Generate vector elements from previous elements - c++

I would like to build a vector of vectors which is really a tree. I have the seed value and going forward, I multiply the seed with u to get the up value and with d to get the down value. I have the below snippet that does what I want but can you please suggest a more efficient approach?
void short_rate_lattice() {
double r00 = 0.06;
double u = 1.25;
double d = 0.9;
int num_periods = 5;
vector<vector<double>> short_rates(num_periods + 1);
short_rates[0].push_back(r00);
for (int i = 1; i <= num_periods; ++i) {
for (int j = 0; j < i; ++j) {
short_rates[i].push_back(d * short_rates[i - 1][j]);
}
short_rates[i].push_back(u * short_rates[i - 1][i - 1]);
}
cout << "short_rates vector is populated" << endl;
}

Related

Anderson Darling Test in C++

I am trying to compute the Anderson-Darling test found here. I followed the steps on Wikipedia and made sure that when I calculate the average and standard deviation of the data I am testing denoted X by using MATLAB. Also, I used a function called phi for computing the standard normal CDF, I have also tested this function to make sure it is correct which it is. Now I seem to have a problem when I actually compute the A-squared (denoted in Wikipedia, I denote it as A in C++).
Here is my function I made for Anderson-Darling Test:
void Anderson_Darling(int n, double X[]){
sort(X,X + n);
// Find the mean of X
double X_avg = 0.0;
double sum = 0.0;
for(int i = 0; i < n; i++){
sum += X[i];
}
X_avg = ((double)sum)/n;
// Find the variance of X
double X_sig = 0.0;
for(int i = 0; i < n; i++){
X_sig += (X[i] - X_avg)*(X[i] - X_avg);
}
X_sig /= n;
// The values X_i are standardized to create new values Y_i
double Y[n];
for(int i = 0; i < n; i++){
Y[i] = (X[i] - X_avg)/(sqrt(X_sig));
//cout << Y[i] << endl;
}
// With a standard normal CDF, we calculate the Anderson_Darling Statistic
double A = 0.0;
for(int i = 0; i < n; i++){
A += -n - 1/n *(2*(i) - 1)*(log(phi(Y[i])) + log(1 - phi(Y[n+1 - i])));
}
cout << A << endl;
}
Note, I know that the formula for Anderson-Darling (A-squared) starts with i = 1 to i = n, although when I changed the index to make it work in C++, I still get the same result without changing the index.
The value I get in C++ is:
-4e+006
The value I should get, received in MATLAB is:
0.2330
Any suggestions are greatly appreciated.
Here is my whole code:
#include <iostream>
#include <math.h>
#include <cmath>
#include <random>
#include <algorithm>
#include <chrono>
using namespace std;
double *Box_Muller(int n, double u[]);
double *Beasley_Springer_Moro(int n, double u[]);
void Anderson_Darling(int n, double X[]);
double phi(double x);
int main(){
int n = 2000;
double Mersenne[n];
random_device rd;
mt19937 e2(1);
uniform_real_distribution<double> dist(0, 1);
for(int i = 0; i < n; i++){
Mersenne[i] = dist(e2);
}
// Print Anderson Statistic for Mersenne 6a
double *result = new double[n];
result = Box_Muller(n,Mersenne);
Anderson_Darling(n,result);
return 0;
}
double *Box_Muller(int n, double u[]){
double *X = new double[n];
