Find a hash function to malfunction insertion sort - algorithm

Below is the original pseudocode for Insertion Sort:
function INSERTIONSORT(A[0..n−1])
for i←1 to n−1 do
j←i−1
while j≥0 and A[j+1]<A[j] do
SWAP(A[j+1],A[j])
j←j−1
A company is using Insertion Sort inside one of their products. You are a cybersecurity expert that was hired by this company to assess any security flaws with their code. After a few tries, you managed to attack their Insertion Sort code and modify it in the following way:
function INSERTIONSORT(A[0..n−1])
for i←1 to n−1 do
j←i−1
while j≥0 and HASH(A,j+1) < HASH(A,j) do
SWAP(A[j+1],A[j])
j←j−1
In other words, instead of indexing the array as A[j] and A[j+1]inside the “while” condition, you now have a hash function that takes the array and a index as the arguments and return an integer. Your job is to implement specific hash functions that will cause the algorithm to malfunction in different ways.
a) Implement a hash function that causes Insertion Sort to keep the original array unchanged. Explain why your solution works.
b) Implement a hash function that causes Insertion Sort to always run in the worst case complexity, even if the resulting array does not end up getting sorted. Explain why your solution works.
c) Implement a hash function that causes Insertion Sort to sort the array in reverse. Explain why your solution works.
I think (a) and (b) is hash(A,j)=j and hash(A,j)=-j, but have no idea if that is correct and have no clue to c.

**Part a) Original array unchanged
#include <stdio.h>
int hash(int arr[], int i) {
return i;
}
void insertionSort(int arr[], int n) {
int i, j, temp;
for (i = 1 ; i <= n - 1; i++)
{
j = i-1;
while ( j >= 0 && hash(arr, j+1) < hash(arr, j))
{
temp = arr[j];
arr[j] = arr[j+1];
arr[j+1] = temp;
j--;
}
}
}
int main()
{
int i;
int arr[] = {5, 6, 7, 3, 2 , 9, 4};
int n = sizeof(arr)/sizeof(arr[0]);
insertionSort(arr, n);
printf("Original array unchanged:\n");
for (i = 0; i <= n - 1; i++)
{
printf("%d\n", arr[i]);
}
return 0;
}
Part b) Worst Case insertion sort
#include <stdio.h>
int hash(int arr[], int i) {
return -i;
}
void insertionSort(int arr[], int n) {
int i, j, temp;
for (i = 1 ; i <= n - 1; i++)
{
j = i-1;
while ( j >= 0 && hash(arr, j+1) < hash(arr, j))
{
temp = arr[j];
arr[j] = arr[j+1];
arr[j+1] = temp;
j--;
}
}
}
int main()
{
int i;
int arr[] = {5, 6, 7, 3, 2 , 9, 4};
int n = sizeof(arr)/sizeof(arr[0]);
insertionSort(arr, n);
printf("In worst case(number of swaps maximum)\n");
for (i = 0; i <= n - 1; i++)
{
printf("%d\n", arr[i]);
}
return 0;
}
Part c) Sorted in reverse order.**
#include <stdio.h>
int hash(int arr[], int i) {
return -arr[i];
}
void insertionSort(int arr[], int n) {
int i, j, temp;
for (i = 1 ; i <= n - 1; i++)
{
j = i-1;
while ( j >= 0 && hash(arr, j+1) < hash(arr, j))
{
temp = arr[j];
arr[j] = arr[j+1];
arr[j+1] = temp;
j--;
}
}
}
int main()
{
int i;
int arr[] = {5, 6, 7, 3, 2 , 9, 4};
int n = sizeof(arr)/sizeof(arr[0]);
insertionSort(arr, n);
printf("Sorted in reverse order:\n");
for (i = 0; i <= n - 1; i++)
{
printf("%d\n", arr[i]);
}
return 0;
}

