Quicksort infinite loop if there are repeating values - c++

I have a quicksort program that works great until I try to sort an array that has a repeating number. The program gets stuck in an infinite loop. I believe this is happening in the While(lower < upper) block of code.
void quickSort(int array[], int size){
if(size < 2) return;
int pivot, lower, upper, temp;
//Set the indeces for the first and last elements
lower = 0;
upper = size - 1;
//Select pivot element randomly
pivot = array[rand() % (size)];
while(lower < upper){
//Lower must be a number < than pivot and upper a number >= pivot
while(array[lower] < pivot){
lower++;
}
while(array[upper] > pivot){
upper--;
}
//Swap upper and lower
temp = array[lower];
array[lower] = array[upper];
array[upper] = temp;
}
//Repeat the past actions on the two partitions of the array recursively
quickSort(array, lower);
quickSort(&array[lower+1], size-lower-1);
}

EDIT: Code added.
From Wikipedia, the pseudo-code for in-place quicksort is as follows:
(Not saying that they should be trusted blindly)
function quicksort(array)
if length(array) > 1
pivot := select any element of array
left := first index of array
right := last index of array
while left ≤ right
while array[left] < pivot
left := left + 1
while array[right] > pivot
right := right - 1
if left ≤ right
swap array[left] with array[right]
left := left + 1
right := right - 1
quicksort(array from first index to right)
quicksort(array from left to last index)
So you see it is quite similar to your algorithm, with minor modifications.
while(lower <= upper){
Also you need to swap only if lower <= upper and then update the indices.
And your code differs in the recursive calls:
quicksort(array from first index to right) {array[0] to array[upper]}
quicksort(array from left to last index) {array[lower] to array[size-1]}
This is because now that it has exited the while loop, upper is less than lower.
Full working code:
#include <iostream>
#include <cstdlib>
using namespace std;
void quickSort(int array[], int size){
if(size < 2) return;
int pivot, lower, upper, temp;
//Set the indeces for the first and last elements
lower = 0;
upper = size - 1;
//Select pivot element randomly
pivot = array[rand() % (size)];
while(lower <= upper){
//Lower must be a number < than pivot and upper a number >= pivot
while(array[lower] < pivot){
lower++;
}
while(array[upper] > pivot){
upper--;
}
//Swap upper and lower
if ( lower <= upper ) {
temp = array[lower];
array[lower] = array[upper];
array[upper] = temp;
lower++;
upper--;
}
}
//Repeat the past actions on the two partitions of the array recursively
quickSort(array, upper+1);
quickSort(&array[lower], size-lower);
}
int main() {
// your code goes here
int myArray[] = { 10, 9, 8, 7, 7, 7, 7, 3, 2, 1};
quickSort( myArray, 10 );
for ( int i = 0; i < 10; i++ )
cout << myArray[i] << " ";
return 0;
}
Output:
1 2 3 7 7 7 7 8 9 10

Related

Why does the quick sort algorithm duration increase when the array has duplicate values?

I am trying to measure the duration for both Merge Sort and Quick Sort functions using std::chrono time calculations and using randomly generated arrays of integers within some range [A, B], the sizes of the arrays vary from 5000 to 100,000 integers.
The goal of my code is to prove that when the method of picking the (pivot) in quick sort is improved, the quick sort function ends up taking less time to process the array than merge sort, the way I pick the pivot is using the random index method to minimize the probability of having a complexity of (n^2), However in some cases which I will describe below, the quick sort ends up taking more time than merge sort and I would like to know why this occurs.
case 1:
The range of the numbers in the array is small which increases the probability of having duplicate numbers in the array.
case 2:
When I use a local IDE like clion, the quick sort function takes a lot more time than merge sort, however an online compiler like IDEONE.com gives similar results in both sorting algorithms (even when the range of the generated integers is small)
here are the results I got in the mentioned cases(the first row of numbers is merge sort results, the second row is quick sort results):
1-clion results narrow range of numbers (-100, 600)
2-clion results with a wide range of numbers (INT_MIN, INT_MAX)
3-IDEONE results with a narrow range of numbers (-100, 600)
4- IDEONE results with a wide range of numbers (INT_MIN, INT_MAX)
#include <bits/stdc++.h>
#include <chrono>
#include <random>
using namespace std;
mt19937 gen(chrono::steady_clock::now().time_since_epoch().count());
int* generateArray(int size)
{
int* arr = new int[size];
uniform_int_distribution<> distribution(INT_MIN, INT_MAX);
for (int i=0; i < size; ++i)
{
arr[i] = distribution(gen);
}
return arr;
}
void merge(int* leftArr, int nL, int* rightArr, int nR, int* mainArr)
{
int i=0, j=0, k=0;
while (i < nL && j < nR)
{
if (leftArr[i] < rightArr[j]) { mainArr[k++] = leftArr[i++]; }
else { mainArr[k++] = rightArr[j++]; }
}
while (i < nL){ mainArr[k++] = leftArr[i++]; }
while (j < nR){ mainArr[k++] = rightArr[j++]; }
}
void mergeSort (int* mainArray, int arrayLength)
{
if (arrayLength < 2) { return; }
int mid = arrayLength/2;
int* leftArray = new int[mid];
int* rightArray = new int[arrayLength - mid];
for (int i=0; i<mid; ++i) {leftArray[i] = mainArray[i];}
for (int i = mid; i<arrayLength; ++i) {rightArray[i - mid] = mainArray[i];}
mergeSort(leftArray, mid);
mergeSort(rightArray, arrayLength-mid);
merge(leftArray, mid, rightArray, arrayLength-mid, mainArray);
delete[] leftArray;
delete[] rightArray;
}
int partition (int* arr, int left, int right)
{
uniform_int_distribution<> distribution(left, right);
int idx = distribution(gen);
swap(arr[right], arr[idx]);
int pivot = arr[right];
int partitionIndex = left;
