VSCode exiting C code with code=3221225477 - c

I wrote the C program below using VSCode on my old 64 bit Windows 10 Enterprise computer. It worked perfectly when I ran it on there, and it also works perfectly when I run it on this online C compiler. However, when I try to run it on VSCode on my new 64 bit Windows 11 Home computer, it exits with code=3221225477. Does anyone know what I should do about this? Thanks.
What I've tried so far:
I've tried writing programs to test each of the functions in it and they all ran perfectly fine on VSCode on my new computer; I'm only getting problems when I run the entire program
Because my new computer has Norton installed on it, it likes to think that some of my C programs are viruses and stops them from being executed. However, I made a folder that I have told it not to interfere with and copied my program there. I still got code=3221225477 when I ran it.
/*
File name : triangulation.c
Author : kene02
Last modified : 20/12/2021
License : All rights reserved
Description:
Uses triangulation to find where a point is.
*/
#define _USE_MATH_DEFINES
#include <stdio.h>
#include <stdlib.h>
#include <math.h>
#include <string.h>
// Function declarations
float distance_between(float *point_1, float *point_2);
float find_gradient(float *point_1, float *point_2);
char *bearing(float *point_1, float *point_2);
float *triangulate(float *a, float *b, float *c, float *d);
int main()
{
// Allocating memory for coordinates
float *point_a = (float *)malloc(2*sizeof(float));
float *point_b = (float *)malloc(2*sizeof(float));
float *point_c = (float *)malloc(2*sizeof(float));
float *point_d = (float *)malloc(2*sizeof(float));
point_a[0] = 328;
point_a[1] = -1445;
point_b[0] = 325;
point_b[1] = -1455;
point_c[0] = 286;
point_c[1] = -1567;
point_d[0] = 292;
point_d[1] = -1575;
// Print coordinates
printf("\nA(%.1f, %.1f)\t", point_a[0], point_a[1]);
printf("B(%.1f, %.1f)\n", point_b[0], point_b[1]);
printf("C(%.1f, %.1f)\t", point_c[0], point_c[1]);
printf("D(%.1f, %.1f)\n\n", point_d[0], point_d[1]);
// Evaluate point of intersection
float *point_x = triangulate(point_a, point_b, point_c, point_d);
// Evaluate bearings
char *bng_ba = bearing(point_b, point_a);
char *bng_dc = bearing(point_d, point_c);
char *bng_xa = bearing(point_x, point_a);
char *bng_xc = bearing(point_x, point_c);
if (strcmp(bng_ba, bng_xa) != 0 || strcmp(bng_dc, bng_xc) != 0) {
printf("Lines do not intersect.\n\n");
} else {
float length_xa = distance_between(point_x, point_a);
float length_xc = distance_between(point_x, point_c);
printf("Point of intersection\t\t\t: ");
printf("X(%.1f, %.1f)\n", point_x[0], point_x[1]);
printf("Distance and bearing of X from A\t: ");
printf("%.1f units, %s\n", length_xa, bng_xa);
printf("Distance and bearing of X from C\t: ");
printf("%.1f units, %s\n\n", length_xc, bng_xc);
}
return 0;
}
/**
* #brief distance_between function: finds the distance between two points.
*
* #param point_1 the (x, y) coordinates of the 1st point
* #param point_2 the (x, y) coordinates of the 2nd point
* #return the distance between the two points
*/
float distance_between(float *point_1, float *point_2)
{
float x_diff = point_2[0] - point_1[0];
float y_diff = point_2[1] - point_1[1];
float distance = sqrt(pow(x_diff, 2) + pow(y_diff, 2));
return distance;
}
/**
* #brief find_gradient function: finds the gradient of the line between two
* points.
*
* #param point_1 the (x, y) coordinates of the 1st point
* #param point_2 the (x, y) coordinates of the 2nd point
* #return the gradient of the line between the two points
*/
float find_gradient(float *point_1, float *point_2)
{
float x_diff = point_2[0] - point_1[0];
float y_diff = point_2[1] - point_1[1];
float gradient = y_diff/x_diff;
return gradient;
}
/**
* #brief traingulate function: finds the point of intersection of the line
* passing through points A & B and the line passing though points C & D.
*
* #param a the coordinates of point A
* #param b the coordinates of point B
* #param c the coordinates of point C
* #param d the coordinates of point D
* #return the point at which the lines intersect
*/
float *triangulate(float *a, float *b, float *c, float *d)
{
float *intersect = (float *)malloc(2*sizeof(float));
float g1 = find_gradient(a, b);
float g2 = find_gradient(c, d);
if (a[0] == b[0]) {
intersect[0] = a[0];
intersect[1] = c[1] + (a[0]-c[0])*g2;
} else if (c[0] == d[0]) {
intersect[0] = c[0];
intersect[1] = a[1] - (a[0]-c[0])*g1;
} else {
intersect[0] = ((a[1]-c[1]) + c[0]*g2 - a[0]*g1)/(g2-g1);
intersect[1] = (a[1]*g2 - c[1]*g1 + (c[0]-a[0])*g2*g1)/(g2-g1);
}
return intersect;
}
/**
* #brief bearing function: finds the compass bearing of point_1 from point_2
*
* #param point_1 the coordinates of the point to find the compass bearing of
* relative to point_2
* #param point_2 the coordinates of the reference point from which the compass
* bearing of point_1 will be measured
* #return the compass bearing of point_1 from point_2
*/
char *bearing(float *point_1, float *point_2)
{
const float RAD_DEG_RATIO = 180/M_PI;
float x_diff = point_1[0] - point_2[0];
float y_diff = point_1[1] - point_2[1];
float gradient = y_diff/x_diff;
char *bearing = (char *)malloc(7*sizeof(char));
if (x_diff == 0 && y_diff > 0) {
sprintf(bearing, "N");
} else if (x_diff == 0 && y_diff < 0) {
sprintf(bearing, "S");
} else if (x_diff > 0 && y_diff == 0) {
sprintf(bearing, "E");
} else if (x_diff < 0 && y_diff == 0) {
sprintf(bearing, "W");
} else if (x_diff > 0 && y_diff > 0) {
float angle = 90 - RAD_DEG_RATIO*atan(gradient);
sprintf(bearing, "N %.2f E", angle);
} else if (x_diff < 0 && y_diff > 0) {
float angle = 90 + RAD_DEG_RATIO*atan(gradient);
sprintf(bearing, "N %.2f W", angle);
} else if (x_diff < 0 && y_diff < 0) {
float angle = 90 - RAD_DEG_RATIO*atan(gradient);
sprintf(bearing, "S %.2f W", angle);
} else if (x_diff > 0 && y_diff < 0) {
float angle = 90 + RAD_DEG_RATIO*atan(gradient);
sprintf(bearing, "S %.2f E", angle);
}
return bearing;
}

3221225477 decimal is gibberish. Translated to hex you get 0xC0000005, which is Windows' error code for access violation (also known as "seg fault"). The most likely cause is array out of bounds access.
The bug is here: malloc(7*sizeof(char)); creates too little memory to contain what your sprintf might produce. This can only hold 6 characters + the mandatory null terminator. Memory is cheap, so change this for something with margins like:
char *bearing = malloc(20);
Why you keep using malloc all over the place to allocate tiny amounts of memory, I have no idea. All you achieve with that is to slow down everything and create potential for memory leaks.
It's better practice to have your function work with caller allocated memory whenever possible. It is not good design to mix up memory allocation and the actual algorithm in the same function.

Related

Is pointers within structures slowing down my code?

I am looking for some help or hints to speed up my code.
I have implemented a routine for computing the gravitational potential at a point (r,phi,lambda) in space from a set of spherical harmonic coefficients C_{n,m} and S_{n,m}. The equation is shown in the link below:
and includes the recursive computation of the latitude (phi) dependent associated Legendre polynomials P_{n,m}, starting with the first two values P{0,0} and P_{1,1}.
At first, I had this implemented as a MATLAB C-MEX code, with only the core part of my code in C-language. I wanted to make a pure C-routine, but found that the code runs 3-5 times slower, which makes me wonder why. Could it be the way I define my structures and use pointers to pointers in the central code?
It seems like it is the core computation part that takes the extra time, but that part did not change although before I was passing using pointers directly to variables and now I am using pointers inside structures.
Any help is appreciated!
