anndata 0.12.4__py3-none-any.whl → 0.12.6__py3-none-any.whl

anndata/_core/anndata.py

@@ -964,7 +964,11 @@ class AnnData(metaclass=utils.DeprecationMixinMeta):  # noqa: PLW1641
     @property
     def isbacked(self) -> bool:
         """`True` if object is backed on disk, `False` otherwise."""
-        return self.filename is not None
+        is_filename_none = self.filename is not None
+        is_x_none = (
+            getattr(self._adata_ref if self._is_view else self, "_X", None) is None
+        )
+        return is_filename_none and is_x_none
 
     @property
     def is_view(self) -> bool:
@@ -1418,7 +1422,7 @@ class AnnData(metaclass=utils.DeprecationMixinMeta):  # noqa: PLW1641
 
     @old_positionals("copy")
     def to_memory(self, *, copy: bool = False) -> AnnData:
-        """Return a new AnnData object with all backed arrays loaded into memory.
+        """Return a new AnnData object with all non-in-memory arrays loaded into memory.
 
         Params
         ------

anndata/_core/file_backing.py

@@ -27,15 +27,24 @@ class AnnDataFileManager:
     def __init__(
         self,
         adata: anndata.AnnData,
-        filename: PathLike[str] | str | None = None,
-        filemode: Literal["r", "r+"] | None = None,
+        file_name: PathLike[str] | str | None = None,
+        file_mode: Literal["r", "r+"] | None = None,
+        file_obj: h5py.File | None = None,
     ):
+        if file_obj is not None and (file_name is not None or file_mode is not None):
+            msg = "Cannot provide both a h5py.File and the name and/or mode arguments to constructor"
+            raise ValueError(msg)
         self._adata_ref = weakref.ref(adata)
-        self.filename = filename
-        self._filemode = filemode
-        self._file = None
-        if filename:
-            self.open()
+        if file_obj is not None:
+            self.filename = filename(file_obj)
+            self._filemode = file_obj.mode
+            self._file = file_obj
+        else:
+            self.filename = file_name
+            self._filemode = file_mode
+            self._file = file_obj
+            if file_name and not self._file:
+                self.open()
 
     def __getstate__(self):
         state = self.__dict__.copy()
@@ -82,16 +91,16 @@ class AnnDataFileManager:
         return self._filename
 
     @filename.setter
-    def filename(self, filename: PathLike[str] | str | None):
-        self._filename = None if filename is None else Path(filename)
+    def filename(self, file_name: PathLike[str] | str | None):
+        self._filename = None if file_name is None else Path(file_name)
 
     def open(
         self,
-        filename: PathLike[str] | str | None = None,
+        file_name: PathLike[str] | str | None = None,
         filemode: Literal["r", "r+"] | None = None,
     ):
-        if filename is not None:
-            self.filename = filename
+        if file_name is not None:
+            self.filename = file_name
         if filemode is not None:
             self._filemode = filemode
         if self.filename is None:

anndata/_core/merge.py

@@ -4,6 +4,7 @@ Code for merging/ concatenating AnnData objects.
 
 from __future__ import annotations
 
+import uuid
 from collections import OrderedDict
 from collections.abc import Callable, Mapping, MutableSet
 from functools import partial, reduce, singledispatch
@@ -1251,6 +1252,7 @@ def make_dask_col_from_extension_dtype(
             chunks=chunk_size,
             meta=np.array([], dtype=dtype),
             dtype=dtype,
+            name=f"{uuid.uuid4()}/{base_path_or_zarr_group}/{elem_name}-{dtype}",
         )
 
     return da.from_array(col.values, chunks=-1)  # in-memory

anndata/_io/specs/lazy_methods.py

@@ -25,7 +25,7 @@ from anndata.compat import (
     ZarrGroup,
 )
 
-from .registry import _LAZY_REGISTRY, IOSpec
+from .registry import _LAZY_REGISTRY, IOSpec, read_elem
 
 if TYPE_CHECKING:
     from collections.abc import Generator, Mapping, Sequence
@@ -195,6 +195,9 @@ def resolve_chunks(
     return elem.chunks
 
 
+# TODO: `map_blocks` of a string array in h5py is so insanely slow on benchmarking that in the case someone has
+# a pure string annotation (not categoricals! or nullables strings!), it's probably better to pay the memory penalty.
+# In the long run, it might be good to figure out what exactly is going on here but for now, this will do.
 @_LAZY_REGISTRY.register_read(H5Array, IOSpec("string-array", "0.2.0"))
 def read_h5_string_array(
     elem: H5Array,
@@ -204,10 +207,8 @@ def read_h5_string_array(
 ) -> DaskArray:
     import dask.array as da
 