for (int i = left; i < right; ++i)
{
if (arr[i] <= pivot)
{
swap(arr[i], arr[partitionIndex]);
partitionIndex++;
}
}
swap(arr[right], arr[partitionIndex]);
return partitionIndex;
}
void quickSort (int* arr, int left, int right)
{
if(left < right)
{
int partitionIndex = partition(arr, left, right);
quickSort(arr, left, partitionIndex-1);
quickSort(arr, partitionIndex+1, right);
}
}
int main()
{
vector <long long> mergeDuration;
vector <long long> quickDuration;
for (int i = 5000; i<= 100000; i += 5000)
{
int* arr = generateArray(i);
auto startTime = chrono::high_resolution_clock::now();
quickSort(arr, 0, i - 1);
auto endTime = chrono::high_resolution_clock::now();
long long duration = chrono::duration_cast<chrono::milliseconds>(endTime - startTime).count();
quickDuration.push_back(duration);
delete[] arr;
}
for (int i = 5000; i <= 100000; i += 5000 )
{
int* arr = generateArray(i);
auto startTime = chrono::high_resolution_clock::now();
mergeSort(arr, i);
auto endTime = chrono::high_resolution_clock::now();
long long duration = chrono::duration_cast<chrono::milliseconds>(endTime - startTime).count();
mergeDuration.push_back(duration);
delete[] arr;
}
for (int i = 0; i<mergeDuration.size(); ++i)
{
cout << mergeDuration[i] << " ";
}
cout << endl;
for (int i = 0; i<quickDuration.size(); ++i)
{
cout << quickDuration[i] << " ";
}
}
Quicksort is known to exhibit poor performance when the input set contains lots of duplicates. The solution is to use three-way partitioning as described on Wikipedia:
Repeated elements
With a partitioning algorithm such as the ones described above (even
with one that chooses good pivot values), quicksort exhibits poor
performance for inputs that contain many repeated elements. The
problem is clearly apparent when all the input elements are equal: at
each recursion, the left partition is empty (no input values are less
than the pivot), and the right partition has only decreased by one
element (the pivot is removed). Consequently, the algorithm takes
quadratic time to sort an array of equal values.
To solve this problem (sometimes called the Dutch national flag
problem), an alternative linear-time partition routine can be used
that separates the values into three groups: values less than the
pivot, values equal to the pivot, and values greater than the pivot.
... The values
equal to the pivot are already sorted, so only the less-than and
greater-than partitions need to be recursively sorted. In pseudocode,
the quicksort algorithm becomes
algorithm quicksort(A, lo, hi) is
if lo < hi then
p := pivot(A, lo, hi)
left, right := partition(A, p, lo, hi) // note: multiple return values
quicksort(A, lo, left - 1)
quicksort(A, right + 1, hi)
The partition algorithm returns indices to the first ('leftmost') and
to the last ('rightmost') item of the middle partition. Every item of
the partition is equal to p and is therefore sorted. Consequently, the
items of the partition need not be included in the recursive calls to
quicksort.
The following modified quickSort gives much better results:
pair<int,int> partition(int* arr, int left, int right)
{
int idx = left + (right - left) / 2;
int pivot = arr[idx]; // to be improved to median-of-three
int i = left, j = left, b = right - 1;
while (j <= b) {
auto x = arr[j];
if (x < pivot) {
swap(arr[i], arr[j]);
i++;
j++;
} else if (x > pivot) {
swap(arr[j], arr[b]);
b--;
} else {
j++;
}
}
return { i, j };
}
void quickSort(int* arr, int left, int right)
{
if (left < right)
{
pair<int, int> part = partition(arr, left, right);
quickSort(arr, left, part.first);
quickSort(arr, part.second, right);
}
}
Output:
0 1 2 3 4 5 6 7 8 9 11 11 12 13 14 15 16 19 18 19
0 0 0 1 0 1 1 1 1 1 2 3 2 2 2 2 3 3 3 3
0 1 2 3 4 5 6 6 8 8 9 12 11 12 13 14 16 17 18 19
0 0 1 1 1 2 3 3 3 4 4 4 5 6 5 6 7 7 8 8
So, the run with lots of duplicates is now much faster.
Why does the quick sort algorithm duration increase when the array has duplicate values?
This is only true if using Lomuto type partition scheme, where duplicate values cause the splitting to get worse.
If using Hoare partition scheme, the algorithm duration generally decreases when the array has duplicate values, because the splitting gets closer to the ideal case of splitting exactly in half and the improved splitting compensates for the extra swaps on a typical system with memory cache.

Confused with Two different implementation of Heap

Function 1
void min_heapify(int arr[],int n, int i){
int j, temp;
temp = arr[i];
j = 2 * i;
while (j <= n)
{
if (j < n && arr[j+1] < arr[j])
j = j + 1;
if (temp < arr[j])
break;
else if (temp >= arr[j])
{
arr[j/2] = arr[j];
j = 2 * j;
}
}
arr[j/2] = temp;
}
Function 2
void max_heapify(int arr[], int n, int i)
{
int largest = i; // Initialize largest as root
int l = 2*i + 1; // left = 2*i + 1
int r = 2*i + 2; // right = 2*i + 2
// If left child is larger than root
if (l < n && arr[l] < arr[largest])
largest = l;
// If right child is larger than largest so far
if (r < n && arr[r] < arr[largest])
largest = r;
// If largest is not root
if (largest != i)
{
swap(arr[i], arr[largest]);
// Recursively heapify the affected sub-tree
heapify(arr, n, largest);
}
}
Problem Details
Here the heapification work the same way to make a min_heap but the problem is, I used heap in this below problem to solve it but unfortunately function 2 which I implemented by watching MIT lecture didn't work for this problem, after looking some time in the web I found the 1st function which worked seamlessly for this problem. I'm just confused are not they the same function? ------
Problem
Yup!! The problem name reflects your task; just add a set of numbers. But you may feel yourselves condescended, to write a C/C++ program just to add a set of numbers. Such a problem will simply question your erudition. So, let’s add some flavor of ingenuity to it.
