Maximum product prefix string - algorithm

The following is a demo question from a coding interview site called codility:
A prefix of a string S is any leading contiguous part of S. For example, "c" and "cod" are prefixes of the string "codility". For simplicity, we require prefixes to be non-empty.
The product of prefix P of string S is the number of occurrences of P multiplied by the length of P. More precisely, if prefix P consists of K characters and P occurs exactly T times in S, then the product equals K * T.
For example, S = "abababa" has the following prefixes:
"a", whose product equals 1 * 4 = 4,
"ab", whose product equals 2 * 3 = 6,
"aba", whose product equals 3 * 3 = 9,
"abab", whose product equals 4 * 2 = 8,
"ababa", whose product equals 5 * 2 = 10,
"ababab", whose product equals 6 * 1 = 6,
"abababa", whose product equals 7 * 1 = 7.
The longest prefix is identical to the original string. The goal is to choose such a prefix as maximizes the value of the product. In above example the maximal product is 10.
Below is my poor solution in Java requiring O(N^2) time. It is apparently possible to do this in O(N). I was thinking Kadanes algorithm. But I can't think of any way that I can encode some information at each step that lets me find the running max. Can any one think of an O(N) algorithm for this?
import java.util.HashMap;
class Solution {
public int solution(String S) {
int N = S.length();
if(N<1 || N>300000){
System.out.println("Invalid length");
return(-1);
}
HashMap<String,Integer> prefixes = new HashMap<String,Integer>();
for(int i=0; i<N; i++){
String keystr = "";
for(int j=i; j>=0; j--) {
keystr += S.charAt(j);
if(!prefixes.containsKey(keystr))
prefixes.put(keystr,keystr.length());
else{
int newval = prefixes.get(keystr)+keystr.length();
if(newval > 1000000000)return 1000000000;
prefixes.put(keystr,newval);
}
}
}
int maax1 = 0;
for(int val : prefixes.values())
if(val>maax1)
maax1 = val;
return maax1;
}
}

Here's a O(n log n) version based on suffix arrays. There are O(n) construction algorithms for suffix arrays, I just don't have the patience to code them.
Example output (this output isn't O(n), but it's only to show that we can indeed compute all the scores):
4*1 a
3*3 aba
2*5 ababa
1*7 abababa
3*2 ab
2*4 abab
1*6 ababab
Basically you have to reverse the string, and compute the suffix array (SA) and the longest common prefix (LCP).
Then you have traverse the SA array backwards looking for LCPs that match the entire suffix (prefix in the original string). If there's a match, increment the counter, otherwise reset it to 1. Each suffix (prefix) receive a "score" (SCR) that corresponds to the number of times it appears in the original string.
#include <iostream>
#include <cstring>
#include <string>
#define MAX 10050
using namespace std;
int RA[MAX], tempRA[MAX];
int SA[MAX], tempSA[MAX];
int C[MAX];
int Phi[MAX], PLCP[MAX], LCP[MAX];
int SCR[MAX];
void suffix_sort(int n, int k) {
memset(C, 0, sizeof C);
for (int i = 0; i < n; i++)
C[i + k < n ? RA[i + k] : 0]++;
int sum = 0;
for (int i = 0; i < max(256, n); i++) {
int t = C[i];
C[i] = sum;
sum += t;
}
for (int i = 0; i < n; i++)
tempSA[C[SA[i] + k < n ? RA[SA[i] + k] : 0]++] = SA[i];
memcpy(SA, tempSA, n*sizeof(int));
}
void suffix_array(string &s) {
int n = s.size();
for (int i = 0; i < n; i++)
RA[i] = s[i] - 1;
for (int i = 0; i < n; i++)
SA[i] = i;
for (int k = 1; k < n; k *= 2) {
suffix_sort(n, k);
suffix_sort(n, 0);
int r = tempRA[SA[0]] = 0;
for (int i = 1; i < n; i++) {
int s1 = SA[i], s2 = SA[i-1];
bool equal = true;
equal &= RA[s1] == RA[s2];
equal &= RA[s1+k] == RA[s2+k];
tempRA[SA[i]] = equal ? r : ++r;
}
memcpy(RA, tempRA, n*sizeof(int));
}
}
void lcp(string &s) {
int n = s.size();
Phi[SA[0]] = -1;
for (int i = 1; i < n; i++)
Phi[SA[i]] = SA[i-1];
int L = 0;
for (int i = 0; i < n; i++) {
if (Phi[i] == -1) {
PLCP[i] = 0;
continue;
}
while (s[i + L] == s[Phi[i] + L])
L++;
PLCP[i] = L;
L = max(L-1, 0);
}
for (int i = 1; i < n; i++)
LCP[i] = PLCP[SA[i]];
}
void score(string &s) {
SCR[s.size()-1] = 1;
int sum = 1;
for (int i=s.size()-2; i>=0; i--) {
if (LCP[i+1] < s.size()-SA[i]-1) {
sum = 1;
} else {
sum++;
}
SCR[i] = sum;
}
}
int main() {
string s = "abababa";
s = string(s.rbegin(), s.rend()) +".";
suffix_array(s);
lcp(s);
score(s);
for(int i=0; i<s.size(); i++) {
string ns = s.substr(SA[i], s.size()-SA[i]-1);
ns = string(ns.rbegin(), ns.rend());
cout << SCR[i] << "*" << ns.size() << " " << ns << endl;
}
}
Most of this code (specially the suffix array and LCP implementations) I have been using for some years in contests. This version in special I adapted from this one I wrote some years ago.

public class Main {
public static void main(String[] args) {
String input = "abababa";
String prefix;
int product;
int maxProduct = 0;
for (int i = 1; i <= input.length(); i++) {
prefix = input.substring(0, i);
String substr;
int occurs = 0;
for (int j = prefix.length(); j <= input.length(); j++) {
substr = input.substring(0, j);
if (substr.endsWith(prefix))
occurs++;
}
product = occurs*prefix.length();
System.out.println("product of " + prefix + " = " +
prefix.length() + " * " + occurs +" = " + product);
maxProduct = (product > maxProduct)?product:maxProduct;
}
System.out.println("maxProduct = " + maxProduct);
}
}

I was working on this challenge for more than 4 days , reading a lot of documentation, I found a solution with O(N) .
I got 81%, the idea is simple using a window slide.
def solution(s: String): Int = {
var max = s.length // length of the string
var i, j = 1 // start with i=j=1 ( is the beginning of the slide and j the end of the slide )
val len = s.length // the length of the string
val count = Array.ofDim[Int](len) // to store intermediate results
while (i < len - 1 || j < len) {
if (i < len && s(0) != s(i)) {
while (i < len && s(0) != s(i)) { // if the begin of the slide is different from
// the first letter of the string skip it
i = i + 1
}
}
j = i + 1
var k = 1
while (j < len && s(j).equals(s(k))) { // check for equality and update the array count
if (count(k) == 0) {
count(k) = 1
}
count(k) = count(k) + 1
max = math.max((k + 1) * count(k), max)
k = k + 1
j = j + 1
}
i = i + 1
}
max // return the max
}

Related

Finding number of pairs, product of whose indices is divisible by another number X