-    from anndata._io.h5ad import read_dataset
-
     chunks = resolve_chunks(elem, chunks, tuple(elem.shape))
-    return da.from_array(read_dataset(elem), chunks=chunks)
+    return da.from_array(read_elem(elem), chunks=chunks)
 
 
 @_LAZY_REGISTRY.register_read(H5Array, IOSpec("array", "0.2.0"))
@@ -303,7 +304,7 @@ def read_dataframe(
     # which is used below as well.
     if not use_range_index:
         dim_name = elem.attrs["_index"]
-        # no sense in reading this in multiple times
+        # no sense in reading this in multiple times since xarray requires an in-memory index
         index = elem_dict[dim_name].compute()
     else:
         dim_name = DUMMY_RANGE_INDEX_KEY

anndata/_io/specs/methods.py

@@ -102,6 +102,12 @@ def zarr_v3_compressor_compat(dataset_kwargs) -> dict:
     return dataset_kwargs
 
 
+def zarr_v3_sharding(dataset_kwargs) -> dict:
+    if "shards" not in dataset_kwargs and ad.settings.auto_shard_zarr_v3:
+        dataset_kwargs = {**dataset_kwargs, "shards": "auto"}
+    return dataset_kwargs
+
+
 def _to_cpu_mem_wrapper(write_func):
     """
     Wrapper to bring cupy types into cpu memory before writing.
@@ -432,6 +438,7 @@ def write_basic(
         f.create_dataset(k, data=elem, shape=elem.shape, dtype=dtype, **dataset_kwargs)
     else:
         dataset_kwargs = zarr_v3_compressor_compat(dataset_kwargs)
+        dataset_kwargs = zarr_v3_sharding(dataset_kwargs)
         f.create_array(k, shape=elem.shape, dtype=dtype, **dataset_kwargs)
         # see https://github.com/zarr-developers/zarr-python/discussions/2712
         if isinstance(elem, ZarrArray | H5Array):
@@ -506,26 +513,17 @@ def write_basic_dask_dask_dense(
     dataset_kwargs: Mapping[str, Any] = MappingProxyType({}),
 ):
     import dask.array as da
-    import dask.config as dc
-
-    is_distributed = dc.get("scheduler", None) == "dask.distributed"
-    is_h5 = isinstance(f, H5Group)
-    if is_distributed and is_h5:
-        msg = "Cannot write dask arrays to hdf5 when using distributed scheduler"
-        raise ValueError(msg)
 
     dataset_kwargs = dataset_kwargs.copy()
+    is_h5 = isinstance(f, H5Group)
     if not is_h5:
         dataset_kwargs = zarr_v3_compressor_compat(dataset_kwargs)
-        # See https://github.com/dask/dask/issues/12109
-        if Version(version("dask")) < Version("2025.4.0") and is_distributed:
-            msg = "Writing dense data with a distributed scheduler to zarr could produce corrupted data with a Lock and will error without one when dask is older than 2025.4.0: https://github.com/dask/dask/issues/12109"
-            raise RuntimeError(msg)
+        dataset_kwargs = zarr_v3_sharding(dataset_kwargs)
     if is_zarr_v2() or is_h5:
         g = f.require_dataset(k, shape=elem.shape, dtype=elem.dtype, **dataset_kwargs)
     else:
         g = f.require_array(k, shape=elem.shape, dtype=elem.dtype, **dataset_kwargs)
-    da.store(elem, g)
+    da.store(elem, g, scheduler="threads")
 
 
 @_REGISTRY.register_read(H5Array, IOSpec("array", "0.2.0"))
@@ -626,6 +624,7 @@ def write_vlen_string_array_zarr(
         filters, fill_value = None, None
         if f.metadata.zarr_format == 2:
             filters, fill_value = [VLenUTF8()], ""
+        dataset_kwargs = zarr_v3_sharding(dataset_kwargs)
         f.create_array(
             k,
             shape=elem.shape,
@@ -694,6 +693,9 @@ def write_recarray_zarr(
     else:
         dataset_kwargs = dataset_kwargs.copy()
         dataset_kwargs = zarr_v3_compressor_compat(dataset_kwargs)
+        # https://github.com/zarr-developers/zarr-python/issues/3546
+        # if "shards" not in dataset_kwargs and ad.settings.auto_shard_zarr_v3:
+        #     dataset_kwargs = {**dataset_kwargs, "shards": "auto"}
         f.create_array(k, shape=elem.shape, dtype=elem.dtype, **dataset_kwargs)
         f[k][...] = elem
 
@@ -730,6 +732,7 @@ def write_sparse_compressed(
                 attr_name, data=attr, shape=attr.shape, dtype=dtype, **dataset_kwargs
             )
         else:
+            dataset_kwargs = zarr_v3_sharding(dataset_kwargs)
             arr = g.create_array(
                 attr_name, shape=attr.shape, dtype=dtype, **dataset_kwargs
             )

anndata/_settings.py

@@ -17,7 +17,7 @@ from .compat import is_zarr_v2, old_positionals
 
 if TYPE_CHECKING:
     from collections.abc import Callable, Sequence
-    from typing import Any, TypeGuard
+    from typing import Any, Self, TypeGuard
 