Addition operation requires cost now, and the cost is the summation of those two to be added. So, to add 1 and 10, you need a cost of 11. If you want to add 1, 2 and 3. There are several ways –
1 + 2 = 3, cost = 3
1 + 3 = 4, cost = 4
2 + 3 = 5, cost = 5
3 + 3 = 6, cost = 6
2 + 4 = 6, cost = 6
1 + 5 = 6, cost = 6
Total = 9
Total = 10
Total = 11
I hope you have understood already your mission, to add a set of integers so that the cost is minimal.
Input
Each test case will start with a positive number, N (2 ≤ N ≤ 5000) followed by N positive integers (all are less than 100000). Input is terminated by a case where the value of N is zero. This case should not be processed.
Output
For each case print the minimum total cost of addition in a single line.
SampleInput
3
1 2 3
4
1 2 3 4
0
SampleOutput
9
19
There is a problem with the swap function in function2.
C is call by value, so
swap(arr[i], arr[largest]);
cannot swap values in the array.
A swap function needs the addresses of the values to swap:
swap(int *v1, int *v2) {
int tmp = *v1;
*v1 = *v2;
*v2 = tmp;
}
And the call would be:
swap(&arr[i], &arr[largest]);
Ok I find out the solution there was a mistake in the condition check, in the if condition where we checking that if (left <= n) this was previously (left < n) this why it was not working for that problem. ok thank you.
void min_heapify(int arr[],int n, int i){
int lowest = i; // Initialize lowest as root
int left = 2*i ;
int right = 2*i + 1;
// If child is lower than root
if(left <= n && arr[left] < arr[lowest]){
lowest = left;
}
// If right child is lower than lowest
if(right <= n && arr[right] < arr[lowest]){
lowest = right;
}
// If lowest is not root
if(lowest != i){ // also break condition
swap(arr[i], arr[lowest]);
//Recursively heapify
min_heapify(arr, n, lowest);
}

Partition algorithm with two loops c++

I was given pseudo code for a partition algorithm but I'm not really sure how to implement it.
Below is the pseudo code and my implementation. Please let me know if this is correct/explain what it's doing. Right now I have a partial understanding of it but it is not correct.
Input: 0.963, 0.003, 0.0251, 0.353, 0.667, 0.838, 0.335, 0.915, 0.796, 0.833, 0.345, 0.871, 0.089, 0.888, 0.701, 0.735
Expected: 0.003 0.0251 0.089 0.335 0.345 0.353 0.667 0.701 0.735 0.796 0.833 0.838 0.871 0.888 0.915 0.963
Actual: 0.003000 0.025100 0.353000 0.667000 0.838000 0.335000 0.915000 0.796000 0.833000 0.345000 0.871000 0.089000 0.888000 0.7 01000 0.735000 0.963000
int partition_data( float xdata[], int ndata, float xmiddle ) {
int left;
int right;
int j,i;
float temp;
for(i = 0; i < xmiddle; i ++){
if(left == right){
left += 1;
}
else{
for( j = ndata - 1; j >= xmiddle; j--){
if(left == right){
right -= 1;
}
else{
temp = xdata[j];
xdata[j] = xdata[i];
xdata[i] = temp;
right -= 1;
if(left == right){
left += 1;
break;
}
}
}
}
}
}
As others already said, both here and at Code Review, the pseudocode is quite non-standard, and hard to read (although it's not true it is mis-indented).
However, if you're not interested in improving it, but just want to implement it 'as is', here it is, word-by-word translated into C language:
int Partition(float X[], int ndata, float xmiddle)
{
int left = 0;
int right = ndata - 1;
while(1) { // 'left' loop
if(X[left] < xmiddle)
{
if(left == right)
return left + 1;
left ++;
}
else
while(1) { // 'right' loop
if(X[right] >= xmiddle)
{
if(left == right)
return left;
right --;
}
else
{
float tmp = X[left]; // these three lines
X[left] = X[right]; // swap the two values
X[right] = tmp; // X[left] and X[right]
right --;
if(left == right)
return left + 1;
left ++;
break; // exit the 'right' loop
}
} // end of 'right' loop
} // end of 'left' loop
} // end of Parition
The code is actually C, in C++ you might make it a function template with a type parameter instead of explicit float, so that the function may partition arrays of different types (as long as operators < and >= are defined). You might also use std::swap for efficient swapping data and dropping the explicit tmp variable.
Maybe the assignment was to implement a full quicksort?
Quicksort with conventional pre-increment / pre-decrement Hoare partition scheme:
int Partition(float x[], int lo, int hi)
{
float xmiddle = x[(lo+hi)/2];
int left = lo - 1;
int right = hi + 1;
float tmp;
while (1){
while (x[++left] < xmiddle);
while (x[--right] > xmiddle);
if(left >= right)
break;
tmp = x[left];
x[left] = x[right];
x[right] = tmp;
}
return right;
}
void QuickSort(float x[], int lo, int hi){
int pivot;
if (lo < hi){
pivot = Partition(x, lo, hi);
QuickSort(x, lo, pivot);
QuickSort(x, pivot+1, hi);
}
}
One issue with quicksort is that a minor bug in the partition scheme may work for most data patterns and only fail for specific data patterns, making it difficult to determine if a quicksort is really bug free.
