anndata 0.12.2__tar.gz → 0.12.4__tar.gz

anndata-0.12.4/.github/dependabot.yml

@@ -0,0 +1,9 @@
+version: 2
+updates:
+  - package-ecosystem: github-actions
+    directory: /
+    schedule:
+      interval: weekly
+    labels:
+      - no milestone
+      - skip-gpu-ci

{anndata-0.12.2 → anndata-0.12.4}/.github/workflows/benchmark.yml

@@ -11,7 +11,10 @@ env:
 
 defaults:
   run:
-    shell: bash -el {0}
+    # Add `-l` to GitHub’s default bash options to activate mamba environments
+    # https://docs.github.com/en/actions/reference/workflows-and-actions/workflow-syntax#exit-codes-and-error-action-preference
+    # https://github.com/mamba-org/setup-micromamba/#readme
+    shell: bash -elo pipefail {0}
 
 jobs:
   benchmark:
@@ -29,9 +32,10 @@ jobs:
       ASV_DIR: "./benchmarks"
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
         with:
           fetch-depth: 0
+          # no blob filter so asv can checkout other commits
 
       - run: git fetch origin main:main
         if: ${{ github.ref_name != 'main' }}
@@ -42,11 +46,10 @@ jobs:
           environment-name: asv
           cache-environment: true
           # Deps documented in https://asv.readthedocs.io/en/latest/installing.html
-          # libmambapy upper bound: https://github.com/airspeed-velocity/asv/issues/1438
           create-args: >-
             python=${{ matrix.python }}
             asv
-            libmambapy<2
+            py_rattler
             conda-build
 
       - name: Cache datasets

anndata-0.12.2/.github/workflows/check-pr-milestoned.yml → anndata-0.12.4/.github/workflows/check-pr.yml

@@ -24,7 +24,7 @@ env:
 
 jobs:
   check-milestone:
-    name: "Triage: Check Milestone"
+    name: "Triage: Check PR title, milestone, and labels"
     runs-on: ubuntu-latest
     steps:
       - name: Check if merging isn’t blocked
@@ -35,3 +35,7 @@ jobs:
         uses: flying-sheep/check@v1
         with:
           success: ${{ github.event.pull_request.milestone != null || contains(env.LABELS, 'no milestone') }}
+      - name: Check if PR title is valid
+        uses: amannn/action-semantic-pull-request@v6
+        env: # Needs repo options: “Squash and merge” with commit message set to “PR title”
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

{anndata-0.12.2 → anndata-0.12.4}/.github/workflows/publish.yml

@@ -11,7 +11,7 @@ jobs:
     permissions:
       id-token: write # to authenticate as Trusted Publisher to pypi.org
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
         with:
           fetch-depth: 0
           filter: blob:none

{anndata-0.12.2 → anndata-0.12.4}/.github/workflows/test-cpu.yml

@@ -10,12 +10,7 @@ on:
 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
+# Cancel the job if new commits are pushed: https://stackoverflow.com/q/66335225/247482
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: true
@@ -26,11 +21,11 @@ jobs:
     outputs:
       envs: ${{ steps.get-envs.outputs.envs }}
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
         with:
           filter: blob:none
           fetch-depth: 0
-      - uses: astral-sh/setup-uv@v5
+      - uses: astral-sh/setup-uv@v6
         with:
           enable-cache: false
       - id: get-envs
@@ -41,17 +36,19 @@ jobs:
               | { name: .key, python: .value.python, args: (.value."extra-args" // [] | join(" ")) }
             )')
           echo "envs=${ENVS_JSON}" | tee $GITHUB_OUTPUT
+
   test:
     needs: get-environments
     runs-on: ubuntu-latest
     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
+        io_mark: ["zarr_io", "not zarr_io", "dask_distributed"] # dask_distributed should not be run with -n auto as it uses a client with processes
+    env:  # environment variables for use in codecov’s env_vars tagging
       ENV_NAME: ${{ matrix.env.name }}
+      IO_MARK: ${{ matrix.io_mark }}
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
         with:
           fetch-depth: 0
           filter: blob:none
@@ -59,43 +56,56 @@ jobs:
       - name: Install system dependencies
         run: sudo apt install -y hdf5-tools
 