 T = TypeVar("T")
 
@@ -55,7 +55,7 @@ class RegisteredOption(NamedTuple, Generic[T]):
     option: str
     default_value: T
     description: str
-    validate: Callable[[T], None]
+    validate: Callable[[T, SettingsManager], None]
     type: object
 
     describe = describe
@@ -206,7 +206,7 @@ class SettingsManager:
         *,
         default_value: T,
         description: str,
-        validate: Callable[[T], None],
+        validate: Callable[[T, Self], None],
         option_type: object | None = None,
         get_from_env: Callable[[str, T], T] = lambda x, y: y,
     ) -> None:
@@ -229,7 +229,7 @@ class SettingsManager:
             Default behavior is to return `default_value` without checking the environment.
         """
         try:
-            validate(default_value)
+            validate(default_value, self)
         except (ValueError, TypeError) as e:
             e.add_note(f"for option {option!r}")
             raise e
@@ -307,7 +307,7 @@ class SettingsManager:
             )
             raise AttributeError(msg)
         registered_option = self._registered_options[option]
-        registered_option.validate(val)
+        registered_option.validate(val, self)
         self._config[option] = val
 
     def __getattr__(self, option: str) -> object:
@@ -364,10 +364,13 @@ class SettingsManager:
         """
         restore = {a: getattr(self, a) for a in overrides}
         try:
-            for attr, value in overrides.items():
-                setattr(self, attr, value)
+            # Preserve order so that settings that depend on each other can be overridden together i.e., always override zarr version before sharding
+            for k in self._config:
+                if k in overrides:
+                    setattr(self, k, overrides.get(k))
             yield None
         finally:
+            # TODO: does the order need to be preserved when restoring?
             for attr, value in restore.items():
                 setattr(self, attr, value)
 
@@ -395,7 +398,7 @@ V = TypeVar("V")
 
 
 def gen_validator(_type: type[V]) -> Callable[[V], None]:
-    def validate_type(val: V) -> None:
+    def validate_type(val: V, settings: SettingsManager) -> None:
         if not isinstance(val, _type):
             msg = f"{val} not valid {_type}"
             raise TypeError(msg)
@@ -434,14 +437,28 @@ settings.register(
 )
 
 
-def validate_zarr_write_format(format: int):
-    validate_int(format)
+def validate_zarr_write_format(format: int, settings: SettingsManager):
+    validate_int(format, settings)
     if format not in {2, 3}:
         msg = "non-v2 zarr on-disk format not supported"
         raise ValueError(msg)
     if format == 3 and is_zarr_v2():
         msg = "Cannot write v3 format against v2 package"
         raise ValueError(msg)
+    if format == 2 and getattr(settings, "auto_shard_zarr_v3", False):
+        msg = "Cannot set `zarr_write_format` to 2 with autosharding on.  Please set to `False` `anndata.settings.auto_shard_zarr_v3`"
+        raise ValueError(msg)
+
+
+def validate_zarr_sharding(auto_shard: bool, settings: SettingsManager):  # noqa: FBT001
+    validate_bool(auto_shard, settings)
+    if auto_shard:
+        if is_zarr_v2():
+            msg = "Cannot use sharding with `zarr-python<3`. Please upgrade package and set `anndata.settings.zarr_write_format` to 3."
+            raise ValueError(msg)
+        if settings.zarr_write_format == 2:
+            msg = "Cannot shard v2 format data. Please set `anndata.settings.zarr_write_format` to 3."
+            raise ValueError(msg)
 
 
 settings.register(
@@ -458,8 +475,8 @@ settings.register(
 )
 
 
-def validate_sparse_settings(val: Any) -> None:
-    validate_bool(val)
+def validate_sparse_settings(val: Any, settings: SettingsManager) -> None:
+    validate_bool(val, settings)
 
 
 settings.register(
@@ -486,6 +503,14 @@ settings.register(
     get_from_env=check_and_get_bool,
 )
 
+settings.register(
+    "auto_shard_zarr_v3",
+    default_value=False,
+    description="Whether or not to use zarr's auto computation of sharding for v3.  For v2 this setting will be ignored. The setting will apply to all calls to anndata's writing mechanism (write_zarr / write_elem) and will **not** override any user-defined kwargs for shards.",
+    validate=validate_zarr_sharding,
+    get_from_env=check_and_get_bool,
+)
+
 
 ##################################################################################
 ##################################################################################

anndata/_settings.pyi

@@ -2,7 +2,7 @@ from collections.abc import Callable as Callable
 from collections.abc import Generator, Iterable
 from contextlib import contextmanager
 from dataclasses import dataclass
-from typing import Literal, TypeVar
+from typing import Literal, Self, TypeVar
 
