mirror of https://github.com/TheAlgorithms/C
Merge pull request #16 from kvedala/documentation/fixes
* added unsupervised learning algorithm * updated with upstream/master
This commit is contained in:
commit
e8cebc36b2
|
@ -29,6 +29,7 @@
|
|||
* [Create Node](https://github.com/TheAlgorithms/C-Plus-Plus/blob/master/data_structures/binary_trees/create_node.c)
|
||||
* [Recursive Traversals](https://github.com/TheAlgorithms/C-Plus-Plus/blob/master/data_structures/binary_trees/recursive_traversals.c)
|
||||
* [Redblacktree](https://github.com/TheAlgorithms/C-Plus-Plus/blob/master/data_structures/binary_trees/redblacktree.c)
|
||||
* [Threaded Binary Trees](https://github.com/TheAlgorithms/C-Plus-Plus/blob/master/data_structures/binary_trees/threaded_binary_trees.c)
|
||||
* Dictionary
|
||||
* [Dict](https://github.com/TheAlgorithms/C-Plus-Plus/blob/master/data_structures/dictionary/dict.c)
|
||||
* [Dict](https://github.com/TheAlgorithms/C-Plus-Plus/blob/master/data_structures/dictionary/dict.h)
|
||||
|
@ -203,6 +204,7 @@
|
|||
|
||||
## Machine Learning
|
||||
* [Adaline Learning](https://github.com/TheAlgorithms/C-Plus-Plus/blob/master/machine_learning/adaline_learning.c)
|
||||
* [Kohonen Som Image](https://github.com/TheAlgorithms/C-Plus-Plus/blob/master/machine_learning/kohonen_som_image.c)
|
||||
* [Kohonen Som Trace](https://github.com/TheAlgorithms/C-Plus-Plus/blob/master/machine_learning/kohonen_som_trace.c)
|
||||
|
||||
## Misc
|
||||
|
|
|
@ -0,0 +1,247 @@
|
|||
/**
|
||||
* @file
|
||||
* \brief This file is a simple implementation of a Threaded Binary Tree
|
||||
*
|
||||
* Threaded Binary Tree is a binary tree variant in which all left child
|
||||
* pointers that are NULL (in Linked list representation) point to its
|
||||
* in-order predecessor, and all right child pointers that are NULL
|
||||
* (in Linked list representation) point to its in-order successor.
|
||||
* It has the following functionalities:
|
||||
* - Insertion
|
||||
* - Search
|
||||
* - Deletion
|
||||
* - Listing of node keys inorder,preorder,postorder
|
||||
*
|
||||
* -see binary_search_tree.c
|
||||
*
|
||||
* \author [Amitha Nayak](https://github.com/amitnayakblr)
|
||||
*/
|
||||
|
||||
#include <stdio.h>
|
||||
#include <stdlib.h>
|
||||
|
||||
/**
|
||||
* Node, the basic data structure of the tree
|
||||
**/
|
||||
typedef struct Node {
|
||||
int data; /**< stores the number */
|
||||
struct Node *llink; /**< link to left child */
|
||||
struct Node *rlink; /**< link to right child */
|
||||
} node;
|
||||
|
||||
/**
|
||||
* creates a new node
|
||||
* param[in] data value to be inserted
|
||||
* \returns a pointer to the new node
|
||||
**/
|
||||
node *create_node(int data) {
|
||||
node *ptr = (node *)malloc(sizeof(node));
|
||||
ptr->rlink = ptr->llink = NULL;
|
||||
ptr->data = data;
|
||||
return ptr;
|
||||
}
|
||||
|
||||
/**
|
||||
* inserts a node into the tree
|
||||
* param[in,out] root pointer to node pointer to the topmost node of the tree
|
||||
* param[in] data value to be inserted into the tree
|
||||
*/
|
||||
void insert_bt(node **root, int data) {
|
||||
node *new_node = create_node(data);
|
||||
node *temp; // to be deleted
|
||||
node *prev; // keeps track of the parent of the element deleted
|
||||
if (*root == NULL) {
|
||||
*root = new_node;
|
||||
} else {
|
||||
temp = *root;
|
||||
prev = NULL;
|
||||
while (temp != NULL) {
|
||||
if (new_node->data > temp->data) {
|
||||
prev = temp;
|
||||
temp = temp->rlink;
|
||||
} else if (new_node->data < temp->data) {
|
||||
prev = temp;
|
||||
temp = temp->llink;
|
||||
} else {
|
||||
return;
|
||||
}
|
||||
}
|
||||
|
||||
if (new_node->data > prev->data) {
|
||||
prev->rlink = new_node;
|
||||
} else {
|
||||
prev->llink = new_node;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* searches for the element
|
||||
* \param[in] root node pointer to the topmost node of the tree
|
||||
* \param[in] ele value searched for
|
||||
*/
|
||||
void search(node *root, int ele) {
|
||||
node *temp = root;
|
||||
while (temp != NULL) {
|
||||
if (temp->data == ele) {
|
||||
break;
|
||||
} else if (ele > temp->data) {
|
||||
temp = temp->rlink;
|
||||
} else {
|
||||
temp = temp->llink;
|
||||
}
|
||||
}
|
||||
|
||||
if (temp == NULL) {
|
||||
printf("%s\n", "Element not found.");
|
||||
} else
|
||||
printf("%s\n", "Element found.");
|
||||
}
|
||||
|
||||
/**
|
||||
* performs inorder traversal
|
||||
* param[in] curr node pointer to the topmost node of the tree
|
||||
*/
|
||||
void inorder_display(node *curr) {
|
||||
if (curr != NULL) {
|
||||
inorder_display(curr->llink);
|
||||
printf("%d\t", curr->data);
|
||||
inorder_display(curr->rlink);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* performs postorder traversal
|
||||
* param[in] curr node pointer to the topmost node of the tree
|
||||
*/
|
||||
void postorder_display(node *curr) {
|
||||
if (curr != NULL) {
|
||||
postorder_display(curr->llink);
|
||||
postorder_display(curr->rlink);
|
||||
printf("%d\t", curr->data);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* performs preorder traversal
|
||||
* param[in] curr node pointer to the topmost node of the tree
|
||||
*/
|
||||
void preorder_display(node *curr) {
|
||||
if (curr != NULL) {
|
||||
printf("%d\t", curr->data);
|
||||
preorder_display(curr->llink);
|
||||
preorder_display(curr->rlink);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* deletion of a node from the tree
|
||||
* if the node isn't present in the tree, it takes no action.
