mirror of
https://github.com/TheAlgorithms/C
synced 2024-11-28 16:23:10 +03:00
fix documentations
This commit is contained in:
Krishna Vedala
parent
05d9af45f3
commit
814f9077b7
@ -35,7 +35,8 @@
|
||||
* the name observation is used to denote
|
||||
* a random point in plane
|
||||
*/
|
||||
typedef struct observation {
|
||||
typedef struct observation
|
||||
{
|
||||
double x; /**< abscissa of 2D data point */
|
||||
double y; /**< ordinate of 2D data point */
|
||||
int group; /**< the group no in which this observation would go */
|
||||
@ -48,13 +49,14 @@ typedef struct observation {
|
||||
* stores the count of observations
|
||||
* belonging to this cluster
|
||||
*/
|
||||
typedef struct cluster {
|
||||
typedef struct cluster
|
||||
{
|
||||
double x; /**< abscissa centroid of this cluster */
|
||||
double y; /**< ordinate of centroid of this cluster */
|
||||
size_t count; /**< count of observations present in this cluster */
|
||||
} cluster;
|
||||
|
||||
/*! @fn calculateNearest
|
||||
/*!
|
||||
* Returns the index of centroid nearest to
|
||||
* given observation
|
||||
*
|
||||
@ -64,16 +66,19 @@ typedef struct cluster {
|
||||
*
|
||||
* @returns the index of nearest centroid for given observation
|
||||
*/
|
||||
int calculateNearst(observation* o, cluster clusters[], int k) {
|
||||
int calculateNearst(observation* o, cluster clusters[], int k)
|
||||
{
|
||||
double minD = DBL_MAX;
|
||||
double dist = 0;
|
||||
int index = -1;
|
||||
int i = 0;
|
||||
for (; i < k; i++) {
|
||||
for (; i < k; i++)
|
||||
{
|
||||
/* Calculate Squared Distance*/
|
||||
dist = (clusters[i].x - o->x) * (clusters[i].x - o->x) +
|
||||
(clusters[i].y - o->y) * (clusters[i].y - o->y);
|
||||
if (dist < minD) {
|
||||
if (dist < minD)
|
||||
{
|
||||
minD = dist;
|
||||
index = i;
|
||||
}
|
||||
@ -81,7 +86,7 @@ int calculateNearst(observation* o, cluster clusters[], int k) {
|
||||
return index;
|
||||
}
|
||||
|
||||
/*! @fn calculateCentroid
|
||||
/*!
|
||||
* Calculate centoid and assign it to the cluster variable
|
||||
*
|
||||
* @param observations an array of observations whose centroid is calculated
|
||||
@ -90,12 +95,14 @@ int calculateNearst(observation* o, cluster clusters[], int k) {
|
||||
* centroid
|
||||
*/
|
||||
void calculateCentroid(observation observations[], size_t size,
|
||||
cluster* centroid) {
|
||||
cluster* centroid)
|
||||
{
|
||||
size_t i = 0;
|
||||
centroid->x = 0;
|
||||
centroid->y = 0;
|
||||
centroid->count = size;
|
||||
for (; i < size; i++) {
|
||||
for (; i < size; i++)
|
||||
{
|
||||
centroid->x += observations[i].x;
|
||||
centroid->y += observations[i].y;
|
||||
observations[i].group = 0;
|
||||
@ -104,7 +111,7 @@ void calculateCentroid(observation observations[], size_t size,
|
||||
centroid->y /= centroid->count;
|
||||
}
|
||||
|
||||
/*! @fn kMeans
|
||||
/*!
|
||||
* --K Means Algorithm--
|
||||
* 1. Assign each observation to one of k groups
|
||||
* creating a random initial clustering
|
||||
@ -117,15 +124,18 @@ void calculateCentroid(observation observations[], size_t size,
|
||||
* 5. Repeat step 2,3,4 until there is no change
|
||||
* the current clustering and is same as last
|
||||
* clustering.