Quicksort using modified version from the psuedo code above. This works for the example data, but I'm not sure it's bug free. Partition should return an index that points to a value == xmiddle:
int Partition(float X[], int lo, int hi)
{
int left = lo;
int right = hi;
float xmiddle = X[(lo+hi)/2];
float tmp;
while(1) {
while(X[left] < xmiddle){
if(left == right)
return left+1;
left++;
}
while(X[right] >= xmiddle){
if(left == right)
return left;
right--;
}
tmp = X[left];
X[left] = X[right];
X[right] = tmp;
right --;
if(left == right)
return left + 1;
left ++;
}
}
void QuickSort(float x[], int lo, int hi){
int pivot;
if (lo < hi){
pivot = Partition(x, lo, hi);
QuickSort(x, lo, pivot);
QuickSort(x, pivot+1, hi);
}
}
Explanation of the algorithm
The routine re-arranges data so that items less than the supplied xmiddle value remain on the left side of the array (at smaller indices) and items greater than xmiddle are put to the right part (at bigger indices). The return value is a length of the left part.
Variables left and right scan the array from both ends to find items which should be swapped.
The 'left loop' (starting at line 4) increments the left index until it finds an item greater than or equal to xmiddle (line 5) or until it reaches the right position (line 6). As right is initially the last index of the array (and later it can only be decremented), the loop must eventually stop incrementing left.
If the left index meets right then all items below and at left are less than xmiddle, so left+1 is returned as a length of the left subarray. Note that if xmiddle is chosen bigger than all items of the array, the return value is equal to the array's length (ndata).
If left stops at an item greater than or equal to xmiddle, then the 'otherwise' branch at line 9 executes and the 'right loop' starts. Similar to the left loop it decrements right, stepping over all items greater than or equal to xmiddle until the right index meets left. If the two indices meet (line 11), then all items below them are less than, and all items above and at them are greater than or equal to xmiddle; then left is returned as the length of the left part.
On the other hand, if the right index finds an item less than xmiddle (i.e. not satisfying the condition at line 10), then it needs to be swapped with the item at index left, which is greater than or equal to xmiddle (it didn't satisfy the condition at line 5). Then the 'otherwise' branch at line 13 is executed.
The branch swaps the two values (line 14), so both left and right part become one item longer. To reflect that, the right index is decremented (line 15) and then compared to left. If they got equal (line 16), i.e. we swapped adjacent items, the partitioning is done, so left+1 is returned as a length of the left part. Otherwise left gets incremented (line 17) and we exit the 'right loop' (line 18) and proceed to the closing brace of the 'left loop' in line 20, which brings the execution back to line 4.
Then again left gets incremented (that is the left part grows) until it meets the right part or finds an item to be swapped. And so on...
The loops invariants are:
left ≤ right
X[i] < xmiddle for 0 ≤ i < left
X[i] ≥ xmiddle for right < i < ndata
and the un-tested part of the array gets reduced (the difference right - left is decremented) at least by 1 in every iteration of a loop.

Insertion Sort algorithm by using binary search error

I run the following code which is Insertion Sort algorithm that use binary search to find the right position of the item being inserted instead of linear search but there are two numbers in the results not sorted correctly!
#include <iostream>
using namespace std;
void insertion_sort (int a[], int n /* the size of array */)
{
int i, temp,j;
for (i = 1; i < n; i++)
{
/* Assume items before a[i] are sorted. */
/* Pick an number */
temp = a[i];
/* Do binary search to find out the
point where b is to be inserted. */
int low = 0, high = i - 1, k;
while (high-low>1)
{
int mid = (high + low) / 2;
if (temp <= a[mid])
high = mid;
else
low = mid;
}
/* Shift items between high and i by 1 */
for (k = i; k > high; k--)
a[k] = a[k - 1];
a[high] = temp;
}
}
int main()
{
int A[15]={9,5,98,2,5,4,66,12,8,54,0,11,99,55,13};
insertion_sort(A,15);
for (int i=0; i<15; i++)
cout<<A[i]<<endl;
system("pause");
return 0;
}
Output:
Why?
#include <iostream>
using namespace std;
void insertion_sort (int a[], int n /* the size of array */)
{
int i, temp,j;
for (i = 1; i < n; i++)
{
/* Assume items before a[i] are sorted. */
/* Pick an number */
temp = a[i];
/* Do binary search to find out the
point where b is to be inserted. */
The high bound should be above the range and exclusive of the search, because you may need to insert at the end, i.e. do nothing.
// int low = 0, high = i - 1, k;
int low = 0, high = i, k;
Here the condition should be low < high, not low + 1 < high
// while (high-low>1)
while (low < high)
{
int mid = (high + low) / 2;
if (temp <= a[mid])
high = mid;
else
Once you have a[mid] strictly greater than temp, the lowest possible position to insert is mid + 1.
// low = mid;
low = mid + 1
}
/* Shift items between high and i by 1 */
for (k = i; k > high; k--)
a[k] = a[k - 1];
a[high] = temp;
}
}
int main()
{
int A[15]={9,5,98,2,5,4,66,12,8,54,0,11,99,55,13};
insertion_sort(A,15);
for (int i=0; i<15; i++)
cout<<A[i]<<endl;
system("pause");
return 0;
}
A few things to be noticed here:
Binary search does not give you anything, as you need to shift all elements to make space anyway. So it actually increases the overall cost of your algorithm (though not asymptotically).
As this is C++ there is no need to declare k anywhere before the for loop in which it is used (just use for(int k; ...)).
Analyse your algorithm's beginning: i=0 -> low = high = 0. So your while loop does not execute. Then, no matter if the element should be moved or not, your for (k) loop swaps elements 0 and 1. This is error number 1.
Second iteration of i: the while loop does not execute once again, as low = 0 and high = 1, and once again no matter what you swap at least elements 1 and 2. Error number 2.
Now notice that every next iteration will, no matter what, move the element which was initially at index 0 (in your test code it is =9) further and further, to the last index.
So you may see just after checking firts two iterations of for(i) loop that the assumption that elements before a[i] are sorted is wrong, and therefore the algorithm is wrong as well.
Easiest possible fix: initialize low and high as int low = -1, high = i;. What you wanted to do was to find indices low and high such that all elements from 0 to low are < a[i] and all elements from high to i-1 are ≥ a[i]. Your initialization didn't work since it didn't capture the corner cases when all elements a[0], ..., a[i-1] are greater than a[i] and the corner case when all these elements were less than a[i].