Given an array and some value X, find the number of pairs such that i < j , a[i] = a[j] and (i * j) % X == 0
Array size <= 10^5
I am thinking of this problem for a while but only could come up with the brute force solution(by checking all pairs) which will obviously time-out [O(N^2) time complexity]
Any better approach?
First of all, store separate search structures for each distinct A[i] as we iterate.
i * j = k * X
i = k * X / j
Let X / j be some fraction. Since i is an integer, k would be of the form m * least_common_multiple(X, j) / X, where m is natural.
Example 1: j = 20, X = 60:
lcm(60, 20) = 60
matching `i`s would be of the form:
(m * 60 / 60) * 60 / 20
=> m * q, where q = 3
Example 2: j = 6, X = 2:
lcm(2, 6) = 6
matching `i`s would be of the form:
(m * 6 / 2) * 2 / 6
=> m * q, where q = 1
Next, I would consider how to efficiently query the number of multiples of a number in a sorted list of arbitrary naturals. One way is to hash the frequency of divisors of each i we add to the search structure of A[i]. But first consider i as j and add to the result the count of divisors q that already exist in the hash map.
JavaScript code with brute force testing at the end:
function gcd(a, b){
return b ? gcd(b, a % b) : a;
}
function getQ(X, j){
return X / gcd(X, j);
}
function addDivisors(n, map){
let m = 1;
while (m*m <= n){
if (n % m == 0){
map[m] = -~map[m];
const l = n / m;
if (l != m)
map[l] = -~map[l];
}
m += 1;
}
}
function f(A, X){
const Ais = {};
let result = 0;
for (let j=1; j<A.length; j++){
if (A[j] == A[0])
result += 1;
// Search
if (Ais.hasOwnProperty(A[j])){
const q = getQ(X, j);
result += Ais[A[j]][q] || 0;
// Initialise this value's
// search structure
} else {
Ais[A[j]] = {};
}
// Add divisors for j
addDivisors(j, Ais[A[j]]);
}
return result;
}
function bruteForce(A, X){
let result = 0;
for (let j=1; j<A.length; j++){
for (let i=0; i<j; i++){
if (A[i] == A[j] && (i*j % X) == 0)
result += 1;
}
}
return result;
}
var numTests = 1000;
var n = 100;
var m = 50;
var x = 100;
for (let i=0; i<numTests; i++){
const A = [];
for (let j=0; j<n; j++)
A.push(Math.ceil(Math.random() * m));
const X = Math.ceil(Math.random() * x);
const _brute = bruteForce(A, X);
const _f = f(A, X);
if (_brute != _f){
console.log("Mismatch!");
console.log(X, JSON.stringify(A));
console.log(_brute, _f);
break;
}
}
console.log("Done testing.")
Just in case If someone needed the java version of this answer - https://stackoverflow.com/a/69690416/19325755 explanation has been provided in that answer.
I spent lot of time in understanding the javascript code so I thought the people who are comfortable with java can refer this for better understanding.
import java.util.HashMap;
public class ThisProblem {
public static void main(String[] args) {
int t = 1000;
int n = 100;
int m = 50;
int x = 100;
for(int i = 0; i<t; i++) {
int[] A = new int[n];
for(int j = 0; j<n; j++) {
A[j] = ((int)Math.random()*m)+1;
}
int X = ((int)Math.random()*x)+1;
int optR = createMaps(A, X);
int brute = bruteForce(A, X);
if(optR != brute) {
System.out.println("Wrong Answer");
break;
}
}
System.out.println("Test Completed");
}
public static int bruteForce(int[] A, int X) {
int result = 0;
int n = A.length;
for(int i = 1; i<n; i++) {
for(int j = 0; j<i; j++) {
if(A[i] == A[j] && (i*j)%X == 0)
result++;
}
}
return result;
}
public static int gcd(int a, int b) {
return b==0 ? a : gcd(b, a%b);
}
public static int getQ(int X, int j) {
return X/gcd(X, j);
}
public static void addDivisors(int n, HashMap<Integer, Integer> map) {
int m = 1;
while(m*m <= n) {
if(n%m == 0) {
map.put(m, map.getOrDefault(m, 0)+1);
int l = n/m;
if(l != m) {
map.put(l, map.getOrDefault(l, 0)+1);
}
}
m++;
}
}
public static int createMaps(int[] A, int X) {
int result = 0;
HashMap<Integer, HashMap<Integer, Integer>> contentsOfA = new HashMap<>();
int n = A.length;
for(int i = 1; i<n; i++) {
if(A[i] == A[0])
result++;
if(contentsOfA.containsKey(A[i])) {
int q = getQ(X, i);
result += contentsOfA.get(A[i]).getOrDefault(q, 0);
} else {
contentsOfA.put(A[i], new HashMap<>());
}
addDivisors(i, contentsOfA.get(A[i]));
}
return result;
}
}

Find minimum cost of tickets

Find minimum cost of tickets required to buy for traveling on known days of the month (1...30). Three types of tickets are available : 1-day ticket valid for 1 days and costs 2 units, 7-days ticket valid for 7 days and costs 7 units, 30-days ticket valid for 30 days and costs 25 units.
For eg: I want to travel on [1,4,6,7,28,30] days of the month i.e. 1st, 4th, 6th ... day of the month. How to buy tickets so that the cost is minimum.
I tried to use dynamic programming to solve this but the solution is not giving me the correct answer for all cases. Here is my solution in Java :
public class TicketsCost {
public static void main(String args[]){
int[] arr = {1,5,6,9,28,30};
System.out.println(findMinCost(arr));
}
public static int findMinCost(int[] arr) {
int[][] dp = new int[arr.length][3];
int[] tDays = {1,7,30};
int[] tCost = {2,7,25};
for (int i = 0; i < arr.length; i++) {
for (int j = 0; j < 3; j++) {
if (j==0){
dp[i][j]= (i+1)*tCost[j];
}
else{
int c = arr[i]-tDays[j];
int tempCost = tCost[j];
int k;
if (c>=arr[0] && i>0){
for (k = i-1; k >= 0; k--) {
if (arr[k]<=c){
c = arr[k];
}
}
tempCost += dp[c][j];
int tempCostX = dp[i-1][j] + tCost[0];
tempCost = Math.min(tempCost,tempCostX);
}
dp[i][j] = Math.min(tempCost,dp[i][j-1]);
}
}
}
return dp[arr.length-1][2];
}
}
The solution doesn't work for {1,7,8,9,10} input, it gives 10 but the correct answer should be 9. Also, for {1,7,8,9,10,15} it give 13 but the correct is 11.
I have posted my solution not for other to debug it for me but just for reference. I was taken a bottom-up dynamic programming approach for this problem. Is this approach correct?
Let MC(d) denote the minimum cost that will pay for all trips on days 1 through d. The desired answer is then MC(30).
To calculate MC(d), observe the following:
If there's no trip on day d, then MC(d) = MC(d − 1).
As a special case, MC(d) = 0 for all d ≤ 0.
Otherwise, the minimum cost involves one of the following:
A 1-day pass on day d. In this case, MC(d) = MC(d − 1) + 2.
A 7-day pass ending on or after day d. In this case, MC(d) = min(MC(d − 7), MC(d − 6), …, MC(d − 1)) + 7.
And since MC is nondecreasing (adding a day never reduces the minimum cost), this can be simplified to MC(d) = MC(d − 7) + 7. (Hat-tip to Ravi for pointing this out.)
A 30-day pass covering the whole period. In this case, MC(d) = 25.
As you've realized, dynamic programming (bottom-up recursion) is well-suited to this.
For ease of coding, I suggest we start by converting the list of days into a lookup table for "is this a trip day?":
boolean[] isDayWithTrip = new boolean[31]; // note: initializes to false