-      - 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
+        uses: astral-sh/setup-uv@v6
         with:
           enable-cache: true
-          cache-dependency-glob: pyproject.toml
+          python-version: ${{ matrix.env.python }}
 
       - name: Install dependencies
-        run: uvx hatch -v env create ${{ matrix.env.name }}
+        run: |
+          # https://github.com/pallets/click/issues/3066
+          uv tool install --with='click!=8.3.0' hatch
+          hatch -v env create ${{ matrix.env.name }}
 
       - name: Run tests
-        run: uvx hatch run ${{ matrix.env.name }}:run-cov -v --color=yes -n auto --cov --cov-report=xml --junitxml=test-data/test-results.xml -m "${{ matrix.io_mark }}" ${{ matrix.env.args }}
+        env:
+          COVERAGE_PROCESS_START: ${{ github.workspace }}/pyproject.toml
+        run: |
+          hatch run ${{ matrix.env.name }}:run-cov -v --color=yes ${{ matrix.io_mark != 'dask_distributed' && '-n auto' || '' }} --junitxml=test-data/test-results.xml -m "${{ matrix.io_mark }}" ${{ matrix.env.args }}
+          hatch run ${{ matrix.env.name }}:cov-combine
+          hatch run ${{ matrix.env.name }}:coverage xml
+
+      - name: Upload test results
+        if: ${{ !cancelled() }}
+        uses: codecov/test-results-action@v1
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
+          env_vars: ENV_NAME,IO_MARK
+          fail_ci_if_error: true
+          file: test-data/test-results.xml
 
       - name: Upload coverage data
         uses: codecov/codecov-action@v5
         with:
           token: ${{ secrets.CODECOV_TOKEN }}
-          env_vars: ENV_NAME
+          env_vars: ENV_NAME,IO_MARK
           fail_ci_if_error: true
           files: test-data/coverage.xml
 
   build:
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-24.04
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
         with:
           fetch-depth: 0
           filter: blob:none
 
-      - name: Set up Python 3.13
+      - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: '3.13'
+          python-version: '3.x'
+          cache: pip
 
       - name: Install build tools and requirements
         run: |
@@ -110,11 +120,6 @@ jobs:
           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:
@@ -123,6 +128,6 @@ jobs:
       - build
     runs-on: ubuntu-latest
     steps:
-        - uses: re-actors/alls-green@release/v1
-          with:
-            jobs: ${{ toJSON(needs) }}
+      - uses: re-actors/alls-green@release/v1
+        with:
+          jobs: ${{ toJSON(needs) }}

{anndata-0.12.2 → anndata-0.12.4}/.github/workflows/test-gpu.yml

@@ -13,10 +13,6 @@ env:
   PYTEST_ADDOPTS: "-v --color=yes"
   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:
@@ -48,7 +44,7 @@ jobs:
     timeout-minutes: 30
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v4 # TODO: upgrade once cirun image supports node 24
         with:
           fetch-depth: 0
           filter: blob:none
@@ -66,28 +62,29 @@ jobs:
           max_version=$(echo "$classifiers" | sort -V | tail -1)
           echo "max_python_version=$max_version" >> $GITHUB_ENV
 
-      - name: Install Python
-        uses: actions/setup-python@v5
-        with:
-          # https://github.com/cupy/cupy/issues/8651 cupy does not support python3.13 yet
-          python-version: "3.12"
-
       - name: Install UV
-        uses: astral-sh/setup-uv@v5
+        uses: astral-sh/setup-uv@v6 # TODO: upgrade once cirun image supports node 24
         with:
           enable-cache: true
-          cache-dependency-glob: pyproject.toml
+          python-version: ${{ env.max_python_version }}
 
       - name: Install AnnData
-        run: uv pip install --system -e ".[dev,test,cu12]" -c ci/constraints.txt
+        run: |
+          uv venv
+          uv pip install -e ".[dev,test,cu12]" -c ci/constraints.txt
 
       - name: Env list
-        run: pip list
+        run: uv pip list
 
       - name: Run test
-        run: coverage run -m pytest -m gpu -n auto --cov --cov-report=xml
+        env:
+          COVERAGE_PROCESS_START: ${{ github.workspace }}/pyproject.toml
+        run: |
+          uv run coverage run -m pytest -m gpu -n auto
+          uv run coverage combine
+          uv run coverage xml
 