|
||||
* param[in,out] root pointer to node pointer to the topmost node of the tree
|
||||
* param[in] ele value to be deleted from the tree
|
||||
*/
|
||||
void delete_bt(node **root, int ele) {
|
||||
node *temp;
|
||||
node *prev;
|
||||
if (*root == NULL)
|
||||
return;
|
||||
else {
|
||||
temp = *root;
|
||||
prev = NULL;
|
||||
// search
|
||||
while (temp != NULL) {
|
||||
if (temp->data == ele) {
|
||||
break;
|
||||
} else if (ele > temp->data) {
|
||||
prev = temp;
|
||||
temp = temp->rlink;
|
||||
} else {
|
||||
prev = temp;
|
||||
temp = temp->llink;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (temp == NULL)
|
||||
return;
|
||||
else {
|
||||
node *replacement; // deleted node's replacement
|
||||
node *t;
|
||||
if (temp->llink == NULL && temp->rlink == NULL) {
|
||||
replacement = NULL;
|
||||
} else if (temp->llink == NULL && temp->rlink != NULL) {
|
||||
replacement = temp->rlink;
|
||||
} else if (temp->llink != NULL && temp->rlink == NULL) {
|
||||
replacement = temp->llink;
|
||||
} else {
|
||||
replacement = temp->rlink; // replaced with inorder successor
|
||||
t = replacement;
|
||||
while (t->llink != NULL) {
|
||||
t = t->llink;
|
||||
}
|
||||
t->llink = temp->llink; // leftmost node of the replacement is linked to
|
||||
// the left child of the deleted node
|
||||
}
|
||||
|
||||
if (temp == *root) {
|
||||
free(*root);
|
||||
*root = replacement;
|
||||
} else if (prev->llink == temp) {
|
||||
free(prev->llink);
|
||||
prev->llink = replacement;
|
||||
} else if (prev->rlink == temp) {
|
||||
free(prev->rlink);
|
||||
prev->rlink = replacement;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* main function
|
||||
*/
|
||||
int main() {
|
||||
printf("BINARY THREADED TREE: \n");
|
||||
node *root = NULL;
|
||||
int choice, n;
|
||||
do {
|
||||
printf("%s\n", "1. Insert into BT");
|
||||
printf("%s\n", "2. Print BT - inorder");
|
||||
printf("%s\n", "3. Print BT - preorder");
|
||||
printf("%s\n", "4. print BT - postorder");
|
||||
printf("%s\n", "5. delete from BT");
|
||||
printf("%s\n", "6. search in BT");
|
||||
printf("%s\n", "Type 0 to exit");
|
||||
scanf("%d", &choice);
|
||||
|
||||
switch (choice) {
|
||||
case 1:
|
||||
printf("%s\n", "Enter a no:");
|
||||
scanf("%d", &n);
|
||||
insert_bt(&root, n);
|
||||
break;
|
||||
case 2:
|
||||
inorder_display(root);
|
||||
printf("\n");
|
||||
break;
|
||||
case 3:
|
||||
preorder_display(root);
|
||||
printf("\n");
|
||||
break;
|
||||
case 4:
|
||||
postorder_display(root);
|
||||
printf("\n");
|
||||
break;
|
||||
case 5:
|
||||
printf("%s\n", "Enter a no:");
|
||||
scanf("%d", &n);
|
||||
delete_bt(&root, n);
|
||||
break;
|
||||
case 6:
|
||||
printf("%s\n", "Enter a no:");
|
||||
scanf("%d", &n);
|
||||
search(root, n);
|
||||
break;
|
||||
}
|
||||
} while (choice != 0);
|
||||
return 0;
|
||||
}
|
|
@ -0,0 +1,700 @@
|
|||
/**
|
||||
* \file
|
||||
* \brief [Kohonen self organizing
|
||||
* map](https://en.wikipedia.org/wiki/Self-organizing_map) (topological map)
|
||||
*
|
||||
* \author [Krishna Vedala](https://github.com/kvedala)
|
||||
*
|
||||
* This example implements a powerful unsupervised learning algorithm called as
|
||||
* a self organizing map. The algorithm creates a connected network of weights
|
||||
* that closely follows the given data points. This thus creates a topological
|
||||
* map of the given data i.e., it maintains the relationship between varipus
|
||||
* data points in a much higher dimesional space by creating an equivalent in a
|
||||
* 2-dimensional space.
