int GetNaa(double cutoff, int type) {
vector<int> tmp = GetSubset(cutoff,type);
int naa = 0;
for (int i=0; i<Nstate; i++) {
naa += tmp[i];
}
return naa;
}
void ToStreamSummary(ostream& os,double c, int type) {
os << weight << '\t';
vector<int> tmp = GetSubset(c,type);
for (int i=0; i<Nstate; i++) {
if (tmp[i]) {
os << AAset[i];
}
}
os << '\t' << GetMaxMinor(tmp);
os << '\n';
}
void AddAllCombinations(const vector<int>& S, size_t Length, vector<vector<int>>& Result)
{
vector<int> combination(Length, 0);
vector<bool> selection(S.size(), false);
for (size_t i = 0; i < Length; ++i)
{
selection[i] = true;
}
do
{
Result.push_back(GetSubset(S, selection));
} while (NextSelection(selection));
}
Genome* Genome::GetSubsetByGeneIndex( int first, int last )
{
Feature* f = genes[first];
Feature* l = genes[last];
return GetSubset(min(f->indices), max(l->indices)+1);
}
mvec<Genome*> Genome::Split( float wanted_ratio, int impTh )
{
/*
% For each gene go and try to divide the genome after each gene, make
% sure we do not cut any genes in the middle and select the ratio
% closest to 0.5 */
float best_ratio = FLT_MAX;
int best_position = 0;
int n = genes.size();
int last_impI = 0;
int last_impJ = 0;
int i = (int)(n * wanted_ratio + 0.5f) - 1;
int j = (int)(n * wanted_ratio + 0.5f);
while ((i > 0 && last_impI < impTh) || (j < n && last_impJ < impTh))
{
if (i > 0 && last_impI < impTh) {
Feature* cur = genes(i);
Feature* next = genes(i + 1);
int cur_end = max(cur->indices);
int next_start = min(next->indices);
int middle = round(0.5 * (cur_end+next_start));
if (CanCut(middle)) {
float ratio = CountGenes(1, middle) / (float)n;
if (fabsf(ratio - wanted_ratio) < fabsf(best_ratio - wanted_ratio)) {
best_ratio = ratio;
d_trace("[+] (%d) New best ratio attained - %f\n", i, best_ratio);
best_position = middle;
last_impI = 0;
} else {
last_impI = last_impI + 1;
}
}
}
i--;
if (j < n && last_impJ < impTh) {
Feature* cur = genes(j);
Feature* next = genes(j + 1);
int cur_end = max(cur->indices);
int next_start = min(next->indices);
int middle = round(0.5 * (cur_end+next_start));
if (CanCut(middle)) {
float ratio = CountGenes(1, middle) / (float) n;
if (fabsf(ratio - wanted_ratio) < fabsf(best_ratio - wanted_ratio)) {
best_ratio = ratio;
d_trace("[+] (%d) New best ratio attained - %f\n", i, best_ratio);
best_position = middle;
last_impJ = 0;
} else {
last_impJ = last_impJ + 1;
}
}
}
j++;
}
// % BTW, this works only coz the genes are sorted in incresing order of
// % their lower index (lower != first)
d_trace("[i] Cutting sequence at %d\n", best_position);
mvec<Genome*> r;
r.push_back(GetSubset(1, best_position)); // train
// train.Sequence = g.Sequence(1:best_position);
//train.gene = get_all_genes(f, 1, best_position);
r.push_back(GetSubset(best_position + 1, sequence.size()));
// test.Sequence = g.Sequence(best_position + 1:seq_length);
// test.gene = get_all_genes(f, best_position + 1, seq_length);
// test.gene = shift_genes(test.gene, best_position);
return r;
}