|
||||
*
|
||||
* @param observations an array of observations to cluster
|
||||
* @param size size of observations array
|
||||
* @param k no of clusters to be made
|
||||
*
|
||||
* @returns pointer to cluster object
|
||||
*/
|
||||
cluster* kMeans(observation observations[], size_t size, int k) {
|
||||
cluster* kMeans(observation observations[], size_t size, int k)
|
||||
{
|
||||
cluster* clusters = NULL;
|
||||
if (k <= 1) {
|
||||
if (k <= 1)
|
||||
{
|
||||
/*
|
||||
If we have to cluster them only in one group
|
||||
then calculate centroid of observations and
|
||||
@ -134,53 +144,66 @@ cluster* kMeans(observation observations[], size_t size, int k) {
|
||||
clusters = (cluster*)malloc(sizeof(cluster));
|
||||
memset(clusters, 0, sizeof(cluster));
|
||||
calculateCentroid(observations, size, clusters);
|
||||
} else if (k < size) {
|
||||
}
|
||||
else if (k < size)
|
||||
{
|
||||
clusters = malloc(sizeof(cluster) * k);
|
||||
memset(clusters, 0, k * sizeof(cluster));
|
||||
/* STEP 1 */
|
||||
for (size_t j = 0; j < size; j++) {
|
||||
for (size_t j = 0; j < size; j++)
|
||||
{
|
||||
observations[j].group = rand() % k;
|
||||
}
|
||||
size_t changed = 0;
|
||||
size_t minAcceptedError =
|
||||
size / 10000; // Do until 99.99 percent points are in correct cluster
|
||||
size /
|
||||
10000; // Do until 99.99 percent points are in correct cluster
|
||||
int t = 0;
|
||||
do {
|
||||
do
|
||||
{
|
||||
/* Initialize clusters */
|
||||
for (int i = 0; i < k; i++) {
|
||||
for (int i = 0; i < k; i++)
|
||||
{
|
||||
clusters[i].x = 0;
|
||||
clusters[i].y = 0;
|
||||
clusters[i].count = 0;
|
||||
}
|
||||
/* STEP 2*/
|
||||
for (size_t j = 0; j < size; j++) {
|
||||
for (size_t j = 0; j < size; j++)
|
||||
{
|
||||
t = observations[j].group;
|
||||
clusters[t].x += observations[j].x;
|
||||
clusters[t].y += observations[j].y;
|
||||
clusters[t].count++;
|
||||
}
|
||||
for (int i = 0; i < k; i++) {
|
||||
for (int i = 0; i < k; i++)
|
||||
{
|
||||
clusters[i].x /= clusters[i].count;
|
||||
clusters[i].y /= clusters[i].count;
|
||||
}
|
||||
/* STEP 3 and 4 */
|
||||
changed = 0; // this variable stores change in clustering
|
||||
for (size_t j = 0; j < size; j++) {
|
||||
for (size_t j = 0; j < size; j++)
|
||||
{
|
||||
t = calculateNearst(observations + j, clusters, k);
|
||||
if (t != observations[j].group) {
|
||||
if (t != observations[j].group)
|
||||
{
|
||||
changed++;
|
||||
observations[j].group = t;
|
||||
}
|
||||
}
|
||||
} while (changed > minAcceptedError); // Keep on grouping until we have
|
||||
// got almost best clustering
|
||||
} else {
|
||||
}
|
||||
else
|
||||
{
|
||||
/* If no of clusters is more than observations
|
||||
each observation can be its own cluster
|
||||
*/
|
||||
clusters = (cluster*)malloc(sizeof(cluster) * k);
|
||||
memset(clusters, 0, k * sizeof(cluster));
|
||||
for (int j = 0; j < size; j++) {
|
||||
for (int j = 0; j < size; j++)
|
||||
{
|
||||
clusters[j].x = observations[j].x;
|
||||
clusters[j].y = observations[j].y;
|
||||
clusters[j].count = 1;
|
||||
@ -195,21 +218,24 @@ cluster* kMeans(observation observations[], size_t size, int k) {
|
||||
* @}
|
||||
*/
|
||||
|
||||
/*! @fn printEPS
|
||||
/*!