|
||||
* <img alt="Trained topological maps for the test cases in the program"
|
||||
* src="https://raw.githubusercontent.com/kvedala/C/docs/images/machine_learning/kohonen/2D_Kohonen_SOM.svg"
|
||||
* />
|
||||
*/
|
||||
#define _USE_MATH_DEFINES // required for MS Visual C
|
||||
#include <math.h>
|
||||
#include <stdio.h>
|
||||
#include <stdlib.h>
|
||||
#include <time.h>
|
||||
#ifdef _OPENMP // check if OpenMP based parallellization is available
|
||||
#include <omp.h>
|
||||
#endif
|
||||
|
||||
#define max(a, b) (a > b ? a : b) // shorthand for maximum value
|
||||
#define min(a, b) (a < b ? a : b) // shorthand for minimum value
|
||||
|
||||
/** to store info regarding 3D arrays */
|
||||
struct array_3d
|
||||
{
|
||||
int dim1, dim2, dim3; /**< lengths of each dimension */
|
||||
double *data; /**< pointer to data */
|
||||
};
|
||||
|
||||
/** Function that returns the pointer to (x, y, z) ^th location in the
|
||||
* linear 3D array given by:
|
||||
* \f[
|
||||
* X_{i,j,k} = i\times M\times N + j\times N + k
|
||||
* \f]
|
||||
* where \f$L\f$, \f$M\f$ and \f$N\f$ are the 3D matrix dimensions.
|
||||
* \param[in] arr pointer to ::array_3d structure
|
||||
* \param[in] x first index
|
||||
* \param[in] y second index
|
||||
* \param[in] z third index
|
||||
* \returns pointer to (x,y,z)^th location of data
|
||||
*/
|
||||
double *data_3d(const struct array_3d *arr, int x, int y, int z)
|
||||
{
|
||||
int offset = (x * arr->dim2 * arr->dim3) + (y * arr->dim3) + z;
|
||||
return arr->data + offset;
|
||||
}
|
||||
|
||||
/**
|
||||
* Helper function to generate a random number in a given interval.
|
||||
* \n Steps:
|
||||
* 1. `r1 = rand() % 100` gets a random number between 0 and 99
|
||||
* 2. `r2 = r1 / 100` converts random number to be between 0 and 0.99
|
||||
* 3. scale and offset the random number to given range of \f$[a,b)\f$
|
||||
* \f[
|
||||
* y = (b - a) \times \frac{\text{(random number between 0 and RAND_MAX)} \;
|
||||
* \text{mod}\; 100}{100} + a \f]
|
||||
*
|
||||
* \param[in] a lower limit
|
||||
* \param[in] b upper limit
|
||||
* \returns random number in the range \f$[a,b)\f$
|
||||
*/
|
||||
double _random(double a, double b)
|
||||
{
|
||||
return ((b - a) * (rand() % 100) / 100.f) + a;
|
||||
}
|
||||
|
||||
/**
|
||||
* Save a given n-dimensional data martix to file.
|
||||
*
|
||||
* \param[in] fname filename to save in (gets overwriten without confirmation)
|
||||
* \param[in] X matrix to save
|
||||
* \param[in] num_points rows in the matrix = number of points
|
||||
* \param[in] num_features columns in the matrix = dimensions of points
|
||||
* \returns 0 if all ok
|
||||
* \returns -1 if file creation failed
|
||||
*/
|
||||
int save_2d_data(const char *fname, double **X, int num_points,
|
||||
int num_features)
|
||||
{
|
||||
FILE *fp = fopen(fname, "wt");
|
||||
if (!fp) // error with fopen
|
||||
{
|
||||
char msg[120];
|
||||
sprintf(msg, "File error (%s): ", fname);
|
||||
perror(msg);
|
||||
return -1;
|
||||
}
|
||||
|
||||
for (int i = 0; i < num_points; i++) // for each point in the array
|
||||
{
|
||||
for (int j = 0; j < num_features; j++) // for each feature in the array
|
||||
{
|
||||
fprintf(fp, "%.4g", X[i][j]); // print the feature value
|
||||
if (j < num_features - 1) // if not the last feature
|
||||
fputc(',', fp); // suffix comma
|
||||
}
|
||||
if (i < num_points - 1) // if not the last row
|
||||
fputc('\n', fp); // start a new line
|
||||
}
|
||||
fclose(fp);
|
||||
return 0;
|
||||
}
|
||||
|
||||
/**
|
||||
* Create the distance matrix or U-matrix from the trained weights and save to
|
||||
* disk.
