int
write_mat_file (const char *filename, const disp_t *d,
double lmin, double lmax, double lstep)
{
FILE *f;
int jinf, jsup, step;
int j;
f = fopen(filename, "w");
if (f == NULL)
return 1;
fprintf (f, "%s\n", CSTR(d->name));
fprintf (f, "nm\n");
fprintf (f, "NK\n");
jinf = rint (lmin * 100.0);
jsup = rint (lmax * 100.0);
step = rint (lstep * 100.0);
for (j = jinf; j <= jsup; j += step)
{
double lambda = j / 100.0;
cmpl n = n_value (d, lambda);
fprintf (f, "%7.2f\t%.7f\t%.7f\n", lambda, creal(n), - cimag(n));
}
fclose (f);
return 0;
}
void *screen_reads(ss_probes *h_probes,
int probe_length,
std::string **buffer,
int n_reads,
int tid,
pthread_mutex_t *mutex,
int n_threads)
{
google::dense_hash_map<std::string, Probe *>::iterator p_iter;
const int n_pos = probe_length/2;
std::string window;
std::string n_value(" ");
int p,i; // pointer to buffer, pointer in read
for (p=0; p!=n_reads; ++p) {
if ((n_threads>1) && (p % n_threads != tid)) continue;
for (i=0; i+probe_length<=(int) buffer[p]->length(); ++i) {
window = buffer[p]->substr(i, probe_length);
n_value[0] = window[n_pos];
window[n_pos] = 'N';
if ((p_iter = h_probes->find(window)) != h_probes->end()) {
pthread_mutex_lock(mutex);
p_iter->second->update_counters(n_value);
pthread_mutex_unlock(mutex);
}
}
}
return 0;
}
void ngram_pos_analyzer::tokenize(corpus::document& doc)
{
// first, get tokens
stream_->set_content(get_content(doc));
std::vector<sequence::sequence> sentences;
sequence::sequence seq;
// put tokens into sequences, excluding sentence markers
while (*stream_)
{
auto next = stream_->next();
if (next.empty() || next == " " || next == "<s>")
continue;
if (next == "</s>")
sentences.emplace_back(std::move(seq));
else
seq.add_observation(
{sequence::symbol_t{next}, sequence::tag_t{"[unknown]"}});
}
auto tagger = crf_->make_tagger();
for (auto& seq : sentences)
{
// generate CRF features
seq_analyzer_.analyze(seq);
// POS-tag sentence
tagger.tag(seq);
// create ngrams
for (size_t i = n_value() - 1; i < seq.size(); ++i)
{
std::string combined = seq_analyzer_.tag(seq[i].label());
for (size_t j = 1; j < n_value(); ++j)
{
std::string next = seq_analyzer_.tag(seq[i - j].label());
combined = next + "_" + combined;
}
doc.increment(combined, 1);
}
}
}
