/**
* Test clustering
*/
int test_cluster_single()
{
int i, j, k, err = 0;
test_printf("Clustering using prototypes (single)");
/* Prepare test data */ ;
farray_t *fa = farray_create("test");
for (i = 0; i < DATA_LEN; i++) {
fvec_t *f = fvec_extract(test_data[i], strlen(test_data[i]), NULL);
farray_add(fa, f, "test");
}
/* Get clustering */
config_set_string(&cfg, "cluster.link_mode", "single");
cluster_t *c = cluster_linkage(fa, 0);
/* Check number of clusters */
err += (c->num != DATA_CLUSTER);
/* Check position of prototypes */
for (k = 0; k < DATA_LEN; k += DATA_LEN / DATA_CLUSTER)
for (j = 0; j < DATA_LEN / DATA_CLUSTER - 1; j++)
err += c->cluster[k + j] != c->cluster[k + j + 1];
/* Clean up */
cluster_destroy(c);
farray_destroy(fa);
test_return(err, 1 + DATA_CLUSTER * (DATA_LEN / DATA_CLUSTER - 1));
return err;
}
/**
* Return an array of prototypes labeled with cluster numbers
* @param c cluster structure
* @param a assignment of prototypes
* @param p prototypes
* @return rejected feature vectors
*/
farray_t *cluster_get_prototypes(cluster_t *c, assign_t *a, farray_t *p)
{
int i;
farray_t *n = farray_create("prototypes");
count_t *hash = NULL, *entry;
for (i = 0; i < a->len; i++) {
/* Skip rejected clusters */
if (!c->cluster[i])
continue;
/* Check if prototype has been added */
int j = a->proto[i];
HASH_FIND_INT(hash, &j, entry);
if (entry)
continue;
/* Add new prototype */
entry = malloc(sizeof(count_t));
entry->label = j;
HASH_ADD_INT(hash, label, entry);
/* Add prototype */
farray_add(n, fvec_clone(p->x[j]), cluster_get_name(c, i));
}
/* Delete hash table */
while (hash) {
entry = hash;
HASH_DEL(hash, entry);
free(entry);
}
return n;
}
/*
* A simple stress test for classification
*/
int test_stress()
{
int i, j, k, err = 0;
fvec_t *f;
farray_t *fa;
char buf[STR_LENGTH + 1], label[32];
test_printf("Stress test for classification");
for (i = 0; i < STRESS_RUNS; i++) {
/* Create array */
fa = farray_create("test");
for (j = 0; j < NUM_VECTORS; j++) {
for (k = 0; k < STR_LENGTH; k++)
buf[k] = rand() % 10 + '0';
buf[k] = 0;
/* Extract features */
f = fvec_extract(buf, strlen(buf), "test");
snprintf(label, 32, "label%.2d", rand() % 10);
/* Add to array */
farray_add(fa, f, label);
}
assign_t *a = class_assign(fa, fa);
assign_destroy(a);
farray_destroy(fa);
}
test_return(err, STRESS_RUNS);
return err;
}
/**
* Return an array of rejected feature vectors
* @param c Cluster structure
* @param f Array of feature vectors
* @return Rejected feature vectors
*/
farray_t *cluster_get_rejected(cluster_t *c, farray_t *f)
{
int i;
farray_t *r = farray_create("rejected");
for (i = 0; i < f->len; i++) {
if (c->cluster[i])
continue;
farray_add(r, fvec_clone(f->x[i]), farray_get_label(f, i));
}
return r;
}
/**
* Simple test cases classification
*/
int test_classify()
{
int i, k, err = 0;
fvec_t *f;
test_printf("Classification using prototypes");
/* Prepare training data */
farray_t *fa1 = farray_create("train");
for (i = 0; train_data[i].str; i++) {
f = fvec_extract(train_data[i].str, strlen(train_data[i].str), NULL);
farray_add(fa1, f, train_data[i].label);
}
/* Prepare testing data */
farray_t *fa2 = farray_create("train");
for (i = 0; test_data[i].str; i++) {
f = fvec_extract(test_data[i].str, strlen(test_data[i].str), NULL);
farray_add(fa2, f, test_data[i].label);
}
/* Classification of test data */
config_set_float(&cfg, "classify.max_dist", 1.41);
assign_t *a = class_assign(fa2, fa1);
/* Check predicted labels */
for (k = 0; test_data[k].str; k++) {
char *l = farray_get_label(fa1, a->proto[k]);
err += strcmp(l, test_data[k].label) != 0;
}
/* Clean up */
assign_destroy(a);
farray_destroy(fa1);
farray_destroy(fa2);
test_return(err, i);
return err;
}
/*
* A simple stress test for clustering
*/
int test_stress()
{
int i, j, k, err = 0;
fvec_t *f;
farray_t *fa;
char buf[STR_LENGTH + 1], label[32];
test_printf("Stress test for clustering");
for (i = 0; i < STRESS_RUNS; i++) {
/* Create array */
fa = farray_create("test");
for (j = 0; j < NUM_VECTORS; j++) {
for (k = 0; k < STR_LENGTH; k++)
buf[k] = rand() % 10 + '0';
buf[k] = 0;
/* Extract features */
f = fvec_extract(buf, strlen(buf), "test");
snprintf(label, 32, "label%.2d", rand() % 10);
/* Add to array */
farray_add(fa, f, label);
}
/* Extract prototypes */
cluster_t *c = cluster_linkage(fa, 0);
/* Destroy features */
cluster_destroy(c);
farray_destroy(fa);
}
test_return(err, STRESS_RUNS);
return err;
}