Searching in a sorted and rotated array

While preparing for an interview I stumbled upon this interesting question:
You've been given an array that is sorted and then rotated.
For example:
Let arr = [1,2,3,4,5], which is sorted
Rotate it twice to the right to give [4,5,1,2,3].
Now how best can one search in this sorted + rotated array?
One can unrotate the array and then do a binary search. But that is no better than doing a linear search in the input array, as both are worst-case O(N).
Please provide some pointers. I've googled a lot on special algorithms for this but couldn't find any.
I understand C and C++.
This can be done in O(logN) using a slightly modified binary search.
The interesting property of a sorted + rotated array is that when you divide it into two halves, atleast one of the two halves will always be sorted.
Let input array arr = [4,5,6,7,8,9,1,2,3]
number of elements = 9
mid index = (0+8)/2 = 4
[4,5,6,7,8,9,1,2,3]
^
left mid right
as seem right sub-array is not sorted while left sub-array is sorted.
If mid happens to be the point of rotation them both left and right sub-arrays will be sorted.
[6,7,8,9,1,2,3,4,5]
^
But in any case one half(sub-array) must be sorted.
We can easily know which half is sorted by comparing start and end element of each half.
Once we find which half is sorted we can see if the key is present in that half - simple comparison with the extremes.
If the key is present in that half we recursively call the function on that half
else we recursively call our search on the other half.
We are discarding one half of the array in each call which makes this algorithm O(logN).
Pseudo code:
function search( arr[], key, low, high)
mid = (low + high) / 2
// key not present
if(low > high)
return -1
// key found
if(arr[mid] == key)
return mid
// if left half is sorted.
if(arr[low] <= arr[mid])
// if key is present in left half.
if (arr[low] <= key && arr[mid] >= key)
return search(arr,key,low,mid-1)
// if key is not present in left half..search right half.
else
return search(arr,key,mid+1,high)
end-if
// if right half is sorted.
else
// if key is present in right half.
if(arr[mid] <= key && arr[high] >= key)
return search(arr,key,mid+1,high)
// if key is not present in right half..search in left half.
else
return search(arr,key,low,mid-1)
end-if
end-if
end-function
The key here is that one sub-array will always be sorted, using which we can discard one half of the array.
The accepted answer has a bug when there are duplicate elements in the array. For example, arr = {2,3,2,2,2} and 3 is what we are looking for. Then the program in the accepted answer will return -1 instead of 1.
This interview question is discussed in detail in the book 'Cracking the Coding Interview'. The condition of duplicate elements is specially discussed in that book. Since the op said in a comment that array elements can be anything, I am giving my solution as pseudo code in below:
function search( arr[], key, low, high)
if(low > high)
return -1
mid = (low + high) / 2
if(arr[mid] == key)
return mid
// if the left half is sorted.
if(arr[low] < arr[mid]) {
// if key is in the left half
if (arr[low] <= key && key <= arr[mid])
// search the left half
return search(arr,key,low,mid-1)
else
// search the right half
return search(arr,key,mid+1,high)
end-if
// if the right half is sorted.
else if(arr[mid] < arr[high])
// if the key is in the right half.
if(arr[mid] <= key && arr[high] >= key)
return search(arr,key,mid+1,high)
else
return search(arr,key,low,mid-1)
end-if
else if(arr[mid] == arr[low])
if(arr[mid] != arr[high])
// Then elements in left half must be identical.
// Because if not, then it's impossible to have either arr[mid] < arr[high] or arr[mid] > arr[high]
// Then we only need to search the right half.
return search(arr, mid+1, high, key)
else
// arr[low] = arr[mid] = arr[high], we have to search both halves.
result = search(arr, low, mid-1, key)
if(result == -1)
return search(arr, mid+1, high, key)
else
return result
end-if
end-function
You can do 2 binary searches: first to find the index i such that arr[i] > arr[i+1].
Apparently, (arr\[1], arr[2], ..., arr[i]) and (arr[i+1], arr[i+2], ..., arr[n]) are both sorted arrays.
Then if arr[1] <= x <= arr[i], you do binary search at the first array, else at the second.
The complexity O(logN)
EDIT:
the code.
My first attempt would be to find using binary search the number of rotations applied - this can be done by finding the index n where a[n] > a[n + 1] using the usual binary search mechanism.
Then do a regular binary search while rotating all indexes per shift found.
int rotated_binary_search(int A[], int N, int key) {
int L = 0;
int R = N - 1;
while (L <= R) {
// Avoid overflow, same as M=(L+R)/2
int M = L + ((R - L) / 2);
if (A[M] == key) return M;
// the bottom half is sorted
if (A[L] <= A[M]) {
if (A[L] <= key && key < A[M])
R = M - 1;
else
L = M + 1;
}
// the upper half is sorted
else {
if (A[M] < key && key <= A[R])
L = M + 1;
else
R = M - 1;
}
}
return -1;
}
If you know that the array has been rotated s to the right, you can simply do a binary search shifted s to the right. This is O(lg N)
By this, I mean, initialize the left limit to s and the right to (s-1) mod N, and do a binary search between these, taking a bit of care to work in the correct area.
If you don't know how much the array has been rotated by, you can determine how big the rotation is using a binary search, which is O(lg N), then do a shifted binary search, O(lg N), a grand total of O(lg N) still.
Reply for the above mentioned post "This interview question is discussed in detail in the book 'Cracking the Coding Interview'. The condition of duplicate elements is specially discussed in that book. Since the op said in comment that array elements can be anything, I am giving my solution as pseudo code in below:"
Your solution is O(n) !! (The last if condition where you check both halves of the array for a single condition makes it a sol of linear time complexity )
I am better off doing a linear search than getting stuck in a maze of bugs and segmentation faults during a coding round.
