autoConfusion Categories_to_Confusion (Categories me, Categories thee) {
try {
if (my size != thy size) {
Melder_throw (U"Categories_to_Confusion: dimensions do not agree.");
}
autoCategories ul1 = Categories_selectUniqueItems (me);
autoCategories ul2 = Categories_selectUniqueItems (thee);
autoConfusion him = Confusion_create (ul1->size, ul2->size);
for (long i = 1; i <= ul1->size; i ++) {
SimpleString s = ul1->at [i];
TableOfReal_setRowLabel (him.get(), i, s -> string);
}
for (long i = 1; i <= ul2->size; i ++) {
SimpleString s = ul2->at [i];
TableOfReal_setColumnLabel (him.get(), i, s -> string);
}
for (long i = 1; i <= my size; i ++) {
SimpleString myi = my at [i], thyi = thy at [i];
Confusion_increase (him.get(), SimpleString_c (myi), SimpleString_c (thyi));
}
return him;
} catch (MelderError) {
Melder_throw (me, U": no Confusion created.");
}
}
autoActivation FFNet_Categories_to_Activation (FFNet me, Categories thee) {
try {
autoCategories uniq = Categories_selectUniqueItems (thee);
if (! my outputCategories) {
Melder_throw (U"The FFNet does not have categories.");
}
long nl = OrderedOfString_isSubsetOf (uniq.get(), my outputCategories.get(), 0);
if (nl == 0) {
Melder_throw (U"The Categories do not match the categories of the FFNet.");
}
autoActivation him = Activation_create (thy size, my nOutputs);
for (long i = 1; i <= thy size; i ++) {
const char32 *citem = OrderedOfString_itemAtIndex_c (thee, i);
long pos = OrderedOfString_indexOfItem_c (my outputCategories.get(), citem);
if (pos < 1) {
Melder_throw (U"The FFNet doesn't know the category ", citem, U".");
}
his z [i] [pos] = 1.0;
}
return him;
} catch (MelderError) {
Melder_throw (me, U": no Activation created.");
}
}
int FFNet_setOutputCategories (FFNet me, Categories thee)
{
Categories uniq = Categories_selectUniqueItems (thee, 1);
if (uniq -> size == thy size)
{
my outputCategories = uniq;
return 1;
}
forget (uniq);
return 0;
}
Activation FFNet_Categories_to_Activation (FFNet me, Categories thee)
{
Activation him = NULL;
Categories uniq;
long i, nl, cSize = thy size, hasCategories = 1;
uniq = Categories_selectUniqueItems (thee, 1);
if (uniq == NULL) Melder_error1 (L"There is not enough memory to create a Categories.");
if (my outputCategories == NULL)
{
if (my nUnitsInLayer[my nLayers] == uniq -> size)
{
my outputCategories = uniq;
hasCategories = 0;
}
else
{
(void) Melder_error1 (L"");
goto end;
}
}
else if (! ( (nl = OrderedOfString_isSubsetOf (uniq, my outputCategories, NULL)) &&
nl == uniq -> size && my nOutputs >= uniq -> size))
{
(void) Melder_error1 (L"The Categories do not match the categories of the FFNet.");
goto end;
}
him = Activation_create (cSize, my nOutputs);
if (him == NULL) goto end;
for (i=1; i <= cSize; i++)
{
long pos = OrderedOfString_indexOfItem_c (my outputCategories, OrderedOfString_itemAtIndex_c (thee, i));
if (pos < 1)
{
(void) Melder_error3 (L"The FFNet doesn't know the category ", OrderedOfString_itemAtIndex_c (thee, i), L" from Categories.");
goto end;
}
his z[i][pos] = 1.0;
}
end:
if (hasCategories) forget (uniq);
if (Melder_hasError ()) forget (him);
return him;
}
long KNN_prune_prune
(
KNN me, // the classifier to be pruned
double n, // pruning degree: noise, 0 <= n <= 1
double r, // pruning redundancy: noise, 0 <= n <= 1
long k // k(!)