for (final int dayWithTrip : arr) {
isDayWithTrip[dayWithTrip] = true;
}
We can then create an array to track the minimum costs, and populate it starting from index 0:
int[] minCostUpThroughDay = new int[31];
minCostUpThroughDay[0] = 0; // technically redundant
for (int d = 1; d <= 30; ++d) {
if (! isDayWithTrip[d]) {
minCostUpThroughDay[d] = minCostUpThroughDay[d-1];
continue;
}
int minCost;
// Possibility #1: one-day pass on day d:
minCost = minCostUpThroughDay[d-1] + 2;
// Possibility #2: seven-day pass ending on or after day d:
minCost =
Math.min(minCost, minCostUpThroughDay[Math.max(0, d-7)] + 7);
// Possibility #3: 30-day pass for the whole period:
minCost = Math.min(minCost, 25);
minCostUpThroughDay[d] = minCost;
}
And minCostUpThroughDay[30] is the result.
You can see the above code in action at: https://ideone.com/1Xx1fd.
One recursive solution in Python3.
from typing import List
def solution(A: List[int]) -> int:
if not any(A):
return 0
tickets = {
1: 2,
7: 7,
30: 25,
}
import sys
min_cost = sys.maxsize
size = len(A)
for length, price in tickets.items():
current_cost = price
idx = 0
last_day = A[idx] + length
while idx < size and A[idx] < last_day:
idx += 1
if current_cost > min_cost:
continue
current_cost += solution(A[idx:])
if current_cost < min_cost:
min_cost = current_cost
return min_cost
if __name__ == '__main__':
cases = {
11: [1, 4, 6, 7, 28, 30],
9: [1, 7, 8, 9, 10],
}
for expect, parameters in cases.items():
status = (expect == solution(parameters))
print("case pass status: %s, detail: %s == solution(%s)" %
(status, expect, parameters))
public class Main03v3
{
public static void main(String[] args)
{
int[] A = {1,7,8,9,10,15,16,17,18,21,25};
System.out.println("Traveling days:\r\n "+Arrays.toString(A));
int cost = solution(A);
System.out.println("\r\nMinimum cost is " + cost);
System.out.println("\r\n" + new String(new char[40]).replace("\0", "-"));
}
public static int solution(int[] A)
{
if (A == null) return -1;
int sevenDays = 7;
int dayCost = 2, weekCost = 7, monthCost = 25;
int ratio_WeekAndDays = weekCost / dayCost;
int len = A.length;
if (len == 0) return -1;
if (len <= 3) return len * dayCost;
int cost[] = new int[len];
int i = 0;
while (i < len)
{
int startIdx = i, endIdx = i + 1;
while (endIdx < len && A[endIdx]-A[startIdx] < sevenDays)
endIdx++;
if (endIdx-startIdx > ratio_WeekAndDays)
{
if (endIdx >= startIdx + sevenDays)
endIdx = startIdx + sevenDays;
int j = startIdx;
cost[j] = ((j == 0) ? 0 : cost[j-1]) + weekCost;
while (++j < endIdx) {
cost[j] = cost[j-1];
}
i = j;
}
else
{
cost[i] = ((i == 0) ? 0 : cost[i-1]) + dayCost;
i++;
}
}
int finalCost = Math.min(cost[len-1], monthCost);
return finalCost;
}
}
Find minimum cost of tickets in JavaScript
case 1 : if input is [1,7,8,9,10] then the required output is 9
case 2 : if input is [1,7,8,9,10,15] then the required output is 11
function calMinCosts(arr){
if(!arr || arr.length===0)
return 0;
var len = arr.length;
var costsOfDateArr = Array.apply(null,{length:arr[len-1]+1}).map(()=>0);
var price1=2,price2=7,price3=25;
var days=7;
var index=0,n=costsOfDateArr.length;
for(var i=1;i<n;i++){
if(i===arr[index]){
if(i>=days+1){
costsOfDateArr[i] = Math.min(costsOfDateArr[i-days-1]+price2, costsOfDateArr[i-1]+price1);
}else{
costsOfDateArr[i] = Math.min(costsOfDateArr[0]+price2, costsOfDateArr[i-1]+price1);
}
index+=1;
}else{
costsOfDateArr[i] = costsOfDateArr[i-1];
}
}
return Math.min(price3,costsOfDateArr[n-1]);
}
console.log(calMinCosts([1,7,8,9,10]))
console.log(calMinCosts([1,7,8,9,10,15]))
Here is the C++ solution including print outs
#include <vector>
#include <iostream>
#include <cmath>
#include <algorithm>
int compute(std::vector<int> &A)
{
int sum[A.size()][A.size()+1];
for (int i = 0; i < A.size(); i++)
{
for(int j =0; j < A.size(); j++)
{
sum[i][j]=2;
}
}
for (int k = 0; k < A.size();k++)
{
sum[k][A.size()]=0;
}
for (int i = 0; i < A.size(); i++)
{
for(int j = 0; j < A.size(); j++)
{
if (i!=j)
{
if (sum[i][i] != 7)
{
int temp = abs(A[j]-A[i]);
if (temp<7 && abs(j-i)>=3)
{
sum[i][i]=7;
sum[i][j]=7;
if (i>j)
{
for(int k = j;k < i;k++)
sum[i][k]=7;
}
else
{
for(int k = i;k < j;k++)
sum[i][k]=7;
}
}
}
}
}
}
for (int i = 0; i < A.size(); ++i)
{
for(int j = 0; j < A.size(); ++j)
{
if (sum[i][j]==7)
{
sum[i][A.size()]+=1;
}
}
}
for (int i = 0; i < A.size(); ++i)
{
for (int j = 0; j < A.size()+1; ++j)
std::cout<<sum[i][j]<<" ";
std::cout<<std::endl;
}
int result = 0;
int row = A.size()-1;
int column = A.size()-1;
while(1)
{
int value = sum[row][A.size()];
if (value == 0)
value=1;
int temp = sum[row][column];
result += temp;
row = row-value;
column = column-value;
while (sum[row][column+1]==7 && row>=0)
{
row-=1;
column-=1;
result+=2;
}
if (row < 0)
break;
}
return result;
}
int solution(std::vector<int> &A) {
if (A.size() > 24)
return 25;
if (A.size() <= 3)
return A.size() * 2;
return std::min(25,compute(A));
}
int main()
{
std::vector<int> AA={1,2,3,4,5,29,30};
std::vector<int> B={1,2,3,4,5};
std::vector<int> A={1,2,3,4,5,9,10,11,12,13,14,17,18,20,21};
std::vector<int> C={1,2,3,12};
std::vector<int> D={1,2,3,4,12,13,14,15,29,30};
std::vector<int> DD={1,2,3,4,5,14,17,18,19,20,23,28,29,30};
std::vector<int> CC={1,2,3,4,5,6,7,9,14,17,18,19,20,23,28,29,30};
std::cout<<solution(AA)<<std::endl;
std::cout<<solution(D)<<std::endl;
std::cout<<solution(B)<<std::endl;
std::cout<<solution(A)<<std::endl;
std::cout<<solution(C)<<std::endl;
std::cout<<solution(DD)<<std::endl;
std::cout<<solution(CC)<<std::endl;
return 0;
}
Solved using the same approach of bottom-up dynamic programming. Here is the full solution :
public class PublicTicketCost {
public static void main(String args[]){
int[] arr = {1,7,8,9,10,15,16,17,18,21,25};
int[] tDays = {1,7,30};
int[] tCost = {2,7,25};
System.out.println(minCost(arr, tDays, tCost));
}
public static int minCost(int[] arr, int[] tDays, int[] tCost) {
int[][] dp = new int[arr.length][tDays.length];
for (int i = 0; i < arr.length; i++) {
for (int j = 0; j < tDays.length; j++) {
int prevDayIndex = findPrevDayIndex(arr,i,tDays,j);
int prevCost = prevDayIndex>=0 ? dp[prevDayIndex][tDays.length-1] : 0;
int currCost = prevCost + tCost[j];
if(j-1>=0){
currCost = Math.min(currCost, dp[i][j-1]);
}
dp[i][j] = currCost;
}
}
//print(dp);
return dp[arr.length-1][tDays.length-1];
}
private static void print(int arr[][]){
for (int i = 0; i < arr.length; i++) {
for (int j = 0; j < arr[0].length; j++) {
System.out.print(arr[i][j]+" ");
}
System.out.println();
}
}
private static int findPrevDayIndex(int[] arr, int i, int[] days, int j){
int validAfterDate = arr[i] - days[j];
if (validAfterDate<1){
return -1;
}
for (int k = i-1; k >= 0; k--) {
if (arr[k]<=validAfterDate){
return k;
}
}
return -1;
}
}
http://ideone.com/sfgxGo