I dont think there is a better solution than O(n) for a search in a rotated sorted array (with duplicates)
If you know how (far) it was rotated you can still do a binary search.
The trick is that you get two levels of indices: you do the b.s. in a virtual 0..n-1 range and then un-rotate them when actually looking up a value.
You don't need to rotate the array first. You can use binary search on the rotated array (with some modifications).
Let N be the number you are searching for:
Read the first number (arr[start]) and the number in the middle of the array (arr[end]):
if arr[start] > arr[end] --> the first half is not sorted but the second half is sorted:
if arr[end] > N --> the number is in index: (middle + N - arr[end])
if N repeat the search on the first part of the array (see end to be the middle of the first half of the array etc.)
(the same if the first part is sorted but the second one isn't)
public class PivotedArray {
//56784321 first increasing than decreasing
public static void main(String[] args) {
// TODO Auto-generated method stub
int [] data ={5,6,7,8,4,3,2,1,0,-1,-2};
System.out.println(findNumber(data, 0, data.length-1,-2));
}
static int findNumber(int data[], int start, int end,int numberToFind){
if(data[start] == numberToFind){
return start;
}
if(data[end] == numberToFind){
return end;
}
int mid = (start+end)/2;
if(data[mid] == numberToFind){
return mid;
}
int idx = -1;
int midData = data[mid];
if(numberToFind < midData){
if(midData > data[mid+1]){
idx=findNumber(data, mid+1, end, numberToFind);
}else{
idx = findNumber(data, start, mid-1, numberToFind);
}
}
if(numberToFind > midData){
if(midData > data[mid+1]){
idx = findNumber(data, start, mid-1, numberToFind);
}else{
idx=findNumber(data, mid+1, end, numberToFind);
}
}
return idx;
}
}
short mod_binary_search( int m, int *arr, short start, short end)
{
if(start <= end)
{
short mid = (start+end)/2;
if( m == arr[mid])
return mid;
else
{
//First half is sorted
if(arr[start] <= arr[mid])
{
if(m < arr[mid] && m >= arr[start])
return mod_binary_search( m, arr, start, mid-1);
return mod_binary_search( m, arr, mid+1, end);
}
//Second half is sorted
else
{
if(m > arr[mid] && m < arr[start])
return mod_binary_search( m, arr, mid+1, end);
return mod_binary_search( m, arr, start, mid-1);
}
}
}
return -1;
}
First, you need to find the shift constant, k.
This can be done in O(lgN) time.
From the constant shift k, you can easily find the element you're looking for using
a binary search with the constant k. The augmented binary search also takes O(lgN) time
The total run time is O(lgN + lgN) = O(lgN)
To find the constant shift, k. You just have to look for the minimum value in the array. The index of the minimum value of the array tells you the constant shift.
Consider the sorted array
[1,2,3,4,5].
The possible shifts are:
[1,2,3,4,5] // k = 0
[5,1,2,3,4] // k = 1
[4,5,1,2,3] // k = 2
[3,4,5,1,2] // k = 3
[2,3,4,5,1] // k = 4
[1,2,3,4,5] // k = 5%5 = 0
To do any algorithm in O(lgN) time, the key is to always find ways to divide the problem by half.
Once doing so, the rest of the implementation details is easy
Below is the code in C++ for the algorithm
// This implementation takes O(logN) time
// This function returns the amount of shift of the sorted array, which is
// equivalent to the index of the minimum element of the shifted sorted array.
#include <vector>
#include <iostream>
using namespace std;
int binarySearchFindK(vector<int>& nums, int begin, int end)
{
int mid = ((end + begin)/2);
// Base cases
if((mid > begin && nums[mid] < nums[mid-1]) || (mid == begin && nums[mid] <= nums[end]))
return mid;
// General case
if (nums[mid] > nums[end])
{
begin = mid+1;
return binarySearchFindK(nums, begin, end);
}
else
{
end = mid -1;
return binarySearchFindK(nums, begin, end);
}
}
int getPivot(vector<int>& nums)
{
if( nums.size() == 0) return -1;
int result = binarySearchFindK(nums, 0, nums.size()-1);
return result;
}
// Once you execute the above, you will know the shift k,
// you can easily search for the element you need implementing the bottom
int binarySearchSearch(vector<int>& nums, int begin, int end, int target, int pivot)
{
if (begin > end) return -1;
int mid = (begin+end)/2;
int n = nums.size();
if (n <= 0) return -1;
while(begin <= end)
{
mid = (begin+end)/2;
int midFix = (mid+pivot) % n;
if(nums[midFix] == target)
{
return midFix;
}
else if (nums[midFix] < target)
{
begin = mid+1;
}
else
{
end = mid - 1;
}
}
return -1;
}
int search(vector<int>& nums, int target) {
int pivot = getPivot(nums);
int begin = 0;
int end = nums.size() - 1;
int result = binarySearchSearch(nums, begin, end, target, pivot);
return result;
}
Hope this helps!=)
Soon Chee Loong,
University of Toronto
For a rotated array with duplicates, if one needs to find the first occurrence of an element, one can use the procedure below (Java code):
public int mBinarySearch(int[] array, int low, int high, int key)
{
if (low > high)
return -1; //key not present
int mid = (low + high)/2;
if (array[mid] == key)
if (mid > 0 && array[mid-1] != key)
return mid;
if (array[low] <= array[mid]) //left half is sorted
{
if (array[low] <= key && array[mid] >= key)
return mBinarySearch(array, low, mid-1, key);
else //search right half
return mBinarySearch(array, mid+1, high, key);
}
else //right half is sorted
{
if (array[mid] <= key && array[high] >= key)
return mBinarySearch(array, mid+1, high, key);
else
return mBinarySearch(array, low, mid-1, key);
}
}
This is an improvement to codaddict's procedure above. Notice the additional if condition as below:
if (mid > 0 && array[mid-1] != key)
There is a simple idea to solve this problem in O(logN) complexity with binary search.
