anndata 0.12.0rc4__tar.gz → 0.12.1__tar.gz

{anndata-0.12.0rc4 → anndata-0.12.1}/.github/workflows/test-cpu.yml

@@ -47,6 +47,7 @@ jobs:
     strategy:
       matrix:
         env: ${{ fromJSON(needs.get-environments.outputs.envs) }}
+        io_mark: ["zarr_io", "not zarr_io"]
     env:  # environment variable for use in codecov’s env_vars tagging
       ENV_NAME: ${{ matrix.env.name }}
     steps:
@@ -70,7 +71,7 @@ jobs:
         run: uvx hatch -v env create ${{ matrix.env.name }}
 
       - name: Run tests
-        run: uvx hatch run ${{ matrix.env.name }}:run-cov -v --color=yes -n auto --cov --cov-report=xml --junitxml=test-data/test-results.xml
+        run: uvx hatch run ${{ matrix.env.name }}:run-cov -v --color=yes -n auto --cov --cov-report=xml --junitxml=test-data/test-results.xml -m "${{matrix.io_mark}}"
 
       - name: Upload coverage data
         uses: codecov/codecov-action@v5

{anndata-0.12.0rc4 → anndata-0.12.1}/.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.11.12
+    rev: v0.12.4
     hooks:
       - id: ruff
         args: ["--fix"]
@@ -10,7 +10,7 @@ repos:
         id: ruff
         args: ["--preview", "--select=PLR0917"]
   - repo: https://github.com/biomejs/pre-commit
-    rev: v1.9.4
+    rev: v2.1.2
     hooks:
       - id: biome-format
   - repo: https://github.com/ComPWA/taplo-pre-commit

{anndata-0.12.0rc4 → anndata-0.12.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: anndata
-Version: 0.12.0rc4
+Version: 0.12.1
 Summary: Annotated data.
 Project-URL: Documentation, https://anndata.readthedocs.io/
 Project-URL: Source, https://github.com/scverse/anndata
@@ -28,11 +28,11 @@ Requires-Dist: array-api-compat>=1.7.1
 Requires-Dist: h5py>=3.8
 Requires-Dist: legacy-api-wrap
 Requires-Dist: natsort
-Requires-Dist: numpy>=1.25
+Requires-Dist: numpy>=1.26
 Requires-Dist: packaging>=24.2
-Requires-Dist: pandas!=2.1.0rc0,!=2.1.2,>=2.0.0
-Requires-Dist: scipy>=1.11
-Requires-Dist: zarr!=3.0.0,!=3.0.1,!=3.0.2,!=3.0.3,!=3.0.4,!=3.0.5,!=3.0.6,!=3.0.7,<3.1,>=2.18.7
+Requires-Dist: pandas!=2.1.2,>=2.1.0
+Requires-Dist: scipy>=1.12
+Requires-Dist: zarr!=3.0.*,>=2.18.7
 Provides-Extra: cu11
 Requires-Dist: cupy-cuda11x; extra == 'cu11'
 Provides-Extra: cu12
@@ -74,13 +74,12 @@ Requires-Dist: boltons; extra == 'test'
 Requires-Dist: dask[array]!=2024.8.*,!=2024.9.*,<2025.2.0,>=2023.5.1; extra == 'test'
 Requires-Dist: dask[distributed]; extra == 'test'
 Requires-Dist: filelock; extra == 'test'
-Requires-Dist: httpx; extra == 'test'
+Requires-Dist: httpx<1.0; extra == 'test'
 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: pandas>=2.1.0; extra == 'test'
-Requires-Dist: pyarrow; extra == 'test'
+Requires-Dist: pyarrow<21; extra == 'test'
 Requires-Dist: pytest-cov; extra == 'test'
 Requires-Dist: pytest-memray; extra == 'test'
 Requires-Dist: pytest-mock; extra == 'test'
@@ -97,12 +96,12 @@ Requires-Dist: boltons; extra == 'test-min'
 Requires-Dist: dask[array]!=2024.8.*,!=2024.9.*,<2025.2.0,>=2023.5.1; extra == 'test-min'
 Requires-Dist: dask[distributed]; extra == 'test-min'
 Requires-Dist: filelock; extra == 'test-min'
-Requires-Dist: httpx; extra == 'test-min'
+Requires-Dist: httpx<1.0; extra == 'test-min'
 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; extra == 'test-min'
+Requires-Dist: pyarrow<21; 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-0.12.0rc4 → anndata-0.12.1}/benchmarks/asv.conf.json

