anndata 0.12.1__py3-none-any.whl → 0.12.2__py3-none-any.whl

anndata/_core/anndata.py

@@ -56,7 +56,7 @@ if TYPE_CHECKING:
 
     from zarr.storage import StoreLike
 
-    from ..compat import Index1D, XDataset
+    from ..compat import Index1D, Index1DNorm, XDataset
     from ..typing import XDataType
     from .aligned_mapping import AxisArraysView, LayersView, PairwiseArraysView
     from .index import Index
@@ -197,6 +197,11 @@ class AnnData(metaclass=utils.DeprecationMixinMeta):  # noqa: PLW1641
 
     _accessors: ClassVar[set[str]] = set()
 
+    # view attributes
+    _adata_ref: AnnData | None
+    _oidx: Index1DNorm | None
+    _vidx: Index1DNorm | None
+
     @old_positionals(
         "obsm",
         "varm",
@@ -226,8 +231,8 @@ class AnnData(metaclass=utils.DeprecationMixinMeta):  # noqa: PLW1641
         asview: bool = False,
         obsp: np.ndarray | Mapping[str, Sequence[Any]] | None = None,
         varp: np.ndarray | Mapping[str, Sequence[Any]] | None = None,
-        oidx: Index1D | None = None,
-        vidx: Index1D | None = None,
+        oidx: Index1DNorm | int | np.integer | None = None,
+        vidx: Index1DNorm | int | np.integer | None = None,
     ):
         # check for any multi-indices that aren’t later checked in coerce_array
         for attr, key in [(obs, "obs"), (var, "var"), (X, "X")]:
@@ -237,6 +242,8 @@ class AnnData(metaclass=utils.DeprecationMixinMeta):  # noqa: PLW1641
             if not isinstance(X, AnnData):
                 msg = "`X` has to be an AnnData object."
                 raise ValueError(msg)
+            assert oidx is not None
+            assert vidx is not None
             self._init_as_view(X, oidx, vidx)
         else:
             self._init_as_actual(
@@ -256,7 +263,12 @@ class AnnData(metaclass=utils.DeprecationMixinMeta):  # noqa: PLW1641
                 filemode=filemode,
             )
 
-    def _init_as_view(self, adata_ref: AnnData, oidx: Index, vidx: Index):
+    def _init_as_view(
+        self,
+        adata_ref: AnnData,
+        oidx: Index1DNorm | int | np.integer,
+        vidx: Index1DNorm | int | np.integer,
+    ):
         if adata_ref.isbacked and adata_ref.is_view:
             msg = (
                 "Currently, you cannot index repeatedly into a backed AnnData, "
@@ -277,6 +289,9 @@ class AnnData(metaclass=utils.DeprecationMixinMeta):  # noqa: PLW1641
             vidx += adata_ref.n_vars * (vidx < 0)
             vidx = slice(vidx, vidx + 1, 1)
         if adata_ref.is_view:
+            assert adata_ref._adata_ref is not None
+            assert adata_ref._oidx is not None
+            assert adata_ref._vidx is not None
             prev_oidx, prev_vidx = adata_ref._oidx, adata_ref._vidx
             adata_ref = adata_ref._adata_ref
             oidx, vidx = _resolve_idxs((prev_oidx, prev_vidx), (oidx, vidx), adata_ref)
@@ -1004,7 +1019,9 @@ class AnnData(metaclass=utils.DeprecationMixinMeta):  # noqa: PLW1641
 
         write_attribute(self.file._file, attr, value)
 
-    def _normalize_indices(self, index: Index | None) -> tuple[slice, slice]:
+    def _normalize_indices(
+        self, index: Index | None
+    ) -> tuple[Index1DNorm | int | np.integer, Index1DNorm | int | np.integer]:
         return _normalize_indices(index, self.obs_names, self.var_names)
 
     # TODO: this is not quite complete...

anndata/_core/index.py

@@ -14,18 +14,18 @@ from ..compat import AwkArray, CSArray, CSMatrix, DaskArray, XDataArray
 from .xarray import Dataset2D
 
 if TYPE_CHECKING:
-    from ..compat import Index, Index1D
+    from ..compat import Index, Index1D, Index1DNorm
 
 
 def _normalize_indices(
     index: Index | None, names0: pd.Index, names1: pd.Index
-) -> tuple[slice, slice]:
+) -> tuple[Index1DNorm | int | np.integer, Index1DNorm | int | np.integer]:
     # deal with tuples of length 1
     if isinstance(index, tuple) and len(index) == 1:
         index = index[0]
     # deal with pd.Series
     if isinstance(index, pd.Series):
-        index: Index = index.values
+        index = index.values
     if isinstance(index, tuple):
         # TODO: The series should probably be aligned first
         index = tuple(i.values if isinstance(i, pd.Series) else i for i in index)
@@ -36,15 +36,8 @@ def _normalize_indices(
 