In the following, I will try to explain my code and show some extracts:
At the beginning of the program, I define three structures. One to hold the spherical harmonic coefficients, C_{n,m} and S_{n,m}, (ggm_struct), one to hold the computation coordinates (comp_struct) and one to hold the results (func_struct):
// Define constant variables
const double deg2rad = M_PI/180.0; // degrees to radians conversion factor
const double sfac = 1.0000E-280; // scaling factor
const double sqrt2 = 1.414213562373095; // sqrt(2)
const double sqrt3 = 1.732050807568877; // sqrt(3)
// Define structure to hold geopotential model
struct ggm_struct {
char product_type[100], modelname[100], errors[100], norm[100], tide_system[100];
double GM, R, *C, *S;
int max_degree, ncoef;
};
// Define structure to hold computation coordinates
struct comp_struct {
double *lat, *lon, *h;
double *r, *phi;
int nlat, nlon;
};
/* Define structure to hold results */
struct func_struct {
double *rval;
int npoints;
};
I then have a (sub-)function that starts by allocating space and then loads the coefficients from an ascii file as
int read_gfc(char mfile[100], int *nmax, int *mmax, struct ggm_struct *ggm)
{
// Set file identifier
FILE *fid;
// Declare variables
char str[200], var[100];
int n, m, nid, l00 = 0, l10 = 0, l11 = 0;
double c, s;
// Determine number of coefficients
ggm->ncoef = (*nmax+2)*(*nmax+1)/2;
// Allocate memory for coefficients
ggm->C = (double*) malloc(ggm->ncoef*sizeof(double));
if (ggm->C == NULL){
printf("Error: Memory for C not allocated!");
return -ENOMEM;
}
ggm->S = (double*) malloc(ggm->ncoef*sizeof(double));
if (ggm->S == NULL){
printf("Error: Memory for S not allocated!");
return -ENOMEM;
}
// Open file
fid = fopen(mfile,"r");
// Check that file was opened correctly
if (fid == NULL){
printf("Error: opening file %s!",mfile);
return -ENOMEM;
}
// Read file header
while (fgets(str,200,fid) != NULL && strncmp(str,"end_of_head",11) != 0){
// Extract model parameters
if (strncmp(str,"product_type",12) == 0){ sscanf(str,"%s %s",var,ggm->product_type); }
if (strncmp(str,"modelname",9) == 0){ sscanf(str,"%s %s",var,ggm->modelname); }
if (strncmp(str,"earth_gravity_constant",22) == 0){ sscanf(str,"%s %lf",var,&ggm->GM); }
if (strncmp(str,"radius",6) == 0){ sscanf(str,"%s %lf",var,&ggm->R); }
if (strncmp(str,"max_degree",10) == 0){ sscanf(str,"%s %d",var,&ggm->max_degree); }
if (strncmp(str,"errors",6) == 0){ sscanf(str,"%s %s",var,ggm->errors); }
if (strncmp(str,"norm",4) == 0){ sscanf(str,"%s %s",var,ggm->norm); }
if (strncmp(str,"tide_system",11) == 0){ sscanf(str,"%s %s",var,ggm->tide_system); }
}
// Read coefficients
while (fgets(str,200,fid) != NULL){
// Extract parameters
sscanf(str,"%s %d %d %lf %lf",var,&n,&m,&c,&s);
// Store parameters
if (n <= *nmax && m <= *mmax) {
// Determine index
nid = (n+1)*n/2 + m;
// Store values
*(ggm->C+nid) = c;
*(ggm->S+nid) = s;
}
}
// Close fil
fclose(fid);
// Return from function
return 0;
}
Afterwards, the computation grid is defined by an array of seven components. As an example, the array [-90 90 -180 180 1 1 0] defines a grid from -90 to 90 degrees latitude at 1-degree increments and from -180 to 180 degrees longitude at 1-degree increments. The height is zero. From this array, a computation grid is generated in a (sub-)function:
int make_grid(double *grid, struct comp_struct *inp)
{
// Declare variables
int n;
/* Echo routine */
printf("Creating grid of coordinates\n");
printf(" [lat1,lat2,dlat] = [%f,%f,%f]\n", *grid, *(grid+1), *(grid+4) );
printf(" [lon1,lon2,dlon] = [%f,%f,%f]\n", *(grid+2), *(grid+3), *(grid+5) );
printf(" h = %f\n", *(grid+6));
/* Latitude ------------------------------------------------------------- */
// Determine number of increments
inp->nlat = ceil( ( *(grid+1) - *grid + *(grid+4) ) / *(grid+4) );
// Allocate memory
inp->lat = (double*) malloc(inp->nlat*sizeof(double));
if (inp->lat== NULL){
printf("Error: Memory for LATITUDE (inp.lat) points not allocated!");
return -ENOMEM;
}
// Fill in values
*(inp->lat) = *(grid+1);
for (n = 1; n < inp->nlat-1; n++) {
*(inp->lat+n) = *(inp->lat+n-1) - *(grid+4);
}
*(inp->lat+inp->nlat-1) = *grid;
/* Longitude ------------------------------------------------------------ */
// Determine number of increments
inp->nlon = ceil( ( *(grid+3) - *(grid+2) + *(grid+5) ) / *(grid+5) );
// Allocate memory
inp->lon = (double*) malloc(inp->nlon*sizeof(double));
if (inp->lon== NULL){
printf("Error: Memory for LONGITUDE (inp.lon) points not allocated!");
return -ENOMEM;
}
// Fill in values
*(inp->lon) = *(grid+2);
for (n = 1; n < inp->nlon-1; n++) {
*(inp->lon+n) = *(inp->lon+n-1) + *(grid+5);
}
*(inp->lon+inp->nlon-1) = *(grid+3);
/* Height --------------------------------------------------------------- */
// Allocate memory
inp->h = (double*) malloc(inp->nlat*sizeof(double));
if (inp->h== NULL){
printf("Error: Memory for HEIGHT (inp.h) points not allocated!");
return -ENOMEM;
}
// Fill in values
for (n = 0; n < inp->nlat; n++) {
*(inp->h+n) = *(inp->h+n-1) + *(grid+6);
}
// Return from function
return 0;
}
These geographic coordinates are then transformed to spherical coordinates for the computation using another (sub-)routine
int geo2sph(struct comp_struct *inp, int *lgrid)
{
// Declare variables
double a = 6378137.0, e2 = 6.69437999014E-3; /* WGS84 parameters */
double x, y, z, sinlat, coslat, sinlon, coslon, R_E;
int i, j, nid;
/* Allocate space ------------------------------------------------------- */
// radius
inp->r = (double*) malloc(inp->nlat*sizeof(double));
if (inp->r== NULL){
printf("Error: Memory for SPHERICAL DISTANCE (inp.r) points not allocated!");
return -ENOMEM;
}
// phi
inp->phi = (double*) malloc(inp->nlat*sizeof(double));
if (inp->phi== NULL){
printf("Error: Memory for SPHERICAL LATITUDE (inp.phi) points not allocated!");
return -ENOMEM;
}
/* Loop over latitude =================================================== */
for (i = 0; i < inp->nlat; i++) {
// Compute sine and cosine of latitude
sinlat = sin(*(inp->lat+i));
coslat = cos(*(inp->lat+i));
// Compute radius of curvature
R_E = a / sqrt( 1.0 - e2*sinlat*sinlat );
// Compute sine and cosine of longitude
sinlon = sin(*(inp->lon));
coslon = cos(*(inp->lon));
// Compute rectangular coordinates
x = ( R_E + *(inp->h+i) ) * coslat * coslon;
y = ( R_E + *(inp->h+i) ) * coslat * sinlon;
z = ( R_E*(1.0-e2) + *(inp->h+i) ) * sinlat;
// Compute sqrt( x^2 + y^2 )
R_E = sqrt( x*x + y*y );
// Derive radial distance
*(inp->r+i) = sqrt( R_E * R_E + z*z );
// Derive spherical latitude
if (R_E < 1) {
if (z > 0) { *(inp->phi+i) = M_PI/2.0; }
else { *(inp->phi+i) = -M_PI/2.0; }
}
else {
*(inp->phi+i) = asin( z / *(inp->r+i) );
}
}
// Return from function
return 0;
}
Finally, the gravitational potential is computed within is own (sub-)function. This is the core part of the code, which is more or less the same as for the MATLAB C-MEX function. The only difference seems to be that before (in MATLAB MEX) everything was defined as (simple) double variables - now the variables are located inside a structure which contains pointers.