@@ -70,6 +70,8 @@
         "pytoml": [""],
         "pytest": [""],
         "pooch": [""],
+        "xarray": [""],
+        "dask": [""],
         // "scanpy": [""],
         // "psutil": [""]
     },

anndata-0.12.1/benchmarks/benchmarks/dataset2d.py

@@ -0,0 +1,61 @@
+from __future__ import annotations
+
+import tempfile
+from pathlib import Path
+from typing import TYPE_CHECKING
+
+import h5py
+import numpy as np
+import pandas as pd
+import zarr
+
+import anndata as ad
+
+if TYPE_CHECKING:
+    from collections.abc import Callable
+
+
+class Dataset2D:
+    param_names = ("gen_store", "chunks")
+    params = (
+        (
+            lambda: h5py.File(Path(tempfile.mkdtemp()) / "data.h5ad", mode="w"),
+            lambda: zarr.open(
+                Path(tempfile.mkdtemp()) / "data.zarr", mode="w", zarr_version=2
+            ),
+        ),
+        ((-1,), None),
+    )
+
+    def setup(
+        self, gen_store: Callable[[], zarr.Group | h5py.File], chunks: None | tuple[int]
+    ):
+        self.n_obs = 100000
+        df = pd.DataFrame(
+            {
+                "a": pd.Categorical(np.array(["a"] * self.n_obs)),
+                "b": np.arange(self.n_obs),
+            },
+            index=[f"cell{i}" for i in range(self.n_obs)],
+        )
+        store = gen_store()
+        ad.io.write_elem(store, "obs", df)
+        self.ds = ad.experimental.read_elem_lazy(store["obs"], chunks=chunks)
+
+    def time_getitem_slice(self, *_):
+        self.ds.iloc[0 : (self.n_obs // 2)].to_memory()
+
+    def peakmem_getitem_slice(self, *_):
+        self.ds.iloc[0 : (self.n_obs // 2)].to_memory()
+
+    def time_full_to_memory(self, *_):
+        self.ds.to_memory()
+
+    def peakmem_full_to_memory(self, *_):
+        self.ds.to_memory()
+
+    def time_getitem_bool_mask(self, *_):
+        self.ds.iloc[np.random.randint(0, self.n_obs, self.n_obs // 2)].to_memory()
+
+    def peakmem_getitem_bool_mask(self, *_):
+        self.ds.iloc[np.random.randint(0, self.n_obs, self.n_obs // 2)].to_memory()

{anndata-0.12.0rc4 → anndata-0.12.1}/benchmarks/benchmarks/sparse_dataset.py

@@ -4,11 +4,13 @@ from types import MappingProxyType
 
 import numpy as np
 import zarr
+from dask.array.core import Array as DaskArray
 from scipy import sparse
 
 from anndata import AnnData
 from anndata._core.sparse_dataset import sparse_dataset
 from anndata._io.specs import write_elem
+from anndata.experimental import read_elem_lazy
 
 
 def make_alternating_mask(n):
@@ -37,27 +39,36 @@ class SparseCSRContiguousSlice:
             # (10_000, 500)
         ],
         _slices.keys(),
+        [True, False],
     )
-    param_names = ("shape", "slice")
+    param_names = ("shape", "slice", "use_dask")
 