double Y[n];
double R_2[n];
double theta[n];
for(int i = 0; i < n; i++){
R_2[i] = -2.0*log(u[i]);
theta[i] = 2.0*M_PI*u[i+1];
}
for(int i = 0; i < n; i++){
X[i] = sqrt(-2.0*log(u[i]))*cos(2.0*M_PI*u[i+1]);
Y[i] = sqrt(-2.0*log(u[i]))*sin(2.0*M_PI*u[i+1]);
}
return X;
}
double *Beasley_Springer_Moro(int n, double u[]){
double y[n];
double r[n+1];
double *x = new double(n);
// Constants needed for algo
double a_0 = 2.50662823884; double b_0 = -8.47351093090;
double a_1 = -18.61500062529; double b_1 = 23.08336743743;
double a_2 = 41.39119773534; double b_2 = -21.06224101826;
double a_3 = -25.44106049637; double b_3 = 3.13082909833;
double c_0 = 0.3374754822726147; double c_5 = 0.0003951896511919;
double c_1 = 0.9761690190917186; double c_6 = 0.0000321767881768;
double c_2 = 0.1607979714918209; double c_7 = 0.0000002888167364;
double c_3 = 0.0276438810333863; double c_8 = 0.0000003960315187;
double c_4 = 0.0038405729373609;
// Set r and x to empty for now
for(int i = 0; i <= n; i++){
r[i] = 0.0;
x[i] = 0.0;
}
for(int i = 1; i <= n; i++){
y[i] = u[i] - 0.5;
if(fabs(y[i]) < 0.42){
r[i] = pow(y[i],2.0);
x[i] = y[i]*(((a_3*r[i] + a_2)*r[i] + a_1)*r[i] + a_0)/((((b_3*r[i] + b_2)*r[i] + b_1)*r[i] + b_0)*r[i] + 1);
}else{
r[i] = u[i];
if(y[i] > 0.0){
r[i] = 1.0 - u[i];
r[i] = log(-log(r[i]));
x[i] = c_0 + r[i]*(c_1 + r[i]*(c_2 + r[i]*(c_3 + r[i]*(c_4 + r[i]*(c_5 + r[i]*(c_6 + r[i]*(c_7 + r[i]*c_8)))))));
}
if(y[i] < 0){
x[i] = -x[i];
}
}
}
return x;
}
double phi(double x){
return 0.5 * erfc(-x * M_SQRT1_2);
}
void Anderson_Darling(int n, double X[]){
sort(X,X + n);
// Find the mean of X
double X_avg = 0.0;
double sum = 0.0;
for(int i = 0; i < n; i++){
sum += X[i];
}
X_avg = ((double)sum)/n;
// Find the variance of X
double X_sig = 0.0;
for(int i = 0; i < n; i++){
X_sig += (X[i] - X_avg)*(X[i] - X_avg);
}
X_sig /= (n-1);
// The values X_i are standardized to create new values Y_i
double Y[n];
for(int i = 0; i < n; i++){
Y[i] = (X[i] - X_avg)/(sqrt(X_sig));
//cout << Y[i] << endl;
}
// With a standard normal CDF, we calculate the Anderson_Darling Statistic
double A = -n;
for(int i = 0; i < n; i++){
A += -1.0/(double)n *(2*(i+1) - 1)*(log(phi(Y[i])) + log(1 - phi(Y[n - i])));
}
cout << A << endl;
}
Let me guess, your n was 2000. Right?
The major issue here is when you do 1/n in the last expression. 1 is an int and ao is n. When you divide 1 by n it performs integer division. Now 1 divided by any number > 1 is 0 under integer division (think if it as only keeping only integer part of the quotient. What you need to do is cast n as double by writing 1/(double)n.
Rest all should work fine.
Summary from discussions -
Indexes to Y[] should be i and n-1-i respectively.
n should not be added in the loop but only once.
Minor fixes like changing divisor to n instead of n-1 while calculating Variance.
You have integer division here:
A += -n - 1/n *(2*(i) - 1)*(log(phi(Y[i])) + log(1 - phi(Y[n+1 - i])));
^^^
1/n is zero when n > 1 - you need to change this to, e.g.: 1.0/n:
A += -n - 1.0/n *(2*(i) - 1)*(log(phi(Y[i])) + log(1 - phi(Y[n+1 - i])));
^^^^^