 
 def _normalize_index(  # noqa: PLR0911, PLR0912
-    indexer: slice
-    | np.integer
-    | int
-    | str
-    | Sequence[bool | int | np.integer]
-    | np.ndarray
-    | pd.Index,
-    index: pd.Index,
-) -> slice | int | np.ndarray:  # ndarray of int or bool
+    indexer: Index1D, index: pd.Index
+) -> Index1DNorm | int | np.integer:
     # TODO: why is this here? All tests pass without it and it seems at the minimum not strict enough.
     if not isinstance(index, pd.RangeIndex) and index.dtype in (np.float64, np.int64):
         msg = f"Don’t call _normalize_index with non-categorical/string names and non-range index {index}"
@@ -212,7 +205,7 @@ def _subset_awkarray(a: AwkArray, subset_idx: Index):
 
 # Registration for SparseDataset occurs in sparse_dataset.py
 @_subset.register(h5py.Dataset)
-def _subset_dataset(d, subset_idx):
+def _subset_dataset(d: h5py.Dataset, subset_idx: Index):
     if not isinstance(subset_idx, tuple):
         subset_idx = (subset_idx,)
     ordered = list(subset_idx)

anndata/_core/raw.py

@@ -17,7 +17,7 @@ if TYPE_CHECKING:
     from collections.abc import Mapping, Sequence
     from typing import ClassVar
 
-    from ..compat import CSMatrix
+    from ..compat import CSMatrix, Index, Index1DNorm
     from .aligned_mapping import AxisArraysView
     from .anndata import AnnData
     from .sparse_dataset import BaseCompressedSparseDataset
@@ -121,7 +121,7 @@ class Raw:
     def obs_names(self) -> pd.Index[str]:
         return self._adata.obs_names
 
-    def __getitem__(self, index):
+    def __getitem__(self, index: Index) -> Raw:
         oidx, vidx = self._normalize_indices(index)
 
         # To preserve two dimensional shape
@@ -169,7 +169,9 @@ class Raw:
             uns=self._adata.uns.copy(),
         )
 
-    def _normalize_indices(self, packed_index):
+    def _normalize_indices(
+        self, packed_index: Index
+    ) -> tuple[Index1DNorm | int | np.integer, Index1DNorm | int | np.integer]:
         # deal with slicing with pd.Series
         if isinstance(packed_index, pd.Series):
             packed_index = packed_index.values

anndata/_core/views.py

@@ -29,8 +29,12 @@ if TYPE_CHECKING:
     from collections.abc import Callable, Iterable, KeysView, Sequence
     from typing import Any, ClassVar
 
+    from numpy.typing import NDArray
+
     from anndata import AnnData
 
+    from ..compat import Index1DNorm
+
 
 @contextmanager
 def view_update(adata_view: AnnData, attr_name: str, keys: tuple[str, ...]):
@@ -433,18 +437,24 @@ except ImportError:
         pass
 
 
-def _resolve_idxs(old, new, adata):
-    t = tuple(_resolve_idx(old[i], new[i], adata.shape[i]) for i in (0, 1))
-    return t
+def _resolve_idxs(
+    old: tuple[Index1DNorm, Index1DNorm],
+    new: tuple[Index1DNorm, Index1DNorm],
+    adata: AnnData,
+) -> tuple[Index1DNorm, Index1DNorm]:
+    o, v = (_resolve_idx(old[i], new[i], adata.shape[i]) for i in (0, 1))
+    return o, v
 
 
 @singledispatch
-def _resolve_idx(old, new, l):
-    return old[new]
+def _resolve_idx(old: Index1DNorm, new: Index1DNorm, l: Literal[0, 1]) -> Index1DNorm:
+    raise NotImplementedError
 
 
 @_resolve_idx.register(np.ndarray)
-def _resolve_idx_ndarray(old, new, l):
+def _resolve_idx_ndarray(
+    old: NDArray[np.bool_] | NDArray[np.integer], new: Index1DNorm, l: Literal[0, 1]
+) -> NDArray[np.bool_] | NDArray[np.integer]:
     if is_bool_dtype(old) and is_bool_dtype(new):
         mask_new = np.zeros_like(old)
         mask_new[np.flatnonzero(old)[new]] = True
@@ -454,21 +464,17 @@ def _resolve_idx_ndarray(old, new, l):
     return old[new]
 
 
-@_resolve_idx.register(np.integer)
-@_resolve_idx.register(int)
-def _resolve_idx_scalar(old, new, l):
-    return np.array([old])[new]
-
-
 @_resolve_idx.register(slice)
-def _resolve_idx_slice(old, new, l):
+def _resolve_idx_slice(
+    old: slice, new: Index1DNorm, l: Literal[0, 1]
+) -> slice | NDArray[np.integer]:
     if isinstance(new, slice):
         return _resolve_idx_slice_slice(old, new, l)
     else:
         return np.arange(*old.indices(l))[new]
 
