Function svm_cross_validation

ml/src/svm.cpp:2677–2810

Stratified cross validation

// Stratified cross validation
void
svm_cross_validation(const svm_problem* prob,
                     const svm_parameter* param,
                     int nr_fold,
                     double* target)
{
  int* fold_start = Malloc(int, nr_fold + 1);
  int l = prob->l;
  int* perm = Malloc(int, l);
  int nr_class;

  // stratified cv may not give leave-one-out rate
  // Each class to l folds -> some folds may have zero elements

  if ((param->svm_type == C_SVC || param->svm_type == NU_SVC) && nr_fold < l) {
    int* start = nullptr;
    int* label = nullptr;
    int* count = nullptr;
    svm_group_classes(prob, &nr_class, &label, &start, &count, perm);

    // random shuffle and then data grouped by fold using the array perm
    int* fold_count = Malloc(int, nr_fold);
    int* index = Malloc(int, l);

    for (int i = 0; i < l; i++)
      index[i] = perm[i];

    for (int c = 0; c < nr_class; c++)
      for (int i = 0; i < count[c]; i++) {
        int j = i + rand() % (count[c] - i);
        swap(index[start[c] + j], index[start[c] + i]);
      }

    for (int i = 0; i < nr_fold; i++) {
      fold_count[i] = 0;

      for (int c = 0; c < nr_class; c++)
        fold_count[i] += (i + 1) * count[c] / nr_fold - i * count[c] / nr_fold;
    }

    fold_start[0] = 0;

    for (int i = 1; i <= nr_fold; i++)
      fold_start[i] = fold_start[i - 1] + fold_count[i - 1];

    for (int c = 0; c < nr_class; c++)
      for (int i = 0; i < nr_fold; i++) {
        int begin = start[c] + i * count[c] / nr_fold;
        int end = start[c] + (i + 1) * count[c] / nr_fold;

        for (int j = begin; j < end; j++) {
          perm[fold_start[i]] = index[j];
          fold_start[i]++;
        }
      }

    fold_start[0] = 0;