int gravpot(struct comp_struct *inp, struct ggm_struct *ggm, int *nmax,
int *mmax, int *lgrid, struct func_struct *out)
{
// Declare variables
double GMr, ar, t, u, u2, arn, gnm, hnm, P, Pp1, Pp2, msum;
double Pmm[*nmax+1], CPnm[*mmax+1], SPnm[*mmax+1];
int i, j, n, m, id;
// Allocate memory
out->rval = (double*) malloc(inp->nlat*inp->nlon*sizeof(double));
if (out->rval== NULL){
printf("Error: Memory for OUTPUT (out.rval) not allocated!");
return -ENOMEM;
}
/* Compute sectorial values of associated Legendre polynomials ========== */
// Define seed values ( divided by u^m )
Pmm[0] = sfac;
Pmm[1] = sqrt3 * sfac;
// Compute sectorial values, [1] eq. 13 and 28 ( divided by u^m )
for (m = 2; m <= *nmax; m++) {
Pmm[m] = sqrt( (2.0*m+1.0) / (2.0*m) ) * Pmm[m-1];
}
/* ====================================================================== */
/* Loop over latitude =================================================== */
for (i = 0; i < inp->nlat; i++) {
// Compute ratios to be used in summation
GMr = ggm->GM / *(inp->r+i);
ar = ggm->R / *(inp->r+i);
/* ---------------------------------------------------------------------
* Compute product of Legendre values and spherical harmonic coefficients.
* Products of similar degree are summed together, resulting in mmax
* values. The degree terms are latitude dependent, such that these mmax
* sums are valid for every point with the same latitude.
* The values of the associated Legendre polynomials, Pnm, are scaled by
* sfac = 10^(-280) and divided by u^m in order to prevent underflow and
* overflow of the coefficients.
* ------------------------------------------------------------------ */
// Form coefficients for Legendre recursive algorithm
t = sin(*(inp->phi+i));
u = cos(*(inp->phi+i));
u2 = u * u;
arn = ar;
/* Degree n = 0 terms ----------------------------------------------- */
// Compute order m = 0 term (S term is zero)
CPnm[0] = Pmm[0] * *(ggm->C);
/* Degree n = 1 terms ----------------------------------------------- */
// Compute (1,1) terms, [1] eq. 3
CPnm[1] = ar * Pmm[1] * *(ggm->C+2);
SPnm[1] = ar * Pmm[1] * *(ggm->S+2);
// Compute (1,0) Legendre value, [1] eq. 18 and 27
P = t * Pmm[1];
// Add (1,0) terms to sum (S term is zero), [1] eq. 3
CPnm[0] = CPnm[0] + ar * P * *(ggm->C+1);
/* Degree n = [2,n_max] --------------------------------------------- */
for (n = 2; n <= *nmax; n++) {
// Compute power term
arn = arn * ar;
/* Compute sectorial (m=n) terms ++++++++++++++++++++++++++++++++ */
// Extract associated Legendre value
Pp1 = Pmm[n];
// Compute product terms, [1] eq. 3
if (n <= *mmax) {
id = (n+1)*n/2 + n;
CPnm[n] = arn * Pp1 * *(ggm->C+id);
SPnm[n] = arn * Pp1 * *(ggm->S+id);
}
/* Compute first non-sectorial terms (m=n-1) ++++++++++++++++++++ */
// Compute associated Legendre value, [1] eq. 18 and 27
gnm = sqrt( 2.0*n );
P = gnm * t * Pp1;
// Add terms to summation, eq. 3 in [1]
if (n-1 <= *mmax) {
id = (n+1)*n/2 + n - 1;
CPnm[n-1] = CPnm[n-1] + arn * P * *(ggm->C+id);
SPnm[n-1] = SPnm[n-1] + arn * P * *(ggm->S+id);
}
/* Compute terms of order m = [n-2,1] +++++++++++++++++++++++++++ */
for (m = n-2; m > 0; m--) {
// Set previous values
Pp2 = Pp1;
Pp1 = P;
// Compute associated Legendre value, [1] eq. 18, 19 and 27
gnm = 2.0*(m+1.0) / sqrt( (n-m)*(n+m+1.0) );
hnm = sqrt( (n+m+2.0)*(n-m-1.0)/(n-m)/(n+m+1.0) );
P = gnm * t * Pp1 - hnm * u2 * Pp2;
// Add product terms to summation, eq. 3 in [1]
if (m <= *mmax) {
id = (n+1)*n/2 + m;
CPnm[m] = CPnm[m] + arn * P * *(ggm->C+id);
SPnm[m] = SPnm[m] + arn * P * *(ggm->S+id);
}
}
/* Compute zonal terms (m=0) ++++++++++++++++++++++++++++++++++++ */
// Compute associated Legendre value, [1] eq. 18, 19 and 27
gnm = 2.0 / sqrt( n*(n+1.0) );
hnm = sqrt( (n+2.0)*(n-1.0)/n/(n+1.0) );
P = ( gnm * t * P - hnm * u2 * Pp1 ) / sqrt2;
// Add terms to summation (S term is zero), [1] eq. 3
id = (n+1)*n/2;
CPnm[0] = CPnm[0] + arn * P * *(ggm->C+id);
} /* ---------------------------------------------------------------- */
/* Loop over longitude ============================================== */
for (j = 0; j < inp->nlon; j++) {
/* -----------------------------------------------------------------
* All associated Legendre polynomials (latitude dependent) are now
* computed and multiplied by the corresponding spherical harmonic
* coefficient. These products are scaled by u^m, meaning that
* Horner's scheme is used in the following summation.
* -------------------------------------------------------------- */
// Initialise order-dependent sum
msum = 0.0;
// Derive longitude id
id = j + i * *lgrid;
// Loop over order (m > 0)
for (m = *mmax; m > 0; m--) {
// Add to order-dependent sum using Horner's scheme, [1] eq. 2, 3 and 31
msum = ( msum + cos( m * *(inp->lon+id) ) * CPnm[m]
+ sin( m * *(inp->lon+id) ) * SPnm[m] ) * u;
}
// Add zero order term to sum
msum = msum + CPnm[0];
// Rescale value into gravitational potential, [1] eq. 1
*(out->rval+i+j*inp->nlat) = GMr * msum / sfac;
} /* ================================================================ */
} /* ==================================================================== */
// Return from function
return 0;
}
Again, any help is greatly appreciated and additional information can be supplied if relevant, but this already became a long post. I have a hard time accepting that pure c-code runs slower than the MATLAB C-MEX code.
To put it simply, yes, pointers can prevent some compiler optimizations resulting in a potential slow down. At least, this is clearly the case with ICC and a bit with GCC. The performance of the program is strongly impacted by pointer aliasing and vectorization.
Indeed, the compiler cannot easily know if the provided pointers alias each other or alias with the address with some fields of the provided data structure. As a result, the compilers tends to be conservative and assume that the pointed value can change at any time and reload them often. This can prevent optimizations like the splitting of some loops in gravpot (with GCC -- see line 119 of this modified code). Moreover, indirections and aliasing tends to prevent the vectorization of the hot loops (ie. the use of SIMD instructions provided by the target processor). Vectorisation can strongly impact the performance of a code.
To give an example, here is the initial code of geo2sph and here is a slightly modified implementation. In the first case, ICC generate a slow scalar implementation, while in the second case, ICC generate a significantly faster vectorized implementation. The only difference between the two implementation is the use of the restrict keyword. This keyword tell to the compiler that for the lifetime of the pointer, only the pointer itself or a value directly derived from it (such as pointer+1) will be used to access the object to which it points (see here for more information). Note that the use of the restrict keyword is dangerous and one should be very careful while using it since the compiler may generate a bad code if the restrict hint is wrong (very hard to debug). Alternatively, you can help the compiler to generate a vectorized code using the OpenMP SIMD directive #pragma omp simd (see here for the result). Note that you should be sure the target code can be safely vectorized (eg. iterations of must be independent).

comparing doubles is not working ( appears always that are different)

I have a program to calculate a poylgn área and perimeter, the program receives a text file with coordinates and calculate the area.
Im with some issues on the calculations. Now Im trying to compare doubles and I dont understand why its not working.