 _T = TypeVar("_T")
 
@@ -25,7 +25,7 @@ class SettingsManager:
         *,
         default_value: _T,
         description: str,
-        validate: Callable[[_T], None],
+        validate: Callable[[_T, Self], None],
         option_type: object | None = None,
         get_from_env: Callable[[str, _T], _T] = ...,
     ) -> None: ...
@@ -46,5 +46,6 @@ class _AnnDataSettingsManager(SettingsManager):
     use_sparse_array_on_read: bool = False
     min_rows_for_chunked_h5_copy: int = 1000
     disallow_forward_slash_in_h5ad: bool = False
+    auto_shard_zarr_v3: bool = False
 
 settings: _AnnDataSettingsManager

anndata/experimental/backed/_io.py

@@ -8,6 +8,7 @@ from typing import TYPE_CHECKING
 
 import h5py
 
+from anndata._core.file_backing import AnnDataFileManager
 from anndata._io.specs.registry import read_elem_lazy
 from anndata._types import AnnDataElem
 from testing.anndata._doctest import doctest_needs
@@ -28,7 +29,7 @@ if TYPE_CHECKING:
 @doctest_needs("xarray")
 @requires_xarray
 def read_lazy(
-    store: PathLike[str] | str | MutableMapping | ZarrGroup | h5py.Dataset,
+    store: PathLike[str] | str | MutableMapping | ZarrGroup | h5py.File | h5py.Group,
     *,
     load_annotation_index: bool = True,
 ) -> AnnData:
@@ -40,6 +41,9 @@ def read_lazy(
     ----------
     store
         A store-like object to be read in.  If :class:`zarr.Group`, it is best for it to be consolidated.
+        If a path to an ``.h5ad`` file is provided, the open HDF5 file will be attached to the {class}`~anndata.AnnData` at the `file` attribute and it will be the user’s responsibility to close it when done with the returned object.
+        For this reason, it is recommended to use an {class}`h5py.File` as the `store` argument when working with h5 files.
+        It must remain open for at least as long as this returned object is in use.
     load_annotation_index
         Whether or not to use a range index for the `{obs,var}` :class:`xarray.Dataset` so as not to load the index into memory.
         If `False`, the real `index` will be inserted as `{obs,var}_names` in the object but not be one of the `coords` thereby preventing read operations.
@@ -83,10 +87,11 @@ def read_lazy(
     AnnData object with n_obs × n_vars = 490 × 33452
         obs: 'donor_id', 'self_reported_ethnicity_ontology_term_id', 'organism_ontology_term_id'...
     """
-    is_h5_store = isinstance(store, h5py.Dataset | h5py.File | h5py.Group)
-    is_h5 = (
+    is_store_arg_h5_store = isinstance(store, h5py.Dataset | h5py.File | h5py.Group)
+    is_store_arg_h5_path = (
         isinstance(store, PathLike | str) and Path(store).suffix == ".h5ad"
-    ) or is_h5_store
+    )
+    is_h5 = is_store_arg_h5_path or is_store_arg_h5_store
 
     has_keys = True  # true if consolidated or h5ad
     if not is_h5:
@@ -104,7 +109,7 @@ def read_lazy(
                 f = zarr.open_group(store, mode="r")
         else:
             f = store
-    elif is_h5_store:
+    elif is_store_arg_h5_store:
         f = store
     else:
         f = h5py.File(store, mode="r")
@@ -151,6 +156,7 @@ def read_lazy(
         return func(elem)
 
     with settings.override(check_uniqueness=load_annotation_index):
-        adata = read_dispatched(f, callback=callback)
-
+        adata: AnnData = read_dispatched(f, callback=callback)
+    if is_store_arg_h5_path and not is_store_arg_h5_store:
+        adata.file = AnnDataFileManager(adata, file_obj=f)
     return adata

anndata/experimental/backed/_lazy_arrays.py

@@ -111,9 +111,9 @@ class CategoricalArray(XBackendArray, Generic[K]):
     def categories(self) -> np.ndarray:
         if isinstance(self._categories, ZarrArray):
             return self._categories[...]
-        from ..._io.h5ad import read_dataset
+        from anndata.io import read_elem
 
-        return read_dataset(self._categories)
+        return read_elem(self._categories)
 
     def __getitem__(
         self, key: xr.core.indexing.ExplicitIndexer

anndata/tests/helpers.py

@@ -14,6 +14,7 @@ import h5py
 import numpy as np
 import pandas as pd
 import pytest
+import zarr
 from pandas.api.types import is_numeric_dtype
 from scipy import sparse
 