-    def setup(self, shape: tuple[int, int], slice: str):
+    def setup(self, shape: tuple[int, int], slice: str, use_dask: bool):  # noqa: FBT001
         X = sparse.random(
             *shape, density=0.01, format="csr", random_state=np.random.default_rng(42)
         )
         self.slice = self._slices[slice]
         g = zarr.group()
         write_elem(g, "X", X)
-        self.x = sparse_dataset(g["X"])
+        self.x = read_elem_lazy(g["X"]) if use_dask else sparse_dataset(g["X"])
         self.adata = AnnData(self.x)
 
     def time_getitem(self, *_):
-        self.x[self.slice]
+        res = self.x[self.slice]
+        if isinstance(res, DaskArray):
+            res.compute()
 
     def peakmem_getitem(self, *_):
-        self.x[self.slice]
+        res = self.x[self.slice]
+        if isinstance(res, DaskArray):
+            res.compute()
 
     def time_getitem_adata(self, *_):
-        self.adata[self.slice]
+        res = self.adata[self.slice]
+        if isinstance(res, DaskArray):
+            res.compute()
 
     def peakmem_getitem_adata(self, *_):
-        self.adata[self.slice]
+        res = self.adata[self.slice]
+        if isinstance(res, DaskArray):
+            res.compute()

{anndata-0.12.0rc4 → anndata-0.12.1}/biome.jsonc

@@ -1,9 +1,9 @@
 {
-    "$schema": "https://biomejs.dev/schemas/1.9.4/schema.json",
+    "$schema": "https://biomejs.dev/schemas/2.1.1/schema.json",
     "formatter": { "useEditorconfig": true },
     "overrides": [
         {
-            "include": ["./.vscode/*.json", "**/*.jsonc", "**/asv.conf.json"],
+            "includes": ["./.vscode/*.json", "**/*.jsonc", "**/asv.conf.json"],
             "json": {
                 "formatter": {
                     "trailingCommas": "all",

{anndata-0.12.0rc4 → anndata-0.12.1}/docs/conf.py

@@ -125,18 +125,19 @@ intersphinx_mapping = dict(
     awkward=("https://awkward-array.org/doc/stable", None),
     cupy=("https://docs.cupy.dev/en/stable", None),
     dask=("https://docs.dask.org/en/stable", None),
+    fsspec=("https://filesystem-spec.readthedocs.io/en/stable/", None),
     h5py=("https://docs.h5py.org/en/latest", None),
     hdf5plugin=("https://hdf5plugin.readthedocs.io/en/latest", None),
+    kvikio=("https://docs.rapids.ai/api/kvikio/stable/", None),
     loompy=("https://linnarssonlab.org/loompy", None),
     numpy=("https://numpy.org/doc/stable", None),
+    obstore=("https://developmentseed.org/obstore/latest/", None),
     pandas=("https://pandas.pydata.org/pandas-docs/stable", None),
     python=("https://docs.python.org/3", None),
     scipy=("https://docs.scipy.org/doc/scipy", None),
     sklearn=("https://scikit-learn.org/stable", None),
-    zarr=("https://zarr.readthedocs.io/en/stable/", None),
     xarray=("https://docs.xarray.dev/en/stable", None),
-    obstore=("https://developmentseed.org/obstore/latest/", None),
-    kvikio=("https://docs.rapids.ai/api/kvikio/stable/", None),
+    zarr=("https://zarr.readthedocs.io/en/stable/", None),
     zarrs=("https://zarrs-python.readthedocs.io/en/stable/", None),
 )
 