|
||||
*
|
||||
* \param[in] fname filename to save in (gets overwriten without confirmation)
|
||||
* \param[in] W model matrix to save
|
||||
* \returns 0 if all ok
|
||||
* \returns -1 if file creation failed
|
||||
*/
|
||||
int save_u_matrix(const char *fname, struct array_3d *W)
|
||||
{
|
||||
FILE *fp = fopen(fname, "wt");
|
||||
if (!fp) // error with fopen
|
||||
{
|
||||
char msg[120];
|
||||
sprintf(msg, "File error (%s): ", fname);
|
||||
perror(msg);
|
||||
return -1;
|
||||
}
|
||||
|
||||
int R = max(W->dim1 >> 3, 2); /* neighborhood range */
|
||||
|
||||
for (int i = 0; i < W->dim1; i++) // for each x
|
||||
{
|
||||
for (int j = 0; j < W->dim2; j++) // for each y
|
||||
{
|
||||
double distance = 0.f;
|
||||
int k;
|
||||
|
||||
int from_x = max(0, i - R);
|
||||
int to_x = min(W->dim1, i + R + 1);
|
||||
int from_y = max(0, j - R);
|
||||
int to_y = min(W->dim2, j + R + 1);
|
||||
int l;
|
||||
#ifdef _OPENMP
|
||||
#pragma omp parallel for reduction(+ : distance)
|
||||
#endif
|
||||
for (l = from_x; l < to_x; l++)
|
||||
{
|
||||
for (int m = from_y; m < to_y; m++)
|
||||
{
|
||||
double d = 0.f;
|
||||
for (k = 0; k < W->dim3; k++) // for each feature
|
||||
{
|
||||
double *w1 = data_3d(W, i, j, k);
|
||||
double *w2 = data_3d(W, l, m, k);
|
||||
d += (w1[0] - w2[0]) * (w1[0] - w2[0]);
|
||||
// distance += w1[0] * w1[0];
|
||||
}
|
||||
distance += sqrt(d);
|
||||
// distance += d;
|
||||
}
|
||||
}
|
||||
|
||||
distance /= R * R; // mean disntance from neighbors
|
||||
fprintf(fp, "%.4g", distance); // print the mean separation
|
||||
if (j < W->dim2 - 1) // if not the last column
|
||||
fputc(',', fp); // suffix comma
|
||||
}
|
||||
if (i < W->dim1 - 1) // if not the last row
|
||||
fputc('\n', fp); // start a new line
|
||||
}
|
||||
fclose(fp);
|
||||
return 0;
|
||||
}
|
||||
|
||||
/**
|
||||
* Get minimum value and index of the value in a matrix
|
||||
* \param[in] X matrix to search
|
||||
* \param[in] N number of points in the vector
|
||||
* \param[out] val minimum value found
|
||||
* \param[out] idx index where minimum value was found
|
||||
*/
|
||||
void get_min_2d(double **X, int N, double *val, int *x_idx, int *y_idx)
|
||||
{
|
||||
val[0] = INFINITY; // initial min value
|
||||
|
||||
for (int i = 0; i < N; i++) // traverse each x-index
|
||||
{
|
||||
for (int j = 0; j < N; j++) // traverse each y-index
|
||||
{
|
||||
if (X[i][j] < val[0]) // if a lower value is found
|
||||
{ // save the value and its index
|
||||
x_idx[0] = i;
|
||||
y_idx[0] = j;
|
||||
val[0] = X[i][j];
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Update weights of the SOM using Kohonen algorithm
|
||||
*
|
||||
* \param[in] X data point
|
||||
* \param[in,out] W weights matrix
|
||||
* \param[in,out] D temporary vector to store distances
|
||||
* \param[in] num_out number of output points
|
||||
* \param[in] num_features number of features per input sample
|
||||
* \param[in] alpha learning rate \f$0<\alpha\le1\f$
|
||||
* \param[in] R neighborhood range
|
||||
*/
|
||||
double update_weights(const double *X, struct array_3d *W, double **D,
|
||||
int num_out, int num_features, double alpha, int R)
|
||||
{
|
||||
int x, y, k;
|
||||
double d_min = 0.f;
|
||||
|
||||
#ifdef _OPENMP
|
||||
#pragma omp for
|
||||
#endif
|
||||
// step 1: for each 2D output point
|
||||
for (x = 0; x < num_out; x++)
|
||||
{
|
||||
for (y = 0; y < num_out; y++)
|
||||
{
|
||||
D[x][y] = 0.f;
|
||||
// compute Euclidian distance of each output
|
||||
// point from the current sample
|
||||
for (k = 0; k < num_features; k++)
|
||||
{
|
||||
double *w = data_3d(W, x, y, k);
|
||||
D[x][y] += (w[0] - X[k]) * (w[0] - X[k]);
|
||||
}
|
||||
D[x][y] = sqrt(D[x][y]);
|
||||
}
|
||||
}
|
||||
|
||||
// step 2: get closest node i.e., node with smallest Euclidian distance to
|
||||
// the current pattern
|
||||
int d_min_x, d_min_y;
|
||||
get_min_2d(D, num_out, &d_min, &d_min_x, &d_min_y);
|
||||
|
||||
// step 3a: get the neighborhood range
|
||||
int from_x = max(0, d_min_x - R);
|
||||
int to_x = min(num_out, d_min_x + R + 1);
|
||||
int from_y = max(0, d_min_y - R);
|
||||
int to_y = min(num_out, d_min_y + R + 1);
|
||||
|
||||
// step 3b: update the weights of nodes in the
|
||||
// neighborhood
|
||||
#ifdef _OPENMP
|
||||
#pragma omp for
|
||||
#endif
|
||||
for (x = from_x; x < to_x; x++)
|
||||
{
|
||||
for (y = from_y; y < to_y; y++)
|
||||
{
|
||||
for (k = 0; k < num_features; k++)
|
||||
{
|
||||
// apply scaling inversely proportional to distance from the
|
||||
// current node
|
||||
double d2 = (d_min_x - x) * (d_min_x - x) +
|
||||
(d_min_y - y) * (d_min_y - y);
|
||||
double scale_factor = exp(-d2 * 0.5 / (alpha * alpha));
|
||||
|
||||
double *w = data_3d(W, x, y, k);
|
||||
|
||||
// update weights of nodes in the neighborhood
|
||||
w[0] += alpha * scale_factor * (X[k] - w[0]);
|
||||
}
|
||||
}
|
||||
}
|
||||
return d_min;
|
||||
}
|
||||
|
||||
/**
|
||||
* Apply incremental algorithm with updating neighborhood and learning rates
|
||||
* on all samples in the given datset.