I have a text file with 3 lines:
1.0 2.5 5.1 5.8 5.9 0.7
1.2 4.1 5.1 5.8 6.8 1.9 2.9 0.2
1.7 4.9 5.1 5.8 7.0 2.8 4.8 0.1 1.5 1.4
And I expect this results:
double expectedarea = 11.77;
double expectedperimeter = 15.64;
double expectedarea1 = 18.10;
double expectedperimeter1 = 17.02;
double expectedarea2 = 21.33;
double expectedperimeter2 = 16.60;
So I would expected that the message "Arrays are the same" appear for the 3 cases because Im giving the correct value, but Im getting the message arrays are different for the 3 cases.
Do you understand why I get always the message arrays are different?
#include <stdio.h>
#include <stdlib.h>
#include <math.h>
#include <string.h>
enum {x, y};
typedef struct triangle {
double v1[2];
double v2[2];
double v3[2];
} triangle;
double area(triangle a);
double perimeter(double *vertices, int size);
double side(double *p1, double *p2);
double expectedarea = 11.77;
double expectedperimeter = 15.64;
double expectedarea1 = 18.10;
double expectedperimeter1 = 17.02;
double expectedarea2 = 21.33;
double expectedperimeter2 = 16.60;
int main()
{
int idx;
int triangles;
int index;
int xycount;
double xy;
double triangle_area;
double polygon_area;
double perim;
double polygon_vertices[50] = {0.0};
triangle a;
FILE* data;
char line[256];
char* token;
if ((data = fopen("test.txt", "r")) == NULL) {
fprintf(stderr, "can't open data file\n");
exit (EXIT_FAILURE);
}
while (fgets(line, sizeof (line), data)){
xycount = 0;
polygon_area = 0;
line[strlen(line) - 1] = 0;
token = strtok(line, " ");
while (token != NULL){
xy = atof(token);
token = strtok(NULL, " ");
polygon_vertices[xycount++] = xy;
}
idx = 0;
triangles = (xycount / 2) - 2;
for (index = 2, idx = 0;idx < triangles;index += 2, ++idx){
a.v1[x] = polygon_vertices[0];
a.v1[y] = polygon_vertices[1];
a.v2[x] = polygon_vertices[index + 0];
a.v2[y] = polygon_vertices[index + 1];
a.v3[x] = polygon_vertices[index + 2];
a.v3[y] = polygon_vertices[index + 3];
triangle_area = area(a);
polygon_area += triangle_area;
}
printf("area=%f\t", polygon_area);
perim = perimeter(polygon_vertices, xycount);
printf("perimeter=%f\n", perim);
if(polygon_area == expectedarea && perim == expectedperimeter) {
printf("Arrays are the same");
}
if(polygon_area == expectedarea1 && perim == expectedperimeter1) {
printf("Arrays are the same");
}
if(polygon_area == expectedarea2 && perim == expectedperimeter2) {
printf("Arrays are the same");
}
else {
printf("Arrays are the different"); }
}
fclose(data);
return 0;
}
/* calculate triangle area with Heron's formula */
double area(triangle a)
{
double s1, s2, s3, S, area;
s1 = side(a.v1, a.v2);
s2 = side(a.v2, a.v3);
s3 = side(a.v3, a.v1);
S = (s1 + s2 + s3) / 2;
area = sqrt(S*(S - s1)*(S - s2)*(S - s3));
return area;
}
/* calculate polygon perimeter */
double perimeter(double *vertices, int size)
{
int idx, jdx;
double p1[2], p2[2], pfirst[2], plast[2];
double perimeter;
perimeter = 0.0;
/* 1st vertex of the polygon */
pfirst[x] = vertices[0];
pfirst[y] = vertices[1];
/* last vertex of polygon */
plast[x] = vertices[size-2];
plast[y] = vertices[size-1];
/* calculate perimeter minus last side */
for(idx = 0; idx <= size-3; idx += 2)
{
for(jdx = 0; jdx < 4; ++jdx)
{
p1[x] = vertices[idx];
p1[y] = vertices[idx+1];
p2[x] = vertices[idx+2];
p2[y] = vertices[idx+3];
}
perimeter += side(p1, p2);
}
/* add last side */
perimeter += side(plast, pfirst);
return perimeter;
}
/* calculate length of side */
double side(double *p1, double *p2)
{
double s1, s2, s3;
s1 = (p1[x] - p2[x]);
s2 = (p1[y] - p2[y]);
s3 = (s1 * s1) + (s2 * s2);
return sqrt(s3);
}
In testing OP's code, the list, as posted, had a space after the 0.7. Normally this white-space is not an issue, yet my saving of the file text.txt caused the line to end with " \r\n" and the '\r' created additional tokens. Additional white-space characters to strtok(NULL, " \n\r\t") solved this.
<1.0 2.5 5.1 5.8 5.9 0.7 >
<1.2 4.1 5.1 5.8 6.8 1.9 2.9 0.2>
<1.7 4.9 5.1 5.8 7.0 2.8 4.8 0.1 1.5 1.4>
Depending on how the list is saved, the last line may or may not end with a '\n'. This becomes an issue with OP's method of lopping off the '\n' with the below as it may render the last line as "1.7 4.9 5.1 5.8 7.0 2.8 4.8 0.1 1.5 1." (last 4 missing).
line[strlen(line) - 1] = 0;
Better to use the below which does not require a final '\n' to work right.
line[strcspn(line, "\n")] = '\0';
OP's code is creating one too many coordinates in its xy list. It also has trouble potential due to other white-spaces. A more complete list is added.
while (token != NULL) {
xy = atof(token);
polygon_vertices[xycount++] = xy;
token = strtok(NULL, " \n\r\t"); // more white-spaces.
if (token == NULL) break;
}
Code will then calculate answer close to the expected values. After that fix, an earlier proposed duplicate applies. Is floating point math broken?
area=11.775000 expected area=11.770000
perimeter=15.645596 expected perimeter=15.640000
Rather than compare FP numbers for exact matching, code need to allow for a small tolerance. See comparing double values in C,
precision of comparing double values with EPSILON in C.
Various simplifications and accuracy improvements possible. Example:
#include <assert.h>
/* calculate polygon perimeter */
double perimeter(double *vertices, int size) {
assert(size % 2 == 0 && size >= 0); // Insure only positive pairs are used
double perimeter = 0.0;
if (size > 1) {
double x_previous = vertices[size - 2];
double y_previous = vertices[size - 2 + 1];
while (size > 1) {
double x = *vertices++;
double y = *vertices++;
// hypot() certainly as accurate than sqrt(x*x + y*y) and avoids overflow
perimeter += hypot(x - x_previous, y - y_previous);
x_previous = x;
y_previous = y;
size -= 2;
}
}
return perimeter;
}

Trouble calculating perimeter of a polygon from reading x, y coordinate input into arrays

Having trouble with program that calculates the perimeter of a polygon from an input of (x,y) coordinates. I need to use arrays and I'm not very confident with them. Mostly having trouble with reading the values into the array from a .txt file (using <) and also how to use the last point and first point to close off the polygon.
The input is:
3 1.0 2.0 1.0 5.0 4.0 5.0
5 1.0 2.0 4.0 5.0 7.8 3.5 5.0 0.4 1.0 0.4
4 1.0 0.4 0.4 0.4 0.4 3.6 1.0 3.6
0
Where the first number in each row indicates the number of points (npoints) and then followed by the coordinates themselves which are in clear groups of two i.e. (x,y).
Each new row indicates a new polygon needing to be read.
#include <stdio.h>
#include <stdlib.h>
#include <math.h>
#define MAX_PTS 100
#define MAX_POLYS 100
#define END_INPUT 0
double
getDistance(int npoints, double x[], double y[]) {
double distance = 0.0;
for (int i = 0; i < npoints; ++i) {
int j =; // I'm stuck here
distance = sqrt((x[i]-x[j]) * (x[i]-x[j]) + (y[i]-y[j]) *(y[i]-y[j]));
}
return distance;
}
int
main(int argc, char *argv[]) {
int npoints, iteration = 0;
double x[MAX_PTS], y[MAX_PTS];
double perimeter = 0.0;
if (npoints == END_INPUT){
scanf("%d", &npoints);
// start with 0 value of parameter.
for (iteration = 0; iteration < npoints; ++iteration) {
scanf("%lf %lf", &(x[iteration]), &(y[iteration]));
// take input for new-point.
