Calculating Big-O notation that has three nested loops - c++

I want to find Big_O notation for my code. It has three nested loops and each loop has parameter that maybe vary.
According to my understanding (I am not sure if that correct).
time complexity is O(NKC) where N is the size in the outer loop, K is a constant inserted by user. C is also constant that may be change when using other dataset.
my code:
for (int m=0; m< size; m++)
{
int array_Y_class_target[2]{};
float CT[2]{};
float SumOf_Each_class_distances[2] = { 0.0 };
int min_index = -1;
for (int i = k; i > 0; --i) {
for (int c = 0; c < 2; ++c) {
for (int j = 0; j < i; ++j) {
int index = index_arr[j];
if (Y_train[index] == c)
{
array_Y_class_target[c] ++;
float dist = array_dist[index_arr[j]];
SumOf_Each_class_distances[c] += dist;
}
}
if (array_Y_class_target[c] != 0)
{
CT[c] = (((float)k / (float)array_Y_class_target[c]) + (SumOf_Each_class_distances[c] / (float)array_Y_class_target[c]));
}
else
{
CT[c] = 1.5; // max CT value
}
}

Related

Matrix multipication is very slow C++

I dont know why but my matrix multipication is very slow and I need to optimize it. and also the print of the matrix (1000X1000) taking long time.
The aim of the function is to calculate the matrix exponential, but my main problem is that this 2 actions are very slow for large matrices like 1000X1000.
These 2 actions implemented at poweMat() function and printeResult() function.
Here is the code:
#define M 1000
#define e 2.71828182845904523536;
//declaration of the functions
void sumMatrices(vector<vector<double> >& mat1, vector<vector<double> >& mat2);
void printResult(vector<vector<double> >&matRes);
void mulMatWithFactorial(long factorialValue);
long factorialCalculate(int n);
void initializeMatrix();
void initializeIdenticalMatrix();
void checkIfTheMatrixIsDiagonal();
void calculateExpoMatrixWithDiagonalMatrix();
void readMatrixFromFile();
void powerMat(vector<vector<double> >& mat, int powNum);
//declaration of the variables
vector<vector<double>> inputMatrix(M, vector<double>(M));
vector<vector<double>> sumMatrixResult(M, vector<double>(M));
vector<vector<double>> powerMatrixResult(M, vector<double>(M));
vector<vector<double>> mulFactorialMatrixResult(M, vector<double>(M));
vector<vector<double>> finalMatrixResult(M, vector<double>(M));
vector<vector<double>> identicalMatrix(M, vector<double>(M));
vector<vector<vector<double>>> listOfMatrices;
bool matrixIsNilpotent = false;
int diagonaMatrixlFlag = 1;
int main() {
//variables
long factorialValue;
initializeIdenticalMatrix();
readMatrixFromFile();
//check if the matrix is diagonal - so we will have easier and faster compute
checkIfTheMatrixIsDiagonal();
if (diagonaMatrixlFlag == 1) {
calculateExpoMatrixWithDiagonalMatrix();
goto endOfLoop;
}
//loop for taylor series
for (int i = 0; i < 5; i++) {
if (i == 0) { // first we add identical matrix when the power is 0
sumMatrices(finalMatrixResult, identicalMatrix); // summarize between this 2 matrices
finalMatrixResult = sumMatrixResult; //copy matrices
}
if (i == 1) { // we add the matrix itself because the power is 1
sumMatrices(finalMatrixResult, inputMatrix);
finalMatrixResult = sumMatrixResult; //copy matrices
}
if (i > 1 ) {
powerMat(inputMatrix, i);
if (matrixIsNilpotent) { // it means that A^i is 0 for some integer, so the series terminates after a finite number
goto endOfLoop;
}
factorialValue = factorialCalculate(i); // calculate the factorial of i
mulMatWithFactorial(factorialValue); // multiply (1/i) * matrix^i - like in the algorithm
sumMatrices(finalMatrixResult, mulFactorialMatrixResult); // summarize it with the previous result
finalMatrixResult = sumMatrixResult; //copy matrices
}
}
endOfLoop:
printResult(finalMatrixResult); // print the final result - e^M