|
||||
*
|
||||
* \param[in] X data set
|
||||
* \param[in,out] W weights matrix
|
||||
* \param[in] D temporary vector to store distances
|
||||
* \param[in] num_samples number of output points
|
||||
* \param[in] num_features number of features per input sample
|
||||
* \param[in] num_out number of output points
|
||||
* \param[in] alpha_min terminal value of alpha
|
||||
*/
|
||||
void kohonen_som(double **X, struct array_3d *W, int num_samples,
|
||||
int num_features, int num_out, double alpha_min)
|
||||
{
|
||||
int R = num_out >> 2, iter = 0;
|
||||
double **D = (double **)malloc(num_out * sizeof(double *));
|
||||
for (int i = 0; i < num_out; i++)
|
||||
D[i] = (double *)malloc(num_out * sizeof(double));
|
||||
|
||||
double dmin = 1.f;
|
||||
// Loop alpha from 1 to slpha_min
|
||||
for (double alpha = 1.f; alpha > alpha_min && dmin > 1e-9;
|
||||
alpha -= 0.005, iter++)
|
||||
{
|
||||
dmin = 0.f;
|
||||
// Loop for each sample pattern in the data set
|
||||
for (int sample = 0; sample < num_samples; sample++)
|
||||
{
|
||||
const double *x = X[sample];
|
||||
// update weights for the current input pattern sample
|
||||
dmin = update_weights(x, W, D, num_out, num_features, alpha, R);
|
||||
}
|
||||
|
||||
// every 20th iteration, reduce the neighborhood range
|
||||
if (iter % 20 == 0 && R > 0)
|
||||
R--;
|
||||
|
||||
dmin /= num_samples;
|
||||
printf("alpha: %.4g\t R: %d\td_min: %.4g\n", alpha, R, dmin);
|
||||
}
|
||||
|
||||
for (int i = 0; i < num_out; i++)
|
||||
free(D[i]);
|
||||
free(D);
|
||||
}
|
||||
|
||||
/** Creates a random set of points distributed in four clusters in
|
||||
* 3D space with centroids at the points
|
||||
* * \f$(0,5, 0.5, 0.5)\f$
|
||||
* * \f$(0,5,-0.5, -0.5)\f$
|
||||
* * \f$(-0,5, 0.5, 0.5)\f$
|
||||
* * \f$(-0,5,-0.5, -0.5)\f$
|
||||
*
|
||||
* \param[out] data matrix to store data in
|
||||
* \param[in] N number of points required
|
||||
*/
|
||||
void test_2d_classes(double *const *data, int N)
|
||||
{
|
||||
const double R = 0.3; // radius of cluster
|
||||
int i;
|
||||
const int num_classes = 4;
|
||||
const double centres[][2] = {
|
||||
// centres of each class cluster
|
||||
{.5, .5}, // centre of class 1
|
||||
{.5, -.5}, // centre of class 2
|
||||
{-.5, .5}, // centre of class 3
|
||||
{-.5, -.5} // centre of class 4
|
||||
};
|
||||
|
||||
#ifdef _OPENMP
|
||||
#pragma omp for
|
||||
#endif
|
||||
for (i = 0; i < N; i++)
|
||||
{
|
||||
int class = rand() % num_classes; // select a random class for the point
|
||||
|
||||
// create random coordinates (x,y,z) around the centre of the class
|
||||
data[i][0] = _random(centres[class][0] - R, centres[class][0] + R);
|
||||
data[i][1] = _random(centres[class][1] - R, centres[class][1] + R);
|
||||
|
||||
/* The follosing can also be used
|
||||
for (int j = 0; j < 2; j++)
|
||||
data[i][j] = _random(centres[class][j] - R, centres[class][j] + R);
|
||||
*/
|
||||
}
|
||||
}
|
||||
|
||||
/** Test that creates a random set of points distributed in four clusters in
|
||||
* 2D space and trains an SOM that finds the topological pattern.
|
||||
* The following [CSV](https://en.wikipedia.org/wiki/Comma-separated_values)
|
||||
* files are created to validate the execution:
|
||||
* * `test1.csv`: random test samples points with a circular pattern
|
||||
* * `w11.csv`: initial random map
|
||||
* * `w12.csv`: trained SOM map
|
||||
*
|
||||
* The outputs can be readily plotted in [gnuplot](https:://gnuplot.info) using
|
||||
* the following snippet
|
||||
* ```gnuplot
|
||||
* set datafile separator ','
|
||||
* plot "test1.csv" title "original", \
|
||||
* "w11.csv" title "w1", \
|
||||
* "w12.csv" title "w2"
|
||||
* ```
|
||||
* ![Sample execution
|
||||
* output](https://raw.githubusercontent.com/kvedala/C/docs/images/machine_learning/kohonen/test1.svg)
|
||||
*/
|
||||
void test1()
|
||||
{
|
||||
int j, N = 300;
|
||||
int features = 2;
|
||||
int num_out = 30; // image size - N x N
|
||||
|
||||
// 2D space, hence size = number of rows * 2
|
||||
double **X = (double **)malloc(N * sizeof(double *));
|
||||
|
||||
// cluster nodex in 'x' * cluster nodes in 'y' * 2
|
||||
struct array_3d W;
|
||||
W.dim1 = num_out;
|
||||
W.dim2 = num_out;
|
||||
W.dim3 = features;
|
||||
W.data = (double *)malloc(num_out * num_out * features *
|
||||
sizeof(double)); // assign rows
|
||||
|
||||
for (int i = 0; i < max(num_out, N); i++) // loop till max(N, num_out)
|
||||
{
|
||||
if (i < N) // only add new arrays if i < N
|
||||
X[i] = (double *)malloc(features * sizeof(double));
|
||||
if (i < num_out) // only add new arrays if i < num_out
|
||||
{
|
||||
for (int k = 0; k < num_out; k++)
|
||||
{
|
||||
#ifdef _OPENMP
|
||||
#pragma omp for
|
||||
#endif
|
||||
// preallocate with random initial weights
|
||||
for (j = 0; j < features; j++)
|
||||
{
|
||||
double *w = data_3d(&W, i, k, j);
|
||||
w[0] = _random(-5, 5);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
test_2d_classes(X, N); // create test data around circumference of a circle