// for next iteration, new-point would be first-point in getDistance
}
perimeter += getDistance(npoints, x, y);
perimeter += getDistance(); // stuck here
// need to add the perimeter
// need to complete the polygon with last-edge joining the last-point
// with initial-point but not sure how to access array
printf("perimeter = %2.2f m\n", perimeter);
}
return 0;
}
The output for the first polygon should be 10.24m
If anyone could give me a hand that would be great, I'm quite stumped
You were almost there. After adding the file input, just a few tweaks here and there. Most importantly, how to make the array point wrap back to the front.
#include <stdio.h>
#include <math.h>
#define MAX_PTS 100
double getDistance(int npoints, double x[], double y[]) {
double distance = 0.0, dx, dy;
int i;
for (i = 0; i < npoints; ++i) {
dx = x[(i+1) % npoints] - x[i]; // wrap the index
dy = y[(i+1) % npoints] - y[i];
distance += sqrt(dx * dx + dy * dy); // accumaulate
}
return distance;
}
int main(int argc, char *argv[]) {
int npoints, point;
double x[MAX_PTS], y[MAX_PTS];
double perimeter;
FILE *fp;
if (argc < 2) {
printf("No file name supplied\n");
return 1;
}
if ((fp = fopen(argv[1], "rt")) == NULL) {
printf("Error opening file\n");
return 1;
}
while (1) {
if (1 != fscanf(fp, "%d", &npoints)) { // check result
printf("Error reading number of sides\n");
return 1;
}
if (npoints == 0)
break; // end of data
if (npoints < 3 || npoints > MAX_PTS) { // check range
printf("Illegal number of sides %d\n", npoints);
return 1;
}
for (point = 0; point < npoints; ++point) {
if (2 != fscanf(fp, "%lf %lf", &x[point], &y[point])) { // check result
printf("Error reading coordinates of %d-sided polygon\n", npoints);
return 1;
}
}
perimeter = getDistance(npoints, x, y); // include args
printf("perimeter = %2.2f\n", perimeter);
}
fclose(fp);
return 0;
}
Program output:
>test polydata.txt
perimeter = 10.24
perimeter = 18.11
perimeter = 7.60
Get rid of the test of npoints == END_INPUT in main(). It serves no purpose and, since npoints is uninitialised, gives undefined behaviour.
As to the question you asked, assuming the points represent a polygon with no edges crossing over, the distance will be the sum of distances between adjacent points (0->1, 1->2, ....., npoint-2 -> npoints-1, npoints-1 -> 0).
The only special one of these is the last. Other than the last, the distance is being computed between point i to point i + 1.
That suggests j is i+1 for i = 0 to npoints-2. Then, for i == npoints-1, j will be equal to 0.
Writing code to implement that is trivial.

How to generate a set of points that are equidistant from each other and lie on a circle

I am trying to generate an array of n points that are equidistant from each other and lie on a circle in C. Basically, I need to be able to pass a function the number of points that I would like to generate and get back an array of points.
It's been a really long time since I've done C/C++, so I've had a stab at this more to see how I got on with it, but here's some code that will calculate the points for you. (It's a VS2010 console application)
// CirclePoints.cpp : Defines the entry point for the console application.
//
#include "stdafx.h"
#include "stdio.h"
#include "math.h"
int _tmain()
{
int points = 8;
double radius = 100;
double step = ((3.14159265 * 2) / points);
double x, y, current = 0;
for (int i = 0; i < points; i++)
{
x = sin(current) * radius;
y = cos(current) * radius;
printf("point: %d x:%lf y:%lf\n", i, x, y);
current += step;
}
return 0;
}
Try something like this:
void make_circle(float *output, size_t num, float radius)
{
size_t i;
for(i = 0; i < num; i++)
{
const float angle = 2 * M_PI * i / num;
*output++ = radius * cos(angle);
*output++ = radius * sin(angle);
}
}
This is untested, there might be an off-by-one hiding in the angle step calculation but it should be close.
This assumes I understood the question correctly, of course.
UPDATE: Redid the angle computation to not be incrementing, to reduce float precision loss due to repeated addition.
Here's a solution, somewhat optimized, untested. Error can accumulate, but using double rather than float probably more than makes up for it except with extremely large values of n.
void make_circle(double *dest, size_t n, double r)
{
double x0 = cos(2*M_PI/n), y0 = sin(2*M_PI/n), x=x0, y=y0, tmp;
for (;;) {
*dest++ = r*x;
*dest++ = r*y;
if (!--n) break;
tmp = x*x0 - y*y0;
y = x*y0 + y*x0;
x = tmp;
}
}
You have to solve this in c language:
In an x-y Cartesian coordinate system, the circle with centre coordinates (a, b) and radius r is the set of all points (x, y) such that
(x - a)^2 + (y - b)^2 = r^2
Here's a javascript implementation that also takes an optional center point.
function circlePoints (radius, numPoints, centerX, centerY) {
centerX = centerX || 0;
centerY = centerY || 0;
var
step = (Math.PI * 2) / numPoints,
current = 0,
i = 0,
results = [],
x, y;
for (; i < numPoints; i += 1) {
x = centerX + Math.sin(current) * radius;
y = centerY + Math.cos(current) * radius;
results.push([x,y]);
console.log('point %d # x:%d, y:%d', i, x, y);
current += step;
}
return results;
}

fast & efficient least squares fit algorithm in C?

I am trying to implement a linear least squares fit onto 2 arrays of data: time vs amplitude. The only technique I know so far is to test all of the possible m and b points in (y = m*x+b) and then find out which combination fits my data best so that it has the least error. However, I think iterating so many combinations is sometimes useless because it tests out everything. Are there any techniques to speed up the process that I don't know about? Thanks.
Try this code. It fits y = mx + b to your (x,y) data.
The arguments to linreg are
linreg(int n, REAL x[], REAL y[], REAL* b, REAL* m, REAL* r)
n = number of data points
x,y = arrays of data
*b = output intercept
*m = output slope
*r = output correlation coefficient (can be NULL if you don't want it)
The return value is 0 on success, !=0 on failure.
Here's the code
#include "linreg.h"
#include <stdlib.h>
#include <math.h> /* math functions */
//#define REAL float
#define REAL double
inline static REAL sqr(REAL x) {
return x*x;
}
int linreg(int n, const REAL x[], const REAL y[], REAL* m, REAL* b, REAL* r){
REAL sumx = 0.0; /* sum of x */
REAL sumx2 = 0.0; /* sum of x**2 */
REAL sumxy = 0.0; /* sum of x * y */
REAL sumy = 0.0; /* sum of y */
REAL sumy2 = 0.0; /* sum of y**2 */
for (int i=0;i<n;i++){
sumx += x[i];
sumx2 += sqr(x[i]);
sumxy += x[i] * y[i];
sumy += y[i];
sumy2 += sqr(y[i]);
}
REAL denom = (n * sumx2 - sqr(sumx));
if (denom == 0) {
// singular matrix. can't solve the problem.
*m = 0;
*b = 0;
if (r) *r = 0;
return 1;
}
*m = (n * sumxy - sumx * sumy) / denom;
*b = (sumy * sumx2 - sumx * sumxy) / denom;
if (r!=NULL) {
*r = (sumxy - sumx * sumy / n) / /* compute correlation coeff */
sqrt((sumx2 - sqr(sumx)/n) *
(sumy2 - sqr(sumy)/n));
}
return 0;
}
Example
You can run this example online.
int main()
{
int n = 6;
REAL x[6]= {1, 2, 4, 5, 10, 20};
REAL y[6]= {4, 6, 12, 15, 34, 68};
REAL m,b,r;
linreg(n,x,y,&m,&b,&r);
printf("m=%g b=%g r=%g\n",m,b,r);
return 0;
}
Here is the output
m=3.43651 b=-0.888889 r=0.999192
Here is the Excel plot and linear fit (for verification).
All values agree exactly with the C code above (note C code returns r while Excel returns R**2).
There are efficient algorithms for least-squares fitting; see Wikipedia for details. There are also libraries that implement the algorithms for you, likely more efficiently than a naive implementation would do; the GNU Scientific Library is one example, but there are others under more lenient licenses as well.