return 0;
}
//Summarize matrices
void sumMatrices(vector<vector<double> >& mat1, vector<vector<double> >& mat2) {
for (int i = 0; i < M; i++)
for (int j = 0; j < M; j++)
sumMatrixResult[i][j] = mat1[i][j] + mat2[i][j];
}
//Print matrix
void printResult(vector<vector<double> >& matRes) {
for (int i = 0; i < M; i++) {
for (int j = 0; j < M; j++) {
printf("%f ", matRes[i][j]);
if (j == M - 1) {
printf("\n");
}
}
}
}
//Calculate the factorial of n
long factorialCalculate(int n) {
long factorial = 1.0;
for (int i = 1; i <= n; ++i) {
factorial *= i;
}
return factorial;
}
// mutiply the matrix with scalar
void mulMatWithFactorial(long factorialValue) {
for (int i = 0; i < M; i++) {
for (int j = 0; j < M; j++) {
mulFactorialMatrixResult[i][j] = powerMatrixResult[i][j] * 1/factorialValue;
}
}
}
//initialize matrix
void initializeMatrix() {
for (int i = 0; i < M; i++) {
for (int j = 0; j < M; j++) {
powerMatrixResult[i][j] = 0;
}
}
}
void checkIfTheMatrixIsDiagonal() {
for (int i = 0; i < M; i++) {
for (int j = 0; j < M; j++) {
if (i == j)
{
if (inputMatrix[i][j] == 0) {
diagonaMatrixlFlag = 0;
goto endOfLoop;
}
}
else
{
if (inputMatrix[i][j] != 0) {
diagonaMatrixlFlag = 0;
goto endOfLoop;
}
}
}
}
endOfLoop:
return;
}
void calculateExpoMatrixWithDiagonalMatrix() {
for (int i = 0; i < M; i++) {
for (int j = 0; j < M; j++) {
if (i == j)
{
for (int k = 0; k < inputMatrix[i][j]; ++k)// loop to calculate the pow of e^alpha
{
finalMatrixResult[i][j] *= e;
}
}
else
{
finalMatrixResult[i][j] = 0;
}
}
}
}
void readMatrixFromFile() {
ifstream f("inv_matrix(1000x1000).txt");
for (int i = 0; i < M; i++)
for (int j = 0; j < M; j++) {
f >> inputMatrix[i][j];
if (f.peek() == ',')
f.ignore();
}
listOfMatrices.push_back(inputMatrix);
}
void initializeIdenticalMatrix() {
for (int i = 0; i < M; i++) {
for (int k = 0; k < M; k++) {
if (i == k) {
identicalMatrix[i][k] = 1;
}
else {
identicalMatrix[i][k] = 0;
}
}
}
}
void powerMat(vector<vector<double> >& mat, int powNum) {
int counterForNilpotent = 0;
initializeMatrix();
auto start = high_resolution_clock::now();
for (int i = 0; i < M; i++) {
for (int k = 0; k < M; k++) {
for (int j = 0; j < M; j++) {
powerMatrixResult[i][j] += mat[i][k] * listOfMatrices[powNum-2][k][j];
}
}
}
auto stop = high_resolution_clock::now();
auto duration = duration_cast<seconds>(stop - start);
cout << duration.count() << " seconds" << endl; // checking run time
listOfMatrices.push_back(powerMatrixResult);
// check if after we we did A^i , the matrix is equal to 0
for (int i = 0; i < M; i++) {
for (int j = 0; j < M; j++) {
if (powerMatrixResult[i][j] == 0) {
counterForNilpotent++;
}
}
}
if (counterForNilpotent == M * M) {
matrixIsNilpotent = true;
}
}
Going through each element of an array of size "n" will have some computational efficiency of O(n^2), meaning for large arrays it will take a while but won't be "life-time-of-the-universe" lengths of time.
Usually to do operations on massive arrays like this, they're reduced in some form first so that the computation can be closer to O(n) or better using some truths about reduced forms of matrices.
So, a faster implementation for matrix multiplication would start with some rref() function upon both matrices and then only evaluating parts of those matrices that would have objects in the columns and rows.
Here are some great places to review/learn (for free) Linear Algebra:
"3b1b (2016): Essence of Linear Algebra" = https://www.youtube.com/watch?v=kjBOesZCoqc&list=PL0-GT3co4r2y2YErbmuJw2L5tW4Ew2O5B
"MIT OpenCourseWare (2009): Linear Algebra" = https://www.youtube.com/watch?v=ZK3O402wf1c&list=PL49CF3715CB9EF31D&index=1
Use SSE2. It’s not a library. It’s a method to use cpu vector hardware.
You set up operations to run in parallel.
https://en.wikipedia.org/wiki/SSE2