 
-def _resolve_idx_slice_slice(old, new, l):
+def _resolve_idx_slice_slice(old: slice, new: slice, l: Literal[0, 1]) -> slice:
     r = range(*old.indices(l))[new]
     # Convert back to slice
     start, stop, step = r.start, r.stop, r.step

anndata/_core/xarray.py

@@ -184,18 +184,6 @@ class Dataset2D:
         Handler class for doing the iloc-style indexing using :meth:`~xarray.Dataset.isel`.
         """
 
-        @dataclass(frozen=True)
-        class IlocGetter:
-            _ds: XDataset
-            _coord: str
-
-            def __getitem__(self, idx) -> Dataset2D:
-                # xarray seems to have some code looking for a second entry in tuples,
-                # so we unpack the tuple
-                if isinstance(idx, tuple) and len(idx) == 1:
-                    idx = idx[0]
-                return Dataset2D(self._ds.isel(**{self._coord: idx}))
-
         return IlocGetter(self.ds, self.index_dim)
 
     # See https://github.com/pydata/xarray/blob/568f3c1638d2d34373408ce2869028faa3949446/xarray/core/dataset.py#L1239-L1248
@@ -402,3 +390,16 @@ class Dataset2D:
     def _items(self):
         for col in self:
             yield col, self[col]
+
+
+@dataclass(frozen=True)
+class IlocGetter:
+    _ds: XDataset
+    _coord: str
+
+    def __getitem__(self, idx) -> Dataset2D:
+        # xarray seems to have some code looking for a second entry in tuples,
+        # so we unpack the tuple
+        if isinstance(idx, tuple) and len(idx) == 1:
+            idx = idx[0]
+        return Dataset2D(self._ds.isel(**{self._coord: idx}))

anndata/_io/h5ad.py

@@ -4,7 +4,7 @@ import re
 from functools import partial
 from pathlib import Path
 from types import MappingProxyType
-from typing import TYPE_CHECKING, TypeVar
+from typing import TYPE_CHECKING, TypeVar, cast
 from warnings import warn
 
 import h5py
@@ -36,11 +36,12 @@ from .utils import (
 )
 
 if TYPE_CHECKING:
-    from collections.abc import Callable, Collection, Mapping, Sequence
+    from collections.abc import Callable, Collection, Container, Mapping, Sequence
     from os import PathLike
     from typing import Any, Literal
 
     from .._core.file_backing import AnnDataFileManager
+    from .._core.raw import Raw
 
 T = TypeVar("T")
 
@@ -82,29 +83,18 @@ def write_h5ad(
         # TODO: Use spec writing system for this
         # Currently can't use write_dispatched here because this function is also called to do an
         # inplace update of a backed object, which would delete "/"
-        f = f["/"]
+        f = cast("h5py.Group", f["/"])
         f.attrs.setdefault("encoding-type", "anndata")
         f.attrs.setdefault("encoding-version", "0.1.0")
 
-        if "X" in as_dense and isinstance(
-            adata.X, CSMatrix | BaseCompressedSparseDataset
-        ):
-            write_sparse_as_dense(f, "X", adata.X, dataset_kwargs=dataset_kwargs)
-        elif not (adata.isbacked and Path(adata.filename) == Path(filepath)):
-            # If adata.isbacked, X should already be up to date
-            write_elem(f, "X", adata.X, dataset_kwargs=dataset_kwargs)
-        if "raw/X" in as_dense and isinstance(
-            adata.raw.X, CSMatrix | BaseCompressedSparseDataset
-        ):
-            write_sparse_as_dense(
-                f, "raw/X", adata.raw.X, dataset_kwargs=dataset_kwargs
-            )
-            write_elem(f, "raw/var", adata.raw.var, dataset_kwargs=dataset_kwargs)
-            write_elem(
-                f, "raw/varm", dict(adata.raw.varm), dataset_kwargs=dataset_kwargs
-            )
-        elif adata.raw is not None:
-            write_elem(f, "raw", adata.raw, dataset_kwargs=dataset_kwargs)
+        _write_x(
+            f,
+            adata,  # accessing adata.X reopens adata.file if it’s backed
+            is_backed=adata.isbacked and adata.filename == filepath,
+            as_dense=as_dense,
+            dataset_kwargs=dataset_kwargs,
+        )
+        _write_raw(f, adata.raw, as_dense=as_dense, dataset_kwargs=dataset_kwargs)
         write_elem(f, "obs", adata.obs, dataset_kwargs=dataset_kwargs)
         write_elem(f, "var", adata.var, dataset_kwargs=dataset_kwargs)
         write_elem(f, "obsm", dict(adata.obsm), dataset_kwargs=dataset_kwargs)
@@ -115,6 +105,41 @@ def write_h5ad(
         write_elem(f, "uns", dict(adata.uns), dataset_kwargs=dataset_kwargs)
 