-      - uses: codecov/codecov-action@v4
+      - uses: codecov/codecov-action@v5
         with:
           token: ${{ secrets.CODECOV_TOKEN }}
           fail_ci_if_error: true

{anndata-0.12.2 → anndata-0.12.4}/.pre-commit-config.yaml

@@ -1,8 +1,8 @@
 repos:
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.12.4
+    rev: v0.13.0
     hooks:
-      - id: ruff
+      - id: ruff-check
         args: ["--fix"]
       - id: ruff-format
       # The following can be removed once PLR0917 is out of preview

{anndata-0.12.2 → anndata-0.12.4}/.readthedocs.yml

@@ -1,6 +1,6 @@
 version: 2
 build:
-  os: ubuntu-20.04
+  os: ubuntu-24.04
   tools:
     python: "3.13"
   jobs:

{anndata-0.12.2 → anndata-0.12.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: anndata
-Version: 0.12.2
+Version: 0.12.4
 Summary: Annotated data.
 Project-URL: Documentation, https://anndata.readthedocs.io/
 Project-URL: Source, https://github.com/scverse/anndata
@@ -38,15 +38,14 @@ Requires-Dist: cupy-cuda11x; extra == 'cu11'
 Provides-Extra: cu12
 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'
+Requires-Dist: dask[array]!=2024.8.*,!=2024.9.*,!=2025.2.*,!=2025.3.*,!=2025.4.*,!=2025.5.*,!=2025.6.*,!=2025.7.*,!=2025.8.*,>=2023.5.1; extra == 'dask'
 Provides-Extra: dev
-Requires-Dist: hatch-vcs; extra == 'dev'
 Requires-Dist: towncrier>=24.8.0; extra == 'dev'
 Provides-Extra: dev-doc
 Requires-Dist: towncrier>=24.8.0; extra == 'dev-doc'
 Provides-Extra: doc
 Requires-Dist: awkward>=2.3; extra == 'doc'
-Requires-Dist: dask[array]!=2024.8.*,!=2024.9.*,<2025.2.0,>=2023.5.1; extra == 'doc'
+Requires-Dist: dask[array]!=2024.8.*,!=2024.9.*,!=2025.2.*,!=2025.3.*,!=2025.4.*,!=2025.5.*,!=2025.6.*,!=2025.7.*,!=2025.8.*,>=2023.5.1; extra == 'doc'
 Requires-Dist: ipython; extra == 'doc'
 Requires-Dist: myst-nb; extra == 'doc'
 Requires-Dist: myst-parser; extra == 'doc'
@@ -64,14 +63,14 @@ Provides-Extra: gpu
 Requires-Dist: cupy; extra == 'gpu'
 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: dask[array]!=2024.8.*,!=2024.9.*,!=2025.2.*,!=2025.3.*,!=2025.4.*,!=2025.5.*,!=2025.6.*,!=2025.7.*,!=2025.8.*,>=2023.5.1; extra == 'lazy'
 Requires-Dist: requests; 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'
 Requires-Dist: boltons; extra == 'test'
-Requires-Dist: dask[array]!=2024.8.*,!=2024.9.*,<2025.2.0,>=2023.5.1; extra == 'test'
+Requires-Dist: dask[array]!=2024.8.*,!=2024.9.*,!=2025.2.*,!=2025.3.*,!=2025.4.*,!=2025.5.*,!=2025.6.*,!=2025.7.*,!=2025.8.*,>=2023.5.1; extra == 'test'
 Requires-Dist: dask[distributed]; extra == 'test'
 Requires-Dist: filelock; extra == 'test'
 Requires-Dist: httpx<1.0; extra == 'test'
@@ -93,7 +92,7 @@ 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'
-Requires-Dist: dask[array]!=2024.8.*,!=2024.9.*,<2025.2.0,>=2023.5.1; extra == 'test-min'
+Requires-Dist: dask[array]!=2024.8.*,!=2024.9.*,!=2025.2.*,!=2025.3.*,!=2025.4.*,!=2025.5.*,!=2025.6.*,!=2025.7.*,!=2025.8.*,>=2023.5.1; extra == 'test-min'
 Requires-Dist: dask[distributed]; extra == 'test-min'
 Requires-Dist: filelock; extra == 'test-min'
 Requires-Dist: httpx<1.0; extra == 'test-min'