|
||||
save_2d_data("test1.csv", X, N, features); // save test data points
|
||||
save_u_matrix("w11.csv", &W); // save initial random weights
|
||||
kohonen_som(X, &W, N, features, num_out, 1e-4); // train the SOM
|
||||
save_u_matrix("w12.csv", &W); // save the resultant weights
|
||||
|
||||
for (int i = 0; i < N; i++)
|
||||
free(X[i]);
|
||||
free(X);
|
||||
free(W.data);
|
||||
}
|
||||
|
||||
/** Creates a random set of points distributed in four clusters in
|
||||
* 3D space with centroids at the points
|
||||
* * \f$(0,5, 0.5, 0.5)\f$
|
||||
* * \f$(0,5,-0.5, -0.5)\f$
|
||||
* * \f$(-0,5, 0.5, 0.5)\f$
|
||||
* * \f$(-0,5,-0.5, -0.5)\f$
|
||||
*
|
||||
* \param[out] data matrix to store data in
|
||||
* \param[in] N number of points required
|
||||
*/
|
||||
void test_3d_classes1(double *const *data, int N)
|
||||
{
|
||||
const double R = 0.2; // radius of cluster
|
||||
int i;
|
||||
const int num_classes = 4;
|
||||
const double centres[][3] = {
|
||||
// centres of each class cluster
|
||||
{.5, .5, .5}, // centre of class 1
|
||||
{.5, -.5, -.5}, // centre of class 2
|
||||
{-.5, .5, .5}, // centre of class 3
|
||||
{-.5, -.5 - .5} // centre of class 4
|
||||
};
|
||||
|
||||
#ifdef _OPENMP
|
||||
#pragma omp for
|
||||
#endif
|
||||
for (i = 0; i < N; i++)
|
||||
{
|
||||
int class = rand() % num_classes; // select a random class for the point
|
||||
|
||||
// create random coordinates (x,y,z) around the centre of the class
|
||||
data[i][0] = _random(centres[class][0] - R, centres[class][0] + R);
|
||||
data[i][1] = _random(centres[class][1] - R, centres[class][1] + R);
|
||||
data[i][2] = _random(centres[class][2] - R, centres[class][2] + R);
|
||||
|
||||
/* The follosing can also be used
|
||||
for (int j = 0; j < 3; j++)
|
||||
data[i][j] = _random(centres[class][j] - R, centres[class][j] + R);
|
||||
*/
|
||||
}
|
||||
}
|
||||
|
||||
/** Test that creates a random set of points distributed in 4 clusters in
|
||||
* 3D space and trains an SOM that finds the topological pattern. The following
|
||||
* [CSV](https://en.wikipedia.org/wiki/Comma-separated_values) files are created
|
||||
* to validate the execution:
|
||||
* * `test2.csv`: random test samples points with a lamniscate pattern
|
||||
* * `w21.csv`: initial random map
|
||||
* * `w22.csv`: trained SOM map
|
||||
*
|
||||
* The outputs can be readily plotted in [gnuplot](https:://gnuplot.info) using
|
||||
* the following snippet
|
||||
* ```gnuplot
|
||||
* set datafile separator ','
|
||||
* plot "test2.csv" title "original", \
|
||||
* "w21.csv" title "w1", \
|
||||
* "w22.csv" title "w2"
|
||||
* ```
|
||||
* ![Sample execution
|
||||
* output](https://raw.githubusercontent.com/kvedala/C/docs/images/machine_learning/kohonen/test2.svg)
|
||||
*/
|
||||
void test2()
|
||||
{
|
||||
int j, N = 500;
|
||||
int features = 3;
|
||||
int num_out = 30; // image size - N x N
|
||||
|
||||
// 3D space, hence size = number of rows * 3
|
||||
double **X = (double **)malloc(N * sizeof(double *));
|
||||
|
||||
// cluster nodex in 'x' * cluster nodes in 'y' * 2
|
||||
struct array_3d W;
|
||||
W.dim1 = num_out;
|
||||
W.dim2 = num_out;
|
||||
W.dim3 = features;
|
||||
W.data = (double *)malloc(num_out * num_out * features *
|
||||
sizeof(double)); // assign rows
|
||||
|
||||
for (int i = 0; i < max(num_out, N); i++) // loop till max(N, num_out)
|
||||
{
|
||||
if (i < N) // only add new arrays if i < N
|
||||
X[i] = (double *)malloc(features * sizeof(double));
|
||||
if (i < num_out) // only add new arrays if i < num_out
|
||||
{
|
||||
for (int k = 0; k < num_out; k++)
|
||||
{
|
||||
#ifdef _OPENMP
|
||||
#pragma omp for
|
||||
#endif
|
||||
for (j = 0; j < features; j++)
|
||||
{ // preallocate with random initial weights
|
||||
double *w = data_3d(&W, i, k, j);
|
||||
w[0] = _random(-5, 5);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
test_3d_classes1(X, N); // create test data
|
||||
save_2d_data("test2.csv", X, N, features); // save test data points
|
||||
save_u_matrix("w21.csv", &W); // save initial random weights
|
||||
kohonen_som(X, &W, N, features, num_out, 1e-4); // train the SOM
|
||||
save_u_matrix("w22.csv", &W); // save the resultant weights
|
||||
|
||||
for (int i = 0; i < N; i++)
|
||||
free(X[i]);
|
||||
free(X);
|
||||
free(W.data);
|
||||
}
|
||||
|
||||
/** Creates a random set of points distributed in four clusters in
|
||||
* 3D space with centroids at the points
|
||||
* * \f$(0,5, 0.5, 0.5)\f$
|
||||
* * \f$(0,5,-0.5, -0.5)\f$
|
||||
* * \f$(-0,5, 0.5, 0.5)\f$
|
||||
* * \f$(-0,5,-0.5, -0.5)\f$
|
||||
*
|
||||
* \param[out] data matrix to store data in
|
||||
* \param[in] N number of points required
|
||||
*/
|
||||
void test_3d_classes2(double *const *data, int N)
|
||||
{
|
||||
const double R = 0.2; // radius of cluster
|
||||
int i;
|
||||
const int num_classes = 8;
|
||||
const double centres[][3] = {
|
||||
// centres of each class cluster
|
||||
{.5, .5, .5}, // centre of class 1