)
{
autoCategories uniqueCategories = Categories_selectUniqueItems (my output.get());
if (Categories_getSize (uniqueCategories.get()) == my nInstances)
return 0;
long removals = 0;
long ncandidates = 0;
autoNUMvector <long> candidates (0L, my nInstances - 1);
if (my nInstances <= 1)
return 0;
for (long y = 1; y <= my nInstances; y ++) {
if (KNN_prune_noisy (my input.get(), my output.get(), y, k)) {
if (n == 1 || NUMrandomUniform (0, 1) <= n) {
KNN_removeInstance (me, y);
++ removals;
}
}
}
for (long y = 1; y <= my nInstances; ++ y) {
if (KNN_prune_superfluous (my input.get(), my output.get(), y, k, 0) && ! KNN_prune_critical (my input.get(), my output.get(), y, k))
candidates [ncandidates ++] = y;
}
KNN_prune_sort (my input.get(), my output.get(), k, candidates.peek(), ncandidates);
for (long y = 0; y < ncandidates; ++ y) {
if (KNN_prune_superfluous (my input.get(), my output.get(), candidates [y], k, 0) && ! KNN_prune_critical (my input.get(), my output.get(), candidates [y], k)) {
if (r == 1.0 || NUMrandomUniform (0.0, 1.0) <= r) {
KNN_removeInstance (me, candidates[y]);
for (long i = y + 1; i < ncandidates; ++ i) {
if(candidates[i] > candidates[y])
-- candidates[i];
}
++ removals;
}
}
}
return removals;
}
void FFNet_setOutputCategories (FFNet me, Categories thee) {
autoCategories uniq = Categories_selectUniqueItems (thee, 1);
if (uniq -> size == thy size) {
my outputCategories = uniq.transfer();
}
}
long KNN_prune_prune
(
///////////////////////////////
// Parameters //
///////////////////////////////
KNN me, // the classifier to be pruned
//
double n, // pruning degree: noise, 0 <= n <= 1
//
double r, // pruning redundancy: noise, 0 <= n <= 1
//
long k // k(!)
//
)
{
Categories uniqueCategories = Categories_selectUniqueItems(my output, 1);
if(Categories_getSize(uniqueCategories) == my nInstances)
return(0);
long removals = 0;
long ncandidates = 0;
long *candidates = NUMlvector (0, my nInstances - 1);
double progress = 1 / (double) my nInstances;
if(my nInstances <= 1)
return(0);
for (long y = 1; y <= my nInstances; y++)
{
if (!Melder_progress1(1 - (double) y * progress, L"Pruning noisy instances")) return(removals);
if (KNN_prune_noisy(my input, my output, y, k))
{
if (n == 1 || NUMrandomUniform(0, 1) <= n)
{
KNN_removeInstance(me, y);
++removals;
}
}
}
Melder_progress1(1.0, NULL);
for (long y = 1; y <= my nInstances; ++y)
{
if (!Melder_progress1(1 - (double) y * progress, L"Identifying superfluous and critical instances")) return(removals);
if (KNN_prune_superfluous(my input, my output, y, k, 0) && !KNN_prune_critical(my input, my output, y, k))
candidates[ncandidates++] = y;
}
Melder_progress1(1.0, NULL);
KNN_prune_sort(my input, my output, k, candidates, ncandidates);
progress = 1 / ncandidates;
for (long y = 0; y < ncandidates; ++y)
{
if (!Melder_progress1(1 - (double) y * progress, L"Pruning superfluous non-critical instances")) return(removals);
if (KNN_prune_superfluous(my input, my output, candidates[y], k, 0) && !KNN_prune_critical(my input, my output, candidates[y], k))
{
if (r == 1 || NUMrandomUniform(0, 1) <= r)
{
KNN_removeInstance(me, candidates[y]);
for(long i = y + 1; i < ncandidates; ++i)
if(candidates[i] > candidates[y])
--candidates[i];
++removals;
}
}
}
Melder_progress1(1.0, NULL);
NUMlvector_free (candidates, 0);
return(removals);
}