{anndata-0.12.2 → anndata-0.12.4}/benchmarks/asv.conf.json

@@ -36,7 +36,7 @@
     // If missing or the empty string, the tool will be automatically
     // determined by looking for tools on the PATH environment
     // variable.
-    "environment_type": "mamba",
+    "environment_type": "rattler",
     // timeout in seconds for installing any dependencies in environment
     // defaults to 10 min
     //"install_timeout": 600,

{anndata-0.12.2 → anndata-0.12.4}/benchmarks/benchmarks/anndata.py

@@ -13,18 +13,16 @@ class GarbargeCollectionSuite:
     # custom because `memory_profiler` is a line-by-line profiler (also: https://github.com/pythonprofilers/memory_profiler/issues/402)
     def track_peakmem_garbage_collection(self, *_):
         def display_top(snapshot, key_type="lineno"):
-            snapshot = snapshot.filter_traces(
-                (
-                    tracemalloc.Filter(
-                        inclusive=False,
-                        filename_pattern="<frozen importlib._bootstrap>",
-                    ),
-                    tracemalloc.Filter(
-                        inclusive=False,
-                        filename_pattern="<unknown>",
-                    ),
-                )
-            )
+            snapshot = snapshot.filter_traces((
+                tracemalloc.Filter(
+                    inclusive=False,
+                    filename_pattern="<frozen importlib._bootstrap>",
+                ),
+                tracemalloc.Filter(
+                    inclusive=False,
+                    filename_pattern="<unknown>",
+                ),
+            ))
             top_stats = snapshot.statistics(key_type)
             total = sum(stat.size for stat in top_stats)
             return total

anndata-0.12.4/benchmarks/benchmarks/backed_hdf5.py

@@ -0,0 +1,112 @@
+from __future__ import annotations
+
+import numpy as np
+import pandas as pd
+from scipy import sparse
+
+import anndata as ad
+
+file_paths = {"sparse": "adata_sparse.h5ad"}
+
+
+class BackedHDF5Indexing:
+    param_names = ("arr_type",)
+    params = ("sparse",)
+
+    def setup_cache(self):
+        X_sparse = sparse.random(
+            10000,
+            50000,
+            density=0.01,
+            format="csr",
+            random_state=np.random.default_rng(42),
+        )
+        for X, arr_type in [
+            (X_sparse, "sparse"),
+        ]:
+            n_obs, n_var = X.shape
+
+            # Create obs and var dataframes
+            obs = pd.DataFrame(
+                {
+                    "cell_type": pd.Categorical(
+                        np.random.choice(["TypeA", "TypeB", "TypeC"], n_obs)
+                    ),
+                    "total_counts": np.random.randint(1000, 5000, n_obs),
+                },
+                index=[f"cell_{i}" for i in range(n_obs)],
+            )
+
+            var = pd.DataFrame(
+                {
+                    "gene_name": [f"gene_{i}" for i in range(n_var)],
+                },
+                index=[f"ENSG_{i:08d}" for i in range(n_var)],
+            )
+
+            # Create AnnData object and save to HDF5
+            adata = ad.AnnData(X=X, obs=obs, var=var)
+
+            # Create temporary file
+            adata.write_h5ad(file_paths[arr_type])
+
+    def setup(self, arr_type):
+        # Open as backed
+        self.adata_backed = ad.read_h5ad(file_paths[arr_type], backed="r")
+        self.n_obs, self.n_var = self.adata_backed.shape
+        # Prepare indices for duplicate index testing
+        self.obs_idx_with_dupes = np.array([0, 1, 0, 2, 1] * (self.n_obs // 100 + 1))[
+            : (self.n_obs // 10)
+        ]
+        self.var_idx_with_dupes = np.array([0, 1, 2, 0, 3] * (self.n_var // 100 + 1))[
+            : (self.n_var // 10)
+        ]
+        self.obs_idx_no_dupes = np.arange(0, self.n_obs, 10)
+        self.var_idx_no_dupes = np.arange(0, self.n_var, 10)
+
+    def time_slice_obs(self, *_):
+        """Time slicing observations from backed HDF5"""
+        self.adata_backed[0 : (self.n_obs // 2), :]
+
+    def time_slice_obs_to_memory(self, *_):
+        """Time slicing observations from backed HDF5"""
+        self.adata_backed[0 : (self.n_obs // 2), :].to_memory()
+
+    def peakmem_slice_obs(self, *_):
+        """Peak memory for slicing observations from backed HDF5"""
+        self.adata_backed[0 : (self.n_obs // 2), :]
+
+    def time_fancy_index_no_dupes(self, *_):
+        """Time fancy indexing without duplicates"""
+        self.adata_backed[self.obs_idx_no_dupes, self.var_idx_no_dupes]
+
+    def peakmem_fancy_index_no_dupes(self, *_):
+        """Peak memory for fancy indexing without duplicates"""
+        self.adata_backed[self.obs_idx_no_dupes, self.var_idx_no_dupes]
+
+    def time_fancy_index_no_dupes_to_memory(self, *_):
+        """Time fancy indexing without duplicates"""
+        self.adata_backed[self.obs_idx_no_dupes, self.var_idx_no_dupes].to_memory()
+
+    def time_index_with_dupes_obs(self, *_):
+        """Time fancy indexing with duplicate observation indices"""
+        self.adata_backed[self.obs_idx_with_dupes, :]
+
+    def peakmem_index_with_dupes_obs(self, *_):
+        """Peak memory for fancy indexing with duplicate observation indices"""
+        self.adata_backed[self.obs_idx_with_dupes, :]
+
+    def time_to_memory_subset(self, *_):
+        """Time converting subset to memory"""
+        subset = self.adata_backed[0 : (self.n_obs // 4), 0 : (self.n_var // 4)]
+        subset.to_memory()
+
+    def peakmem_to_memory_subset(self, *_):
+        """Peak memory for converting subset to memory"""
+        subset = self.adata_backed[0 : (self.n_obs // 4), 0 : (self.n_var // 4)]
+        subset.to_memory()
+
+    def teardown(self, *_):
+        """Clean up temporary files"""
+        if hasattr(self, "adata_backed"):
+            self.adata_backed.file.close()