Related

This is merge sort program. I am getting confused in logic at mergesort function

This is the merge sort program. I am getting confused in logic at mergesort function where low = 0 and high = 6
in the if statement. if(0<6) then go inside it and mid = (0+6)/2= 3;
then it's again calling mergesort fucntion with giving the value to the low=0 and mid=3; than mergesort will call giving the value to low=0 and high =3; and again this will calls continously and hit the last when 0<1 and then the statement will never gets false Am I right please help me.
#include <stdio.h>
void printArray(int *A, int n)
{
for (int i = 0; i < n; i++)
{
printf("%d ", A[i]);
}
printf("\n");
}
void merge(int A[], int mid, int low, int high)
{
int i, j, k, B[100];
i = low;
j = mid + 1;
k = low;
while (i <= mid && j <= high)
{
if (A[i] < A[j])
{
B[k] = A[i];
i++;
k++;
}
else
{
B[k] = A[j];
j++;
k++;
}
}
while (i <= mid)
{
B[k] = A[i];
k++;
i++;
}
while (j <= high)
{
B[k] = A[j];
k++;
j++;
}
for (int i = low; i <= high; i++)
{
A[i] = B[i];
}
}
void mergeSort(int A[], int low, int high)
{
int mid;
if (low < high)
{
mid = (low + high) / 2;
mergeSort(A, low, mid);
mergeSort(A, mid + 1, high);
merge(A, mid, low, high);
}
}
int main()
{
// int A[] = {9, 14, 4, 8, 7, 5, 6};
int A[] = {9, 1, 4, 14, 4, 15, 6};
int n = 7;
printArray(A, n);
mergeSort(A, 0, 6);
printArray(A, n);
return 0;
}

Please spot the error in this merge sort code

I have provided the code for sorting an array using the merge sort algorithm, I'm unable to find the error, this code is not giving the correctly sorted array as it's output. The function mergesort is called recursively to divide the array till its size is reduced to 1. Then multiple arrays are merged using the merge function.
#include <bits/stdc++.h>
using namespace std;
void merge(int a[], int m, int l, int h) {
int n1 = m - l + 1, n2 = h - m;
int t1[n1], t2[n2];
for (int i = 0; i < n1; i++) {
t1[i] = a[i + l];
}
for (int i = 0; i < n2; i++) {
t2[i] = a[i + m + 1];
}
int k = 0, p = 0, r = 0;
while (k < n1 && p < n2) {
if (t1[k] <= t2[p]) {
a[r] = t1[k];
k++;
r++;
} else {
a[r] = t2[p];
p++;
r++;
}
}
while (k < n1) {
a[r] = t1[k];
k++;
r++;
}
while (p < n2) {
a[r] = t2[p];
p++;
r++;
}
}
void mergesort(int a[], int l, int h) {
if (l < h) {
int m = l + (h - l) / 2;
mergesort(a, l, m);
mergesort(a, m + 1, h);
merge(a, m, l, h);
}
}
int main() {
int a[5] = { 1, 2, 3, 4, 5 };
mergesort(a, 0, 4);
for (int i = 0; i < 5; i++) {
cout << a[i] << " ";
}
return 0;
}
The bug in the merge function is r should be initialized to l, not 0. You are not merging the slices into the original position.
Also note that the last loop while (p < n2) in this function is redundant: the remaining elements in the right slice are already in the proper place in the original array.
Here is a modified version:
void merge(int a[], int m, int l, int h) {
int n1 = m - l + 1, n2 = h - m;
int t1[n1], t2[n2];
for (int i = 0; i < n1; i++) {
t1[i] = a[i + l];
}
for (int i = 0; i < n2; i++) {
t2[i] = a[i + m + 1];
}
int k = 0, p = 0, r = l;
while (k < n1 && p < n2) {
if (t1[k] <= t2[p]) {
a[r] = t1[k];
k++;
r++;
} else {
a[r] = t2[p];
p++;
r++;
}
}
while (k < n1) {
a[r] = t1[k];
k++;
r++;
}
}
To further simplify the code, here are some more remarks:
it is less confusing to make use the convention that h be the first index beyond the end of the slice. This way the initial call uses the array length and mergesort can compute the slice length as h - l.
variable name l looks confusingly close to number 1.
the arguments to merge are usually in the order l, m, h, and m is the index of the start of the right slice.
the right slice does not need saving.
using variable length arrays with automatic storage t1[n2] may cause a stack overflow for large arrays.
Here is a modified version:
#include <bits/stdc++.h>
using namespace std;
void merge(int a[], int lo, int m, int hi) {
int i, j, k;
int n1 = m - lo;
int t1[n1];
for (i = 0; i < n1; i++) {
t1[i] = a[lo + i];
}
i = 0;
j = m;
k = lo;
while (i < n1 && j < hi) {
if (t1[i] <= a[j]) {
a[k++] = t1[i++];
} else {
a[k++] = a[j++];
}
}
while (i < n1) {
a[k++] = t1[i++];
}
}
void mergesort(int a[], int lo, int hi) {
if (hi - lo >= 2) {
int m = lo + (hi - lo) / 2;
mergesort(a, lo, m);
mergesort(a, m, hi);
merge(a, lo, m, hi);
}
}
int main() {
int a[5] = { 1, 5, 2, 4, 3 };
mergesort(a, 0, 5);
for (int i = 0; i < 5; i++) {
cout << a[i] << " ";
}
cout << "\n";
return 0;
}