|
||||
* A function to print observations and clusters
|
||||
* The code is taken from
|
||||
* @link http://rosettacode.org/wiki/K-means%2B%2B_clustering
|
||||
* its C implementation
|
||||
* http://rosettacode.org/wiki/K-means%2B%2B_clustering.
|
||||
* Even the K Means code is also inspired from it
|
||||
*
|
||||
* Note: To print in a file use pipeline operator ( ./a.out > image.eps )
|
||||
* @note To print in a file use pipeline operator
|
||||
* ```sh
|
||||
* ./k_means_clustering > image.eps
|
||||
* ```
|
||||
*
|
||||
* @param observations observations array
|
||||
* @param len size of observation array
|
||||
* @param cent clusters centroid's array
|
||||
* @param k size of cent array
|
||||
*/
|
||||
void printEPS(observation pts[], size_t len, cluster cent[], int k) {
|
||||
void printEPS(observation pts[], size_t len, cluster cent[], int k)
|
||||
{
|
||||
int W = 400, H = 400;
|
||||
double min_x = DBL_MAX, max_x = DBL_MIN, min_y = DBL_MAX, max_y = DBL_MIN;
|
||||
double scale = 0, cx = 0, cy = 0;
|
||||
@ -217,20 +243,27 @@ void printEPS(observation pts[], size_t len, cluster cent[], int k) {
|
||||
int i;
|
||||
size_t j;
|
||||
double kd = k * 1.0;
|
||||
for (i = 0; i < k; i++) {
|
||||
for (i = 0; i < k; i++)
|
||||
{
|
||||
*(colors + 3 * i) = (3 * (i + 1) % k) / kd;
|
||||
*(colors + 3 * i + 1) = (7 * i % k) / kd;
|
||||
*(colors + 3 * i + 2) = (9 * i % k) / kd;
|
||||
}
|
||||
|
||||
for (j = 0; j < len; j++) {
|
||||
if (max_x < pts[j].x) max_x = pts[j].x;
|
||||
if (min_x > pts[j].x) min_x = pts[j].x;
|
||||
if (max_y < pts[j].y) max_y = pts[j].y;
|
||||
if (min_y > pts[j].y) min_y = pts[j].y;
|
||||
for (j = 0; j < len; j++)
|
||||
{
|
||||
if (max_x < pts[j].x)
|
||||
max_x = pts[j].x;
|
||||
if (min_x > pts[j].x)
|
||||
min_x = pts[j].x;
|
||||
if (max_y < pts[j].y)
|
||||
max_y = pts[j].y;
|
||||
if (min_y > pts[j].y)
|
||||
min_y = pts[j].y;
|
||||
}
|
||||
scale = W / (max_x - min_x);
|
||||
if (scale > (H / (max_y - min_y))) {
|
||||
if (scale > (H / (max_y - min_y)))
|
||||
{
|
||||
scale = H / (max_y - min_y);
|
||||
};
|
||||
cx = (max_x + min_x) / 2;
|
||||
@ -244,11 +277,14 @@ void printEPS(observation pts[], size_t len, cluster cent[], int k) {
|
||||
"/s { moveto -2 0 m 2 2 l 2 -2 l -2 -2 l closepath "
|
||||
" gsave 1 setgray fill grestore gsave 3 setlinewidth"
|
||||
" 1 setgray stroke grestore 0 setgray stroke }def\n");
|
||||
for (int i = 0; i < k; i++) {
|
||||
printf("%g %g %g setrgbcolor\n", *(colors + 3 * i), *(colors + 3 * i + 1),
|
||||
*(colors + 3 * i + 2));
|
||||
for (j = 0; j < len; j++) {
|
||||
if (pts[j].group != i) continue;
|
||||
for (int i = 0; i < k; i++)
|
||||
{
|
||||
printf("%g %g %g setrgbcolor\n", *(colors + 3 * i),
|
||||
*(colors + 3 * i + 1), *(colors + 3 * i + 2));
|
||||
for (j = 0; j < len; j++)
|
||||
{
|
||||
if (pts[j].group != i)
|
||||
continue;
|
||||
printf("%.3f %.3f c\n", (pts[j].x - cx) * scale + W / 2,
|
||||
(pts[j].y - cy) * scale + H / 2);
|
||||
}
|
||||
@ -261,7 +297,7 @@ void printEPS(observation pts[], size_t len, cluster cent[], int k) {
|
||||
free(colors);
|
||||
}
|
||||
|
||||
/*! @fn test
|
||||
/*!
