How to use the lineflow.cross_validation.SubDataset function in lineflow

To help you get started, we’ve selected a few lineflow examples, based on popular ways it is used in public projects.

Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.

github tofunlp / lineflow / lineflow / cross_validation.py View on Github external
def split_dataset_n(dataset: Dataset,
                    n: int,
                    indices: List[int] = None) -> List[SubDataset]:
    n_examples = len(dataset)
    sub_size = n_examples // n
    return [SubDataset(dataset, sub_size * i, sub_size * (i + 1), indices)
            for i in range(n)]
github tofunlp / lineflow / lineflow / cross_validation.py View on Github external
def split_dataset_n_random(dataset: Dataset,
                           n: int,
                           seed=None) -> List[SubDataset]:
    n_examples = len(dataset)
    sub_size = n_examples // n
    random.seed(seed)
    indices = list(range(len(dataset)))
    random.shuffle(indices)
    return [SubDataset(dataset, sub_size * i, sub_size * (i + 1), indices)
            for i in range(n)]
github tofunlp / lineflow / lineflow / cross_validation.py View on Github external
def split_dataset(dataset: Dataset,
                  split_at: int,
                  indices: List[int] = None) -> Tuple[SubDataset]:
    n_examples = len(dataset)
    if not isinstance(split_at, int):
        raise TypeError(f'split_at must be int, got {type(split_at)} instead')
    if split_at < 0:
        raise ValueError('split_at must be non-negative')
    if split_at > n_examples:
        raise ValueError('split_at exceeds the dataset size')
    subset1 = SubDataset(dataset, 0, split_at, indices)
    subset2 = SubDataset(dataset, split_at, n_examples, indices)
    return subset1, subset2
github tofunlp / lineflow / lineflow / cross_validation.py View on Github external
def split_dataset(dataset: Dataset,
                  split_at: int,
                  indices: List[int] = None) -> Tuple[SubDataset]:
    n_examples = len(dataset)
    if not isinstance(split_at, int):
        raise TypeError(f'split_at must be int, got {type(split_at)} instead')
    if split_at < 0:
        raise ValueError('split_at must be non-negative')
    if split_at > n_examples:
        raise ValueError('split_at exceeds the dataset size')
    subset1 = SubDataset(dataset, 0, split_at, indices)
    subset2 = SubDataset(dataset, split_at, n_examples, indices)
    return subset1, subset2