Number of binary trees with equal values

There is array of values:
1 - n_1 times
2 - n_2 times
...
k - n_k times
How many trees with this nodes exist?
I create simple algorythm:
int get_count(const vector<int> n_i) {
if (n_i.size() <= 1) {
return 1;
} else {
int total_count = 0;
for (int i = 0; i < n_i.size(); ++i) {
vector<int> first;
vector<int> second;
for (int j = 0; j < i; ++j) {
first.push_back(n_i[j]);
}
if (n_i[i] != 1) {
second.push_back(n_i[i] - 1);
}
for (int j = i + 1; j < n_i.size(); ++j) {
second.push_back(n_i[j]);
}
total_count += (get_count(first) * get_count(second));
}
return total_count;
}
}
Because
#(n_1, n_2, ... n_k) = #(n_1 - 1, n_2, ..., n_k) + #(n_1) #(n_2 - 1, ... n_k) + ... + #(n_1, ..., n_k - 1)
and
#(0, n_i, n_j, ...) = #(n_i, n_j, ...)
But my code is so slow.
Is there a final formula via Cathalan's numbers, for example?
I guess that the problem can be split into calculating the number of permutations and calculating the number of binary trees of given size. I converted my initial recursive Java code (which gives up on n1=10,n2=10,n3=10) into this iterative one:
static int LIMIT = 1000;
static BigInteger[] numberOfBinaryTreesOfSize = numberOfBinaryTreesBelow(LIMIT);
static BigInteger[] numberOfBinaryTreesBelow(int m) {
BigInteger[] arr = new BigInteger[m];
arr[0] = BigInteger.ZERO;
arr[1] = arr[2] = BigInteger.ONE;
for (int n = 3; n < m; n++) {
BigInteger s = BigInteger.ZERO;
for (int i = 1; i < n; i++)
s = s.add(arr[i].multiply(arr[n - i]));
arr[n] = s;
}
return arr;
}
static BigInteger[] fac = facBelow(LIMIT);
static BigInteger[] facBelow(int m) {
BigInteger[] arr = new BigInteger[m];
arr[0] = arr[1] = BigInteger.ONE;
for (int i = 2; i < m; i++)
arr[i] = arr[i - 1].multiply(BigInteger.valueOf(i));
return arr;
}
static BigInteger getCountFast(int[] arr) {
// s: sum of n_i
int s = 0; for (int i = 0; i < arr.length; i++) { s += arr[i]; }
// p: number of permutations
BigInteger p = fac[s]; for (int i = 0; i < arr.length; i++) { p = p.divide(fac[arr[i]]); }
BigInteger count = p.multiply(numberOfBinaryTreesOfSize[s]);
return count;
}
public static void main(String[] args) {
System.out.println(getCountFast(new int[]{ 150, 150, 150, 150, 150 }));
}
The LIMIT limits the sum of the n_i. The above example takes about two seconds on my machine. Maybe it helps you with a C++ solution.