|
||||
{.5, .5, -.5}, // centre of class 2
|
||||
{.5, -.5, .5}, // centre of class 3
|
||||
{.5, -.5, -.5}, // centre of class 4
|
||||
{-.5, .5, .5}, // centre of class 5
|
||||
{-.5, .5, -.5}, // centre of class 6
|
||||
{-.5, -.5, .5}, // centre of class 7
|
||||
{-.5, -.5, -.5} // centre of class 8
|
||||
};
|
||||
|
||||
#ifdef _OPENMP
|
||||
#pragma omp for
|
||||
#endif
|
||||
for (i = 0; i < N; i++)
|
||||
{
|
||||
int class = rand() % num_classes; // select a random class for the point
|
||||
|
||||
// create random coordinates (x,y,z) around the centre of the class
|
||||
data[i][0] = _random(centres[class][0] - R, centres[class][0] + R);
|
||||
data[i][1] = _random(centres[class][1] - R, centres[class][1] + R);
|
||||
data[i][2] = _random(centres[class][2] - R, centres[class][2] + R);
|
||||
|
||||
/* The follosing can also be used
|
||||
for (int j = 0; j < 3; j++)
|
||||
data[i][j] = _random(centres[class][j] - R, centres[class][j] + R);
|
||||
*/
|
||||
}
|
||||
}
|
||||
|
||||
/** Test that creates a random set of points distributed in eight clusters in
|
||||
* 3D space and trains an SOM that finds the topological pattern. The following
|
||||
* [CSV](https://en.wikipedia.org/wiki/Comma-separated_values) files are created
|
||||
* to validate the execution:
|
||||
* * `test3.csv`: random test samples points with a circular pattern
|
||||
* * `w31.csv`: initial random map
|
||||
* * `w32.csv`: trained SOM map
|
||||
*
|
||||
* The outputs can be readily plotted in [gnuplot](https:://gnuplot.info) using
|
||||
* the following snippet
|
||||
* ```gnuplot
|
||||
* set datafile separator ','
|
||||
* plot "test3.csv" title "original", \
|
||||
* "w31.csv" title "w1", \
|
||||
* "w32.csv" title "w2"
|
||||
* ```
|
||||
* ![Sample execution
|
||||
* output](https://raw.githubusercontent.com/kvedala/C/docs/images/machine_learning/kohonen/test3.svg)
|
||||
*/
|
||||
void test3()
|
||||
{
|
||||
int j, N = 500;
|
||||
int features = 3;
|
||||
int num_out = 30;
|
||||
double **X = (double **)malloc(N * sizeof(double *));
|
||||
|
||||
// cluster nodex in 'x' * cluster nodes in 'y' * 2
|
||||
struct array_3d W;
|
||||
W.dim1 = num_out;
|
||||
W.dim2 = num_out;
|
||||
W.dim3 = features;
|
||||
W.data = (double *)malloc(num_out * num_out * features *
|
||||
sizeof(double)); // assign rows
|
||||
|
||||
for (int i = 0; i < max(num_out, N); i++) // loop till max(N, num_out)
|
||||
{
|
||||
if (i < N) // only add new arrays if i < N
|
||||
X[i] = (double *)malloc(features * sizeof(double));
|
||||
if (i < num_out) // only add new arrays if i < num_out
|
||||
{
|
||||
for (int k = 0; k < num_out; k++)
|
||||
{
|
||||
#ifdef _OPENMP
|
||||
#pragma omp for
|
||||
#endif
|
||||
// preallocate with random initial weights
|
||||
for (j = 0; j < features; j++)
|
||||
{
|
||||
double *w = data_3d(&W, i, k, j);
|
||||
w[0] = _random(-5, 5);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
test_3d_classes2(X, N); // create test data around the lamniscate
|
||||
save_2d_data("test3.csv", X, N, features); // save test data points
|
||||
save_u_matrix("w31.csv", &W); // save initial random weights
|
||||
kohonen_som(X, &W, N, features, num_out, 0.01); // train the SOM
|
||||
save_u_matrix("w32.csv", &W); // save the resultant weights
|
||||
|
||||
for (int i = 0; i < N; i++)
|
||||
free(X[i]);
|
||||
free(X);
|
||||
free(W.data);
|
||||
}
|
||||
|
||||
/**
|
||||
* Convert clock cycle difference to time in seconds
|
||||
*
|
||||
* \param[in] start_t start clock
|
||||
* \param[in] end_t end clock
|
||||
* \returns time difference in seconds
|
||||
*/
|
||||
double get_clock_diff(clock_t start_t, clock_t end_t)
|
||||
{
|
||||
return (double)(end_t - start_t) / (double)CLOCKS_PER_SEC;
|
||||
}
|
||||
|
||||
/** Main function */
|
||||
int main(int argc, char **argv)
|
||||
{
|
||||
#ifdef _OPENMP
|
||||
printf("Using OpenMP based parallelization\n");
|
||||
#else
|
||||
printf("NOT using OpenMP based parallelization\n");
|
||||
#endif
|
||||
clock_t start_clk, end_clk;
|
||||
|
||||
start_clk = clock();
|
||||
test1();
|
||||
end_clk = clock();
|
||||
printf("Test 1 completed in %.4g sec\n",
|
||||
get_clock_diff(start_clk, end_clk));
|
||||
|
||||
start_clk = clock();
|
||||
test2();
|
||||
end_clk = clock();
|
||||
printf("Test 2 completed in %.4g sec\n",
|
||||
get_clock_diff(start_clk, end_clk));
|
||||
|
||||
start_clk = clock();
|
||||
test3();
|
||||
end_clk = clock();
|
||||
printf("Test 3 completed in %.4g sec\n",
|
||||
get_clock_diff(start_clk, end_clk));
|
||||
|
||||
printf("(Note: Calculated times include: creating test sets, training "
|
||||
"model and writing files to disk.)\n\n");
|
||||
return 0;
|
||||
}
|
|
@ -19,6 +19,9 @@
|
|||
#include <omp.h>
|
||||
#endif
|
||||
|
||||
#define max(a, b) (a > b ? a : b) // shorthand for maximum value
|
||||
#define min(a, b) (a < b ? a : b) // shorthand for minimum value
|
||||
|
||||
/**
|
||||
* Helper function to generate a random number in a given interval.