The idea is,
If the middle element is greater than the left element, then the left part is sorted. Otherwise, the right part is sorted.
Once the sorted part is determined, all you need is to check if the value falls under that sorted part or not. If not, you can divide the unsorted part and find the sorted part from that (the unsorted part) and continue binary search.
For example, consider the image below. An array can be left rotated or right rotated.
Below image shows the relation of the mid element compared with the left most one and how this relates to which part of the array is purely sorted.
If you see the image, you find that the mid element is >= the left element and in that case, the left part is purely sorted.
An array can be left rotated by number of times, like once, twice, thrice and so on. Below image shows that for each rotation, the property of if mid >= left, left part is sorted still prevails.
More explanation with images can be found in below link. (Disclaimer: I am associated with this blog)
https://foolishhungry.com/search-in-rotated-sorted-array/.
Hope this will be helpful.
Happy coding! :)
Here is a simple (time,space)efficient non-recursive O(log n) python solution that doesn't modify the original array. Chops down the rotated array in half until I only have two indices to check and returns the correct answer if one index matches.
def findInRotatedArray(array, num):
lo,hi = 0, len(array)-1
ix = None
while True:
if hi - lo <= 1:#Im down to two indices to check by now
if (array[hi] == num): ix = hi
elif (array[lo] == num): ix = lo
else: ix = None
break
mid = lo + (hi - lo)/2
print lo, mid, hi
#If top half is sorted and number is in between
if array[hi] >= array[mid] and num >= array[mid] and num <= array[hi]:
lo = mid
#If bottom half is sorted and number is in between
elif array[mid] >= array[lo] and num >= array[lo] and num <= array[mid]:
hi = mid
#If top half is rotated I know I need to keep cutting the array down
elif array[hi] <= array[mid]:
lo = mid
#If bottom half is rotated I know I need to keep cutting down
elif array[mid] <= array[lo]:
hi = mid
print "Index", ix
Try this solution
bool search(int *a, int length, int key)
{
int pivot( length / 2 ), lewy(0), prawy(length);
if (key > a[length - 1] || key < a[0]) return false;
while (lewy <= prawy){
if (key == a[pivot]) return true;
if (key > a[pivot]){
lewy = pivot;
pivot += (prawy - lewy) / 2 ? (prawy - lewy) / 2:1;}
else{
prawy = pivot;
pivot -= (prawy - lewy) / 2 ? (prawy - lewy) / 2:1;}}
return false;
}
This code in C++ should work for all cases, Although It works with duplicates, please let me know if there's bug in this code.
#include "bits/stdc++.h"
using namespace std;
int searchOnRotated(vector<int> &arr, int low, int high, int k) {
if(low > high)
return -1;
if(arr[low] <= arr[high]) {
int p = lower_bound(arr.begin()+low, arr.begin()+high, k) - arr.begin();
if(p == (low-high)+1)
return -1;
else
return p;
}
int mid = (low+high)/2;
if(arr[low] <= arr[mid]) {
if(k <= arr[mid] && k >= arr[low])
return searchOnRotated(arr, low, mid, k);
else
return searchOnRotated(arr, mid+1, high, k);
}
else {
if(k <= arr[high] && k >= arr[mid+1])
return searchOnRotated(arr, mid+1, high, k);
else
return searchOnRotated(arr, low, mid, k);
}
}
int main() {
int n, k; cin >> n >> k;
vector<int> arr(n);
for(int i=0; i<n; i++) cin >> arr[i];
int p = searchOnRotated(arr, 0, n-1, k);
cout<<p<<"\n";
return 0;
}
In Javascript
var search = function(nums, target,low,high) {
low= (low || low === 0) ? low : 0;
high= (high || high == 0) ? high : nums.length -1;
if(low > high)
return -1;
let mid = Math.ceil((low + high) / 2);
if(nums[mid] == target)
return mid;
if(nums[low] < nums[mid]) {
// if key is in the left half
if (nums[low] <= target && target <= nums[mid])
// search the left half
return search(nums,target,low,mid-1);
else
// search the right half
return search(nums,target,mid+1,high);
} else {
// if the key is in the right half.
if(nums[mid] <= target && nums[high] >= target)
return search(nums,target,mid+1,high)
else
return search(nums,target,low,mid-1)
}
};
Input: nums = [4,5,6,7,0,1,2], target = 0
Output: 4
import java.util.*;
class Main{
public static void main(String args[]){
Scanner sc = new Scanner(System.in);
int n=sc.nextInt();
int arr[]=new int[n];
int max=Integer.MIN_VALUE;
int min=Integer.MAX_VALUE;
int min_index=0,max_index=n;
for(int i=0;i<n;i++){
arr[i]=sc.nextInt();
if(arr[i]>max){
max=arr[i];
max_index=i;
}
if(arr[i]<min){
min=arr[i];
min_index=i;
}
}
int element=sc.nextInt();
int index;
if(element>arr[n-1]){
index=Arrays.binarySearch(arr,0,max_index+1,element);
}
else {
index=Arrays.binarySearch(arr,min_index,n,element);
}
if(index>=0){
System.out.println(index);
}
else{
System.out.println(-1);
}
}
}
Here are my two cents:
If the array does not contain duplicates, one can find the solution in O(log(n)). As many people have shown it the case, a tweaked version of binary search can be used to find the target element.
However, if the array contains duplicates, I think there is no way to find the target element in O(log(n)). Here is an example shows why I think O(log(n)) is not possible. Consider the two arrays below:
a = [2,.....................2...........3,6,2......2]
b = [2.........3,6,2........2......................2]
All the dots are filled with the number 2. You can see that both arrays are sorted and rotated. If one wants to consider binary search, then they have to cut the search domain by half every iteration -- this is how we get O(log(n)). Let us assume we are searching for the number 3. In the frist case, we can see it hiding in the right side of the array, and on the second case it is hiding in the second side of the array. Here is what we know about the array at this stage:
left = 0
right = length - 1;
mid = left + (right - left) / 2;
arr[mid] = 2;
arr[left] = 2;
arr[right] = 2;
target = 3;
This is all the information we have. We can clearly see it is not enough to make a decision to exclude one half of the array. As a result of that, the only way is to do linear search. I am not saying we can't optimize that O(n) time, all I am saying is that we can't do O(log(n)).