Find a pair of elements from an array whose sum equals a given number

Given array of n integers and given a number X, find all the unique pairs of elements (a,b), whose summation is equal to X.
The following is my solution, it is O(nLog(n)+n), but I am not sure whether or not it is optimal.
int main(void)
{
int arr [10] = {1,2,3,4,5,6,7,8,9,0};
findpair(arr, 10, 7);
}
void findpair(int arr[], int len, int sum)
{
std::sort(arr, arr+len);
int i = 0;
int j = len -1;
while( i < j){
while((arr[i] + arr[j]) <= sum && i < j)
{
if((arr[i] + arr[j]) == sum)
cout << "(" << arr[i] << "," << arr[j] << ")" << endl;
i++;
}
j--;
while((arr[i] + arr[j]) >= sum && i < j)
{
if((arr[i] + arr[j]) == sum)
cout << "(" << arr[i] << "," << arr[j] << ")" << endl;
j--;
}
}
}
There are 3 approaches to this solution:
Let the sum be T and n be the size of array
Approach 1:
The naive way to do this would be to check all combinations (n choose 2). This exhaustive search is O(n2).
Approach 2:
A better way would be to sort the array. This takes O(n log n)
Then for each x in array A,
use binary search to look for T-x. This will take O(nlogn).
So, overall search is O(n log n)
Approach 3 :
The best way
would be to insert every element into a hash table (without sorting). This takes O(n) as constant time insertion.
Then for every x,
we can just look up its complement, T-x, which is O(1).
Overall the run time of this approach is O(n).
You can refer more here.Thanks.
# Let arr be the given array.
# And K be the give sum
for i=0 to arr.length - 1 do
# key is the element and value is its index.
hash(arr[i]) = i
end-for
for i=0 to arr.length - 1 do
# if K-th element exists and it's different then we found a pair
if hash(K - arr[i]) != i
print "pair i , hash(K - arr[i]) has sum K"
end-if
end-for
Implementation in Java : Using codaddict's algorithm (Maybe slightly different)
import java.util.HashMap;
public class ArrayPairSum {
public static void main(String[] args) {
int []a = {2,45,7,3,5,1,8,9};
printSumPairs(a,10);
}
public static void printSumPairs(int []input, int k){
Map<Integer, Integer> pairs = new HashMap<Integer, Integer>();
for(int i=0;i<input.length;i++){
if(pairs.containsKey(input[i]))
System.out.println(input[i] +", "+ pairs.get(input[i]));
else
pairs.put(k-input[i], input[i]);
}
}
}
For input = {2,45,7,3,5,1,8,9} and if Sum is 10
Output pairs:
3,7
8,2
9,1
Some notes about the solution :
We iterate only once through the array --> O(n) time
Insertion and lookup time in Hash is O(1).
Overall time is O(n), although it uses extra space in terms of hash.
Solution in java. You can add all the String elements to an ArrayList of strings and return the list. Here I am just printing it out.
void numberPairsForSum(int[] array, int sum) {
HashSet<Integer> set = new HashSet<Integer>();
for (int num : array) {
if (set.contains(sum - num)) {
String s = num + ", " + (sum - num) + " add up to " + sum;
System.out.println(s);
}
set.add(num);
}
}
Python Implementation:
import itertools
list = [1, 1, 2, 3, 4, 5,]
uniquelist = set(list)
targetsum = 5
for n in itertools.combinations(uniquelist, 2):
if n[0] + n[1] == targetsum:
print str(n[0]) + " + " + str(n[1])
Output:
1 + 4
2 + 3
C++11, run time complexity O(n):
#include <vector>
#include <unordered_map>
#include <utility>
std::vector<std::pair<int, int>> FindPairsForSum(
const std::vector<int>& data, const int& sum)
{
std::unordered_map<int, size_t> umap;
std::vector<std::pair<int, int>> result;
for (size_t i = 0; i < data.size(); ++i)
{
if (0 < umap.count(sum - data[i]))
{
size_t j = umap[sum - data[i]];
result.push_back({data[i], data[j]});
}
else
{
umap[data[i]] = i;
}
}
return result;
}
Here is a solution witch takes into account duplicate entries. It is written in javascript and assumes array is sorted. The solution runs in O(n) time and does not use any extra memory aside from variable.
var count_pairs = function(_arr,x) {
if(!x) x = 0;
var pairs = 0;
var i = 0;
var k = _arr.length-1;
if((k+1)<2) return pairs;
var halfX = x/2;
while(i<k) {
var curK = _arr[k];
var curI = _arr[i];
var pairsThisLoop = 0;
if(curK+curI==x) {
// if midpoint and equal find combinations
if(curK==curI) {
var comb = 1;
while(--k>=i) pairs+=(comb++);
break;
}
// count pair and k duplicates
pairsThisLoop++;
while(_arr[--k]==curK) pairsThisLoop++;
// add k side pairs to running total for every i side pair found
pairs+=pairsThisLoop;
while(_arr[++i]==curI) pairs+=pairsThisLoop;
} else {
// if we are at a mid point
if(curK==curI) break;
var distK = Math.abs(halfX-curK);
var distI = Math.abs(halfX-curI);
if(distI > distK) while(_arr[++i]==curI);
else while(_arr[--k]==curK);
}
}
return pairs;
}
I solved this during an interview for a large corporation. They took it but not me.
So here it is for everyone.
Start at both side of the array and slowly work your way inwards making sure to count duplicates if they exist.
It only counts pairs but can be reworked to
find the pairs
find pairs < x
find pairs > x
Enjoy!
O(n)
def find_pairs(L,sum):
s = set(L)
edgeCase = sum/2
if L.count(edgeCase) ==2:
print edgeCase, edgeCase
s.remove(edgeCase)
for i in s:
diff = sum-i
if diff in s:
print i, diff
L = [2,45,7,3,5,1,8,9]
sum = 10
find_pairs(L,sum)
Methodology: a + b = c, so instead of looking for (a,b) we look for a = c -
b
Implementation in Java : Using codaddict's algorithm:
import java.util.Hashtable;
public class Range {
public static void main(String[] args) {
// TODO Auto-generated method stub
Hashtable mapping = new Hashtable();
int a[]= {80,79,82,81,84,83,85};
int k = 160;
for (int i=0; i < a.length; i++){
mapping.put(a[i], i);
}
for (int i=0; i < a.length; i++){
if (mapping.containsKey(k - a[i]) && (Integer)mapping.get(k-a[i]) != i){
System.out.println(k-a[i]+", "+ a[i]);
}
}
}
}
Output:
81, 79
79, 81
If you want duplicate pairs (eg: 80,80) also then just remove && (Integer)mapping.get(k-a[i]) != i from the if condition and you are good to go.
Just attended this question on HackerRank and here's my 'Objective C' Solution:
-(NSNumber*)sum:(NSArray*) a andK:(NSNumber*)k {
NSMutableDictionary *dict = [NSMutableDictionary dictionary];
long long count = 0;
for(long i=0;i<a.count;i++){
if(dict[a[i]]) {
count++;
NSLog(#"a[i]: %#, dict[array[i]]: %#", a[i], dict[a[i]]);
}
else{
NSNumber *calcNum = #(k.longLongValue-((NSNumber*)a[i]).longLongValue);
dict[calcNum] = a[i];
}
}
return #(count);
}
Hope it helps someone.
this is the implementation of O(n*lg n) using binary search implementation inside a loop.
#include <iostream>
using namespace std;
bool *inMemory;
int pairSum(int arr[], int n, int k)
{
int count = 0;
if(n==0)
return count;
for (int i = 0; i < n; ++i)
{
int start = 0;
int end = n-1;
while(start <= end)
{
int mid = start + (end-start)/2;
if(i == mid)
break;
else if((arr[i] + arr[mid]) == k && !inMemory[i] && !inMemory[mid])
{
count++;
inMemory[i] = true;
inMemory[mid] = true;
}
else if(arr[i] + arr[mid] >= k)
{
end = mid-1;
}
else
start = mid+1;
}
}
return count;
}
int main()
{
int arr[] = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10};
inMemory = new bool[10];
for (int i = 0; i < 10; ++i)
{
inMemory[i] = false;
}
cout << pairSum(arr, 10, 11) << endl;
return 0;
}
In python
arr = [1, 2, 4, 6, 10]
diff_hash = {}
expected_sum = 3
for i in arr:
if diff_hash.has_key(i):
print i, diff_hash[i]
key = expected_sum - i
diff_hash[key] = i
Nice solution from Codeaddict. I took the liberty of implementing a version of it in Ruby:
def find_sum(arr,sum)
result ={}
h = Hash[arr.map {|i| [i,i]}]
arr.each { |l| result[l] = sum-l if h[sum-l] && !result[sum-l] }
result
end
To allow duplicate pairs (1,5), (5,1) we just have to remove the && !result[sum-l] instruction
Here is Java code for three approaches:
1. Using Map O(n), HashSet can also be used here.
2. Sort array and then use BinarySearch to look for complement O(nLog(n))
3. Traditional BruteForce two loops O(n^2)
public class PairsEqualToSum {
public static void main(String[] args) {
int a[] = {1,10,5,8,2,12,6,4};
findPairs1(a,10);
findPairs2(a,10);
findPairs3(a,10);
}
//Method1 - O(N) use a Map to insert values as keys & check for number's complement in map
static void findPairs1(int[]a, int sum){
Map<Integer, Integer> pairs = new HashMap<Integer, Integer>();
for(int i=0; i<a.length; i++){
if(pairs.containsKey(sum-a[i]))
System.out.println("("+a[i]+","+(sum-a[i])+")");
else
pairs.put(a[i], 0);
}
}
//Method2 - O(nlog(n)) using Sort
static void findPairs2(int[]a, int sum){
Arrays.sort(a);
for(int i=0; i<a.length/2; i++){
int complement = sum - a[i];
int foundAtIndex = Arrays.binarySearch(a,complement);
if(foundAtIndex >0 && foundAtIndex != i) //to avoid situation where binarySearch would find the original and not the complement like "5"
System.out.println("("+a[i]+","+(sum-a[i])+")");
}
}
//Method 3 - Brute Force O(n^2)
static void findPairs3(int[]a, int sum){
for(int i=0; i<a.length; i++){
for(int j=i; j<a.length;j++){
if(a[i]+a[j] == sum)
System.out.println("("+a[i]+","+a[j]+")");
}
}
}
}
A Simple program in java for arrays having unique elements:
import java.util.*;
public class ArrayPairSum {
public static void main(String[] args) {
int []a = {2,4,7,3,5,1,8,9,5};
sumPairs(a,10);
}
public static void sumPairs(int []input, int k){
Set<Integer> set = new HashSet<Integer>();
for(int i=0;i<input.length;i++){
if(set.contains(input[i]))
System.out.println(input[i] +", "+(k-input[i]));
else
set.add(k-input[i]);
}
}
}