anndata-0.12.1/docs/release-notes/0.12.0.md

@@ -0,0 +1,51 @@
+(v0.12.0)=
+### 0.12.0 {small}`2025-07-16`
+
+- (v0.12.0rc4)=
+  {guilabel}`rc4` 2025-06-18
+- (v0.12.0rc3)=
+  {guilabel}`rc3` 2025-05-20
+- (v0.12.0rc2)=
+  {guilabel}`rc2` 2025-05-15
+- (v0.12.0rc1)=
+  {guilabel}`rc1` 2025-04-09
+
+#### Breaking changes
+
+- {guilabel}`rc1` Remove `anndata.read` {user}`ilan-gold` ({pr}`1766`)
+- {guilabel}`rc1` Tighten usage of {class}`scipy.sparse.spmatrix` for describing sparse matrices in types and instance checks to only {class}`scipy.sparse.csr_matrix` and {class}`scipy.sparse.csc_matrix` {user}`ilan-gold` ({pr}`1768`)
+- {guilabel}`rc1` Disallow declaration of {class}`~anndata.AnnData` with non-`cs{r,c}` sparse data-structures {user}`ilan-gold` ({pr}`1829`)
+- {guilabel}`rc1` Upgrade all `DeprecationWarning`s to `FutureWarning`s {user}`ilan-gold` ({pr}`1874`)
+- {guilabel}`rc4` Lower bound `xarray` by `2025.06.01`.  {class}`pandas.arrays.StringArray` was previously used as the in-memory `nullable-string-array` container in `xarray`, but due to {issue}`pydata/xarray#10419` now uses {class}`numpy.ndarray` with an object data type.  {user}`ilan-gold` ({pr}`2008`)
+
+#### Bug fixes
+
+- Fix {func}`anndata.experimental.backed.Dataset2D.reindex` internal setting {user}`ilan-gold` ({pr}`2018`)
+- {guilabel}`rc1` Disallow writing of {class}`~anndata.experimental.backed.Dataset2D` objects {user}`ilan-gold` ({pr}`1887`)
+- {guilabel}`rc1` Upgrade old deprecation warning to a `FutureWarning` on `BaseCompressedSparseDataset.__setitem__`, showing our intent to remove the feature in the next release.  {user}`ilan-gold` ({pr}`1928`)
+- {guilabel}`rc1` Don't use {func}`asyncio.run` internally for any operations {user}`ilan-gold` ({pr}`1933`)
+- {guilabel}`rc1` Disallow forward slashes in keys for writing {user}`ilan-gold` ({pr}`1940`)
+- {guilabel}`rc2` Convert 1d {class}`numpy.ndarray` and {class}`cupy.ndarray`s in {attr}`anndata.AnnData.obsm` and {attr}`anndata.AnnData.varm` to 2d {user}`ilan-gold` ({pr}`1962`)
+- {guilabel}`rc3` Update zarr v3 bound to >3.0.8 to prevent corrupted data {issue}`zarr-developers/zarr-python#3061` {user}`ilan-gold` ({pr}`1993`)
+
+#### Features
+
+- {guilabel}`rc1` {data}`None` values can now be serialized to `.h5ad` and `.zarr`,
+  preserving e.g. {attr}`~anndata.AnnData.uns` structure through saving and loading {user}`flying-sheep` ({pr}`999`)
+- {guilabel}`rc1` Add {func}`~anndata.experimental.read_elem_lazy` (in place of `read_elem_as_dask`) to handle backed dataframes, sparse arrays, and dense arrays, as well as a {func}`~anndata.experimental.read_lazy` to handle reading in as much of the on-disk data as possible to produce a {class}`~anndata.AnnData` object {user}`ilan-gold` ({pr}`1247`)
+- {guilabel}`rc1` Support {mod}`zarr` version 3 python package {user}`ilan-gold` ({pr}`1726`)
+- {guilabel}`rc1` Adopt the Scientific Python [deprecation schedule](https://scientific-python.org/specs/spec-0000/) {user}`ilan-gold` ({pr}`1768`)
+- {guilabel}`rc1` Allow {mod}`zarr` v3 writing of data {user}`ilan-gold` ({pr}`1892`)
+- {guilabel}`rc1` {func}`anndata.register_anndata_namespace` functionality for adding custom functionality to an {class}`~anndata.AnnData` object {user}`srivarra` ({pr}`1870`)
+- {guilabel}`rc2` Allow xarray Datasets to be used for obs/var/obsm/varm. {user}`ilia-kats` ({pr}`1966`)
+- {guilabel}`rc4` {class}`anndata.experimental.backed.Dataset2D` now takes a compositional approach to wrapping {class}`xarray.Dataset` which may have breaking changes over the past release versions. {user}`ilan-gold` ({pr}`1997`)
+- {guilabel}`rc4` Use {attr}`numpy.dtypes.StringDType` with `na_object` set to {attr}`pandas.NA` for nullable string data with {class}`anndata.experimental.backed.Dataset2D` {user}`ilan-gold` ({pr}`2011`)
+
+#### Performance
+
+- {guilabel}`rc2` Load AnnLoader lazily to prevent expensive unnecessary `torch` imports when its available on the system. {user}`Zethson` & {user}`flying-sheep` ({pr}`1950`)
+- {guilabel}`rc4` Improve {func}`~anndata.experimental.read_elem_lazy` performance for `h5ad` files by not caching `indptr`. {user}`ilan-gold` ({pr}`2005`)
+
+#### Development
+
+- {guilabel}`rc4` Temporarily bound {mod}`zarr` to `<3.1` until {pr}`1995` is merged to handle the new data type structure.  {user}`ilan-gold` ({pr}`2013`)

