def make_subsampled_dataset()

in datasets.py [0:0]

• 31 lines of code
• 14 McCabe index (conditional complexity)

def make_subsampled_dataset(
        directory, class_to_idx, extensions=None,is_valid_file=None, sampling_ratio=1., nb_classes=None):

    instances = []
    directory = os.path.expanduser(directory)
    both_none = extensions is None and is_valid_file is None
    both_something = extensions is not None and is_valid_file is not None
    if both_none or both_something:
        raise ValueError("Both extensions and is_valid_file cannot be None or not None at the same time")
    if extensions is not None:
        def is_valid_file(x: str) -> bool:
            return has_file_allowed_extension(x, cast(Tuple[str, ...], extensions))
    is_valid_file = cast(Callable[[str], bool], is_valid_file)
    for i, target_class in enumerate(sorted(class_to_idx.keys())):
        if nb_classes is not None and i>=nb_classes:
            break
        class_index = class_to_idx[target_class]
        target_dir = os.path.join(directory, target_class)
        if not os.path.isdir(target_dir):
            continue
        num_imgs = int(len(os.listdir(target_dir))*sampling_ratio)
        imgs=0
        for root, _, fnames in sorted(os.walk(target_dir, followlinks=True)):
            for fname in sorted(fnames):
                if imgs==num_imgs :
                    break
                path = os.path.join(root, fname)
                if is_valid_file(path):
                    item = path, class_index
                    instances.append(item)
                    imgs+=1
    return instances