FastText

fasttext.cc

void Dictionary::readFromFile(std::istream& in) {
  std::string word;
  int64_t minThreshold = 1;
  while (readWord(in, word)) {
    add(word);
    if (ntokens_ % 1000000 == 0 && args_->verbose > 1) {
      std::cerr << "\rRead " << ntokens_  / 1000000 << "M words" << std::flush;
    }
    if (size_ > 0.75 * MAX_VOCAB_SIZE) {
      minThreshold++;
      threshold(minThreshold, minThreshold);
    }
  }
  threshold(args_->minCount, args_->minCountLabel);
  initTableDiscard();
  initNgrams();