I am trying to find effective solution for my Homework. Bubble Sort or Insertion Sort?

Hello everyone i have a question. It's my task which one is below:
Let A[] be a natural numbers array of length N, which is partially sorted, i.e. there exists such index i(0 < i < N-1), that the subaray A[0],...,A[i] is incrementally sorted and also the subarray A[i+1],...,A[N] is incrementally sorted. Design the algorithm, which sorts the whole array A[] and works in place (so has space complexity O(1)) and the result must be stored in the same array A[]. Describe the algorithm, its correctness and its time complexity approximation.
For this question which approaching is better? Bubble sorting or Insertion sort? Or is there more effective solution? I prefered bubble sorting for this task but i am open to other opinions
static void bubbleSort(int arr[], int n)
{
int i, j, temp;
boolean swapped;
for (i = 0; i < n - 1; i++)
{
swapped = false;
for (j = 0; j < n - i - 1; j++)
{
if (arr[j] > arr[j + 1])
{
// swap arr[j] and arr[j+1]
temp = arr[j];
arr[j] = arr[j + 1];
arr[j + 1] = temp;
swapped = true;
}
}
if (swapped == false)
break;
}
}
static void printArray(int arr[], int size)
{
int i;
for (i = 0; i < size; i++)
System.out.print(arr[i] + " ");
System.out.println();
}
public static void main(String args[])
{
int arr[] = { 1, 8, 45, 12, 22, 11, 90 };
int n = arr.length;
bubbleSort(arr, n);
System.out.println("Sorted array: ");
printArray(arr, n);
}
}
Bubble sort algorithm complexity is O(n^2). Even using if (swapped == false) break; this will not help to reduce the complexity (try for {2,3,4,5,1}, you will find out).
Since there exists such index i(0 < i < N-1), that the subaray A[0],...,A[i] is incrementally sorted and also the subarray A[i+1],...,A[N] is incrementally sorted.This problem can be solve in O(n) run time complexity. If we can find the index i where A[0:i] and A[i+1:n] are sorted, then we can think this problem as merging two sorted array into one array which can be done in O(n) time. Algorithm is given below:
void sortPartialSortedArray(int arr[], int n)
{
int pos = 0;
// find the position for which arr[0:pos] and arr[pos+1:n] is sorted
for(int i=0; i+1<n; i++) {
if(arr[i]>arr[i+1]) {
pos = i;
}
}
int i = pos, j= n-1;
// sort it from last position
while(i>=0 && j>=0) {
if(arr[i] > arr[j]) {
swap(arr[i],arr[j]);
}
j--;
if(i==j) {
i--;
}
}
}