@@ -34,6 +35,7 @@ from anndata.compat import (
     XDataArray,
     XDataset,
     ZarrArray,
+    ZarrGroup,
     is_zarr_v2,
 )
 from anndata.utils import asarray
@@ -628,8 +630,9 @@ def assert_equal_arrayview(
 
 @assert_equal.register(BaseCompressedSparseDataset)
 @assert_equal.register(sparse.spmatrix)
+@assert_equal.register(CSArray)
 def assert_equal_sparse(
-    a: BaseCompressedSparseDataset | sparse.spmatrix,
+    a: BaseCompressedSparseDataset | sparse.spmatrix | CSArray,
     b: object,
     *,
     exact: bool = False,
@@ -639,13 +642,6 @@ def assert_equal_sparse(
     assert_equal(b, a, exact=exact, elem_name=elem_name)
 
 
-@assert_equal.register(CSArray)
-def assert_equal_sparse_array(
-    a: CSArray, b: object, *, exact: bool = False, elem_name: str | None = None
-):
-    return assert_equal_sparse(a, b, exact=exact, elem_name=elem_name)
-
-
 @assert_equal.register(CupySparseMatrix)
 def assert_equal_cupy_sparse(
     a: CupySparseMatrix, b: object, *, exact: bool = False, elem_name: str | None = None
@@ -878,29 +874,53 @@ def _(a):
 
 
 @singledispatch
-def as_sparse_dask_array(a) -> DaskArray:
-    import dask.array as da
-
-    return da.from_array(sparse.csr_matrix(a), chunks=_half_chunk_size(a.shape))
+def _as_sparse_dask(
+    a: NDArray | CSArray | CSMatrix | DaskArray,
+    *,
+    typ: type[CSArray | CSMatrix | CupyCSRMatrix],
+    chunks: tuple[int, ...] | None = None,
+) -> DaskArray:
+    """Convert a to a sparse dask array, preserving sparse format and container (`cs{rc}_{array,matrix}`)."""
+    raise NotImplementedError
 
 
-@as_sparse_dask_array.register(CSMatrix)
-def _(a):
+@_as_sparse_dask.register(CSArray | CSMatrix | np.ndarray)
+def _(
+    a: CSArray | CSMatrix | NDArray,
+    *,
+    typ: type[CSArray | CSMatrix | CupyCSRMatrix],
+    chunks: tuple[int, ...] | None = None,
+) -> DaskArray:
     import dask.array as da
 
-    return da.from_array(a, _half_chunk_size(a.shape))
+    chunks = _half_chunk_size(a.shape) if chunks is None else chunks
+    return da.from_array(_as_sparse_dask_inner(a, typ=typ), chunks=chunks)
 
 
-@as_sparse_dask_array.register(CSArray)
-def _(a):
-    import dask.array as da
+@_as_sparse_dask.register(DaskArray)
+def _(
+    a: DaskArray,
+    *,
+    typ: type[CSArray | CSMatrix | CupyCSRMatrix],
+    chunks: tuple[int, ...] | None = None,
+) -> DaskArray:
+    assert chunks is None  # TODO: if needed we can add a .rechunk(chunks)
+    return a.map_blocks(_as_sparse_dask_inner, typ=typ, dtype=a.dtype, meta=typ((2, 2)))
 
-    return da.from_array(sparse.csr_matrix(a), _half_chunk_size(a.shape))
 
+def _as_sparse_dask_inner(
+    a: NDArray | CSArray | CSMatrix, *, typ: type[CSArray | CSMatrix | CupyCSRMatrix]
+) -> CSArray | CSMatrix:
+    """Convert into a a sparse container that dask supports (or complain)."""
+    if issubclass(typ, CSArray):  # convert sparray to spmatrix
+        msg = "AnnData doesn't support `cs_{r,c}_array` inside Dask"
+        raise TypeError(msg)
+    if issubclass(typ, CupySparseMatrix):
+        a = as_cupy(a)  # can’t Cupy sparse constructors don’t accept numpy ndarrays
+    return typ(a)
 
-@as_sparse_dask_array.register(DaskArray)
-def _(a):
-    return a.map_blocks(sparse.csr_matrix)
+
+as_sparse_dask_matrix = partial(_as_sparse_dask, typ=sparse.csr_matrix)
 
 
 @singledispatch
@@ -945,14 +965,11 @@ except ImportError:
     format_to_memory_class = {}
 
 
-# TODO: If there are chunks which divide along columns, then a coo_matrix is returned by compute
-# We should try and fix this upstream in dask/ cupy
 @singledispatch
-def as_cupy_sparse_dask_array(a, format="csr"):
-    memory_class = format_to_memory_class[format]
-    cpu_da = as_sparse_dask_array(a)
-    return cpu_da.rechunk((cpu_da.chunks[0], -1)).map_blocks(
-        memory_class, dtype=a.dtype, meta=memory_class(cpu_da._meta)
+def as_cupy_sparse_dask_array(a, format="csr") -> DaskArray:
+    chunk_rows, _ = _half_chunk_size(a.shape)
+    return _as_sparse_dask(
+        a, typ=format_to_memory_class[format], chunks=(chunk_rows, -1)
     )
 