anndata-0.12.1/docs/release-notes/0.12.1.md

@@ -0,0 +1,10 @@
+(v0.12.1)=
+### 0.12.1 {small}`2025-07-23`
+
+### Bug fixes
+
+- Fix `chunks` argument for {func}`anndata.experimental.read_elem_lazy` so that it uses the on-disk chunking when possible, and allow users to pass this argument through to the reading of {class}`anndata.experimental.backed.Dataset2D` {user}`ilan-gold` ({pr}`2033`)
+
+### Performance
+
+- Improve integer indexing performance of `h5` 1d arrays that are opened via {func}`anndata.experimental.read_elem_lazy` {user}`ilan-gold` ({pr}`2035`)

{anndata-0.12.0rc4 → anndata-0.12.1}/docs/tutorials/zarr-v3.md

@@ -4,6 +4,23 @@
 Users should notice a significant performance improvement, especially for cloud data, but also likely for local data as well.
 Here is a quick guide on some of our learnings so far:
 
+## Consolidated Metadata
+
+All `zarr` stores are now consolidated by default when written via {func}`anndata.io.write_zarr` or {meth}`anndata.AnnData.write_zarr`.  For more information on this topic, please seee {ref}`the zarr docs <zarr:user-guide-consolidated-metadata>`.  Practcally, this changes means that once a store has been written, it should be treated as immutable **unless you remove the consolidated metadata and/or rewrite after the mutating operation** i.e., if you wish to use `anndata.io.write_elem` to add a column to `obs`, a `layer` etc. to an existing store.  For example, to mutate an existing store on-disk, you may do:
+
+```python
+g = zarr.open_group(orig_path, mode="a", use_consolidated=False)
+ad.io.write_elem(
+    g,
+    "obs",
+    obs,
+    dataset_kwargs=dict(chunks=(250,)),
+)
+zarr.consolidate_metadata(g.store)
+```
+
+In this example, the store was opened unconsolidated (trying to open it as a consolidated store would error out), edited, and then reconsolidated.  Alternatively, one could simple delete the file containing the consolidated metadata first at the root, `.zmetadata`.
+
 ## Remote data
 
 We now provide the {func}`anndata.experimental.read_lazy` feature for reading as much of the {class}`~anndata.AnnData` object as lazily as possible, using `dask` and {mod}`xarray`.