Bit-reversal algorithm by Rutkowska

I found a very interesting paper about bit-reversal algorithm suitable for in-place FFT: "A simple algorithm for the bit-reversal permutation" by
Urszula Rutkowska from 1990 (doi.org/10.1016/0165-1684(91)90008-7).
However, her algorithm G1 does not appear to work as the very first iteration results in out-of-bounds error for that N1 = L << 1 and swap(a + 1, a + N1);. I assume L means the length of input vector.
Please, does anyone know if there was any errata for the paper or how to fix the algorithm?
The paper's pseudocode:
G1(L)
{int i,j,L1
N1,N2,a,b;
unsigned k;
j=0; L1=L-1;
N1=L<<1;N2=N1+1;
for(i=0;i<L1;i++)
{if(i<j)
{ a=i<<1;
b=j<<1;
swap(a,b);
swap(a+N2,b+N2);
swap(a+1,b+N1);
swap(b+1,a+N1);
}
else
if(i==j)
{ a=i<<1;
swap(a+1,a+N1);
}
k=L>>1;
while(k<=j){ j=j-k;
k=k>>1;
}
j+=k;
}
i<<=1;
swap(i+1,i+N1);
}
Screenshot of the paper:
It was pretty garbled, frankly. I had to read the paper for the idea (run Gold's algorithm (G) for L/4 and then derive the swaps for L) and then sort of massage the code into the right form. Here's my final result.
#include <assert.h>
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
static bool is_power_of_two(int L) { return L > 0 && (L & (L - 1)) == 0; }
static void swap(int i, int j) { printf("swap %d,%d\n", i, j); }
static void G(int L) {
assert(is_power_of_two(L));
int j = 0;
for (int i = 0; i < L - 1; i++) {
if (i < j) {
swap(i, j);
}
int k = L >> 1;
while (j >= k) {
j -= k;
k >>= 1;
}
j += k;
}
}
static void G1(int L) {
assert(is_power_of_two(L));
if (L < 4) {
return;
}
int j = 0;
int N1 = L >> 1;
int N2 = N1 + 1;
int L2 = L >> 2;
for (int i = 0; i < L2 - 1; i++) {
if (i < j) {
int a = i << 1;
int b = j << 1;
swap(a, b);
swap(a + N2, b + N2);
swap(a + 1, b + N1);
swap(b + 1, a + N1);
} else if (i == j) {
int a = i << 1;
swap(a + 1, a + N1);
}
int k = L2 >> 1;
while (j >= k) {
j -= k;
k >>= 1;
}
j += k;
}
int a = (L2 - 1) << 1;
swap(a + 1, a + N1);
}
int main(int argc, char *argv[]) {
assert(1 < argc);
int L = atoi(argv[1]);
G(L);
putchar('\n');
G1(L);
}

Algorithm. How to find longest subsequence of integers in an array such that gcd of any two consecutive number in the sequence is greather than 1?