A simple Java code snippet for printing the pairs below:
public static void count_all_pairs_with_given_sum(int arr[], int S){
if(arr.length < 2){
return;
}
HashSet values = new HashSet(arr.length);
for(int value : arr)values.add(value);
for(int value : arr){
int difference = S - value;
if(values.contains(difference) && value<difference){
System.out.printf("(%d, %d) %n", value, difference);
}
}
}
Another solution in Swift: the idea is to create an hash that store values of (sum - currentValue) and compare this to the current value of the loop. The complexity is O(n).
func findPair(list: [Int], _ sum: Int) -> [(Int, Int)]? {
var hash = Set<Int>() //save list of value of sum - item.
var dictCount = [Int: Int]() //to avoid the case A*2 = sum where we have only one A in the array
var foundKeys = Set<Int>() //to avoid duplicated pair in the result.
var result = [(Int, Int)]() //this is for the result.
for item in list {
//keep track of count of each element to avoid problem: [2, 3, 5], 10 -> result = (5,5)
if (!dictCount.keys.contains(item)) {
dictCount[item] = 1
} else {
dictCount[item] = dictCount[item]! + 1
}
//if my hash does not contain the (sum - item) value -> insert to hash.
if !hash.contains(sum-item) {
hash.insert(sum-item)
}
//check if current item is the same as another hash value or not, if yes, return the tuple.
if hash.contains(item) &&
(dictCount[item] > 1 || sum != item*2) // check if we have item*2 = sum or not.
{
if !foundKeys.contains(item) && !foundKeys.contains(sum-item) {
foundKeys.insert(item) //add to found items in order to not to add duplicated pair.
result.append((item, sum-item))
}
}
}
return result
}
//test:
let a = findPair([2,3,5,4,1,7,6,8,9,5,3,3,3,3,3,3,3,3,3], 14) //will return (8,6) and (9,5)
My Solution - Java - Without duplicates
public static void printAllPairSum(int[] a, int x){
System.out.printf("printAllPairSum(%s,%d)\n", Arrays.toString(a),x);
if(a==null||a.length==0){
return;
}
int length = a.length;
Map<Integer,Integer> reverseMapOfArray = new HashMap<>(length,1.0f);
for (int i = 0; i < length; i++) {
reverseMapOfArray.put(a[i], i);
}
for (int i = 0; i < length; i++) {
Integer j = reverseMapOfArray.get(x - a[i]);
if(j!=null && i<j){
System.out.printf("a[%d] + a[%d] = %d + %d = %d\n",i,j,a[i],a[j],x);
}
}
System.out.println("------------------------------");
}
This prints the pairs and avoids duplicates using bitwise manipulation.
public static void findSumHashMap(int[] arr, int key) {
Map<Integer, Integer> valMap = new HashMap<Integer, Integer>();
for(int i=0;i<arr.length;i++)
valMap.put(arr[i], i);
int indicesVisited = 0;
for(int i=0;i<arr.length;i++) {
if(valMap.containsKey(key - arr[i]) && valMap.get(key - arr[i]) != i) {
if(!((indicesVisited & ((1<<i) | (1<<valMap.get(key - arr[i])))) > 0)) {
int diff = key-arr[i];
System.out.println(arr[i] + " " +diff);
indicesVisited = indicesVisited | (1<<i) | (1<<valMap.get(key - arr[i]));
}
}
}
}
I bypassed the bit manuplation and just compared the index values. This is less than the loop iteration value (i in this case). This will not print the duplicate pairs and duplicate array elements also.
public static void findSumHashMap(int[] arr, int key) {
Map<Integer, Integer> valMap = new HashMap<Integer, Integer>();
for (int i = 0; i < arr.length; i++) {
valMap.put(arr[i], i);
}
for (int i = 0; i < arr.length; i++) {
if (valMap.containsKey(key - arr[i])
&& valMap.get(key - arr[i]) != i) {
if (valMap.get(key - arr[i]) < i) {
int diff = key - arr[i];
System.out.println(arr[i] + " " + diff);
}
}
}
}
in C#:
int[] array = new int[] { 1, 5, 7, 2, 9, 8, 4, 3, 6 }; // given array
int sum = 10; // given sum
for (int i = 0; i <= array.Count() - 1; i++)
if (array.Contains(sum - array[i]))
Console.WriteLine("{0}, {1}", array[i], sum - array[i]);
One Solution can be this, but not optimul (The complexity of this code is O(n^2)):
public class FindPairsEqualToSum {
private static int inputSum = 0;
public static List<String> findPairsForSum(int[] inputArray, int sum) {
List<String> list = new ArrayList<String>();
List<Integer> inputList = new ArrayList<Integer>();
for (int i : inputArray) {
inputList.add(i);
}
for (int i : inputArray) {
int tempInt = sum - i;
if (inputList.contains(tempInt)) {
String pair = String.valueOf(i + ", " + tempInt);
list.add(pair);
}
}
return list;
}
}
A simple python version of the code that find a pair sum of zero and can be modify to find k:
def sumToK(lst):
k = 0 # <- define the k here
d = {} # build a dictionary
# build the hashmap key = val of lst, value = i
for index, val in enumerate(lst):
d[val] = index
# find the key; if a key is in the dict, and not the same index as the current key
for i, val in enumerate(lst):
if (k-val) in d and d[k-val] != i:
return True
return False
The run time complexity of the function is O(n) and Space: O(n) as well.
public static int[] f (final int[] nums, int target) {
int[] r = new int[2];
r[0] = -1;
r[1] = -1;
int[] vIndex = new int[0Xfff];
for (int i = 0; i < nums.length; i++) {
int delta = 0Xff;
int gapIndex = target - nums[i] + delta;
if (vIndex[gapIndex] != 0) {
r[0] = vIndex[gapIndex];
r[1] = i + 1;
return r;
} else {
vIndex[nums[i] + delta] = i + 1;
}
}
return r;
}
less than o(n) solution will be=>
function(array,k)
var map = {};
for element in array
map(element) = true;
if(map(k-element))
return {k,element}
Solution in Python using list comprehension
f= [[i,j] for i in list for j in list if j+i==X];
O(N2)
also gives two ordered pairs- (a,b) and (b,a) as well
I can do it in O(n). Let me know when you want the answer. Note it involves simply traversing the array once with no sorting, etc... I should mention too that it exploits commutativity of addition and doesn't use hashes but wastes memory.
using System;
using System.Collections.Generic;
/*
An O(n) approach exists by using a lookup table. The approach is to store the value in a "bin" that can easily be looked up(e.g., O(1)) if it is a candidate for an appropriate sum.
e.g.,
for each a[k] in the array we simply put the it in another array at the location x - a[k].
Suppose we have [0, 1, 5, 3, 6, 9, 8, 7] and x = 9
We create a new array,
indexes value
9 - 0 = 9 0
9 - 1 = 8 1
9 - 5 = 4 5
9 - 3 = 6 3
9 - 6 = 3 6
9 - 9 = 0 9
9 - 8 = 1 8
9 - 7 = 2 7
THEN the only values that matter are the ones who have an index into the new table.
So, say when we reach 9 or equal we see if our new array has the index 9 - 9 = 0. Since it does we know that all the values it contains will add to 9. (note in this cause it's obvious there is only 1 possible one but it might have multiple index values in it which we need to store).
So effectively what we end up doing is only having to move through the array once. Because addition is commutative we will end up with all the possible results.
For example, when we get to 6 we get the index into our new table as 9 - 6 = 3. Since the table contains that index value we know the values.
This is essentially trading off speed for memory.
*/
namespace sum
{
class Program
{
static void Main(string[] args)
{
int num = 25;
int X = 10;
var arr = new List<int>();
for(int i = 0; i <= num; i++) arr.Add((new Random((int)(DateTime.Now.Ticks + i*num))).Next(0, num*2));
Console.Write("["); for (int i = 0; i < num - 1; i++) Console.Write(arr[i] + ", "); Console.WriteLine(arr[arr.Count-1] + "] - " + X);
var arrbrute = new List<Tuple<int,int>>();
var arrfast = new List<Tuple<int,int>>();
for(int i = 0; i < num; i++)
for(int j = i+1; j < num; j++)
if (arr[i] + arr[j] == X)
arrbrute.Add(new Tuple<int, int>(arr[i], arr[j]));
int M = 500;
var lookup = new List<List<int>>();
for(int i = 0; i < 1000; i++) lookup.Add(new List<int>());
for(int i = 0; i < num; i++)
{
// Check and see if we have any "matches"
if (lookup[M + X - arr[i]].Count != 0)
{
foreach(var j in lookup[M + X - arr[i]])
arrfast.Add(new Tuple<int, int>(arr[i], arr[j]));
}
lookup[M + arr[i]].Add(i);
}
for(int i = 0; i < arrbrute.Count; i++)
Console.WriteLine(arrbrute[i].Item1 + " + " + arrbrute[i].Item2 + " = " + X);
Console.WriteLine("---------");
for(int i = 0; i < arrfast.Count; i++)
Console.WriteLine(arrfast[i].Item1 + " + " + arrfast[i].Item2 + " = " + X);
Console.ReadKey();
}
}
}
I implemented logic in Scala with out a Map. It gives duplicate pairs since the counter loops thru entire elements of the array. If duplicate pairs are needed, you can simply return the value pc
val arr = Array[Int](8, 7, 2, 5, 3, 1, 5)
val num = 10
var pc = 0
for(i <- arr.indices) {
if(arr.contains(Math.abs(arr(i) - num))) pc += 1
}
println(s"Pairs: ${pc/2}")
It is working with duplicates values in the array as well.
GOLANG Implementation
func findPairs(slice1 []int, sum int) [][]int {
pairMap := make(map[int]int)
var SliceOfPairs [][]int
for i, v := range slice1 {
if valuei, ok := pairMap[v]; ok {
//fmt.Println("Pair Found", i, valuei)
SliceOfPairs = append(SliceOfPairs, []int{i, valuei})
} else {
pairMap[sum-v] = i
}
}
return SliceOfPairs
}
function findPairOfNumbers(arr, targetSum) {
arr = arr.sort();
var low = 0, high = arr.length - 1, sum, result = [];
while(low < high) {
sum = arr[low] + arr[high];
if(sum < targetSum)
low++;
else if(sum > targetSum)
high--;
else if(sum === targetSum) {
result.push({val1: arr[low], val2: arr[high]});
high--;
}
}
return (result || false);
}
var pairs = findPairOfNumbers([1,2,3,4,5,6,7,8,9,0], 7);
if(pairs.length) {
console.log(pairs);
} else {
console.log("No pair of numbers found that sums to " + 7);
}