 
@@ -962,7 +979,8 @@ def _(a, format="csr"):
     import dask.array as da
 
     memory_class = format_to_memory_class[format]
-    return da.from_array(memory_class(a), chunks=(_half_chunk_size(a.shape)[0], -1))
+    chunk_rows, _ = _half_chunk_size(a.shape)
+    return da.from_array(memory_class(a), chunks=(chunk_rows, -1))
 
 
 @as_cupy_sparse_dask_array.register(DaskArray)
@@ -980,9 +998,9 @@ def resolve_cupy_type(val):
 
     if issubclass(input_typ, np.ndarray):
         typ = CupyArray
-    elif issubclass(input_typ, sparse.csr_matrix):
+    elif issubclass(input_typ, sparse.csr_matrix | sparse.csr_array):
         typ = CupyCSRMatrix
-    elif issubclass(input_typ, sparse.csc_matrix):
+    elif issubclass(input_typ, sparse.csc_matrix | sparse.csc_array):
         typ = CupyCSCMatrix
     else:
         msg = f"No default target type for input type {input_typ}"
@@ -1003,7 +1021,7 @@ def as_cupy(val, typ=None):
     if issubclass(typ, CupyArray):
         import cupy as cp
 
-        if isinstance(val, CSMatrix):
+        if isinstance(val, CSMatrix | CSArray):
             val = val.toarray()
         return cp.array(val)
     elif issubclass(typ, CupyCSRMatrix):
@@ -1059,7 +1077,7 @@ BASE_MATRIX_PARAMS = [
 
 DASK_MATRIX_PARAMS = [
     pytest.param(as_dense_dask_array, id="dense_dask_array"),
-    pytest.param(as_sparse_dask_array, id="sparse_dask_array"),
+    pytest.param(as_sparse_dask_matrix, id="sparse_dask_matrix"),
 ]
 
 CUPY_MATRIX_PARAMS = [
@@ -1187,3 +1205,23 @@ def get_multiindex_columns_df(shape: tuple[int, int]) -> pd.DataFrame:
             + list(itertools.product(["b"], range(shape[1] // 2)))
         ),
     )
+
+
+def visititems_zarr(
+    z: ZarrGroup, visitor: Callable[[str, ZarrGroup | zarr.Array], None]
+) -> None:
+    for key in z:
+        maybe_group = z[key]
+        if isinstance(maybe_group, ZarrGroup):
+            visititems_zarr(maybe_group, visitor)
+        else:
+            visitor(key, maybe_group)
+
+
+def check_all_sharded(g: ZarrGroup):
+    def visit(key: str, arr: zarr.Array | zarr.Group):
+        # Check for recarray via https://numpy.org/doc/stable/user/basics.rec.html#manipulating-and-displaying-structured-datatypes
+        if isinstance(arr, zarr.Array) and arr.shape != () and arr.dtype.names is None:
+            assert arr.shards is not None
+
+    visititems_zarr(g, visitor=visit)

{anndata-0.12.4.dist-info → anndata-0.12.6.dist-info}/METADATA

@@ -1,12 +1,12 @@
 Metadata-Version: 2.4
 Name: anndata
-Version: 0.12.4
+Version: 0.12.6
 Summary: Annotated data.
 Project-URL: Documentation, https://anndata.readthedocs.io/
 Project-URL: Source, https://github.com/scverse/anndata
 Project-URL: Home-page, https://github.com/scverse/anndata
-Author: Philipp Angerer, Alex Wolf, Isaac Virshup, Sergei Rybakov
-Maintainer-email: Isaac Virshup <ivirshup@gmail.com>, Philipp Angerer <philipp.angerer@helmholtz-munich.de>, Ilan Gold <ilan.gold@helmholtz-munich.de>
+Author: Philipp Angerer, Alex Wolf, Isaac Virshup, Sergei Rybakov, Ilan Gold
+Maintainer-email: Philipp Angerer <philipp.angerer@helmholtz-munich.de>, Ilan Gold <ilan.gold@helmholtz-munich.de>
 License-Expression: BSD-3-Clause
 License-File: LICENSE
 Classifier: Environment :: Console
@@ -21,6 +21,7 @@ Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
 Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
 Classifier: Topic :: Scientific/Engineering :: Visualization
 Requires-Python: >=3.11
@@ -78,7 +79,7 @@ Requires-Dist: joblib; extra == 'test'
 Requires-Dist: loompy>=3.0.5; extra == 'test'
 Requires-Dist: matplotlib; extra == 'test'
 Requires-Dist: openpyxl; extra == 'test'
-Requires-Dist: pyarrow<21; extra == 'test'
+Requires-Dist: pyarrow; extra == 'test'
 Requires-Dist: pytest-cov; extra == 'test'
 Requires-Dist: pytest-memray; extra == 'test'
 Requires-Dist: pytest-mock; extra == 'test'
@@ -100,7 +101,7 @@ Requires-Dist: joblib; extra == 'test-min'
 Requires-Dist: loompy>=3.0.5; extra == 'test-min'
 Requires-Dist: matplotlib; extra == 'test-min'
 Requires-Dist: openpyxl; extra == 'test-min'
-Requires-Dist: pyarrow<21; extra == 'test-min'
+Requires-Dist: pyarrow; extra == 'test-min'
 Requires-Dist: pytest-cov; extra == 'test-min'
 Requires-Dist: pytest-memray; extra == 'test-min'
 Requires-Dist: pytest-mock; extra == 'test-min'

