(arr[i]);
heighestIndex.highestValue=arr[i];
heighestIndex.chainLength+=1;
}catch (Exception e){
LinkedList<Integer> aList=new LinkedList<>();
aList.add(arr[i]);
seqList.add(aList);
valuePairs.add(new ChainHighestValue(arr[i],1));
}
}
}
ChainHighestValue heighestIndex=valuePairs.stream().max(ChainHighestValue::compareTo).get();
int index=valuePairs.indexOf(heighestIndex);
return seqList.get(index);
}
public static void main(String[] args){
int arry[]={5,1,3,6,11,30,32,5,3,73,79};
//int arryB[]={3,1,5,2,6,4,9};
LinkedList<Integer> LIS=LongestSubsequent(arry, arry.length);
System.out.println("Longest Incrementing Subsequence:");
for(Integer a: LIS){
System.out.print(a+" ");
}
}
}
这是另一个O(n²)JAVA实现。不需要递归/记忆来生成实际的子序列。只是一个字符串数组,存储每个阶段的实际LIS和一个数组,存储每个元素的LIS的长度。非常简单。看看吧:
import java.io.BufferedReader;
import java.io.InputStreamReader;
/**
* Created by Shreyans on 4/16/2015
*/
class LNG_INC_SUB//Longest Increasing Subsequence
{
public static void main(String[] args) throws Exception
{
BufferedReader br=new BufferedReader(new InputStreamReader(System.in));
System.out.println("Enter Numbers Separated by Spaces to find their LIS\n");
String[] s1=br.readLine().split(" ");
int n=s1.length;
int[] a=new int[n];//Array actual of Numbers
String []ls=new String[n];// Array of Strings to maintain LIS for every element
for(int i=0;i<n;i++)
{
a[i]=Integer.parseInt(s1[i]);
}
int[]dp=new int[n];//Storing length of max subseq.
int max=dp[0]=1;//Defaults
String seq=ls[0]=s1[0];//Defaults
for(int i=1;i<n;i++)
{
dp[i]=1;
String x="";
for(int j=i-1;j>=0;j--)
{
//First check if number at index j is less than num at i.
// Second the length of that DP should be greater than dp[i]
// -1 since dp of previous could also be one. So we compare the dp[i] as empty initially
if(a[j]<a[i]&&dp[j]>dp[i]-1)
{
dp[i]=dp[j]+1;//Assigning temp length of LIS. There may come along a bigger LIS of a future a[j]
x=ls[j];//Assigning temp LIS of a[j]. Will append a[i] later on
}
}
x+=(" "+a[i]);
ls[i]=x;
if(dp[i]>max)
{
max=dp[i];
seq=ls[i];
}
}
System.out.println("Length of LIS is: " + max + "\nThe Sequence is: " + seq);
}
}
实际代码:http://ideone.com/sBiOQx