From Numerical Recipes: The Art of Scientific Computing in (15.2) Fitting Data to a Straight Line:
Linear Regression:
Consider the problem of fitting a set of N data points (xi, yi) to a straight-line model:
Assume that the uncertainty: sigmai associated with each yi and that the xi’s (values of the dependent variable) are known exactly. To measure how well the model agrees with the data, we use the chi-square function, which in this case is:
The above equation is minimized to determine a and b. This is done by finding the derivative of the above equation with respect to a and b, equate them to zero and solve for a and b. Then we estimate the probable uncertainties in the estimates of a and b, since obviously the measurement errors in the data must introduce some uncertainty in the determination of those parameters. Additionally, we must estimate the goodness-of-fit of the data to the
model. Absent this estimate, we have not the slightest indication that the parameters a and b in the model have any meaning at all.
The below struct performs the mentioned calculations:
struct Fitab {
// Object for fitting a straight line y = a + b*x to a set of
// points (xi, yi), with or without available
// errors sigma i . Call one of the two constructors to calculate the fit.
// The answers are then available as the variables:
// a, b, siga, sigb, chi2, and either q or sigdat.
int ndata;
double a, b, siga, sigb, chi2, q, sigdat; // Answers.
vector<double> &x, &y, &sig;
// Constructor.
Fitab(vector<double> &xx, vector<double> &yy, vector<double> &ssig)
: ndata(xx.size()), x(xx), y(yy), sig(ssig), chi2(0.), q(1.), sigdat(0.)
{
// Given a set of data points x[0..ndata-1], y[0..ndata-1]
// with individual standard deviations sig[0..ndata-1],
// sets a,b and their respective probable uncertainties
// siga and sigb, the chi-square: chi2, and the goodness-of-fit
// probability: q
Gamma gam;
int i;
double ss=0., sx=0., sy=0., st2=0., t, wt, sxoss; b=0.0;
for (i=0;i < ndata; i++) { // Accumulate sums ...
wt = 1.0 / SQR(sig[i]); //...with weights
ss += wt;
sx += x[i]*wt;
sy += y[i]*wt;
}
sxoss = sx/ss;
for (i=0; i < ndata; i++) {
t = (x[i]-sxoss) / sig[i];
st2 += t*t;
b += t*y[i]/sig[i];
}
b /= st2; // Solve for a, b, sigma-a, and simga-b.
a = (sy-sx*b) / ss;
siga = sqrt((1.0+sx*sx/(ss*st2))/ss);
sigb = sqrt(1.0/st2); // Calculate chi2.
for (i=0;i<ndata;i++) chi2 += SQR((y[i]-a-b*x[i])/sig[i]);
if (ndata>2) q=gam.gammq(0.5*(ndata-2),0.5*chi2); // goodness of fit
}
// Constructor.
Fitab(vector<double> &xx, vector<double> &yy)
: ndata(xx.size()), x(xx), y(yy), sig(xx), chi2(0.), q(1.), sigdat(0.)
{
// As above, but without known errors (sig is not used).
// The uncertainties siga and sigb are estimated by assuming
// equal errors for all points, and that a straight line is
// a good fit. q is returned as 1.0, the normalization of chi2
// is to unit standard deviation on all points, and sigdat
// is set to the estimated error of each point.
int i;
double ss,sx=0.,sy=0.,st2=0.,t,sxoss;
b=0.0; // Accumulate sums ...
for (i=0; i < ndata; i++) {
sx += x[i]; // ...without weights.
sy += y[i];
}
ss = ndata;
sxoss = sx/ss;
for (i=0;i < ndata; i++) {
t = x[i]-sxoss;
st2 += t*t;
b += t*y[i];
}
b /= st2; // Solve for a, b, sigma-a, and sigma-b.
a = (sy-sx*b)/ss;
siga=sqrt((1.0+sx*sx/(ss*st2))/ss);
sigb=sqrt(1.0/st2); // Calculate chi2.
for (i=0;i<ndata;i++) chi2 += SQR(y[i]-a-b*x[i]);
if (ndata > 2) sigdat=sqrt(chi2/(ndata-2));
// For unweighted data evaluate typical
// sig using chi2, and adjust
// the standard deviations.
siga *= sigdat;
sigb *= sigdat;
}
};
where struct Gamma:
struct Gamma : Gauleg18 {
// Object for incomplete gamma function.
// Gauleg18 provides coefficients for Gauss-Legendre quadrature.
static const Int ASWITCH=100; When to switch to quadrature method.
static const double EPS; // See end of struct for initializations.
static const double FPMIN;
double gln;
double gammp(const double a, const double x) {
// Returns the incomplete gamma function P(a,x)
if (x < 0.0 || a <= 0.0) throw("bad args in gammp");
if (x == 0.0) return 0.0;
else if ((Int)a >= ASWITCH) return gammpapprox(a,x,1); // Quadrature.
else if (x < a+1.0) return gser(a,x); // Use the series representation.
else return 1.0-gcf(a,x); // Use the continued fraction representation.
}
double gammq(const double a, const double x) {
// Returns the incomplete gamma function Q(a,x) = 1 - P(a,x)
if (x < 0.0 || a <= 0.0) throw("bad args in gammq");
if (x == 0.0) return 1.0;
else if ((Int)a >= ASWITCH) return gammpapprox(a,x,0); // Quadrature.
else if (x < a+1.0) return 1.0-gser(a,x); // Use the series representation.
else return gcf(a,x); // Use the continued fraction representation.
}
double gser(const Doub a, const Doub x) {
// Returns the incomplete gamma function P(a,x) evaluated by its series representation.
// Also sets ln (gamma) as gln. User should not call directly.
double sum,del,ap;
gln=gammln(a);
ap=a;
del=sum=1.0/a;
for (;;) {
++ap;
del *= x/ap;
sum += del;
if (fabs(del) < fabs(sum)*EPS) {
return sum*exp(-x+a*log(x)-gln);
}
}
}
double gcf(const Doub a, const Doub x) {
// Returns the incomplete gamma function Q(a, x) evaluated
// by its continued fraction representation.
// Also sets ln (gamma) as gln. User should not call directly.
int i;
double an,b,c,d,del,h;
gln=gammln(a);
b=x+1.0-a; // Set up for evaluating continued fraction
// by modified Lentz’s method with with b0 = 0.
c=1.0/FPMIN;
d=1.0/b;
h=d;
for (i=1;;i++) {
// Iterate to convergence.
an = -i*(i-a);
b += 2.0;
d=an*d+b;
if (fabs(d) < FPMIN) d=FPMIN;
c=b+an/c;
if (fabs(c) < FPMIN) c=FPMIN;
d=1.0/d;
del=d*c;
h *= del;
if (fabs(del-1.0) <= EPS) break;
}
return exp(-x+a*log(x)-gln)*h; Put factors in front.
}
double gammpapprox(double a, double x, int psig) {
// Incomplete gamma by quadrature. Returns P(a,x) or Q(a, x),
// when psig is 1 or 0, respectively. User should not call directly.
int j;
double xu,t,sum,ans;
double a1 = a-1.0, lna1 = log(a1), sqrta1 = sqrt(a1);
gln = gammln(a);
// Set how far to integrate into the tail:
if (x > a1) xu = MAX(a1 + 11.5*sqrta1, x + 6.0*sqrta1);
else xu = MAX(0.,MIN(a1 - 7.5*sqrta1, x - 5.0*sqrta1));
sum = 0;
for (j=0;j<ngau;j++) { // Gauss-Legendre.
t = x + (xu-x)*y[j];
sum += w[j]*exp(-(t-a1)+a1*(log(t)-lna1));
}
ans = sum*(xu-x)*exp(a1*(lna1-1.)-gln);
return (psig?(ans>0.0? 1.0-ans:-ans):(ans>=0.0? ans:1.0+ans));
}
double invgammp(Doub p, Doub a);
// Inverse function on x of P(a,x) .
