anndata 0.12.0rc3__tar.gz → 0.12.0rc4__tar.gz

anndata-0.12.0rc4/.github/workflows/test-cpu.yml

@@ -0,0 +1,124 @@
+name: CI
+
+on:
+  push:
+    branches:
+      - main
+      - "[0-9]+.[0-9]+.x"
+  pull_request:
+
+env:
+  FORCE_COLOR: "1"
+
+defaults:
+  run:
+    shell: bash -el {0}
+
+# Cancel the job if new commits are pushed
+# https://stackoverflow.com/questions/66335225/how-to-cancel-previous-runs-in-the-pr-when-you-push-new-commitsupdate-the-curre
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  get-environments:
+    runs-on: ubuntu-latest
+    outputs:
+      envs: ${{ steps.get-envs.outputs.envs }}
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          filter: blob:none
+          fetch-depth: 0
+      - uses: astral-sh/setup-uv@v5
+        with:
+          enable-cache: false
+      - id: get-envs
+        run: |
+          ENVS_JSON=$(NO_COLOR=1 uvx hatch env show --json | jq -c 'to_entries
+            | map(
+              select(.key | startswith("hatch-test"))
+              | { name: .key, python: .value.python }
+            )')
+          echo "envs=${ENVS_JSON}" | tee $GITHUB_OUTPUT
+  test:
+    needs: get-environments
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        env: ${{ fromJSON(needs.get-environments.outputs.envs) }}
+    env:  # environment variable for use in codecov’s env_vars tagging
+      ENV_NAME: ${{ matrix.env.name }}
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          filter: blob:none
+
+      - name: Set up Python ${{ matrix.env.python }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.env.python }}
+
+      - name: Install UV
+        uses: astral-sh/setup-uv@v5
+        with:
+          enable-cache: true
+          cache-dependency-glob: pyproject.toml
+
+      - name: Install dependencies
+        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
+
+      - name: Upload coverage data
+        uses: codecov/codecov-action@v5
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
+          env_vars: ENV_NAME
+          fail_ci_if_error: true
+          files: test-data/coverage.xml
+
+  build:
+    runs-on: ubuntu-22.04
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          filter: blob:none
+
+      - name: Set up Python 3.13
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.13'
+
+      - name: Install build tools and requirements
+        run: |
+          python -m pip install --upgrade pip
+          pip install build twine
+
+      - name: Display installed versions
+        run: pip list
+
+      - name: Build & Twine check
+        run: |
+          python -m build --sdist --wheel .
+          twine check dist/*
+
+      - name: Check runtime version
+        run: |
+          pip install dist/*.whl
+          python -c 'import anndata; print(anndata.__version__)'
+
+  check:
+    if: always()
+    needs:
+      - get-environments
+      - test
+      - build
+    runs-on: ubuntu-latest
+    steps:
+        - uses: re-actors/alls-green@release/v1
+          with:
+            jobs: ${{ toJSON(needs) }}

{anndata-0.12.0rc3 → anndata-0.12.0rc4}/.gitignore

@@ -12,6 +12,7 @@ __pycache__/
 # Distribution / packaging
 /dist/
 /ci/min-deps.txt
+/ci/pre-deps.txt
 /requirements*.lock
 /.python-version
 

{anndata-0.12.0rc3 → anndata-0.12.0rc4}/.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.11.4
+    rev: v0.11.12
     hooks:
       - id: ruff
         args: ["--fix"]

