std::shared_ptr FastText::getInputMatrixFromFile()

in src/fasttext.cc [680:723]

• 42 lines of code
• 8 McCabe index (conditional complexity)

std::shared_ptr<Matrix> FastText::getInputMatrixFromFile(
    const std::string& filename) const {
  std::ifstream in(filename);
  std::vector<std::string> words;
  std::shared_ptr<DenseMatrix> mat; // temp. matrix for pretrained vectors
  int64_t n, dim;
  if (!in.is_open()) {
    throw std::invalid_argument(filename + " cannot be opened for loading!");
  }
  in >> n >> dim;
  if (dim != args_->dim) {
    throw std::invalid_argument(
        "Dimension of pretrained vectors (" + std::to_string(dim) +
        ") does not match dimension (" + std::to_string(args_->dim) + ")!");
  }
  mat = std::make_shared<DenseMatrix>(n, dim);
  for (size_t i = 0; i < n; i++) {
    std::string word;
    in >> word;
    words.push_back(word);
    dict_->add(word);
    for (size_t j = 0; j < dim; j++) {
      in >> mat->at(i, j);
    }
  }
  in.close();

  dict_->threshold(1, 0);
  dict_->init();
  std::shared_ptr<DenseMatrix> input = std::make_shared<DenseMatrix>(
      dict_->nwords() + args_->bucket, args_->dim);
  input->uniform(1.0 / args_->dim, args_->thread, args_->seed);

  for (size_t i = 0; i < n; i++) {
    int32_t idx = dict_->getId(words[i]);
    if (idx < 0 || idx >= dict_->nwords()) {
      continue;
    }
    for (size_t j = 0; j < dim; j++) {
      input->at(idx, j) = mat->at(i, j);
    }
  }
  return input;
}