There is something i don't like about binary search because of mid, mid-1 etc that's why i always use binary stride/jump search
How to use it on a rotated array?
use twice(once find shift and then use a .at() to find the shifted index -> original index)
Or compare the first element, if it is less than first element, it has to be near the end
do a backwards jump search from end, stop if any pivot tyoe leement is found
if it is > start element just do a normal jump search :)
Implemented using C#
public class Solution {
public int Search(int[] nums, int target) {
if (nums.Length == 0) return -1;
int low = 0;
int high = nums.Length - 1;
while (low <= high)
{
int mid = (low + high) / 2;
if (nums[mid] == target) return mid;
if (nums[low] <= nums[mid]) // 3 4 5 6 0 1 2
{
if (target >= nums[low] && target <= nums[mid])
high = mid;
else
low = mid + 1;
}
else // 5 6 0 1 2 3 4
{
if (target >= nums[mid] && target <= nums[high])
low= mid;
else
high = mid - 1;
}
}
return -1;
}
}
Search An Element In A Sorted And Rotated Array In Java
package yourPackageNames;
public class YourClassName {
public static void main(String[] args) {
int[] arr = {3, 4, 5, 1, 2};
// int arr[]={16,19,21,25,3,5,8,10};
int key = 1;
searchElementAnElementInRotatedAndSortedArray(arr, key);
}
public static void searchElementAnElementInRotatedAndSortedArray(int[] arr, int key) {
int mid = arr.length / 2;
int pivotIndex = 0;
int keyIndex = -1;
boolean keyIndexFound = false;
boolean pivotFound = false;
for (int rightSide = mid; rightSide < arr.length - 1; rightSide++) {
if (arr[rightSide] > arr[rightSide + 1]) {
pivotIndex = rightSide;
pivotFound = true;
System.out.println("1st For Loop - PivotFound: " + pivotFound + ". Pivot is: " + arr[pivotIndex] + ". Pivot Index is: " + pivotIndex);
break;
}
}
if (!pivotFound) {
for (int leftSide = 0; leftSide < arr.length - mid; leftSide++) {
if (arr[leftSide] > arr[leftSide + 1]) {
pivotIndex = leftSide;
pivotFound = true;
System.out.println("2nd For Loop - PivotFound: " + pivotFound + ". Pivot is: " + arr[pivotIndex] + ". Pivot Index is: " + pivotIndex);
break;
}
}
}
for (int i = 0; i <= pivotIndex; i++) {
if (arr[i] == key) {
keyIndex = i;
keyIndexFound = true;
break;
}
}
if (!keyIndexFound) {
for (int i = pivotIndex; i < arr.length; i++) {
if (arr[i] == key) {
keyIndex = i;
break;
}
}
}
System.out.println(keyIndex >= 0 ? key + " found at index: " + keyIndex : key + " was not found in the array.");
}
}
Another approach that would work with repeated values is to find the rotation and then do a regular binary search applying the rotation whenever we access the array.
test = [3, 4, 5, 1, 2]
test1 = [2, 3, 2, 2, 2]
def find_rotated(col, num):
pivot = find_pivot(col)
return bin_search(col, 0, len(col), pivot, num)
def find_pivot(col):
prev = col[-1]
for n, curr in enumerate(col):
if prev > curr:
return n
prev = curr
raise Exception("Col does not seem like rotated array")
def rotate_index(col, pivot, position):
return (pivot + position) % len(col)
def bin_search(col, low, high, pivot, num):
if low > high:
return None
mid = (low + high) / 2
rotated_mid = rotate_index(col, pivot, mid)
val = col[rotated_mid]
if (val == num):
return rotated_mid
elif (num > val):
return bin_search(col, mid + 1, high, pivot, num)
else:
return bin_search(col, low, mid - 1, pivot, num)
print(find_rotated(test, 2))
print(find_rotated(test, 4))
print(find_rotated(test1, 3))
My simple code :-
public int search(int[] nums, int target) {
int l = 0;
int r = nums.length-1;
while(l<=r){
int mid = (l+r)>>1;
if(nums[mid]==target){
return mid;
}
if(nums[mid]> nums[r]){
if(target > nums[mid] || nums[r]>= target)l = mid+1;
else r = mid-1;
}
else{
if(target <= nums[r] && target > nums[mid]) l = mid+1;
else r = mid -1;
}
}
return -1;
}
Time Complexity O(log(N)).
Question: Search in Rotated Sorted Array
public class SearchingInARotatedSortedARRAY {
public static void main(String[] args) {
int[] a = { 4, 5, 6, 0, 1, 2, 3 };
System.out.println(search1(a, 6));
}
private static int search1(int[] a, int target) {
int start = 0;
int last = a.length - 1;
while (start + 1 < last) {
int mid = start + (last - start) / 2;
if (a[mid] == target)
return mid;
// if(a[start] < a[mid]) => Then this part of the array is not rotated
if (a[start] < a[mid]) {
if (a[start] <= target && target <= a[mid]) {
last = mid;
} else {
start = mid;
}
}
// this part of the array is rotated
else {
if (a[mid] <= target && target <= a[last]) {
start = mid;
} else {
last = mid;
}
}
} // while
if (a[start] == target) {
return start;
}
if (a[last] == target) {
return last;
}
return -1;
}
}
Swift Solution 100% working tested
func searchInArray(A:[Int],key:Int)->Int{
for i in 0..<A.count{
if key == A[i] {
print(i)
return i
}
}
print(-1)
return -1
}