{anndata-0.12.0rc3 → anndata-0.12.0rc4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: anndata
-Version: 0.12.0rc3
+Version: 0.12.0rc4
 Summary: Annotated data.
 Project-URL: Documentation, https://anndata.readthedocs.io/
 Project-URL: Source, https://github.com/scverse/anndata
@@ -32,7 +32,7 @@ Requires-Dist: numpy>=1.25
 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,>=2.18.7
+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
 Provides-Extra: cu11
 Requires-Dist: cupy-cuda11x; extra == 'cu11'
 Provides-Extra: cu12
@@ -40,31 +40,8 @@ Requires-Dist: cupy-cuda12x; extra == 'cu12'
 Provides-Extra: dask
 Requires-Dist: dask[array]!=2024.8.*,!=2024.9.*,<2025.2.0,>=2023.5.1; extra == 'dask'
 Provides-Extra: dev
-Requires-Dist: aiohttp; extra == 'dev'
-Requires-Dist: awkward>=2.3.2; extra == 'dev'
-Requires-Dist: boltons; extra == 'dev'
-Requires-Dist: dask[array]!=2024.8.*,!=2024.9.*,<2025.2.0,>=2023.5.1; extra == 'dev'
-Requires-Dist: dask[distributed]; extra == 'dev'
-Requires-Dist: filelock; extra == 'dev'
 Requires-Dist: hatch-vcs; extra == 'dev'
-Requires-Dist: httpx; extra == 'dev'
-Requires-Dist: joblib; extra == 'dev'
-Requires-Dist: loompy>=3.0.5; extra == 'dev'
-Requires-Dist: matplotlib; extra == 'dev'
-Requires-Dist: openpyxl; extra == 'dev'
-Requires-Dist: pandas>=2.1.0; extra == 'dev'
-Requires-Dist: pyarrow; extra == 'dev'
-Requires-Dist: pytest-cov; extra == 'dev'
-Requires-Dist: pytest-memray; extra == 'dev'
-Requires-Dist: pytest-mock; extra == 'dev'
-Requires-Dist: pytest-randomly; extra == 'dev'
-Requires-Dist: pytest-xdist[psutil]; extra == 'dev'
-Requires-Dist: pytest<8.3.4,>=8.2; extra == 'dev'
-Requires-Dist: requests; extra == 'dev'
-Requires-Dist: scanpy>=1.10; extra == 'dev'
-Requires-Dist: scikit-learn; extra == 'dev'
 Requires-Dist: towncrier>=24.8.0; extra == 'dev'
-Requires-Dist: xarray>=2025.04.0; extra == 'dev'
 Provides-Extra: dev-doc
 Requires-Dist: towncrier>=24.8.0; extra == 'dev-doc'
 Provides-Extra: doc
@@ -89,7 +66,7 @@ Provides-Extra: lazy
 Requires-Dist: aiohttp; extra == 'lazy'
 Requires-Dist: dask[array]!=2024.8.*,!=2024.9.*,<2025.2.0,>=2023.5.1; extra == 'lazy'
 Requires-Dist: requests; extra == 'lazy'
-Requires-Dist: xarray>=2025.04.0; extra == 'lazy'
+Requires-Dist: xarray>=2025.06.1; extra == 'lazy'
 Provides-Extra: test
 Requires-Dist: aiohttp; extra == 'test'
 Requires-Dist: awkward>=2.3.2; extra == 'test'
@@ -113,7 +90,7 @@ Requires-Dist: pytest<8.3.4,>=8.2; extra == 'test'
 Requires-Dist: requests; extra == 'test'
 Requires-Dist: scanpy>=1.10; extra == 'test'
 Requires-Dist: scikit-learn; extra == 'test'
-Requires-Dist: xarray>=2025.04.0; extra == 'test'
+Requires-Dist: xarray>=2025.06.1; extra == 'test'
 Provides-Extra: test-min
 Requires-Dist: awkward>=2.3.2; extra == 'test-min'
 Requires-Dist: boltons; extra == 'test-min'