 
+def _write_x(
+    f: h5py.Group,
+    adata: AnnData,
+    *,
+    is_backed: bool,
+    as_dense: Container[str],
+    dataset_kwargs: Mapping[str, Any],
+) -> None:
+    if "X" in as_dense and isinstance(adata.X, CSMatrix | BaseCompressedSparseDataset):
+        write_sparse_as_dense(f, "X", adata.X, dataset_kwargs=dataset_kwargs)
+    elif is_backed:
+        pass  # If adata.isbacked, X should already be up to date
+    elif adata.X is None:
+        f.pop("X", None)
+    else:
+        write_elem(f, "X", adata.X, dataset_kwargs=dataset_kwargs)
+
+
+def _write_raw(
+    f: h5py.Group,
+    raw: Raw,
+    *,
+    as_dense: Container[str],
+    dataset_kwargs: Mapping[str, Any],
+) -> None:
+    if "raw/X" in as_dense and isinstance(
+        raw.X, CSMatrix | BaseCompressedSparseDataset
+    ):
+        write_sparse_as_dense(f, "raw/X", raw.X, dataset_kwargs=dataset_kwargs)
+        write_elem(f, "raw/var", raw.var, dataset_kwargs=dataset_kwargs)
+        write_elem(f, "raw/varm", dict(raw.varm), dataset_kwargs=dataset_kwargs)
+    elif raw is not None:
+        write_elem(f, "raw", raw, dataset_kwargs=dataset_kwargs)
+
+
 @report_write_key_on_error
 @write_spec(IOSpec("array", "0.2.0"))
 def write_sparse_as_dense(

anndata/_io/read.py

@@ -48,7 +48,9 @@ def read_csv(
     dtype
         Numpy data type.
     """
-    return read_text(filename, delimiter, first_column_names, dtype)
+    return read_text(
+        filename, delimiter, first_column_names=first_column_names, dtype=dtype
+    )
 
 
 def read_excel(
@@ -360,18 +362,26 @@ def read_text(
         Numpy data type.
     """
     if not isinstance(filename, PathLike | str | bytes):
-        return _read_text(filename, delimiter, first_column_names, dtype)
+        return _read_text(
+            filename, delimiter, first_column_names=first_column_names, dtype=dtype
+        )
 
     filename = Path(filename)
     if filename.suffix == ".gz":
         with gzip.open(str(filename), mode="rt") as f:
-            return _read_text(f, delimiter, first_column_names, dtype)
+            return _read_text(
+                f, delimiter, first_column_names=first_column_names, dtype=dtype
+            )
     elif filename.suffix == ".bz2":
         with bz2.open(str(filename), mode="rt") as f:
-            return _read_text(f, delimiter, first_column_names, dtype)
+            return _read_text(
+                f, delimiter, first_column_names=first_column_names, dtype=dtype
+            )
     else:
         with filename.open() as f:
-            return _read_text(f, delimiter, first_column_names, dtype)
+            return _read_text(
+                f, delimiter, first_column_names=first_column_names, dtype=dtype
+            )
 
 
 def _iter_lines(file_like: Iterable[str]) -> Generator[str, None, None]:
@@ -385,7 +395,8 @@ def _iter_lines(file_like: Iterable[str]) -> Generator[str, None, None]:
 def _read_text(  # noqa: PLR0912, PLR0915
     f: Iterator[str],
     delimiter: str | None,
-    first_column_names: bool | None,  # noqa: FBT001
+    *,
+    first_column_names: bool | None,
     dtype: str,
 ) -> AnnData:
     comments = []

anndata/_io/specs/methods.py

@@ -275,7 +275,8 @@ def write_anndata(
     dataset_kwargs: Mapping[str, Any] = MappingProxyType({}),
 ):
     g = f.require_group(k)
-    _writer.write_elem(g, "X", adata.X, dataset_kwargs=dataset_kwargs)
+    if adata.X is not None:
+        _writer.write_elem(g, "X", adata.X, dataset_kwargs=dataset_kwargs)
     _writer.write_elem(g, "obs", adata.obs, dataset_kwargs=dataset_kwargs)
     _writer.write_elem(g, "var", adata.var, dataset_kwargs=dataset_kwargs)
     _writer.write_elem(g, "obsm", dict(adata.obsm), dataset_kwargs=dataset_kwargs)
@@ -629,7 +630,7 @@ def write_vlen_string_array_zarr(
         dataset_kwargs = zarr_v3_compressor_compat(dataset_kwargs)
         dtype = VariableLengthUTF8()
         filters, fill_value = None, None
-        if ad.settings.zarr_write_format == 2:
+        if f.metadata.zarr_format == 2:
             filters, fill_value = [VLenUTF8()], ""
         f.create_array(
             k,
@@ -695,12 +696,11 @@ def write_recarray_zarr(
     from anndata.compat import _to_fixed_length_strings
 