};
const Doub Gamma::EPS = numeric_limits<Doub>::epsilon();
const Doub Gamma::FPMIN = numeric_limits<Doub>::min()/EPS
and stuct Gauleg18:
struct Gauleg18 {
// Abscissas and weights for Gauss-Legendre quadrature.
static const Int ngau = 18;
static const Doub y[18];
static const Doub w[18];
};
const Doub Gauleg18::y[18] = {0.0021695375159141994,
0.011413521097787704,0.027972308950302116,0.051727015600492421,
0.082502225484340941, 0.12007019910960293,0.16415283300752470,
0.21442376986779355, 0.27051082840644336, 0.33199876341447887,
0.39843234186401943, 0.46931971407375483, 0.54413605556657973,
0.62232745288031077, 0.70331500465597174, 0.78649910768313447,
0.87126389619061517, 0.95698180152629142};
const Doub Gauleg18::w[18] = {0.0055657196642445571,
0.012915947284065419,0.020181515297735382,0.027298621498568734,
0.034213810770299537,0.040875750923643261,0.047235083490265582,
0.053244713977759692,0.058860144245324798,0.064039797355015485
0.068745323835736408,0.072941885005653087,0.076598410645870640,
0.079687828912071670,0.082187266704339706,0.084078218979661945,
0.085346685739338721,0.085983275670394821};
and, finally fuinction Gamma::invgamp():
double Gamma::invgammp(double p, double a) {
// Returns x such that P(a,x) = p for an argument p between 0 and 1.
int j;
double x,err,t,u,pp,lna1,afac,a1=a-1;
const double EPS=1.e-8; // Accuracy is the square of EPS.
gln=gammln(a);
if (a <= 0.) throw("a must be pos in invgammap");
if (p >= 1.) return MAX(100.,a + 100.*sqrt(a));
if (p <= 0.) return 0.0;
if (a > 1.) {
lna1=log(a1);
afac = exp(a1*(lna1-1.)-gln);
pp = (p < 0.5)? p : 1. - p;
t = sqrt(-2.*log(pp));
x = (2.30753+t*0.27061)/(1.+t*(0.99229+t*0.04481)) - t;
if (p < 0.5) x = -x;
x = MAX(1.e-3,a*pow(1.-1./(9.*a)-x/(3.*sqrt(a)),3));
} else {
t = 1.0 - a*(0.253+a*0.12); and (6.2.9).
if (p < t) x = pow(p/t,1./a);
else x = 1.-log(1.-(p-t)/(1.-t));
}
for (j=0;j<12;j++) {
if (x <= 0.0) return 0.0; // x too small to compute accurately.
err = gammp(a,x) - p;
if (a > 1.) t = afac*exp(-(x-a1)+a1*(log(x)-lna1));
else t = exp(-x+a1*log(x)-gln);
u = err/t;
// Halley’s method.
x -= (t = u/(1.-0.5*MIN(1.,u*((a-1.)/x - 1))));
// Halve old value if x tries to go negative.
if (x <= 0.) x = 0.5*(x + t);
if (fabs(t) < EPS*x ) break;
}
return x;
}
Here is my version of a C/C++ function that does simple linear regression. The calculations follow the wikipedia article on simple linear regression. This is published as a single-header public-domain (MIT) library on github: simple_linear_regression. The library (.h file) is tested to work on Linux and Windows, and from C and C++ using -Wall -Werror and all -std versions supported by clang/gcc.
#define SIMPLE_LINEAR_REGRESSION_ERROR_INPUT_VALUE -2
#define SIMPLE_LINEAR_REGRESSION_ERROR_NUMERIC -3
int simple_linear_regression(const double * x, const double * y, const int n, double * slope_out, double * intercept_out, double * r2_out) {
double sum_x = 0.0;
double sum_xx = 0.0;
double sum_xy = 0.0;
double sum_y = 0.0;
double sum_yy = 0.0;
double n_real = (double)(n);
int i = 0;
double slope = 0.0;
double denominator = 0.0;
if (x == NULL || y == NULL || n < 2) {
return SIMPLE_LINEAR_REGRESSION_ERROR_INPUT_VALUE;
}
for (i = 0; i < n; ++i) {
sum_x += x[i];
sum_xx += x[i] * x[i];
sum_xy += x[i] * y[i];
sum_y += y[i];
sum_yy += y[i] * y[i];
}
denominator = n_real * sum_xx - sum_x * sum_x;
if (denominator == 0.0) {
return SIMPLE_LINEAR_REGRESSION_ERROR_NUMERIC;
}
slope = (n_real * sum_xy - sum_x * sum_y) / denominator;
if (slope_out != NULL) {
*slope_out = slope;
}
if (intercept_out != NULL) {
*intercept_out = (sum_y - slope * sum_x) / n_real;
}
if (r2_out != NULL) {
denominator = ((n_real * sum_xx) - (sum_x * sum_x)) * ((n_real * sum_yy) - (sum_y * sum_y));
if (denominator == 0.0) {
return SIMPLE_LINEAR_REGRESSION_ERROR_NUMERIC;
}
*r2_out = ((n_real * sum_xy) - (sum_x * sum_y)) * ((n_real * sum_xy) - (sum_x * sum_y)) / denominator;
}
return 0;
}
Usage example:
#define SIMPLE_LINEAR_REGRESSION_IMPLEMENTATION
#include "simple_linear_regression.h"
#include <stdio.h>
/* Some data that we want to find the slope, intercept and r2 for */
static const double x[] = { 1.47, 1.50, 1.52, 1.55, 1.57, 1.60, 1.63, 1.65, 1.68, 1.70, 1.73, 1.75, 1.78, 1.80, 1.83 };
static const double y[] = { 52.21, 53.12, 54.48, 55.84, 57.20, 58.57, 59.93, 61.29, 63.11, 64.47, 66.28, 68.10, 69.92, 72.19, 74.46 };
int main() {
double slope = 0.0;
double intercept = 0.0;
double r2 = 0.0;
int res = 0;
res = simple_linear_regression(x, y, sizeof(x) / sizeof(x[0]), &slope, &intercept, &r2);
if (res < 0) {
printf("Error: %s\n", simple_linear_regression_error_string(res));
return res;
}
printf("slope: %f\n", slope);
printf("intercept: %f\n", intercept);
printf("r2: %f\n", r2);
return 0;
}
The original example above worked well for me with slope and offset but I had a hard time with the corr coef. Maybe I don't have my parenthesis working the same as the assumed precedence? Anyway, with some help of other web pages I finally got values that match the linear trend-line in Excel. Thought I would share my code using Mark Lakata's variable names. Hope this helps.