{anndata-0.12.2 → anndata-0.12.4}/benchmarks/benchmarks/dataset2d.py

@@ -1,7 +1,5 @@
 from __future__ import annotations
 
-import tempfile
-from pathlib import Path
 from typing import TYPE_CHECKING
 
 import h5py
@@ -12,35 +10,39 @@ import zarr
 import anndata as ad
 
 if TYPE_CHECKING:
-    from collections.abc import Callable
+    from typing import Literal
 
 
 class Dataset2D:
-    param_names = ("gen_store", "chunks")
+    param_names = ("store_type", "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
-            ),
-        ),
+        ("zarr", "h5ad"),
         ((-1,), None),
     )
 
-    def setup(
-        self, gen_store: Callable[[], zarr.Group | h5py.File], chunks: None | tuple[int]
-    ):
-        self.n_obs = 100000
+    def setup_cache(self):
+        n_obs = 100000
         df = pd.DataFrame(
             {
-                "a": pd.Categorical(np.array(["a"] * self.n_obs)),
-                "b": np.arange(self.n_obs),
+                "a": pd.Categorical(np.array(["a"] * n_obs)),
+                "b": np.arange(n_obs),
             },
-            index=[f"cell{i}" for i in range(self.n_obs)],
+            index=[f"cell{i}" for i in range(n_obs)],
+        )
+        for store in [
+            h5py.File("data.h5ad", mode="w"),
+            zarr.open("data.zarr", mode="w", zarr_version=2),
+        ]:
+            ad.io.write_elem(store, "obs", df)
+
+    def setup(self, store_type: Literal["zarr", "h5ad"], chunks: None | tuple[int]):
+        store = (
+            h5py.File("data.h5ad", mode="r")
+            if store_type == "h5ad"
+            else zarr.open("data.zarr")
         )
-        store = gen_store()
-        ad.io.write_elem(store, "obs", df)
         self.ds = ad.experimental.read_elem_lazy(store["obs"], chunks=chunks)
+        self.n_obs = self.ds.shape[0]
 
     def time_getitem_slice(self, *_):
         self.ds.iloc[0 : (self.n_obs // 2)].to_memory()