     elem = _to_fixed_length_strings(elem)
-    if isinstance(f, H5Group) or is_zarr_v2():
+    if is_zarr_v2():
         f.create_dataset(k, data=elem, shape=elem.shape, **dataset_kwargs)
     else:
         dataset_kwargs = dataset_kwargs.copy()
         dataset_kwargs = zarr_v3_compressor_compat(dataset_kwargs)
-        # TODO: zarr’s on-disk format v3 doesn’t support this dtype
         f.create_array(k, shape=elem.shape, dtype=elem.dtype, **dataset_kwargs)
         f[k][...] = elem
 
@@ -1283,7 +1283,7 @@ def write_scalar_zarr(
         from numcodecs import VLenUTF8
         from zarr.core.dtype import VariableLengthUTF8
 
-        match ad.settings.zarr_write_format, value:
+        match f.metadata.zarr_format, value:
             case 2, str():
                 filters, dtype, fill_value = [VLenUTF8()], VariableLengthUTF8(), ""
             case 3, str():

anndata/_io/zarr.py

@@ -1,6 +1,5 @@
 from __future__ import annotations
 
-from pathlib import Path
 from typing import TYPE_CHECKING, TypeVar
 from warnings import warn
 
@@ -37,8 +36,6 @@ def write_zarr(
     **ds_kwargs,
 ) -> None:
     """See :meth:`~anndata.AnnData.write_zarr`."""
-    if isinstance(store, Path):
-        store = str(store)
     if convert_strings_to_categoricals:
         adata.strings_to_categoricals()
         if adata.raw is not None:
@@ -75,9 +72,6 @@ def read_zarr(store: PathLike[str] | str | MutableMapping | zarr.Group) -> AnnDa
     store
         The filename, a :class:`~typing.MutableMapping`, or a Zarr storage class.
     """
-    if isinstance(store, Path):
-        store = str(store)
-
     f = store if isinstance(store, zarr.Group) else zarr.open(store, mode="r")
 
     # Read with handling for backwards compat

anndata/_settings.py

@@ -447,7 +447,7 @@ def validate_zarr_write_format(format: int):
 settings.register(
     "zarr_write_format",
     default_value=2,
-    description="Which version of zarr to write to.",
+    description="Which version of zarr to write to when anndata must internally open a write-able zarr group.",
     validate=validate_zarr_write_format,
     get_from_env=lambda name, default: check_and_get_environ_var(
         f"ANNDATA_{name.upper()}",

anndata/compat/__init__.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 from codecs import decode
-from collections.abc import Mapping
+from collections.abc import Mapping, Sequence
 from functools import cache, partial, singledispatch
 from importlib.util import find_spec
 from types import EllipsisType
@@ -12,6 +12,7 @@ import h5py
 import numpy as np
 import pandas as pd
 import scipy
+from numpy.typing import NDArray
 from packaging.version import Version
 from zarr import Array as ZarrArray  # noqa: F401
 from zarr import Group as ZarrGroup
@@ -19,6 +20,7 @@ from zarr import Group as ZarrGroup
 if TYPE_CHECKING:
     from typing import Any
 
+
 #############################
 # scipy sparse array comapt #
 #############################
@@ -32,7 +34,26 @@ class Empty:
     pass
 
 
-Index1D = slice | int | str | np.int64 | np.ndarray | pd.Series
+Index1DNorm = slice | NDArray[np.bool_] | NDArray[np.integer]
+# TODO: pd.Index[???]
+Index1D = (
+    # 0D index
+    int
+    | str
+    | np.int64
+    # normalized 1D idex
+    | Index1DNorm
+    # different containers for mask, obs/varnames, or numerical index
+    | Sequence[int]
+    | Sequence[str]
+    | Sequence[bool]
+    | pd.Series  # bool, int, str
+    | pd.Index
+    | NDArray[np.str_]
+    | np.matrix  # bool
+    | CSMatrix  # bool
+    | CSArray  # bool
+)
 IndexRest = Index1D | EllipsisType
 Index = (
     IndexRest
@@ -286,8 +307,12 @@ def _to_fixed_length_strings(value: np.ndarray) -> np.ndarray:
     """\
     Convert variable length strings to fixed length.
 