|
||||
* A function to test the kMeans function
|
||||
* Generates 100000 points in a circle of
|
||||
* radius 20.0 with center at (0,0)
|
||||
@ -270,15 +306,19 @@ void printEPS(observation pts[], size_t len, cluster cent[], int k) {
|
||||
* <img alt="Output for 100000 points divided in 5 clusters" src=
|
||||
* "https://raw.githubusercontent.com/TheAlgorithms/C/docs/images/machine_learning/k_means_clustering/kMeansTest1.png"
|
||||
* width="400px" heiggt="400px">
|
||||
* @returns None
|
||||
*/
|
||||
static void test() {
|
||||
static void test()
|
||||
{
|
||||
size_t size = 100000L;
|
||||
observation* observations = (observation*)malloc(sizeof(observation) * size);
|
||||
observation* observations =
|
||||
(observation*)malloc(sizeof(observation) * size);
|
||||
double maxRadius = 20.00;
|
||||
double radius = 0;
|
||||
double ang = 0;
|
||||
size_t i = 0;
|
||||
for (; i < size; i++) {
|
||||
for (; i < size; i++)
|
||||
{
|
||||
radius = maxRadius * ((double)rand() / RAND_MAX);
|
||||
ang = 2 * M_PI * ((double)rand() / RAND_MAX);
|
||||
observations[i].x = radius * cos(ang);
|
||||
@ -292,7 +332,7 @@ static void test() {
|
||||
free(clusters);
|
||||
}
|
||||
|
||||
/*! @fn test2
|
||||
/*!
|
||||
* A function to test the kMeans function
|
||||
* Generates 1000000 points in a circle of
|
||||
* radius 20.0 with center at (0,0)
|
||||
@ -301,15 +341,19 @@ static void test() {
|
||||
* <img alt="Output for 1000000 points divided in 11 clusters" src=
|
||||
* "https://raw.githubusercontent.com/TheAlgorithms/C/docs/images/machine_learning/k_means_clustering/kMeansTest2.png"
|
||||
* width="400px" heiggt="400px">
|
||||
* @returns None
|
||||
*/
|
||||
void test2() {
|
||||
void test2()
|
||||
{
|
||||
size_t size = 1000000L;
|
||||
observation* observations = (observation*)malloc(sizeof(observation) * size);
|
||||
observation* observations =
|
||||
(observation*)malloc(sizeof(observation) * size);
|
||||
double maxRadius = 20.00;
|
||||
double radius = 0;
|
||||
double ang = 0;
|
||||
size_t i = 0;
|
||||
for (; i < size; i++) {
|
||||
for (; i < size; i++)
|
||||
{
|
||||
radius = maxRadius * ((double)rand() / RAND_MAX);
|
||||
ang = 2 * M_PI * ((double)rand() / RAND_MAX);
|
||||
observations[i].x = radius * cos(ang);
|
||||
@ -323,11 +367,12 @@ void test2() {
|
||||
free(clusters);
|
||||
}
|
||||
|
||||
/*! @fn main
|
||||
/*!
|
||||
* This function calls the test
|
||||
* function
|
||||
*/
|
||||
int main() {
|
||||
int main()
|
||||
{
|
||||
srand(time(NULL));
|
||||
test();
|
||||
/* test2(); */
|
||||
|
||||
Loading…
Reference in New Issue
Block a user