{anndata-0.12.0rc4 → anndata-0.12.1}/pyproject.toml

@@ -36,18 +36,16 @@ classifiers = [
     "Topic :: Scientific/Engineering :: Visualization",
 ]
 dependencies = [
-    # pandas 2.1.0rc0 has pandas/issues/54622
-    "pandas >=2.0.0, !=2.1.0rc0, !=2.1.2",
-    "numpy>=1.25",
+    "pandas >=2.1.0, !=2.1.2",
+    "numpy>=1.26",
     # https://github.com/scverse/anndata/issues/1434
-    "scipy >=1.11",
+    "scipy >=1.12",
     "h5py>=3.8",
     "natsort",
     "packaging>=24.2",
     "array_api_compat>=1.7.1",
     "legacy-api-wrap",
-    # <3.1 on account of https://github.com/scverse/anndata/pull/1995
-    "zarr >=2.18.7, !=3.0.0, !=3.0.1, !=3.0.2, !=3.0.3, !=3.0.4, !=3.0.5, !=3.0.6, !=3.0.7, <3.1",
+    "zarr >=2.18.7, !=3.0.*",
 ]
 dynamic = [ "version" ]
 
@@ -96,16 +94,14 @@ test-min = [
     "joblib",
     "boltons",
     "scanpy>=1.10",
-    "httpx",                # For data downloading
+    # TODO: Is 1.0dev1 a real pre-release? https://pypi.org/project/httpx/#history
+    "httpx<1.0",         # For data downloading
     "dask[distributed]",
     "awkward>=2.3.2",
-    "pyarrow",
+    "pyarrow<21",        # https://github.com/scikit-hep/awkward/issues/3579
     "anndata[dask]",
 ]
-test = [
-    "anndata[test-min,lazy]",
-    "pandas>=2.1.0",
-] # pandas 2.1.0 needs to be specified for xarray to work with min-deps script
+test = [ "anndata[test-min,lazy]" ]
 gpu = [ "cupy" ]
 cu12 = [ "cupy-cuda12x" ]
 cu11 = [ "cupy-cuda11x" ]
@@ -172,7 +168,7 @@ testpaths = [
 ]
 # For some reason this effects how logging is shown when tests are run
 xfail_strict = true
-markers = [ "gpu: mark test to run on GPU" ]
+markers = [ "gpu: mark test to run on GPU", "zarr_io: mark tests that involve zarr io" ]
 
 [tool.ruff]
 src = [ "src" ]
@@ -212,6 +208,7 @@ ignore = [
     "E731",    # Do not assign a lambda expression, use a def -> AnnData allows lambda expression assignments,
     "E741",    # allow I, O, l as variable names -> I is the identity matrix, i, j, k, l is reasonable indexing notation
     "TID252",  # We use relative imports from parent modules
+    "PLC0415", # We use a lot of non-top-level imports
     "PLR2004", # “2” is often not too “magic” a number
     "PLW2901", # Shadowing loop variables isn’t a big deal
 ]

{anndata-0.12.0rc4 → anndata-0.12.1}/src/anndata/_core/aligned_df.py

@@ -59,7 +59,7 @@ def _gen_dataframe_mapping(
         df = pd.DataFrame(
             anno,
             index=None if length is None else mk_index(length),
-            columns=None if len(anno) else [],
+            columns=None if anno else [],
         )
 
     if length is None:

{anndata-0.12.0rc4 → anndata-0.12.1}/src/anndata/_core/anndata.py

@@ -62,7 +62,7 @@ if TYPE_CHECKING:
     from .index import Index
 
 
-class AnnData(metaclass=utils.DeprecationMixinMeta):
+class AnnData(metaclass=utils.DeprecationMixinMeta):  # noqa: PLW1641
     """\
     An annotated data matrix.
 