-    Currently a workaround for
-    https://github.com/zarr-developers/zarr-python/pull/422
+    Formerly a workaround for
+    https://github.com/zarr-developers/zarr-python/pull/422,
+    resolved in https://github.com/zarr-developers/zarr-python/pull/813.
+
+    But if we didn't do this conversion, we would have to use a special codec in v2
+    for objects and v3 doesn't support objects at all.  So we leave this function as-is.
     """
     new_dtype = []
     for dt_name, (dt_type, dt_offset) in value.dtype.fields.items():

anndata/tests/helpers.py

@@ -42,12 +42,15 @@ if TYPE_CHECKING:
     from collections.abc import Callable, Collection, Iterable
     from typing import Literal, TypeGuard, TypeVar
 
+    from numpy.typing import NDArray
     from zarr.abc.store import ByteRequest
     from zarr.core.buffer import BufferPrototype
 
     from .._types import ArrayStorageType
+    from ..compat import Index1D
 
     DT = TypeVar("DT")
+    _SubsetFunc = Callable[[pd.Index[str], int], Index1D]
 
 
 try:
@@ -428,7 +431,7 @@ def gen_adata(  # noqa: PLR0913
     return adata
 
 
-def array_bool_subset(index, min_size=2):
+def array_bool_subset(index: pd.Index[str], min_size: int = 2) -> NDArray[np.bool_]:
     b = np.zeros(len(index), dtype=bool)
     selected = np.random.choice(
         range(len(index)),
@@ -439,11 +442,11 @@ def array_bool_subset(index, min_size=2):
     return b
 
 
-def list_bool_subset(index, min_size=2):
+def list_bool_subset(index: pd.Index[str], min_size: int = 2) -> list[bool]:
     return array_bool_subset(index, min_size=min_size).tolist()
 
 
-def matrix_bool_subset(index, min_size=2):
+def matrix_bool_subset(index: pd.Index[str], min_size: int = 2) -> np.matrix:
     with warnings.catch_warnings():
         warnings.simplefilter("ignore", PendingDeprecationWarning)
         indexer = np.matrix(
@@ -452,19 +455,26 @@ def matrix_bool_subset(index, min_size=2):
     return indexer
 
 
-def spmatrix_bool_subset(index, min_size=2):
+def spmatrix_bool_subset(index: pd.Index[str], min_size: int = 2) -> sparse.csr_matrix:
     return sparse.csr_matrix(
         array_bool_subset(index, min_size=min_size).reshape(len(index), 1)
     )
 
 
-def sparray_bool_subset(index, min_size=2):
+def sparray_bool_subset(index: pd.Index[str], min_size: int = 2) -> sparse.csr_array:
     return sparse.csr_array(
         array_bool_subset(index, min_size=min_size).reshape(len(index), 1)
     )
 
 
-def array_subset(index, min_size=2):
+def single_subset(index: pd.Index[str], min_size: int = 1) -> str:
+    if min_size > 1:
+        msg = "max_size must be ≤1"
+        raise AssertionError(msg)
+    return index[np.random.randint(0, len(index))]
+
+
+def array_subset(index: pd.Index[str], min_size: int = 2) -> NDArray[np.str_]:
     if len(index) < min_size:
         msg = f"min_size (={min_size}) must be smaller than len(index) (={len(index)}"
         raise ValueError(msg)
@@ -473,7 +483,7 @@ def array_subset(index, min_size=2):
     )
 
 
-def array_int_subset(index, min_size=2):
+def array_int_subset(index: pd.Index[str], min_size: int = 2) -> NDArray[np.int64]:
     if len(index) < min_size:
         msg = f"min_size (={min_size}) must be smaller than len(index) (={len(index)}"
         raise ValueError(msg)
@@ -484,11 +494,11 @@ def array_int_subset(index, min_size=2):
     )
 
 
-def list_int_subset(index, min_size=2):
+def list_int_subset(index: pd.Index[str], min_size: int = 2) -> list[int]:
     return array_int_subset(index, min_size=min_size).tolist()
 
 
-def slice_subset(index, min_size=2):
+def slice_int_subset(index: pd.Index[str], min_size: int = 2) -> slice:
     while True:
         points = np.random.choice(np.arange(len(index) + 1), size=2, replace=False)
         s = slice(*sorted(points))
@@ -497,25 +507,33 @@ def slice_subset(index, min_size=2):
     return s
 
 
-def single_subset(index):
-    return index[np.random.randint(0, len(index))]
+def single_int_subset(index: pd.Index[str], min_size: int = 1) -> int:
+    if min_size > 1:
+        msg = "max_size must be ≤1"
+        raise AssertionError(msg)
+    return np.random.randint(0, len(index))
+
+
+_SUBSET_FUNCS: list[_SubsetFunc] = [
+    # str (obs/var name)
+    single_subset,
+    array_subset,
+    # int (numeric index)
+    single_int_subset,
+    slice_int_subset,
+    array_int_subset,
+    list_int_subset,
+    # bool (mask)
+    array_bool_subset,
+    list_bool_subset,
+    matrix_bool_subset,
+    spmatrix_bool_subset,
+    sparray_bool_subset,
+]
 