Optimization of C++ code - std::vector operations

I have this funcition (RotateSlownessTop) and it's called about 800 times computing the corresponding values. But the calculation is slow and is there a way I can make the computations faster.
The number of element in X/Y is 7202. (Fairly large set)
I did the performance analysis and the screenshot has been attached.
void RotateSlownessTop(vector <double> &XR1, vector <double> &YR1, float theta = 0.0)
{
Matrix2d a;
a(0,0) = cos(theta);
a(0,1) = -sin(theta);
a(1, 0) = sin(theta);
a(1, 1) = cos(theta);
vector <double> XR2(7202), YR2(7202);
for (size_t i = 0; i < X.size(); ++i)
{
XR2[i] = (a(0, 0)*X[i] + a(0, 1)*Y[i]);
YR2[i] = (a(1, 0)*X[i] + a(1, 1)*Y[i]);
}
size_t i = 0;
size_t j = 0;
while (i < YR2.size())
{
if (i > 0)
if ((XR2[i]>0) && (XR2[i-1]<0))
j = i;
if (YR2[i] > (-1e-10) && YR2[i]<0.0)
YR2[i] = 0.0;
if (YR2[i] < (1e-10) && YR2[i]>0.0)
YR2[i] = -YR2[i];
if ( YR2[i]<0.0)
{
YR2.erase(YR2.begin() + i);
XR2.erase(XR2.begin() + i);
--i;
}
++i;
}
size_t k = 0;
while (j < YR2.size())
{
YR1[k] = (YR2[j]);
XR1[k] = (XR2[j]);
YR2.erase(YR2.begin() + j);
XR2.erase(XR2.begin() + j);
++k;
}
size_t l = 0;
for (; k < XR1.size(); ++k)
{
XR1[k] = XR2[l];
YR1[k] = YR2[l];
l++;
}
}
Edit1: I have updated the code by replacing all push_back() with operator[], since I read somewhere that this is much faster.
However the whole program is still slow. Any suggestions are appreciated.
If the size is large, you can improve the push_back by pre-allocating the space needed. Add this before the loop:
XR2.reserve(X.size());
YR2.reserve(X.size());

Gradient descent converging towards the wrong value

I'm trying to implement a gradient descent algorithm in C++. Here's the code I have so far :
#include <iostream>
double X[] {163,169,158,158,161,172,156,161,154,145};
double Y[] {52, 68, 49, 73, 71, 99, 50, 82, 56, 46 };
double m, p;
int n = sizeof(X)/sizeof(X[0]);
int main(void) {
double alpha = 0.00004; // 0.00007;
m = (Y[1] - Y[0]) / (X[1] - X[0]);
p = Y[0] - m * X[0];
for (int i = 1; i <= 8; i++) {
gradientStep(alpha);
}
return 0;
}
double Loss_function(void) {
double res = 0;
double tmp;
for (int i = 0; i < n; i++) {
tmp = Y[i] - m * X[i] - p;
res += tmp * tmp;
}
return res / 2.0 / (double)n;
}
void gradientStep(double alpha) {
double pg = 0, mg = 0;
for (int i = 0; i < n; i++) {
pg += Y[i] - m * X[i] - p;
mg += X[i] * (Y[i] - m * X[i] - p);
}
p += alpha * pg / n;
m += alpha * mg / n;
}
This code converges towards m = 2.79822, p = -382.666, and an error of 102.88. But if I use my calculator to find out the correct linear regression model, I find that the correct values of m and p should respectively be 1.601 and -191.1.
I also noticed that the algorithm won't converge for alpha > 0.00007, which seems quite low, and the value of p barely changes during the 8 iterations (or even after 2000 iterations).
What's wrong with my code?
Here's a good overview of the algorithm I'm trying to implement. The values of theta0 and theta1 are called p and m in my program.
Other implementation in python
More about the algorithm
This link gives a comprehensive view of the algorithm; it turns out I was following a completely wrong approach.
The following code does not work properly (and I have no plans to work on it further), but should put on track anyone who's confronted to the same problem as me :
#include <vector>
#include <iostream>
typedef std::vector<double> vect;
std::vector<double> y, omega(2, 0), omega2(2, 0);;
std::vector<std::vector<double>> X;
int n = 10;
int main(void) {
/* Initialize x so that each members contains (1, x_i) */
/* Initialize x so that each members contains y_i */
double alpha = 0.00001;
display();
for (int i = 1; i <= 8; i++) {
gradientStep(alpha);
display();
}
return 0;
}
double f_function(const std::vector<double> &x) {
double c;
for (unsigned int i = 0; i < omega.size(); i++) {
c += omega[i] * x[i];
}
return c;
}
void gradientStep(double alpha) {
for (int i = 0; i < n; i++) {
for (unsigned int j = 0; j < X[0].size(); j++) {
omega2[j] -= alpha/(double)n * (f_function(X[i]) - y[i]) * X[i][j];
}
}
omega = omega2;
}
void display(void) {
double res = 0, tmp = 0;
for (int i = 0; i < n; i++) {
tmp = y[i] - f_function(X[i]);
res += tmp * tmp; // Loss functionn
}
std::cout << "omega = ";
for (unsigned int i = 0; i < omega.size(); i++) {
std::cout << "[" << omega[i] << "] ";
}
std::cout << "\tError : " << res * .5/(double)n << std::endl;
}