|
||||
* \n Steps:
|
||||
|
@ -132,8 +135,8 @@ void update_weights(double const *x, double *const *W, double *D, int num_out,
|
|||
get_min_1d(D, num_out, &d_min, &d_min_idx);
|
||||
|
||||
// step 3a: get the neighborhood range
|
||||
int from_node = 0 > (d_min_idx - R) ? 0 : d_min_idx - R;
|
||||
int to_node = num_out < (d_min_idx + R + 1) ? num_out : d_min_idx + R + 1;
|
||||
int from_node = max(0, d_min_idx - R);
|
||||
int to_node = min(num_out, d_min_idx + R + 1);
|
||||
|
||||
// step 3b: update the weights of nodes in the
|
||||
// neighborhood
|
||||
|
@ -240,10 +243,14 @@ void test1()
|
|||
int j, N = 500;
|
||||
int features = 2;
|
||||
int num_out = 50;
|
||||
|
||||
// 2D space, hence size = number of rows * 2
|
||||
double **X = (double **)malloc(N * sizeof(double *));
|
||||
|
||||
// number of clusters nodes * 2
|
||||
double **W = (double **)malloc(num_out * sizeof(double *));
|
||||
for (int i = 0; i < (num_out > N ? num_out : N);
|
||||
i++) // loop till max(N, num_out)
|
||||
|
||||
for (int i = 0; i < max(num_out, N); i++) // loop till max(N, num_out)
|
||||
{
|
||||
if (i < N) // only add new arrays if i < N
|
||||
X[i] = (double *)malloc(features * sizeof(double));
|
||||
|
@ -266,7 +273,7 @@ void test1()
|
|||
kohonen_som_tracer(X, W, N, features, num_out, 0.1); // train the SOM
|
||||
save_nd_data("w12.csv", W, num_out, features); // save the resultant weights
|
||||
|
||||
for (int i = 0; i < (num_out > N ? num_out : N); i++)
|
||||
for (int i = 0; i < max(num_out, N); i++)
|
||||
{
|
||||
if (i < N)
|
||||
free(X[i]);
|
||||
|
@ -335,7 +342,7 @@ void test2()
|
|||
int num_out = 20;
|
||||
double **X = (double **)malloc(N * sizeof(double *));
|
||||
double **W = (double **)malloc(num_out * sizeof(double *));
|
||||
for (int i = 0; i < (num_out > N ? num_out : N); i++)
|
||||
for (int i = 0; i < max(num_out, N); i++)
|
||||
{
|
||||
if (i < N) // only add new arrays if i < N
|
||||
X[i] = (double *)malloc(features * sizeof(double));
|
||||
|
@ -359,7 +366,7 @@ void test2()
|
|||
kohonen_som_tracer(X, W, N, features, num_out, 0.01); // train the SOM
|
||||
save_nd_data("w22.csv", W, num_out, features); // save the resultant weights
|
||||
|
||||
for (int i = 0; i < (num_out > N ? num_out : N); i++)
|
||||
for (int i = 0; i < max(num_out, N); i++)
|
||||
{
|
||||
if (i < N)
|
||||
free(X[i]);
|
||||
|
@ -438,7 +445,7 @@ void test3()
|
|||
int num_out = 20;
|
||||
double **X = (double **)malloc(N * sizeof(double *));
|
||||
double **W = (double **)malloc(num_out * sizeof(double *));
|
||||
for (int i = 0; i < (num_out > N ? num_out : N); i++)
|
||||
for (int i = 0; i < max(num_out, N); i++)
|
||||
{
|
||||
if (i < N) // only add new arrays if i < N
|
||||
X[i] = (double *)malloc(features * sizeof(double));
|
||||
|
@ -462,7 +469,7 @@ void test3()
|
|||
kohonen_som_tracer(X, W, N, features, num_out, 0.01); // train the SOM
|
||||
save_nd_data("w32.csv", W, num_out, features); // save the resultant weights
|
||||
|
||||
for (int i = 0; i < (num_out > N ? num_out : N); i++)
|
||||
for (int i = 0; i < max(num_out, N); i++)
|
||||
{
|
||||
if (i < N)
|
||||
free(X[i]);
|
||||
|
|
Loading…
Reference in New Issue