{anndata-0.12.0rc4 → anndata-0.12.1}/src/anndata/_core/merge.py

@@ -904,12 +904,6 @@ def concat_arrays(  # noqa: PLR0911, PLR0912
             ],
             format="csr",
         )
-        scipy_version = Version(scipy.__version__)
-        # Bug where xstack produces a matrix not an array in 1.11.*
-        if use_sparse_array and (scipy_version.major, scipy_version.minor) == (1, 11):
-            if mat.format == "csc":
-                return sparse.csc_array(mat)
-            return sparse.csr_array(mat)
         return mat
     else:
         return np.concatenate(

{anndata-0.12.0rc4 → anndata-0.12.1}/src/anndata/_core/sparse_dataset.py

@@ -165,7 +165,11 @@ class BackedSparseMatrix(_cs_matrix):
     def _get_contiguous_compressed_slice(
         self, s: slice
     ) -> tuple[np.ndarray, np.ndarray, np.ndarray]:
-        new_indptr = self.indptr[s.start : s.stop + 1].copy()
+        new_indptr = self.indptr[s.start : s.stop + 1]
+        # If indptr is cached, we need to make a copy of the subset
+        # so as not to alter the underlying cached data.
+        if isinstance(self.indptr, np.ndarray):
+            new_indptr = new_indptr.copy()
 
         start = new_indptr[0]
         stop = new_indptr[-1]

{anndata-0.12.0rc4 → anndata-0.12.1}/src/anndata/_core/xarray.py

@@ -245,7 +245,7 @@ class Dataset2D:
         if df.index.name != index_key and index_key is not None:
             df = df.set_index(index_key)
         for col in set(self.columns) - non_nullable_string_cols:
-            df[col] = pd.array(self[col].data, dtype="string")
+            df[col] = df[col].astype(dtype="string")
         df.index.name = None  # matches old AnnData object
         return df
 
@@ -389,9 +389,12 @@ class Dataset2D:
         }
         el = self.ds.drop_vars(extension_arrays.keys())
         el = el.reindex({index_dim: index}, method=None, fill_value=fill_value)
-        for col in self.ds:
-            el[col] = pd.Series(self.ds[col], index=self.index).reindex(
-                index, fill_value=fill_value
+        for col, data in extension_arrays.items():
+            el[col] = XDataArray.from_series(
+                pd.Series(data.data, index=self.index).reindex(
+                    index.rename(self.index.name) if index is not None else index,
+                    fill_value=fill_value,
+                )
             )
         return Dataset2D(el)
 

{anndata-0.12.0rc4 → anndata-0.12.1}/src/anndata/_io/h5ad.py

@@ -176,7 +176,7 @@ def read_h5ad_backed(
 
 def read_h5ad(
     filename: PathLike[str] | str,
-    backed: Literal["r", "r+"] | bool | None = None,
+    backed: Literal["r", "r+"] | bool | None = None,  # noqa: FBT001
     *,
     as_sparse: Sequence[str] = (),
     as_sparse_fmt: type[CSMatrix] = sparse.csr_matrix,

{anndata-0.12.0rc4 → anndata-0.12.1}/src/anndata/_io/read.py

@@ -22,9 +22,11 @@ if TYPE_CHECKING:
     from collections.abc import Generator, Iterable, Iterator, Mapping
 
 
+@old_positionals("first_column_names", "dtype")
 def read_csv(
     filename: PathLike[str] | str | Iterator[str],
     delimiter: str | None = ",",
+    *,
     first_column_names: bool | None = None,
     dtype: str = "float32",
 ) -> AnnData:
@@ -331,9 +333,11 @@ def read_mtx(filename: PathLike[str] | str, dtype: str = "float32") -> AnnData:
     return AnnData(X)
 
 
+@old_positionals("first_column_names", "dtype")
 def read_text(
     filename: PathLike[str] | str | Iterator[str],
     delimiter: str | None = None,
+    *,
     first_column_names: bool | None = None,
     dtype: str = "float32",
 ) -> AnnData:
@@ -381,7 +385,7 @@ 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,
+    first_column_names: bool | None,  # noqa: FBT001
     dtype: str,
 ) -> AnnData:
     comments = []