Max value 2d array using pointer arithmetic

I'm trying to write a programm to find a maximum value in column in a initialized 5x5 matrix, and change it to -1. I found out the way to do it, but i want to find a better solution.
Input:
double array2d[5][5];
double *ptr;
ptr = array2d[0];
// initializing matrix
for (int i = 0; i < 5; ++i) {
for (int j = 0; j < 5; ++j) {
if (j % 2 != 0) {
array2d[i][j] = (i + 1) - 2.5;
} else {
array2d[i][j] = 2 * (i + 1) + 0.5;
}
}
}
This is my solution for the first column :
// Changing the matrix using pointer arithmetic
for (int i = 0; i < (sizeof(array2d) / sizeof(array2d[0][0])); ++i) {
if (i % 5 == 0) {
if (maxTemp <= *(ptr + i)) {
maxTemp = *(ptr + i);
}
}
}
for (int i = 0; i < (sizeof(array2d) / sizeof(array2d[0][0])); ++i) {
if (i % 5 == 0) {
if (*(ptr + i) == maxTemp) {
*(ptr + i) = -1;
}
}
}
I can repeat this code 5 times, and get the result, but i want a better solution. THX.
Below is the complete program that uses pointer arithmetic. This program replaces all the maximum values in each column of the 2D array -1 as you desire.
#include <iostream>
int main()
{
double array2d[5][5];
double *ptr;
ptr = array2d[0];
// initializing matrix
for (int i = 0; i < 5; ++i) {
for (int j = 0; j < 5; ++j) {
if (j % 2 != 0) {
array2d[i][j] = (i + 1) - 2.5;
} else {
array2d[i][j] = 2 * (i + 1) + 0.5;
}
}
}
//these(from this point on) are the things that i have added.
//Everything above this comment is the same as your code.
double (*rowBegin)[5] = std::begin(array2d);
double (*rowEnd)[5] = std::end(array2d);
while(rowBegin != rowEnd)
{
double *colBegin = std::begin(rowBegin[0]);
double *colEnd = std::end(rowBegin[0]);
double lowestvalue = *colBegin;//for comparing elements
//double *pointerToMaxValue = colBegin;
while(colBegin!= colEnd)
{
if(*colBegin > lowestvalue)
{
lowestvalue = *colBegin;
//pointerToMaxValue = colBegin ;
}
colBegin = colBegin + 1;
}
double *newcolBegin = std::begin(rowBegin[0]);
double *newcolEnd = std::end(rowBegin[0]);
while(newcolBegin!=newcolEnd)
{
if(*newcolBegin == lowestvalue)
{
*newcolBegin = -1;
}
++newcolBegin;
}
++rowBegin;
}
return 0;
}
The program can be checked here.
You can add print out all the element of the array to check whether the above program replaced all the maximum value in each column with -1.
I have written it in java but I think u can understand. This one is for all 5 columns at the same time. You can try this:
int count = 0;
double max = 0;
for (int i = 0; i < 5; ++i) {
for (int j = 0; j < 5; ++j) {
if (j == 0) {
max = array2d[j][I];
count = 0;
}
if (array2d[j][i] > max) {
count = j;
}
}
array2d[count][i] = -1;
}

Water the plants (competitive programming)

I was trying to solve this proble:
A gallery with plants is divided into n parts, numbered : 0,1,2,3...n-1. There are provisions for attaching water sprinklers at every partition. A sprinkler with range x at partition i can water all partitions from i-x to i+x.
Given an array gallery[ ] consisting of n integers, where gallery[i] is the range of sprinkler at partition i (power==-1 indicates no sprinkler attached), return the minimum number of sprinklers that need to be turned on to water the complete gallery.
If there is no possible way to water the full length using the given sprinklers, print -1.
and this is how I ended up trying-
Create a frequency array such that the ith element contains the number of sprinklers that are watering the ith part of the gallery.
If any element of this array is zero after going through all the sprinklers, then return -1 as even if all the sprinklers tried they couldn't water each part.
Then, std::stable_sort all the sprinklers based on their range, in increasing order.
Then, remove a sprinkler if it is redundant, starting from the smallest range to the largest.
My implementation of the same-
typedef struct sprinkler {
int l;
int r;
} sprinkler;
int min_sprinklers(int gallery[], int n)
{
int freq[n];
vector<sprinkler> vec;
for(int i = 0; i < n; i++) freq[i] = 0;
for(int i = 0 ; i < n; i++) {
int x = gallery[i];
if(x == -1) continue;
int l = max(0, i - x);
int r = min(n-1, i + x);
sprinkler s;
s.l = l;
s.r = r;
vec.push_back(s);
for(int j = l; j <= r; j++) {
freq[j]++;
}
}
for(int i = 0; i < n; i++) {
if(freq[i] == 0) return -1;
}
stable_sort(vec.begin(), vec.end(), [](sprinkler s1, sprinkler s2) { return s1.r-s1.l < s2.r-s2.l; });
int sprinklers = vec.size();
for(int i = 0; i < vec.size(); i++) {
int l = vec[i].l;
int r = vec[i].r;
bool flag = false;
for(int j = l; j <= r; j++) {
if(freq[j] == 1) {
flag = true;
break;
}
}
if(!flag) {
for(int j = l; j <= r; j++) freq[j]--;
sprinklers--;
}
}
return sprinklers;
}
But I still seem to be missing something and still don't know what.
Link to try my code:
https://practice.geeksforgeeks.org/problems/410d51d667ab93f2219b15126f001f32e8bb029e/0/?category[]=Greedy&category[]=Greedy&difficulty[]=1&page=1&query=category[]Greedydifficulty[]1page1category[]Greedy#