{anndata-0.12.4.dist-info → anndata-0.12.6.dist-info}/RECORD

@@ -1,6 +1,6 @@
 anndata/__init__.py,sha256=daAzY8GGouJxCe30Lcr2pl9Jwo2dcGXHPi7WxnHpuOE,1710
-anndata/_settings.py,sha256=Y6d28jAF7qnZLfDdg-0L_-Z7zXZR8zjSYlmvWRU_HO4,15949
-anndata/_settings.pyi,sha256=88wa1EG5Bz3ZKIJ68iw41nwGPA8asnpqYsnATsC5mpc,1594
+anndata/_settings.py,sha256=AvCdIKCynrP6xUjVtYpvN8dFTefsGPu6anGp4c8M58I,17532
+anndata/_settings.pyi,sha256=mJQQ3I66Y3sng8K-_aGjYuo5UoNgC5syw0yuNc1FADU,1643
 anndata/_types.py,sha256=c71REP9wS7Vz2cYrNxuNjPYdnq8MJ5g04MNrSi85ATA,5427
 anndata/_warnings.py,sha256=iFXa9EzPyuPbzRAzoG04oTXAyjnXhQa5zxAMZdsGLwM,702
 anndata/abc.py,sha256=jG64k59ZZ9Hfn-QWt_btZLuF7eGv_YNYwH91WdbR240,1645
@@ -13,11 +13,11 @@ anndata/_core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 anndata/_core/access.py,sha256=pts7fGUKgGZANSsu_qAA7L10qHM-jT1zIehbl3441OY,873
 anndata/_core/aligned_df.py,sha256=EC01OveJ0tS5bQQHc_OprYSPprl-YtJQK-kIOY_4SX0,4214
 anndata/_core/aligned_mapping.py,sha256=BYU1jslMWIhtFTtUMaXY8ZCyt0J4_ZsJTmj6J2yAXTQ,14257
-anndata/_core/anndata.py,sha256=e9ISy2CI7QaG6mievs8Aw33sho8ZN1CMgqPQZ-ZfbSw,78782
+anndata/_core/anndata.py,sha256=PmR6vKglxX8G837lOah6OhPANALbTWYNlUWHf1A-SPw,78963
 anndata/_core/extensions.py,sha256=9Rsho6qnr3PJHULrYGiZHCBinBZYJK6zyf3cFsl_gBY,10425
-anndata/_core/file_backing.py,sha256=kT71R_kZp_CiHImBK8IaZXsvYVtbX2Mg-7L2ldAWojM,5113
+anndata/_core/file_backing.py,sha256=6DhBfLQPDFDpoe6wSgnOFtpC4Hnbh-UgOPbqvYDxm8g,5603
 anndata/_core/index.py,sha256=F3TQBUbWpt09Pb4MpwB7xfCI9uPuv7jrqx8X74CwVDU,13472
-anndata/_core/merge.py,sha256=HVVLWEqk3PdU_U8UoOyKJaIp0ZQIfWy0cWM2iac4_H8,60366
+anndata/_core/merge.py,sha256=vRW9z_PbobmRGDzQIVxAoFc7G9Rq-y6ry57k_XMmsLc,60460
 anndata/_core/raw.py,sha256=x_PwwaDQscVQOFJ38kF7sNQ47LxowpS38h2RQfU5Zwo,7925
 anndata/_core/sparse_dataset.py,sha256=mE-PRX4znkDyuum3BBBv7MJwyn4XL9C3nIQNRjZJ94w,26877
 anndata/_core/storage.py,sha256=mHzqp7YBJ-rGQFulMAx__D-Z7y4omHPyb1cP7YxfbFE,2555
@@ -30,8 +30,8 @@ anndata/_io/utils.py,sha256=3Lg27Q0Uo3HYlz980bG2Y02_VFIt0PiXMNIj_o-mgC4,9490
 anndata/_io/write.py,sha256=r55w6yPIIuUSLW9wyYL8GnkzHHQdAxy6xiCEw9cAC38,4811
 anndata/_io/zarr.py,sha256=Z996SZ8LV1Fpa_q8o70vHnBzNLOLlVjhf_Rs5EM_Slo,5461
 anndata/_io/specs/__init__.py,sha256=Z6l8xqa7B480U3pqrNIg4-fhUvpBW85w4xA3i3maAUM,427
-anndata/_io/specs/lazy_methods.py,sha256=k-s-YwOtwXpdjsyrM0IAsGSadPFxDsVDA3d_Nbpb7Ak,12261
-anndata/_io/specs/methods.py,sha256=T7926LkdvUJzvTAneRbDxM8YVIZNGz9GKgccEcsBumU,46264
