def __init__(
self,
adata_manager: AnnDataManager,
unlabeled_category,
train_size: float = 0.9,
validation_size: Optional[float] = None,
n_samples_per_label: Optional[int] = None,
use_gpu: bool = False,
**kwargs,
):
super().__init__()
self.adata_manager = adata_manager
self.unlabeled_category = unlabeled_category
self.train_size = float(train_size)
self.validation_size = validation_size
self.data_loader_kwargs = kwargs
self.n_samples_per_label = n_samples_per_label
original_key = adata_manager.get_state_registry(
REGISTRY_KEYS.LABELS_KEY
).original_key
labels = np.asarray(adata_manager.adata.obs[original_key]).ravel()
self._unlabeled_indices = np.argwhere(labels == unlabeled_category).ravel()
self._labeled_indices = np.argwhere(labels != unlabeled_category).ravel()
self.data_loader_kwargs = kwargs
self.use_gpu = use_gpu
def _get_batch_code_from_category(adata_manager: AnnDataManager,
category: Sequence[Union[Number, str]]):
if not isinstance(category, IterableClass) or isinstance(category, str):
category = [category]
batch_mappings = adata_manager.get_state_registry(
REGISTRY_KEYS.BATCH_KEY).categorical_mapping
batch_code = []
for cat in category:
if cat is None:
batch_code.append(None)
elif cat not in batch_mappings:
raise ValueError('"{}" not a valid batch category.'.format(cat))
else:
batch_loc = np.where(batch_mappings == cat)[0][0]
batch_code.append(batch_loc)
return batch_code
def __init__(
self,
adata_manager: AnnDataManager,
unlabeled_category: str,
n_samples_per_label: Optional[int] = None,
indices: Optional[List[int]] = None,
shuffle: bool = False,
batch_size: int = 128,
data_and_attributes: Optional[dict] = None,
drop_last: Union[bool, int] = False,
**data_loader_kwargs,
):
adata = adata_manager.adata
if indices is None:
indices = np.arange(adata.n_obs)
self.indices = indices
if len(indices) == 0:
return None
self.n_samples_per_label = n_samples_per_label
labels_obs_key = adata_manager.get_state_registry(
REGISTRY_KEYS.LABELS_KEY).original_key
labels = np.asarray(adata_manager.adata.obs[labels_obs_key]).ravel()
# save a nested list of the indices per labeled category
self.labeled_locs = []
for label in np.unique(labels):
if label != unlabeled_category:
label_loc_idx = np.where(labels[indices] == label)[0]
label_loc = indices[label_loc_idx]
self.labeled_locs.append(label_loc)
labelled_idx = self.subsample_labels()
super().__init__(
adata_manager=adata_manager,
indices_list=[indices, labelled_idx],
shuffle=shuffle,
batch_size=batch_size,
data_and_attributes=data_and_attributes,
drop_last=drop_last,
**data_loader_kwargs,
)