Getting the submatrix with maximum sum?

Input: A 2-dimensional array NxN - Matrix - with positive and negative elements.Output: A submatrix of any size such that its summation is the maximum among all possible submatrices.
Requirement: Algorithm complexity to be of O(N^3)
History: With the help of the Algorithmist, Larry and a modification of Kadane's Algorithm, i managed to solve the problem partly which is determining the summation only - below in Java.
Thanks to Ernesto who managed to solve the rest of the problem which is determining the boundaries of the matrix i.e. top-left, bottom-right corners - below in Ruby.
Here's an explanation to go with the posted code. There are two key tricks to make this work efficiently: (I) Kadane's algorithm and (II) using prefix sums. You also need to (III) apply the tricks to the matrix.
Part I: Kadane's algorithm
Kadane's algorithm is a way to find a contiguous subsequence with maximum sum. Let's start with a brute force approach for finding the max contiguous subsequence and then consider optimizing it to get Kadane's algorithm.
Suppose you have the sequence:
-1, 2, 3, -2
For the brute force approach, walk along the sequence generating all possible subsequences as shown below. Considering all possibilities, we can start, extend, or end a list with each step.
At index 0, we consider appending the -1
-1, 2, 3, -2
^
Possible subsequences:
-1 [sum -1]
At index 1, we consider appending the 2
-1, 2, 3, -2
^
Possible subsequences:
-1 (end) [sum -1]
-1, 2 [sum 1]
2 [sum 2]
At index 2, we consider appending the 3
-1, 2, 3, -2
^
Possible subsequences:
-1, (end) [sum -1]
-1, 2 (end) [sum -1]
2 (end) [sum 2]
-1, 2, 3 [sum 4]
2, 3 [sum 5]
3 [sum 3]
At index 3, we consider appending the -2
-1, 2, 3, -2
^
Possible subsequences:
-1, (end) [sum -1]
-1, 2 (end) [sum 1]
2 (end) [sum 2]
-1, 2 3 (end) [sum 4]
2, 3 (end) [sum 5]
3, (end) [sum 3]
-1, 2, 3, -2 [sum 2]
2, 3, -2 [sum 3]
3, -2 [sum 1]
-2 [sum -2]
For this brute force approach, we finally pick the list with the best sum, (2, 3), and that's the answer. However, to make this efficient, consider that you really don't need to keep every one of the lists. Out of the lists that have not ended, you only need to keep the best one, the others cannot do any better. Out of the lists that have ended, you only might need to keep the best one, and only if it's better than ones that have not ended.
So, you can keep track of what you need with just a position array and a sum array. The position array is defined like this: position[r] = s keeps track of the list which ends at r and starts at s. And, sum[r] gives a sum for the subsequence ending at index r. This is optimized approach is Kadane's algorithm.
Running through the example again keeping track of our progress this way:
At index 0, we consider appending the -1
-1, 2, 3, -2
^
We start a new subsequence for the first element.
position[0] = 0
sum[0] = -1
At index 1, we consider appending the 2
-1, 2, 3, -2
^
We choose to start a new subsequence because that gives a higher sum than extending.
position[0] = 0 sum[0] = -1
position[1] = 1 sum[1] = 2
At index 2, we consider appending the 3
-1, 2, 3, -2
^
We choose to extend a subsequence because that gives a higher sum than starting a new one.
position[0] = 0 sum[0] = -1
position[1] = 1 sum[1] = 2
position[2] = 1 sum[2] = 5
Again, we choose to extend because that gives a higher sum that starting a new one.
-1, 2, 3, -2
^
position[0] = 0 sum[0] = -1
position[1] = 1 sum[1] = 2
position[2] = 1 sum[2] = 5
positions[3] = 3 sum[3] = 3
Again, the best sum is 5 and the list is from index 1 to index 2, which is (2, 3).
Part II: Prefix sums
We want to have a way to compute the sum along a row, for any start point to any endpoint. I want to compute that sum in O(1) time rather than just adding, which takes O(m) time where m is the number of elements in the sum. With some precomputing, this can be achieved. Here's how. Suppose you have a matrix:
a d g
b e h
c f i
You can precompute this matrix:
a d g
a+b d+e g+h
a+b+c d+e+f g+h+i
Once that is done you can get the sum running along any column from any start to endpoint in the column just by subtracting two values.
Part III: Bringing tricks together to find the max submatrix
Assume that you know the top and bottom row of the max submatrix. You could do this:
Ignore rows above your top row and ignore rows below your bottom
row.
With what matrix remains, consider the using sum of each column to
form a sequence (sort of like a row that represents multiple rows).
(You can compute any element of this sequence rapidly with the prefix
sums approach.)
Use Kadane's approach to figure out best subsequence in this
sequence. The indexes you get will tell you the left and right
positions of the best submatrix.
Now, what about actually figuring out the top and bottom row? Just try all possibilities. Try putting the top anywhere you can and putting the bottom anywhere you can, and run the Kadane-base procedure described previously for every possibility. When you find a max, you keep track of the top and bottom position.
Finding the row and column takes O(M^2) where M is the number of rows. Finding the column takes O(N) time where N is the number of columns. So total time is O(M^2 * N). And, if M=N, the time required is O(N^3).
About recovering the actual submatrix, and not just the maximum sum, here's what I got. Sorry I do not have time to translate my code to your java version, so I'm posting my Ruby code with some comments in the key parts
def max_contiguous_submatrix_n3(m)
rows = m.count
cols = rows ? m.first.count : 0
vps = Array.new(rows)
for i in 0..rows
vps[i] = Array.new(cols, 0)
end
for j in 0...cols
vps[0][j] = m[0][j]
for i in 1...rows
vps[i][j] = vps[i-1][j] + m[i][j]
end
end
max = [m[0][0],0,0,0,0] # this is the result, stores [max,top,left,bottom,right]
# these arrays are used over Kadane
sum = Array.new(cols) # obvious sum array used in Kadane
pos = Array.new(cols) # keeps track of the beginning position for the max subseq ending in j
for i in 0...rows
for k in i...rows
# Kadane over all columns with the i..k rows
sum.fill(0) # clean both the sum and pos arrays for the upcoming Kadane
pos.fill(0)
local_max = 0 # we keep track of the position of the max value over each Kadane's execution
# notice that we do not keep track of the max value, but only its position
sum[0] = vps[k][0] - (i==0 ? 0 : vps[i-1][0])
for j in 1...cols
value = vps[k][j] - (i==0 ? 0 : vps[i-1][j])
if sum[j-1] > 0
sum[j] = sum[j-1] + value
pos[j] = pos[j-1]
else
sum[j] = value
pos[j] = j
end
if sum[j] > sum[local_max]
local_max = j
end
end
# Kadane ends here
# Here's the key thing
# If the max value obtained over the past Kadane's execution is larger than
# the current maximum, then update the max array with sum and bounds
if sum[local_max] > max[0]
# sum[local_max] is the new max value
# the corresponding submatrix goes from rows i..k.
# and from columns pos[local_max]..local_max
# the array below contains [max_sum,top,left,bottom,right]
max = [sum[local_max], i, pos[local_max], k, local_max]
end
end
end
return max # return the array with [max_sum,top,left,bottom,right]
end
Some notes for clarification:
I use an array to store all the values pertaining to the result for convenience. You can just use five standalone variables: max, top, left, bottom, right. It's just easier to assign in one line to the array and then the subroutine returns the array with all the needed information.
If you copy and paste this code in a text-highlight-enabled editor with Ruby support you'll obviously understand it better. Hope this helps!
There are already plenty of answers, but here is another Java implementation I wrote. It compares 3 solutions:
Naïve (brute force) - O(n^6) time
The obvious DP solution - O(n^4) time and O(n^3) space
The more clever DP solution based on Kadane's algorithm - O(n^3) time and O(n^2) space
There are sample runs for n = 10 thru n = 70 in increments of 10 with a nice output comparing run time and space requirements.
Code:
public class MaxSubarray2D {
static int LENGTH;
final static int MAX_VAL = 10;
public static void main(String[] args) {
for (int i = 10; i <= 70; i += 10) {
LENGTH = i;
int[][] a = new int[LENGTH][LENGTH];
for (int row = 0; row < LENGTH; row++) {
for (int col = 0; col < LENGTH; col++) {
a[row][col] = (int) (Math.random() * (MAX_VAL + 1));
if (Math.random() > 0.5D) {
a[row][col] = -a[row][col];
}
//System.out.printf("%4d", a[row][col]);
}
//System.out.println();
}
System.out.println("N = " + LENGTH);
System.out.println("-------");
long start, end;
start = System.currentTimeMillis();
naiveSolution(a);
end = System.currentTimeMillis();
System.out.println(" run time: " + (end - start) + " ms no auxiliary space requirements");
start = System.currentTimeMillis();
dynamicProgammingSolution(a);
end = System.currentTimeMillis();
System.out.println(" run time: " + (end - start) + " ms requires auxiliary space for "
+ ((int) Math.pow(LENGTH, 4)) + " integers");
start = System.currentTimeMillis();
kadane2D(a);
end = System.currentTimeMillis();
System.out.println(" run time: " + (end - start) + " ms requires auxiliary space for " +
+ ((int) Math.pow(LENGTH, 2)) + " integers");
System.out.println();
System.out.println();
}
}
// O(N^2) !!!
public static void kadane2D(int[][] a) {
int[][] s = new int[LENGTH + 1][LENGTH]; // [ending row][sum from row zero to ending row] (rows 1-indexed!)
for (int r = 0; r < LENGTH + 1; r++) {
for (int c = 0; c < LENGTH; c++) {
s[r][c] = 0;
}
}
for (int r = 1; r < LENGTH + 1; r++) {
for (int c = 0; c < LENGTH; c++) {
s[r][c] = s[r - 1][c] + a[r - 1][c];
}
}
int maxSum = Integer.MIN_VALUE;
int maxRowStart = -1;
int maxColStart = -1;
int maxRowEnd = -1;
int maxColEnd = -1;
for (int r1 = 1; r1 < LENGTH + 1; r1++) { // rows 1-indexed!
for (int r2 = r1; r2 < LENGTH + 1; r2++) { // rows 1-indexed!
int[] s1 = new int[LENGTH];
for (int c = 0; c < LENGTH; c++) {
s1[c] = s[r2][c] - s[r1 - 1][c];
}
int max = 0;
int c1 = 0;
for (int c = 0; c < LENGTH; c++) {
max = s1[c] + max;
if (max <= 0) {
max = 0;
c1 = c + 1;
}
if (max > maxSum) {
maxSum = max;
maxRowStart = r1 - 1;
maxColStart = c1;
maxRowEnd = r2 - 1;
maxColEnd = c;
}
}
}
}
System.out.print("KADANE SOLUTION | Max sum: " + maxSum);
System.out.print(" Start: (" + maxRowStart + ", " + maxColStart +
") End: (" + maxRowEnd + ", " + maxColEnd + ")");
}
// O(N^4) !!!