+anndata/_io/specs/lazy_methods.py,sha256=hnZ3ggrVCXR_rCMVH2Of9YE3s4saWg2WODcCtj0WaIQ,12600
+anndata/_io/specs/methods.py,sha256=nn9DFcUEWvCeAPPifiFxpuYW3AmtFhNDUbxo7i0toow,46314
 anndata/_io/specs/registry.py,sha256=6Z_ffk3uOIagzRPcDCvEoszcgD-U3n8wYnGiPA71ZeI,17539
 anndata/compat/__init__.py,sha256=lsLHB7je0SHSePi9noY3p7kRbOAHhZzmMT1hs_ZSXys,12702
 anndata/experimental/__init__.py,sha256=polIxriEkby0iEqw-IXkUzp8k0wp92BpYY4zl4BsHH0,1648
@@ -39,19 +39,19 @@ anndata/experimental/_dispatch_io.py,sha256=JzH8Uvewabc1gIF3L16RZnM9m2NAG28bQIQ5
 anndata/experimental/merge.py,sha256=pl4MtDs_M76cTEqrJ_YJ8zyB6ID7QGzjntlAL7vp_qk,23303
 anndata/experimental/backed/__init__.py,sha256=4dc9M_-_SlfUidDrbWt8PRyD_8bYjypHJ86IpdThHus,230
 anndata/experimental/backed/_compat.py,sha256=rM7CnSJEZCko5wPBFRfvZA9ZKUSpaOVcWFy5u09p1go,519
-anndata/experimental/backed/_io.py,sha256=7bFzn3h8ut49NzppUvsqAX1gjXxAVCFK55Ln0XWzZdY,5965
-anndata/experimental/backed/_lazy_arrays.py,sha256=9uuEgP4p5oT49qhkzWHxC8eNFJFE1gRlYwAjMKFRejI,7474
+anndata/experimental/backed/_io.py,sha256=YM5FL6sKdLyQTHUa43cF0pDNbyj2xD9X7lzUiQesV20,6681
+anndata/experimental/backed/_lazy_arrays.py,sha256=WgTYQ88w7rTAP719nGjvyNkIz8cBT2bbkKJhPIxG4_g,7467
 anndata/experimental/multi_files/__init__.py,sha256=T7iNLlRbe-KnLT3o7Tb7_nE4Iy_hLkG66UjBOvj2Bj8,107
 anndata/experimental/multi_files/_anncollection.py,sha256=d_d-v8X2WJTGNjAJoo2Mdykd-woSTM_oXEf2PUIqS6A,35254
 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=27p_Nc5vFIiW-7EhV85g3QiE0dStMnUg0uFBRyroZUg,36072
+anndata/tests/helpers.py,sha256=hvcLsWY-fMR4EUrwPd6laiS8kwUlIxvlVq3oeH3jf9g,37618
 testing/anndata/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 testing/anndata/_doctest.py,sha256=Qew0N0zLLNiPKN1CLunqY5cTinFLaEhY5GagiYfm6KI,344
 testing/anndata/_pytest.py,sha256=cg4oWbtH9J1sRNul0n2oOraU1h7cprugr27EUPGDaN0,3997
 testing/anndata/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-anndata-0.12.4.dist-info/METADATA,sha256=8SqT0BaH42j9XfqXxmF0_Z6GCk0pd6lN7h1Rn3V3FTg,9937
-anndata-0.12.4.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-anndata-0.12.4.dist-info/licenses/LICENSE,sha256=VcrXoEVMhtNuvMvKYGP-I5lMT8qZ_6dFf22fsL180qA,1575
-anndata-0.12.4.dist-info/RECORD,,
+anndata-0.12.6.dist-info/METADATA,sha256=nWoP_t6iBExzxOziJ_t0KVJ_lDa6lxsNV4rPXf1EobM,9957
+anndata-0.12.6.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+anndata-0.12.6.dist-info/licenses/LICENSE,sha256=VcrXoEVMhtNuvMvKYGP-I5lMT8qZ_6dFf22fsL180qA,1575
+anndata-0.12.6.dist-info/RECORD,,