From mathematic function to c++ code

I am trying to implement this F(S) function:
bellow is my code but is not working:
double EnergyFunction::evaluate(vector<short> field) {
double e = 0.0;
for (int k = 1; k < field.size() - 1; k++){
double c = 0.0;
for (int i = 1; i < field.size() - k; i++) {
c += field[i] * field[i + k];
}
e += pow(c, 2);
}
double f = pow(field.size(), 2) / ( 2 * e );
return f;
}
For example F(S) function should return value 8644 for vector:
1,1,1,-1,-1,-1,1,-1,1,1,-1,1,-1,1,-1,1,-1,-1,1,1,1,1,-1,-1,-1,1,1,1,1,-1,1,-1,1,1,-1,-1,1,1,1,1,-1,-1,-1,1,-1,-1,1,-1,-1,1,1,-1,1,-1,-1,1,1,-1,1,-1,1,-1,1,-1,1,-1,1,1,-1,-1,-1,-1,-1,-1,1,-1,1,1,1,-1,1,1,-1,1,1,-1,1,-1,1,1,1,-1,-1,1,1,-1,-1,1,1,1,1,1,1,1,1,-1,1,-1,1,-1,1,-1,-1,1,-1,-1,1,-1,-1,1,-1,-1,-1,-1,-1,1,1,1,1,1,-1,-1,-1,1,-1,-1,1,-1,-1,1,-1,-1,1,-1,1,-1,-1,1,1,1,1,1,1,-1,1,-1,1,-1,1,1,1,1,1,1,-1,1,-1,-1,-1,1,-1,1,1,-1,-1,-1,-1,1,-1,-1,-1,1,1,-1,-1,1,1,1,-1,-1,1,1,1,1,-1,1,1,-1,1,-1,-1,1,-1,-1,-1,-1,1,-1,-1,-1,1,-1,-1,1,1,-1,-1,-1,-1,-1,1,-1,-1,-1,1,1,-1,1,1,-1,-1,-1,1,-1,-1,1,-1,-1,-1,1,1,1,-1,-1,-1,-1,1,1,1,-1,1,-1,-1,1,-1,1,1,-1,-1,-1,-1,1,-1,1,1,1,1,1,1,-1,1,1,1,-1,-1,-1,-1,1,-1,1,1,1,1,-1,1,1,1,1,1,-1,-1,-1,1,-1,-1,1,1,1,-1,1,1,1,-1,1,1
I need another par of eyes to look at my code because I am a bit lost here. :)
after refactoring:
double EnergyFunction::evaluate(vector<short> field) {
double e = 0.0;
int l = field.size()
for (int k = 1; k < l; k++){
double c = 0.0;
for (int i = 0, j = k; j < l; i++, j++) {
c += field[i] * field[j];
}
e += c*c;
}
return l*l / ( e+e );
}
explanation:
1. we need to iterate (L-1) times
2. we need to shift the base and offset indexes until we reach the last one
3. c*c and e+e are quicker and easier to read
You are mapping variables into different ranges using the same names, which is always going to be confusing. Better is to keep ranges and names the same as in the math, and only subtract one for 0-base indexes at indexing time. Also might as well use L explicitly:
int L = field.size();
for (int k = 1; k <= L-1; k++){
...
for (int i = 1; i <= L-k; i++) {
c += field[i -1] * field[i+k -1];
...