 
-@pytest.fixture(
-    params=[
-        array_subset,
-        slice_subset,
-        single_subset,
-        array_int_subset,
-        list_int_subset,
-        array_bool_subset,
-        list_bool_subset,
-        matrix_bool_subset,
-        spmatrix_bool_subset,
-        sparray_bool_subset,
-    ]
-)
-def subset_func(request):
+@pytest.fixture(params=_SUBSET_FUNCS)
+def subset_func(request: pytest.FixtureRequest) -> _SubsetFunc:
     return request.param
 
 

{anndata-0.12.1.dist-info → anndata-0.12.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: anndata
-Version: 0.12.1
+Version: 0.12.2
 Summary: Annotated data.
 Project-URL: Documentation, https://anndata.readthedocs.io/
 Project-URL: Source, https://github.com/scverse/anndata

{anndata-0.12.1.dist-info → anndata-0.12.2.dist-info}/RECORD

@@ -1,5 +1,5 @@
 anndata/__init__.py,sha256=GdrXtUOgciN34rNOl3CxpzvoBgl0yERqrDLWjlwF3RI,1468
-anndata/_settings.py,sha256=Le3ysSfuG0vuYCtnUN3DV4HOnyiGgC-k9Gv0JShosSs,15654
+anndata/_settings.py,sha256=UR6tHlWmEEgoaC3e4LuYavveeHICgaC7XOZOyEgNX-0,15712
 anndata/_settings.pyi,sha256=KUJEheJy1zvCBN2NvNEXAGcjLPUQcdhk0STIcU4mM4I,1545
 anndata/_types.py,sha256=c71REP9wS7Vz2cYrNxuNjPYdnq8MJ5g04MNrSi85ATA,5427
 anndata/_version.py,sha256=qsRPKvJAzUrnf49DHZk-FYfXKOASg5nJV2qomuOttX0,2160
@@ -14,27 +14,27 @@ anndata/_core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 anndata/_core/access.py,sha256=pts7fGUKgGZANSsu_qAA7L10qHM-jT1zIehbl3441OY,873
 anndata/_core/aligned_df.py,sha256=MrGdi1zNZZlkkv4IeS2yY-R5ldXpchTlMlJK7PKRa7A,3833
 anndata/_core/aligned_mapping.py,sha256=BYU1jslMWIhtFTtUMaXY8ZCyt0J4_ZsJTmj6J2yAXTQ,14257
-anndata/_core/anndata.py,sha256=BADYc8TpS6yc1-bw5sh5cPzB4v63O5ZH0YFFChKO7TY,77747
+anndata/_core/anndata.py,sha256=ZQF9L5Zt4k1Bg0npd9iL-PS_pYx62MfQzW1llN4QcRA,78291
 anndata/_core/extensions.py,sha256=9Rsho6qnr3PJHULrYGiZHCBinBZYJK6zyf3cFsl_gBY,10425
 anndata/_core/file_backing.py,sha256=kT71R_kZp_CiHImBK8IaZXsvYVtbX2Mg-7L2ldAWojM,5113
-anndata/_core/index.py,sha256=lyVuDfKvEeQYpgKjDsnuZNt4k4wV3adFowO_RrcohpE,9353
+anndata/_core/index.py,sha256=6oED8kjTFKXnZSJXbkGFwscRtqV346h05Dx_Spd68WY,9298
 anndata/_core/merge.py,sha256=v0PxVs49KUZx6X252EtGt7XUHbO3mytTPK_o3Vd1nuo,60302
-anndata/_core/raw.py,sha256=EfTLoizP_mLtfYn0BR1Rpya0iZoGF4CupojWyeLGWpc,7797
+anndata/_core/raw.py,sha256=x_PwwaDQscVQOFJ38kF7sNQ47LxowpS38h2RQfU5Zwo,7925
 anndata/_core/sparse_dataset.py,sha256=syXVDdQsEPSBvEi4eyBiAxPiq2TSk7qGStP8QSBTwBg,26801
 anndata/_core/storage.py,sha256=mHzqp7YBJ-rGQFulMAx__D-Z7y4omHPyb1cP7YxfbFE,2555
-anndata/_core/views.py,sha256=rbmI7P4dEcefhjons2l42H9D509xhxyXKTeyWiIBdtw,14657
-anndata/_core/xarray.py,sha256=pvAMSxrHmuz2d-xbalYmuNi56GrLPw_2Ehko8nss9Xg,16157
+anndata/_core/views.py,sha256=eOFSV9pKhgcfPvK-c9nxfYdD6o0EVSxE7eSJissojwU,15018
+anndata/_core/xarray.py,sha256=JeQjTuSQEiZF8cryKDYf9d7yt-ufQEVo9x94YaczuPQ,16078
 anndata/_io/__init__.py,sha256=GTNeUZ8d8aA3sK4P33tyljIc60KapLbkqBC6J1y3l9U,346