{anndata-0.12.0rc3 → anndata-0.12.0rc4}/docs/api.md

@@ -178,9 +178,10 @@ Types used by the former:
    experimental.ReadCallback
    experimental.WriteCallback
    experimental.StorageType
-   experimental.backed._lazy_arrays.MaskedArray
-   experimental.backed._lazy_arrays.CategoricalArray
-   _core.xarray.Dataset2D
+   experimental.backed.MaskedArray
+   experimental.backed.CategoricalArray
+   experimental.backed.Dataset2D
+   experimental.Dataset2DIlocIndexer
 ```
 
 (extensions-api)=

{anndata-0.12.0rc3 → anndata-0.12.0rc4}/docs/conf.py

@@ -99,6 +99,27 @@ def setup(app: Sphinx):
     app.add_generic_role("small", partial(nodes.inline, classes=["small"]))
     app.add_generic_role("smaller", partial(nodes.inline, classes=["smaller"]))
 
+    # TODO: move to scanpydoc
+    if TYPE_CHECKING:
+        from docutils.nodes import TextElement, reference
+        from sphinx.addnodes import pending_xref
+        from sphinx.environment import BuildEnvironment
+
+    def res(
+        app: Sphinx, env: BuildEnvironment, node: pending_xref, contnode: TextElement
+    ) -> reference | None:
+        return env.domains["py"].resolve_xref(
+            env,
+            node["refdoc"],
+            app.builder,
+            node["reftype"],
+            node["reftarget"],
+            node,
+            contnode,
+        )
+
+    app.connect("missing-reference", res, priority=502)
+
 
 intersphinx_mapping = dict(
     awkward=("https://awkward-array.org/doc/stable", None),
@@ -133,6 +154,7 @@ qualname_overrides = {
     "anndata._types.WriteCallback": "anndata.experimental.WriteCallback",
     "anndata._types.Read": "anndata.experimental.Read",
     "anndata._types.Write": "anndata.experimental.Write",
+    "anndata._types.Dataset2DIlocIndexer": "anndata.experimental.Dataset2DIlocIndexer",
     "zarr.core.array.Array": "zarr.Array",
     "zarr.core.group.Group": "zarr.Group",
     # Buffer is not yet exported, so the buffer class registry is the closest thing
@@ -142,6 +164,7 @@ qualname_overrides = {
     "anndata.compat.CupyArray": "cupy.ndarray",
     "anndata.compat.CupySparseMatrix": "cupyx.scipy.sparse.spmatrix",
     "anndata.compat.XDataArray": "xarray.DataArray",
+    "anndata.compat.XDataset": "xarray.Dataset",
     "awkward.highlevel.Array": "ak.Array",
     "numpy.int64": ("py:attr", "numpy.int64"),
     "pandas.DataFrame.iloc": ("py:attr", "pandas.DataFrame.iloc"),

anndata-0.12.0rc4/docs/extensions/autosummary_skip_inherited.py

@@ -0,0 +1,55 @@
+"""Extension to skip inherited methods and properties in autosummary."""
+
+from __future__ import annotations
+
+from traceback import walk_stack
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from typing import Literal
+
+    from sphinx.application import Sphinx
+    from sphinx.ext.autodoc import Options
+
+
+def skip_inherited(  # noqa: PLR0917
+    app: Sphinx,
+    what: Literal[
+        "module", "class", "exception", "function", "method", "attribute", "property"
+    ],
+    name: str,
+    obj: object,
+    skip: bool,  # noqa: FBT001
+    options: Options | dict[str, object],
+) -> bool | None:
+    """Skip inherited members."""
+    # Skip `getdoc` property
+    if what == "method" and name == "getdoc":
+        return True
+
+    # find parent class
+    for frame, _ in walk_stack(None):
+        if frame.f_code.co_name == "_get_members" and frame.f_code.co_filename.endswith(
+            "/generate.py"
+        ):
+            parent = frame.f_locals["obj"]
+            if not isinstance(parent, type):
+                return None
+            break
+    else:
+        return None
+
+    # return if it’s a member of the parent class
+    typ = parent
+    while typ is not type:
+        if name in typ.__dict__:
+            return None
+        typ = type(typ)
+
+    # skip since we know it’s not a member of the parent class
+    return True
+
+
+def setup(app: Sphinx) -> None:
+    """App setup hook."""
+    app.connect("autodoc-skip-member", skip_inherited)

{anndata-0.12.0rc3 → anndata-0.12.0rc4}/docs/release-notes/0.12.0rc1.md

@@ -10,7 +10,7 @@
 
 #### Bug fixes
 
-- Disallow writing of {class}`~anndata._core.xarray.Dataset2D` objects {user}`ilan-gold` ({pr}`1887`)
+- Disallow writing of {class}`~anndata.experimental.backed.Dataset2D` objects {user}`ilan-gold` ({pr}`1887`)