Given`en an array of integers. We have to find the length of the longest subsequence of integers such that gcd of any two consecutive elements in the sequence is greater than 1.
for ex: if array = [12, 8, 2, 3, 6, 9]
then one such subsequence can be = {12, 8, 2, 6, 9}
other one can be= {12, 3, 6, 9}
I tried to solve this problem by dynamic programming. Assume that maxCount is the array such that maxCount[i] will have the length of such longest subsequence
ending at index i.
`maxCount[0]=1 ;
for(i=1; i<N; i++)
{
max = 1 ;
for(j=i-1; j>=0; j--)
{
if(gcd(arr[i], arr[j]) > 1)
{
temp = maxCount[j] + 1 ;
if(temp > max)
max = temp ;
}
}
maxCount[i]=max;
}``
max = 0;
for(i=0; i<N; i++)
{
if(maxCount[i] > max)
max = maxCount[i] ;
}
cout<<max<<endl ;
`
But, this approach is getting timeout. As its time complexity is O(N^2). Can we improve the time complexity?
The condition "gcd is greater than 1" means that numbers have at least one common divisor. So, let dp[i] equals to the length of longest sequence finishing on a number divisible by i.
int n;
cin >> n;
const int MAX_NUM = 100 * 1000;
static int dp[MAX_NUM];
for(int i = 0; i < n; ++i)
{
int x;
cin >> x;
int cur = 1;
vector<int> d;
for(int i = 2; i * i <= x; ++i)
{
if(x % i == 0)
{
cur = max(cur, dp[i] + 1);
cur = max(cur, dp[x / i] + 1);
d.push_back(i);
d.push_back(x / i);
}
}
if(x > 1)
{
cur = max(cur, dp[x] + 1);
d.push_back(x);
}
for(int j : d)
{
dp[j] = cur;
}
}
cout << *max_element(dp, dp + MAX_NUM) << endl;
This solution has O(N * sqrt(MAX_NUM)) complexity. Actually you can calculate dp values only for prime numbers. To implement this you should be able to get prime factorization in less than O(N^0.5) time (this method, for example). That optimization should cast complexity to O(N * factorization + Nlog(N)). As memory optimization, you can replace dp array with map or unordered_map.
GCD takes log m time, where m is the maximum number in the array. Therefore, using a Segment Tree and binary search, one can reduce the time complexity to O(n log (m² * n)) (with O(n log m) preprocessing). This list details other data structures that can be used for RMQ-type queries and to reduce the complexity further.
Here is one possible implementation of this:
#include <bits/stdc++.h>
using namespace std;
struct SegTree {
using ftype = function<int(int, int)>;
vector<int> vec;
int l, og, dummy;
ftype f;
template<typename T> SegTree(const vector<T> &v, const T &x, const ftype &func) : og(v.size()), f(func), l(1), dummy(x) {
assert(og >= 1);
while (l < og) l *= 2;
vec = vector<int>(l*2);
for (int i = l; i < l+og; i++) vec[i] = v[i-l];
for (int i = l+og; i < 2*l; i++) vec[i] = dummy;
for (int i = l-1; i >= 1; i--) {
if (vec[2*i] == dummy && vec[2*i+1] == dummy) vec[i] = dummy;
else if (vec[2*i] == dummy) vec[i] = vec[2*i+1];
else if (vec[2*i+1] == dummy) vec[i] = vec[2*i];
else vec[i] = f(vec[2*i], vec[2*i+1]);
}
}
SegTree() {}
void valid(int x) {assert(x >= 0 && x < og);}
int get(int a, int b) {
valid(a); valid(b); assert(b >= a);
a += l; b += l;
int s = vec[a];
a++;
while (a <= b) {
if (a % 2 == 1) {
if (vec[a] != dummy) s = f(s, vec[a]);
a++;
}
if (b % 2 == 0) {
if (vec[b] != dummy) s = f(s, vec[b]);
b--;
}
a /= 2; b /= 2;
}
return s;
}
void add(int x, int c) {
valid(x);
x += l;
vec[x] += c;
for (x /= 2; x >= 1; x /= 2) {
if (vec[2*x] == dummy && vec[2*x+1] == dummy) vec[x] = dummy;
else if (vec[2*x] == dummy) vec[x] = vec[2*x+1];
else if (vec[2*x+1] == dummy) vec[x] = vec[2*x];
else vec[x] = f(vec[2*x], vec[2*x+1]);
}
}
void update(int x, int c) {add(x, c-vec[x+l]);}
};
// Constructor (where val is something that an element in the array is
// guaranteed to never reach):
// SegTree st(vec, val, func);
// finds longest subsequence where GCD is greater than 1
int longest(const vector<int> &vec) {
int l = vec.size();
SegTree st(vec, -1, [](int a, int b){return __gcd(a, b);});
// checks if a certain length is valid in O(n log (m² * n)) time
auto valid = [&](int n) -> bool {
for (int i = 0; i <= l-n; i++) {
if (st.get(i, i+n-1) != 1) {
return true;
}
}
return false;
};
int length = 0;
// do a "binary search" on the best possible length
for (int i = l; i >= 1; i /= 2) {
while (length+i <= l && valid(length+i)) {
length += i;
}
}
return length;
}

Resources