public static void dynamicProgammingSolution(int[][] a) {
int[][][][] dynTable = new int[LENGTH][LENGTH][LENGTH + 1][LENGTH + 1]; // [row][col][height][width]
int maxSum = Integer.MIN_VALUE;
int maxRowStart = -1;
int maxColStart = -1;
int maxRowEnd = -1;
int maxColEnd = -1;
for (int r = 0; r < LENGTH; r++) {
for (int c = 0; c < LENGTH; c++) {
for (int h = 0; h < LENGTH + 1; h++) {
for (int w = 0; w < LENGTH + 1; w++) {
dynTable[r][c][h][w] = 0;
}
}
}
}
for (int r = 0; r < LENGTH; r++) {
for (int c = 0; c < LENGTH; c++) {
for (int h = 1; h <= LENGTH - r; h++) {
int rowTotal = 0;
for (int w = 1; w <= LENGTH - c; w++) {
rowTotal += a[r + h - 1][c + w - 1];
dynTable[r][c][h][w] = rowTotal + dynTable[r][c][h - 1][w];
}
}
}
}
for (int r = 0; r < LENGTH; r++) {
for (int c = 0; c < LENGTH; c++) {
for (int h = 0; h < LENGTH + 1; h++) {
for (int w = 0; w < LENGTH + 1; w++) {
if (dynTable[r][c][h][w] > maxSum) {
maxSum = dynTable[r][c][h][w];
maxRowStart = r;
maxColStart = c;
maxRowEnd = r + h - 1;
maxColEnd = c + w - 1;
}
}
}
}
}
System.out.print(" DP SOLUTION | Max sum: " + maxSum);
System.out.print(" Start: (" + maxRowStart + ", " + maxColStart +
") End: (" + maxRowEnd + ", " + maxColEnd + ")");
}
// O(N^6) !!!
public static void naiveSolution(int[][] a) {
int maxSum = Integer.MIN_VALUE;
int maxRowStart = -1;
int maxColStart = -1;
int maxRowEnd = -1;
int maxColEnd = -1;
for (int rowStart = 0; rowStart < LENGTH; rowStart++) {
for (int colStart = 0; colStart < LENGTH; colStart++) {
for (int rowEnd = 0; rowEnd < LENGTH; rowEnd++) {
for (int colEnd = 0; colEnd < LENGTH; colEnd++) {
int sum = 0;
for (int row = rowStart; row <= rowEnd; row++) {
for (int col = colStart; col <= colEnd; col++) {
sum += a[row][col];
}
}
if (sum > maxSum) {
maxSum = sum;
maxRowStart = rowStart;
maxColStart = colStart;
maxRowEnd = rowEnd;
maxColEnd = colEnd;
}
}
}
}
}
System.out.print(" NAIVE SOLUTION | Max sum: " + maxSum);
System.out.print(" Start: (" + maxRowStart + ", " + maxColStart +
") End: (" + maxRowEnd + ", " + maxColEnd + ")");
}
}
Here is a Java version of Ernesto implementation with some modifications:
public int[][] findMaximumSubMatrix(int[][] matrix){
int dim = matrix.length;
//computing the vertical prefix sum for columns
int[][] ps = new int[dim][dim];
for (int i = 0; i < dim; i++) {
for (int j = 0; j < dim; j++) {
if (j == 0) {
ps[j][i] = matrix[j][i];
} else {
ps[j][i] = matrix[j][i] + ps[j - 1][i];
}
}
}
int maxSum = matrix[0][0];
int top = 0, left = 0, bottom = 0, right = 0;
//Auxiliary variables
int[] sum = new int[dim];
int[] pos = new int[dim];
int localMax;
for (int i = 0; i < dim; i++) {
for (int k = i; k < dim; k++) {
// Kadane over all columns with the i..k rows
reset(sum);
reset(pos);
localMax = 0;
//we keep track of the position of the max value over each Kadane's execution
// notice that we do not keep track of the max value, but only its position
sum[0] = ps[k][0] - (i==0 ? 0 : ps[i-1][0]);
for (int j = 1; j < dim; j++) {
if (sum[j-1] > 0){
sum[j] = sum[j-1] + ps[k][j] - (i==0 ? 0 : ps[i-1][j]);
pos[j] = pos[j-1];
}else{
sum[j] = ps[k][j] - (i==0 ? 0 : ps[i-1][j]);
pos[j] = j;
}
if (sum[j] > sum[localMax]){
localMax = j;
}
}//Kadane ends here
if (sum[localMax] > maxSum){
/* sum[localMax] is the new max value
the corresponding submatrix goes from rows i..k.
and from columns pos[localMax]..localMax
*/
maxSum = sum[localMax];
top = i;
left = pos[localMax];
bottom = k;
right = localMax;
}
}
}
System.out.println("Max SubMatrix determinant = " + maxSum);
//composing the required matrix
int[][] output = new int[bottom - top + 1][right - left + 1];
for(int i = top, k = 0; i <= bottom; i++, k++){
for(int j = left, l = 0; j <= right ; j++, l++){
output[k][l] = matrix[i][j];
}
}
return output;
}
private void reset(int[] a) {
for (int index = 0; index < a.length; index++) {
a[index] = 0;
}
}
With the help of the Algorithmist and Larry and a modification of Kadane's Algorithm, here is my solution:
int dim = matrix.length;
//computing the vertical prefix sum for columns
int[][] ps = new int[dim][dim];
for (int i = 0; i < dim; i++) {
for (int j = 0; j < dim; j++) {
if (j == 0) {
ps[j][i] = matrix[j][i];
} else {
ps[j][i] = matrix[j][i] + ps[j - 1][i];
}
}
}
int maxSoFar = 0;
int min , subMatrix;
//iterate over the possible combinations applying Kadane's Alg.
for (int i = 0; i < dim; i++) {
for (int j = i; j < dim; j++) {
min = 0;
subMatrix = 0;
for (int k = 0; k < dim; k++) {
if (i == 0) {
subMatrix += ps[j][k];
} else {
subMatrix += ps[j][k] - ps[i - 1 ][k];
}
if(subMatrix < min){
min = subMatrix;
}
if((subMatrix - min) > maxSoFar){
maxSoFar = subMatrix - min;
}
}
}
}
The only thing left is to determine the submatrix elements, i.e: the top left and the bottom right corner of the submatrix. Anyone suggestion?
this is my implementation of 2D Kadane algorithm. I think it is more clear. The concept is based on just kadane algorithm. The first and second loop of the main part (that is in the bottom of the code) is to pick every combination of the rows and 3rd loop is to use 1D kadane algorithm by every following column sum (that can be computed in const time because of preprocessing of matrix by subtracting values from two picked (from combintation) rows). Here is the code:
int [][] m = {
{1,-5,-5},
{1,3,-5},
{1,3,-5}
};
int N = m.length;
// summing columns to be able to count sum between two rows in some column in const time
for (int i=0; i<N; ++i)
m[0][i] = m[0][i];
for (int j=1; j<N; ++j)
for (int i=0; i<N; ++i)
m[j][i] = m[j][i] + m[j-1][i];
int total_max = 0, sum;
for (int i=0; i<N; ++i) {
for (int k=i; k<N; ++k) { //for each combination of rows
sum = 0;
for (int j=0; j<N; j++) { //kadane algorithm for every column
sum += i==0 ? m[k][j] : m[k][j] - m[i-1][j]; //for first upper row is exception
total_max = Math.max(sum, total_max);
}
}
}
System.out.println(total_max);
I am going to post an answer here and can add actual c++ code if it is requested because I had recently worked through this. Some rumors of a divide and conqueror that can solve this in O(N^2) are out there but I haven't seen any code to support this. In my experience the following is what I have found.
O(i^3j^3) -- naive brute force method
o(i^2j^2) -- dynamic programming with memoization
O(i^2j) -- using max contiguous sub sequence for an array
if ( i == j )
O(n^6) -- naive
O(n^4) -- dynamic programming
O(n^3) -- max contiguous sub sequence
Have a look at JAMA package; I believe it will make your life easier.
Here is the C# solution. Ref: http://www.algorithmist.com/index.php/UVa_108
public static MaxSumMatrix FindMaxSumSubmatrix(int[,] inMtrx)
{
MaxSumMatrix maxSumMtrx = new MaxSumMatrix();
// Step 1. Create SumMatrix - do the cumulative columnar summation
// S[i,j] = S[i-1,j]+ inMtrx[i-1,j];
int m = inMtrx.GetUpperBound(0) + 2;
int n = inMtrx.GetUpperBound(1)+1;
int[,] sumMatrix = new int[m, n];
for (int i = 1; i < m; i++)
{
for (int j = 0; j < n; j++)
{
sumMatrix[i, j] = sumMatrix[i - 1, j] + inMtrx[i - 1, j];
}
}
PrintMatrix(sumMatrix);
// Step 2. Create rowSpans starting each rowIdx. For these row spans, create a 1-D array r_ij
for (int x = 0; x < n; x++)
{
for (int y = x; y < n; y++)
{
int[] r_ij = new int[n];
for (int k = 0; k < n; k++)
{
r_ij[k] = sumMatrix[y + 1,k] - sumMatrix[x, k];
}
// Step 3. Find MaxSubarray of this r_ij. If the sum is greater than the last recorded sum =>
// capture Sum, colStartIdx, ColEndIdx.
// capture current x as rowTopIdx, y as rowBottomIdx.
MaxSum currMaxSum = KadanesAlgo.FindMaxSumSubarray(r_ij);
if (currMaxSum.maxSum > maxSumMtrx.sum)
{
maxSumMtrx.sum = currMaxSum.maxSum;
maxSumMtrx.colStart = currMaxSum.maxStartIdx;
maxSumMtrx.colEnd = currMaxSum.maxEndIdx;
maxSumMtrx.rowStart = x;
maxSumMtrx.rowEnd = y;
}
}
}
return maxSumMtrx;
}
public static void PrintMatrix(int[,] matrix)
{
int endRow = matrix.GetUpperBound(0);
int endCol = matrix.GetUpperBound(1);
PrintMatrix(matrix, 0, endRow, 0, endCol);
}
public static void PrintMatrix(int[,] matrix, int startRow, int endRow, int startCol, int endCol)
{
StringBuilder sb = new StringBuilder();
for (int i = startRow; i <= endRow; i++)
{
sb.Append(Environment.NewLine);
for (int j = startCol; j <= endCol; j++)
{
sb.Append(string.Format("{0} ", matrix[i,j]));
}
}
Console.WriteLine(sb.ToString());
}
// Given an NxN matrix of positive and negative integers, write code to find the sub-matrix with the largest possible sum
public static MaxSum FindMaxSumSubarray(int[] inArr)
{
int currMax = 0;
int currStartIndex = 0;
// initialize maxSum to -infinity, maxStart and maxEnd idx to 0.
MaxSum mx = new MaxSum(int.MinValue, 0, 0);
// travers through the array
for (int currEndIndex = 0; currEndIndex < inArr.Length; currEndIndex++)
{
// add element value to the current max.
currMax += inArr[currEndIndex];
// if current max is more that the last maxSum calculated, set the maxSum and its idx
if (currMax > mx.maxSum)
{
mx.maxSum = currMax;
mx.maxStartIdx = currStartIndex;
mx.maxEndIdx = currEndIndex;
}
if (currMax < 0) // if currMax is -ve, change it back to 0
{
currMax = 0;
currStartIndex = currEndIndex + 1;
}
}
return mx;
}
struct MaxSum
{
public int maxSum;
public int maxStartIdx;
public int maxEndIdx;
public MaxSum(int mxSum, int mxStart, int mxEnd)
{
this.maxSum = mxSum;
this.maxStartIdx = mxStart;
this.maxEndIdx = mxEnd;
}
}
class MaxSumMatrix
{
public int sum = int.MinValue;
public int rowStart = -1;
public int rowEnd = -1;
public int colStart = -1;
public int colEnd = -1;
}
Here is my solution. It's O(n^3) in time and O(n^2) space.
https://gist.github.com/toliuweijing/6097144
// 0th O(n) on all candidate bottoms #B.
// 1th O(n) on candidate tops #T.
// 2th O(n) on finding the maximum #left/#right match.
int maxRect(vector<vector<int> >& mat) {
int n = mat.size();
vector<vector<int> >& colSum = mat;
for (int i = 1 ; i < n ; ++i)
for (int j = 0 ; j < n ; ++j)
colSum[i][j] += colSum[i-1][j];
int optrect = 0;
for (int b = 0 ; b < n ; ++b) {
for (int t = 0 ; t <= b ; ++t) {
int minLeft = 0;
int rowSum[n];
for (int i = 0 ; i < n ; ++i) {
int col = t == 0 ? colSum[b][i] : colSum[b][i] - colSum[t-1][i];
rowSum[i] = i == 0? col : col + rowSum[i-1];
optrect = max(optrect, rowSum[i] - minLeft);
minLeft = min(minLeft, rowSum[i]);
}
}
}
return optrect;
}
I would just parse the NxN array removing the -ves whatever remains is the highest sum of a sub matrix.
The question doesn't say you have to leave the original matrix intact or that the order matters.

Resources