double slope = ((n * sumxy) - (sumx * sumy )) / denom;
double intercept = ((sumy * sumx2) - (sumx * sumxy)) / denom;
double term1 = ((n * sumxy) - (sumx * sumy));
double term2 = ((n * sumx2) - (sumx * sumx));
double term3 = ((n * sumy2) - (sumy * sumy));
double term23 = (term2 * term3);
double r2 = 1.0;
if (fabs(term23) > MIN_DOUBLE) // Define MIN_DOUBLE somewhere as 1e-9 or similar
r2 = (term1 * term1) / term23;
as an assignment I had to code in C a simple linear regression using RMSE loss function. The program is dynamic and you can enter your own values and choose your own loss function which is for now limited to Root Mean Square Error. But first here are the algorithms I used:
now the code... you need gnuplot to display the chart, sudo apt install gnuplot
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <math.h>
#include <sys/types.h>
#define BUFFSIZE 64
#define MAXSIZE 100
static double vector_x[MAXSIZE] = {0};
static double vector_y[MAXSIZE] = {0};
static double vector_predict[MAXSIZE] = {0};
static double max_x;
static double max_y;
static double mean_x;
static double mean_y;
static double teta_0_intercept;
static double teta_1_grad;
static double RMSE;
static double r_square;
static double prediction;
static char intercept[BUFFSIZE];
static char grad[BUFFSIZE];
static char xrange[BUFFSIZE];
static char yrange[BUFFSIZE];
static char lossname_RMSE[BUFFSIZE] = "Simple Linear Regression using RMSE'";
static char cmd_gnu_0[BUFFSIZE] = "set title '";
static char cmd_gnu_1[BUFFSIZE] = "intercept = ";
static char cmd_gnu_2[BUFFSIZE] = "grad = ";
static char cmd_gnu_3[BUFFSIZE] = "set xrange [0:";
static char cmd_gnu_4[BUFFSIZE] = "set yrange [0:";
static char cmd_gnu_5[BUFFSIZE] = "f(x) = (grad * x) + intercept";
static char cmd_gnu_6[BUFFSIZE] = "plot f(x), 'data.temp' with points pointtype 7";
static char const *commands_gnuplot[] = {
cmd_gnu_0,
cmd_gnu_1,
cmd_gnu_2,
cmd_gnu_3,
cmd_gnu_4,
cmd_gnu_5,
cmd_gnu_6,
};
static size_t size;
static void user_input()
{
printf("Enter x,y vector size, MAX = 100\n");
scanf("%lu", &size);
if (size > MAXSIZE) {
printf("Wrong input size is too big\n");
user_input();
}
printf("vector's size is %lu\n", size);
size_t i;
for (i = 0; i < size; i++) {
printf("Enter vector_x[%ld] values\n", i);
scanf("%lf", &vector_x[i]);
}
for (i = 0; i < size; i++) {
printf("Enter vector_y[%ld] values\n", i);
scanf("%lf", &vector_y[i]);
}
}
static void display_vector()
{
size_t i;
for (i = 0; i < size; i++){
printf("vector_x[%lu] = %lf\t", i, vector_x[i]);
printf("vector_y[%lu] = %lf\n", i, vector_y[i]);
}
}
static void concatenate(char p[], char q[]) {
int c;
int d;
c = 0;
while (p[c] != '\0') {
c++;
}
d = 0;
while (q[d] != '\0') {
p[c] = q[d];
d++;
c++;
}
p[c] = '\0';
}
static void compute_mean_x_y()
{
size_t i;
double tmp_x = 0.0;
double tmp_y = 0.0;
for (i = 0; i < size; i++) {
tmp_x += vector_x[i];
tmp_y += vector_y[i];
}
mean_x = tmp_x / size;
mean_y = tmp_y / size;
printf("mean_x = %lf\n", mean_x);
printf("mean_y = %lf\n", mean_y);
}
static void compute_teta_1_grad()
{
double numerator = 0.0;
double denominator = 0.0;
double tmp1 = 0.0;
double tmp2 = 0.0;
size_t i;
for (i = 0; i < size; i++) {
numerator += (vector_x[i] - mean_x) * (vector_y[i] - mean_y);
}
for (i = 0; i < size; i++) {
tmp1 = vector_x[i] - mean_x;
tmp2 = tmp1 * tmp1;
denominator += tmp2;
}
teta_1_grad = numerator / denominator;
printf("teta_1_grad = %lf\n", teta_1_grad);
}
static void compute_teta_0_intercept()
{
teta_0_intercept = mean_y - (teta_1_grad * mean_x);
printf("teta_0_intercept = %lf\n", teta_0_intercept);
}
static void compute_prediction()
{
size_t i;
for (i = 0; i < size; i++) {
vector_predict[i] = teta_0_intercept + (teta_1_grad * vector_x[i]);
printf("y^[%ld] = %lf\n", i, vector_predict[i]);
}
printf("\n");
}
static void compute_RMSE()
{
compute_prediction();
double error = 0;
size_t i;
for (i = 0; i < size; i++) {
error = (vector_predict[i] - vector_y[i]) * (vector_predict[i] - vector_y[i]);
printf("error y^[%ld] = %lf\n", i, error);
RMSE += error;
}
/* mean */
RMSE = RMSE / size;
/* square root mean */
RMSE = sqrt(RMSE);
printf("\nRMSE = %lf\n", RMSE);
}
static void compute_loss_function()
{
int input = 0;
printf("Which loss function do you want to use?\n");
printf(" 1 - RMSE\n");
scanf("%d", &input);
switch(input) {
case 1:
concatenate(cmd_gnu_0, lossname_RMSE);
compute_RMSE();
printf("\n");
break;
default:
printf("Wrong input try again\n");
compute_loss_function(size);
}
}
static void compute_r_square(size_t size)
{
double num_err = 0.0;
double den_err = 0.0;
size_t i;
for (i = 0; i < size; i++) {
num_err += (vector_y[i] - vector_predict[i]) * (vector_y[i] - vector_predict[i]);
den_err += (vector_y[i] - mean_y) * (vector_y[i] - mean_y);
}
r_square = 1 - (num_err/den_err);
printf("R_square = %lf\n", r_square);
}
static void compute_predict_for_x()
{
double x = 0.0;
printf("Please enter x value\n");
scanf("%lf", &x);
prediction = teta_0_intercept + (teta_1_grad * x);
printf("y^ if x = %lf -> %lf\n",x, prediction);
}
static void compute_max_x_y()
{
size_t i;
double tmp1= 0.0;
double tmp2= 0.0;
for (i = 0; i < size; i++) {
if (vector_x[i] > tmp1) {
tmp1 = vector_x[i];
max_x = vector_x[i];
}
if (vector_y[i] > tmp2) {
tmp2 = vector_y[i];
max_y = vector_y[i];
}
}
printf("vector_x max value %lf\n", max_x);
printf("vector_y max value %lf\n", max_y);
}
static void display_model_line()
{
sprintf(intercept, "%0.7lf", teta_0_intercept);
sprintf(grad, "%0.7lf", teta_1_grad);
sprintf(xrange, "%0.7lf", max_x + 1);
sprintf(yrange, "%0.7lf", max_y + 1);
concatenate(cmd_gnu_1, intercept);
concatenate(cmd_gnu_2, grad);
concatenate(cmd_gnu_3, xrange);
concatenate(cmd_gnu_3, "]");
concatenate(cmd_gnu_4, yrange);
concatenate(cmd_gnu_4, "]");
printf("grad = %s\n", grad);
printf("intercept = %s\n", intercept);
printf("xrange = %s\n", xrange);
printf("yrange = %s\n", yrange);
printf("cmd_gnu_0: %s\n", cmd_gnu_0);
printf("cmd_gnu_1: %s\n", cmd_gnu_1);
printf("cmd_gnu_2: %s\n", cmd_gnu_2);
printf("cmd_gnu_3: %s\n", cmd_gnu_3);
printf("cmd_gnu_4: %s\n", cmd_gnu_4);
printf("cmd_gnu_5: %s\n", cmd_gnu_5);
printf("cmd_gnu_6: %s\n", cmd_gnu_6);
/* print plot */
FILE *gnuplot_pipe = (FILE*)popen("gnuplot -persistent", "w");
FILE *temp = (FILE*)fopen("data.temp", "w");
/* create data.temp */
size_t i;
for (i = 0; i < size; i++)
{
fprintf(temp, "%f %f \n", vector_x[i], vector_y[i]);
}
/* display gnuplot */
for (i = 0; i < 7; i++)
{
fprintf(gnuplot_pipe, "%s \n", commands_gnuplot[i]);
}
}
int main(void)
{
printf("===========================================\n");
printf("INPUT DATA\n");
printf("===========================================\n");
user_input();
display_vector();
printf("\n");
printf("===========================================\n");
printf("COMPUTE MEAN X:Y, TETA_1 TETA_0\n");
printf("===========================================\n");
compute_mean_x_y();
compute_max_x_y();
compute_teta_1_grad();
compute_teta_0_intercept();
printf("\n");
printf("===========================================\n");
printf("COMPUTE LOSS FUNCTION\n");
printf("===========================================\n");
compute_loss_function();
printf("===========================================\n");
printf("COMPUTE R_square\n");
printf("===========================================\n");
compute_r_square(size);
printf("\n");
printf("===========================================\n");
printf("COMPUTE y^ according to x\n");
printf("===========================================\n");
compute_predict_for_x();
printf("\n");
printf("===========================================\n");
printf("DISPLAY LINEAR REGRESSION\n");
printf("===========================================\n");
display_model_line();
printf("\n");
return 0;
}
Look at Section 1 of this paper. This section expresses a 2D linear regression as a matrix multiplication exercise. As long as your data is well-behaved, this technique should permit you to develop a quick least squares fit.
Depending on the size of your data, it might be worthwhile to algebraically reduce the matrix multiplication to simple set of equations, thereby avoiding the need to write a matmult() function. (Be forewarned, this is completely impractical for more than 4 or 5 data points!)
The fastest, most efficient way to solve least squares, as far as I am aware, is to subtract (the gradient)/(the 2nd order gradient) from your parameter vector. (2nd order gradient = i.e. the diagonal of the Hessian.)
Here is the intuition:
Let's say you want to optimize least squares over a single parameter. This is equivalent to finding the vertex of a parabola. Then, for any random initial parameter, x0, the vertex of the loss function is located at x0 - f(1) / f(2). That's because adding - f(1) / f(2) to x will always zero out the derivative, f(1).
Side note: Implementing this in Tensorflow, the solution appeared at w0 - f(1) / f(2) / (number of weights), but I'm not sure if that's due to Tensorflow or if it's due to something else..

Resources