 - 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`)
 - Don't use {func}`asyncio.run` internally for any operations {user}`ilan-gold` ({pr}`1933`)
 - Disallow forward slashes in keys for writing {user}`ilan-gold` ({pr}`1940`)

anndata-0.12.0rc4/docs/release-notes/0.12.0rc4.md

@@ -0,0 +1,15 @@
+(v0.12.0rc4)=
+### 0.12.0rc4 {small}`2025-06-18`
+
+### Bug fixes
+
+- 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`)
+
+### Features
+
+- {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`)
+- 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
+
+- Improve {func}`~anndata.experimental.read_elem_lazy` performance for `h5ad` files by not caching `indptr`. {user}`ilan-gold` ({pr}`2005`)

anndata-0.12.0rc4/docs/release-notes/2013.development.md

@@ -0,0 +1 @@
+Bound {mod}`zarr` to `<3.1` until {pr}`1995` is merged to handle the new data type structure.  {user}`ilan-gold`

{anndata-0.12.0rc3 → anndata-0.12.0rc4}/hatch.toml

@@ -20,10 +20,14 @@ extra-dependencies = [ "ipykernel" ]
 env-vars.UV_CONSTRAINT = "ci/constraints.txt"
 overrides.matrix.deps.env-vars = [
     { if = [ "pre" ], key = "UV_PRERELEASE", value = "allow" },
+    { if = [ "pre" ], key = "UV_CONSTRAINT", value = "ci/pre-deps.txt" },
     { if = [ "min" ], key = "UV_CONSTRAINT", value = "ci/constraints.txt ci/min-deps.txt" },
 ]
 overrides.matrix.deps.pre-install-commands = [
     { if = [ "min" ], value = "uv run ci/scripts/min-deps.py pyproject.toml --all-extras -o ci/min-deps.txt" },
+    # To prevent situations like https://github.com/pydata/xarray/issues/10419 going forward
+    { if = [ "pre" ], value = "echo xarray @ git+https://github.com/pydata/xarray.git > ci/pre-deps.txt" },
+
 ]
 overrides.matrix.deps.python = [
     { if = [ "min" ], value = "3.11" },

{anndata-0.12.0rc3 → anndata-0.12.0rc4}/pyproject.toml

@@ -46,7 +46,8 @@ dependencies = [
     "packaging>=24.2",
     "array_api_compat>=1.7.1",
     "legacy-api-wrap",
-    "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 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",
 ]
 dynamic = [ "version" ]
 
@@ -60,7 +61,7 @@ Home-page = "https://github.com/scverse/anndata"
 dev = [
     # runtime dev version generation
     "hatch-vcs",
-    "anndata[dev-doc,test]",
+    "anndata[dev-doc]",
 ]
 doc = [
     "sphinx>=8.2.1",
@@ -109,7 +110,7 @@ gpu = [ "cupy" ]
 cu12 = [ "cupy-cuda12x" ]
 cu11 = [ "cupy-cuda11x" ]
 # requests and aiohttp needed for zarr remote data
-lazy = [ "xarray>=2025.04.0", "aiohttp", "requests", "anndata[dask]" ]
+lazy = [ "xarray>=2025.06.1", "aiohttp", "requests", "anndata[dask]" ]
 # https://github.com/dask/dask/issues/11290
 # https://github.com/dask/dask/issues/11752
 dask = [ "dask[array]>=2023.5.1,!=2024.8.*,!=2024.9.*,<2025.2.0" ]

{anndata-0.12.0rc3 → anndata-0.12.0rc4}/src/anndata/_core/aligned_mapping.py

@@ -79,7 +79,7 @@ class AlignedMappingBase(MutableMapping[str, Value], ABC):
         elif isinstance(val, np.ndarray | CupyArray) and len(val.shape) == 1:
             val = val.reshape((val.shape[0], 1))
         elif isinstance(val, XDataset):
-            val = Dataset2D(data_vars=val.data_vars, coords=val.coords, attrs=val.attrs)
+            val = Dataset2D(val)
         for i, axis in enumerate(self.axes):
             if self.parent.shape[axis] == axis_len(val, i):
                 continue

{anndata-0.12.0rc3 → anndata-0.12.0rc4}/src/anndata/_core/index.py

@@ -198,7 +198,8 @@ def _subset_sparse(a: CSMatrix | CSArray, subset_idx: Index):
 
 
 @_subset.register(pd.DataFrame)
-def _subset_df(df: pd.DataFrame, subset_idx: Index):
+@_subset.register(Dataset2D)
+def _subset_df(df: pd.DataFrame | Dataset2D, subset_idx: Index):
     return df.iloc[subset_idx]
 
 
@@ -209,15 +210,6 @@ def _subset_awkarray(a: AwkArray, subset_idx: Index):
     return a[subset_idx]
 
 
-@_subset.register(Dataset2D)
-def _(a: Dataset2D, subset_idx: Index):
-    key = a.index_dim
-    # xarray seems to have some code looking for a second entry in tuples
-    if isinstance(subset_idx, tuple) and len(subset_idx) == 1:
-        subset_idx = subset_idx[0]
-    return a.isel(**{key: subset_idx})
-
-
 # Registration for SparseDataset occurs in sparse_dataset.py
 @_subset.register(h5py.Dataset)
 def _subset_dataset(d, subset_idx):