Sorting Algorithm - Bubble Sort

I was trying to understand bubble sort. While implementing my own version of it for practicing, I implemented it in such a way:
public int[] sort(int[] nums) {
int x = 0;
for (int i = 0; i < nums.length; i++) {
for (int j = 0; j < i; j++) {
System.out.println(++x);
if (nums[j] > nums[i]) {
int temp = nums[j];
nums[j] = nums[i];
nums[i] = temp;
}
}
}
return nums;
}
Notice how the inner loop goes from 0 to i.
When I googled this algorithm to find the conventional implementation, I found this implementation:
public int[] sortnew(int[] nums) {
int x = 0;
for (int i = 0; i < nums.length - 1; i++) {
for (int j = 0; j < nums.length - i - 1; j++) {
System.out.println(++x);
if (nums[j] > nums[j+1]) {
int temp = nums[j];
nums[j] = nums[j+1];
nums[j+1] = temp;
}
}
}
return nums;
}
Here i goes from 0 to array length - i - 1.
In both the cases the number of prints of 'x' are the same. This I believe indicates that the number of computations are same. Then what exactly is the difference between the two practically?
Thank you!

better algorithm for counting points in grids

Suppose I have a point P in [0,1]*[0,1], and [0,1] is divided into m(say 200) grids. I use A[m][m] to indicate whether [a small square centred at P with length 2h] covers each grid or not. So for a point P, A[i][j] is either (increase by) 1 or 0.
Suppose I have n such points(P1,...,Pn), I want to calculate A(for each point Pi, I redo the above procedure, adding 1 or not). How can I do this efficiently(with C++) rather than writing 3 layers of for loops to check for each grid and each point(So O(nm^2))?
I tried the naive 3 for loops with C++. It takes longer time than using some of the vectorized operations(like vector<= number for comparing n numbers together, A[bool vector, bool vector] for subsetting) in R.
Since C++ is generally faster than R, is there any smart way to implement this process?
#include <Rcpp.h>
#include <cmath>
using namespace Rcpp;
// [[Rcpp::export]]
double myfun(NumericVector u, NumericVector v)
{
double n = u.size();
double A[200][200] = {0};
double pos[200];
int i = 0, j = 0, k = 0;
for (i = 0; i < 200; i++)
{
pos[i] = (double)i / 201;
}
for (k = 0; k < n; k++)
{
for (i = 0; i < 200; i++)
{
for (j = 0; j < 200; j++)
{
if ( (fabs(u[k] - pos[i]) <= h) && (fabs(v[k] - pos[j]) <=h ) )
{
A[i][j]++;
}
}
}
}
double s = 0, avg = 0;
for (i = 0; i <200; i++)
{
for (j = 0; j < 200; j++)
{
s += A[i][j];
}
}
avg = s / (200 * 200);
return (avg);
}
The two inner loops only determine index of the point in your grid. But you can compute the index directly:
int i = (int)(u[k]*200);
int j = (int)(v[k]*200);
You probably also need to check that i and j don't reach the index 200. This only happens though, when u[k] == 1.0 or v[k] == 1.0.
double n = u.size();
double A[200][200] = {0};
for (int k = 0; k < n; k++)
{
int i = (int)(u[k]*200);
int j = (int)(v[k]*200);
if (i == 200)
i = 199;
if (j == 200)
j = 199;
A[i][j]++;
}