-anndata/_io/h5ad.py,sha256=ekfuxldN6LuhR3b1aXJKvjfivOBlRP_A4rhEqvej-8Q,13633
-anndata/_io/read.py,sha256=oc8Af3r9ieh0-SFN3GKRIFxenijrbng55-Ds-WUhbdE,15691
+anndata/_io/h5ad.py,sha256=gABV7M7YjThZ7X9VAsHWs7baqQ4L0Zp90dBz4Kle7ys,14191
+anndata/_io/read.py,sha256=MuTR6dR2WItV2y0sKYvxSO2fu7OlDjaCRYJuT5UbuBo,15933
 anndata/_io/utils.py,sha256=dB2RRaWm9V-CMGI46KhqpmzBGA6LLBnsJc83Q85OcgM,9613
 anndata/_io/write.py,sha256=r55w6yPIIuUSLW9wyYL8GnkzHHQdAxy6xiCEw9cAC38,4811
-anndata/_io/zarr.py,sha256=6ejnp9VNsxSihSd3HXAv2uVkrv7dRnuox4Jt1Y0yyGY,5261
+anndata/_io/zarr.py,sha256=hLi7nkgTiqe0ftgVaVSpwlU0Y7VurSTf_C3DfILdfAo,5117
 anndata/_io/specs/__init__.py,sha256=Z6l8xqa7B480U3pqrNIg4-fhUvpBW85w4xA3i3maAUM,427
 anndata/_io/specs/lazy_methods.py,sha256=64rr1C83aaiN-iO7m1R03dqd6TbiJQbhzOQI5lXHD0o,12270
-anndata/_io/specs/methods.py,sha256=qRRZfz4pqjaxRrkhiYiZe9_mXuWjAj4OLhbL-CO_VSM,46485
+anndata/_io/specs/methods.py,sha256=dz-lfDjoLRpnRXdKjzDaA9_DBbOdys5BIL5ivMCHqvs,46405
 anndata/_io/specs/registry.py,sha256=hno-mvefhcDHmACrBjcKmlf5T87FPoe-N1Gd3i9otYo,17459
-anndata/compat/__init__.py,sha256=FZZbV36BG0L0v-N5IXQbrCa5jNgBRsFY44vmdG-2y_4,12227
+anndata/compat/__init__.py,sha256=zCh9_7FcePbTTvXceZYY6mPemlKFgiYCy3x7srFQum4,12915
 anndata/experimental/__init__.py,sha256=polIxriEkby0iEqw-IXkUzp8k0wp92BpYY4zl4BsHH0,1648
 anndata/experimental/_dispatch_io.py,sha256=JzH8Uvewabc1gIF3L16RZnM9m2NAG28bQIQ57uP097k,1869
 anndata/experimental/merge.py,sha256=Y18C1AT9R1IF60Y7YxyprJ1hz-ySNb2okXHA6IR6fCU,21914
@@ -47,12 +47,12 @@ anndata/experimental/multi_files/_anncollection.py,sha256=RQ79_7r8sdV_kx66UJUuY9
 anndata/experimental/pytorch/__init__.py,sha256=4CkgrahLO8Kc-s2bmv6lVQfDxbO3IUyV0v4ygBDkttY,95
 anndata/experimental/pytorch/_annloader.py,sha256=7mpsFV5vBfxKIje1cPjahtDZ5afkU-H663XB4FJhmok,8075
 anndata/tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-anndata/tests/helpers.py,sha256=yVFdqB2PDDw8jNOkKAo-6VR7vk8yUlbafZbtDyibB8c,35111
+anndata/tests/helpers.py,sha256=27p_Nc5vFIiW-7EhV85g3QiE0dStMnUg0uFBRyroZUg,36072
 testing/anndata/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 testing/anndata/_doctest.py,sha256=Qew0N0zLLNiPKN1CLunqY5cTinFLaEhY5GagiYfm6KI,344
 testing/anndata/_pytest.py,sha256=a1Qn5KR5mjCcQI05negkMEv0e2aJX2P_teyl0UMfoeQ,4160
 testing/anndata/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-anndata-0.12.1.dist-info/METADATA,sha256=ah9uvJCDn4h1tspyYlcwiSC7mGBhwWHVs6irKQ8LzXY,9643
-anndata-0.12.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-anndata-0.12.1.dist-info/licenses/LICENSE,sha256=VcrXoEVMhtNuvMvKYGP-I5lMT8qZ_6dFf22fsL180qA,1575
-anndata-0.12.1.dist-info/RECORD,,
+anndata-0.12.2.dist-info/METADATA,sha256=M4Jcewb7LkN2pgT41Trw2y3YvZ4Z1EzZAzcQ78K03SE,9643
+anndata-0.12.2.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+anndata-0.12.2.dist-info/licenses/LICENSE,sha256=VcrXoEVMhtNuvMvKYGP-I5lMT8qZ_6dFf22fsL180qA,1575
+anndata-0.12.2.dist-info/RECORD,,