Laguerre interpolation algorithm, something's wrong with my implementation

This is a problem I have been struggling for a week, coming back just to give up after wasted hours...
I am supposed to find coefficents for the following Laguerre polynomial:
P0(x) = 1
P1(x) = 1 - x
Pn(x) = ((2n - 1 - x) / n) * P(n-1) - ((n - 1) / n) * P(n-2)
I believe there is an error in my implementation, because for some reason the coefficents I get seem way too big. This is the output this program generates:
a1 = -190.234
a2 = -295.833
a3 = 378.283
a4 = -939.537
a5 = 774.861
a6 = -400.612
Description of code (given below):
If you scroll the code down a little to the part where I declare array, you'll find given x's and y's.
The function polynomial just fills an array with values of said polynomial for certain x. It's a recursive function. I believe it works well, because I have checked the output values.
The gauss function finds coefficents by performing Gaussian elimination on output array. I think this is where the problems begin. I am wondering, if there's a mistake in this code or perhaps my method of veryfying results is bad? I am trying to verify them like that:
-190.234 * 1.5 ^ 5 - 295.833 * 1.5 ^ 4 ... - 400.612 = -3017,817625 =/= 2
Code:
#include "stdafx.h"
#include <conio.h>
#include <iostream>
#include <iomanip>
#include <math.h>
using namespace std;
double polynomial(int i, int j, double **tab)
{
double n = i;
double **array = tab;
double x = array[j][0];
if (i == 0) {
return 1;
} else if (i == 1) {
return 1 - x;
} else {
double minusone = polynomial(i - 1, j, array);
double minustwo = polynomial(i - 2, j, array);
double result = (((2.0 * n) - 1 - x) / n) * minusone - ((n - 1.0) / n) * minustwo;
return result;
}
}
int gauss(int n, double tab[6][7], double results[7])
{
double multiplier, divider;
for (int m = 0; m <= n; m++)
{
for (int i = m + 1; i <= n; i++)
{
multiplier = tab[i][m];
divider = tab[m][m];
if (divider == 0) {
return 1;
}
for (int j = m; j <= n; j++)
{
if (i == n) {
break;
}
tab[i][j] = (tab[m][j] * multiplier / divider) - tab[i][j];
}
for (int j = m; j <= n; j++) {
tab[i - 1][j] = tab[i - 1][j] / divider;
}
}
}
double s = 0;
results[n - 1] = tab[n - 1][n];
int y = 0;
for (int i = n-2; i >= 0; i--)
{
s = 0;
y++;
for (int x = 0; x < n; x++)
{
s = s + (tab[i][n - 1 - x] * results[n-(x + 1)]);
if (y == x + 1) {
break;
}
}
results[i] = tab[i][n] - s;
}
}
int _tmain(int argc, _TCHAR* argv[])
{
int num;
double **array;
array = new double*[5];
for (int i = 0; i <= 5; i++)
{
array[i] = new double[2];
}
//i 0 1 2 3 4 5
array[0][0] = 1.5; //xi 1.5 2 2.5 3.5 3.8 4.1
array[0][1] = 2; //yi 2 5 -1 0.5 3 7
array[1][0] = 2;
array[1][1] = 5;
array[2][0] = 2.5;
array[2][1] = -1;
array[3][0] = 3.5;
array[3][1] = 0.5;
array[4][0] = 3.8;
array[4][1] = 3;
array[5][0] = 4.1;
array[5][1] = 7;
double W[6][7]; //n + 1
for (int i = 0; i <= 5; i++)
{
for (int j = 0; j <= 5; j++)
{
W[i][j] = polynomial(j, i, array);
}
W[i][6] = array[i][1];
}
for (int i = 0; i <= 5; i++)
{
for (int j = 0; j <= 6; j++)
{
cout << W[i][j] << "\t";
}
cout << endl;
}
double results[6];
gauss(6, W, results);
for (int i = 0; i < 6; i++) {
cout << "a" << i + 1 << " = " << results[i] << endl;
}
_getch();
return 0;
}
I believe your interpretation of the recursive polynomial generation either needs revising or is a bit too clever for me.
given P[0][5] = {1,0,0,0,0,...}; P[1][5]={1,-1,0,0,0,...};
then P[2] is a*P[0] + convolution(P[1], { c, d });
where a = -((n - 1) / n)
c = (2n - 1)/n and d= - 1/n
This can be generalized: P[n] == a*P[n-2] + conv(P[n-1], { c,d });
In every step there is involved a polynomial multiplication with (c + d*x), which increases the degree by one (just by one...) and adding to P[n-1] multiplied with a scalar a.
Then most likely the interpolation factor x is in range [0..1].
(convolution means, that you should implement polynomial multiplication, which luckily is easy...)
[a,b,c,d]
* [e,f]
------------------
af,bf,cf,df +
ae,be,ce,de, 0 +
--------------------------
(= coefficients of the final polynomial)
The definition of P1(x) = x - 1 is not implemented as stated. You have 1 - x in the computation.
I did not look any further.