{anndata-0.12.2 → anndata-0.12.4}/benchmarks/benchmarks/readwrite.py

@@ -38,52 +38,15 @@ from .utils import get_actualsize, get_peak_mem, sedate
 
 PBMC_3K_URL = "https://falexwolf.de/data/pbmc3k_raw.h5ad"
 
-# PBMC_3K_PATH = Path(__file__).parent / "data/pbmc3k_raw.h5ad"
-# PBMC_REDUCED_PATH = Path(__file__).parent / "10x_pbmc68k_reduced.h5ad"
-# BM_43K_CSR_PATH = Path(__file__).parent.parent / "datasets/BM2_43k-cells.h5ad"
-# BM_43K_CSC_PATH = Path(__file__).parent.parent / "datasets/BM2_43k-cells_CSC.h5ad"
-
-
-# class ZarrReadSuite:
-#     params = []
-#     param_names = ["input_url"]
-
-#     def setup(self, input_url):
-#         self.filepath = pooch.retrieve(url=input_url, known_hash=None)
-
-#     def time_read_full(self, input_url):
-#         anndata.read_zarr(self.filepath)
-
-#     def peakmem_read_full(self, input_url):
-#         anndata.read_zarr(self.filepath)
-
-#     def mem_readfull_object(self, input_url):
-#         return anndata.read_zarr(self.filepath)
-
-#     def track_read_full_memratio(self, input_url):
-#         mem_recording = memory_usage(
-#             (sedate(anndata.read_zarr, 0.005), (self.filepath,)), interval=0.001
-#         )
-#         adata = anndata.read_zarr(self.filepath)
-#         base_size = mem_recording[-1] - mem_recording[0]
-#         print(np.max(mem_recording) - np.min(mem_recording))
-#         print(base_size)
-#         return (np.max(mem_recording) - np.min(mem_recording)) / base_size
-
-#     def peakmem_read_backed(self, input_url):
-#         anndata.read_zarr(self.filepath, backed="r")
-
-#     def mem_read_backed_object(self, input_url):
-#         return anndata.read_zarr(self.filepath, backed="r")
-
 
 class H5ADInMemorySizeSuite:
-    _urls = MappingProxyType(dict(pbmc3k=PBMC_3K_URL))
-    params = _urls.keys()
-    param_names = ("input_data",)
+    filepath = "pbmc_in_mem.h5ad"
 
-    def setup(self, input_data: str):
-        self.filepath = pooch.retrieve(url=self._urls[input_data], known_hash=None)
+    def setup_cache(self):
+        # Need to specify path because the working directory is special for asv
+        pooch.retrieve(
+            url=PBMC_3K_URL, known_hash=None, path=Path.cwd(), fname=self.filepath
+        )
 
     def track_in_memory_size(self, *_):
         adata = anndata.read_h5ad(self.filepath)
@@ -99,12 +62,13 @@ class H5ADInMemorySizeSuite:
 
 
 class H5ADReadSuite:
-    _urls = MappingProxyType(dict(pbmc3k=PBMC_3K_URL))
-    params = _urls.keys()
-    param_names = ("input_data",)
+    filepath = "pbmc_read.h5ad"
 
-    def setup(self, input_data: str):
-        self.filepath = pooch.retrieve(url=self._urls[input_data], known_hash=None)
+    def setup_cache(self):
+        # Need to specify path because the working directory is special for asv
+        pooch.retrieve(
+            url=PBMC_3K_URL, known_hash=None, path=Path.cwd(), fname=self.filepath
+        )
 
     def time_read_full(self, *_):
         anndata.read_h5ad(self.filepath)
@@ -171,9 +135,11 @@ class H5ADWriteSuite:
         self.adata.write_h5ad(self.writepth, compression="gzip")
 
     def track_peakmem_write_compressed(self, *_):
-        return get_peak_mem(
-            (sedate(self.adata.write_h5ad), (self.writepth,), {"compression": "gzip"})
-        )
+        return get_peak_mem((
+            sedate(self.adata.write_h5ad),
+            (self.writepth,),
+            {"compression": "gzip"},
+        ))
 
 
 class H5ADBackedWriteSuite(H5ADWriteSuite):