{anndata-0.12.0rc4 → anndata-0.12.1}/src/anndata/_io/specs/lazy_methods.py

@@ -132,7 +132,7 @@ def read_sparse_as_dask(
     path_or_sparse_dataset = (
         Path(filename(elem))
         if isinstance(elem, H5Group)
-        else ad.io.sparse_dataset(elem)
+        else ad.io.sparse_dataset(elem, should_cache_indptr=False)
     )
     elem_name = get_elem_name(elem)
     shape: tuple[int, int] = tuple(elem.attrs["shape"])
@@ -177,21 +177,37 @@ def read_sparse_as_dask(
     return da_mtx
 
 
+def resolve_chunks(
+    elem: H5Array | ZarrArray,
+    chunks_arg: tuple[int, ...] | None,
+    shape: tuple[int, ...],
+) -> tuple[int, ...]:
+    shape = tuple(elem.shape)
+    if chunks_arg is not None:
+        # None and -1 on a given axis indicate that one should use the shape
+        # in `dask`'s semantics.
+        return tuple(
+            c if c not in {None, -1} else s
+            for c, s in zip(chunks_arg, shape, strict=True)
+        )
+    elif elem.chunks is None:  # h5 unchunked
+        return tuple(min(_DEFAULT_STRIDE, s) for s in shape)
+    return elem.chunks
+
+
 @_LAZY_REGISTRY.register_read(H5Array, IOSpec("string-array", "0.2.0"))
 def read_h5_string_array(
     elem: H5Array,
     *,
     _reader: LazyReader,
-    chunks: tuple[int, int] | None = None,
+    chunks: tuple[int] | None = None,
 ) -> DaskArray:
     import dask.array as da
 
     from anndata._io.h5ad import read_dataset
 
-    return da.from_array(
-        read_dataset(elem),
-        chunks=chunks if chunks is not None else (_DEFAULT_STRIDE,) * len(elem.shape),
-    )
+    chunks = resolve_chunks(elem, chunks, tuple(elem.shape))
+    return da.from_array(read_dataset(elem), chunks=chunks)
 
 
 @_LAZY_REGISTRY.register_read(H5Array, IOSpec("array", "0.2.0"))
@@ -204,13 +220,7 @@ def read_h5_array(
     elem_name: str = elem.name
     shape = tuple(elem.shape)
     dtype = elem.dtype
-    chunks = (
-        tuple(
-            c if c not in {None, -1} else s for c, s in zip(chunks, shape, strict=True)
-        )
-        if chunks is not None
-        else tuple(min(_DEFAULT_STRIDE, s) for s in shape)
-    )
+    chunks = resolve_chunks(elem, chunks, shape)
 
     chunk_layout = tuple(
         compute_chunk_layout_for_axis_size(chunks[i], shape[i])
@@ -228,7 +238,6 @@ def read_h5_array(
 def read_zarr_array(
     elem: ZarrArray, *, _reader: LazyReader, chunks: tuple[int, ...] | None = None
 ) -> DaskArray:
-    chunks: tuple[int, ...] = chunks if chunks is not None else elem.chunks
     import dask.array as da
 
     return da.from_zarr(elem, chunks=chunks)
@@ -284,9 +293,10 @@ def read_dataframe(
     *,
     _reader: LazyReader,
     use_range_index: bool = False,
+    chunks: tuple[int] | None = None,
 ) -> Dataset2D:
     elem_dict = {
-        k: _reader.read_elem(elem[k])
+        k: _reader.read_elem(elem[k], chunks=chunks)
         for k in [*elem.attrs["column-order"], elem.attrs["_index"]]
     }
     # If we use a range index, the coord axis needs to have the special dim name