Merge branch 'main' into create_cat_regressor

.gitignore

@@ -27,7 +27,6 @@
 
 # Python build files
 __pycache__/
-/src/scanpy/_version.py
 /ci/scanpy-min-deps.txt
 /dist/
 /*-env/
@@ -42,7 +41,6 @@ Thumbs.db
 
 # IDEs and editors
 /.idea/
-/.vscode/
 
 # asv benchmark files
 /benchmarks/.asv

.pre-commit-config.yaml

@@ -1,16 +1,13 @@
 repos:
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.8.2
+    rev: v0.9.2
     hooks:
     -   id: ruff
-        types_or: [python, pyi, jupyter]
         args: ["--fix"]
     -   id: ruff-format
-        types_or: [python, pyi, jupyter]
     # The following can be removed once PLR0917 is out of preview
     -   name: ruff preview rules
         id: ruff
-        types_or: [python, pyi, jupyter]
         args: ["--preview", "--select=PLR0917"]
 -   repo: https://github.com/flying-sheep/bibfmt
     rev: v4.3.0
@@ -19,6 +16,15 @@ repos:
         args:
         - --sort-by-bibkey
         - --drop=abstract
+-   repo: https://github.com/biomejs/pre-commit
+    rev: v0.6.1
+    hooks:
+    -   id: biome-format
+        additional_dependencies: ["@biomejs/[email protected]"]
+-   repo: https://github.com/ComPWA/taplo-pre-commit
+    rev: v0.9.3
+    hooks:
+    -   id: taplo-format
 -   repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v5.0.0
     hooks:
@@ -34,6 +40,3 @@ repos:
     -   id: detect-private-key
     -   id: no-commit-to-branch
         args: ["--branch=main"]
-
-ci:
-    autofix_prs: false

.taplo.toml

@@ -0,0 +1,5 @@
+[formatting]
+array_auto_collapse = false
+column_width = 120
+compact_arrays = false
+indent_string = '    '

.vscode/launch.json

@@ -0,0 +1,26 @@
+{
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "Python: Build Documentation",
+            "type": "debugpy",
+            "request": "launch",
+            "module": "sphinx",
+            "args": ["-M", "html", ".", "_build"],
+            "cwd": "${workspaceFolder}/docs",
+            "console": "internalConsole",
+            "justMyCode": false,
+        },
+        {
+            "name": "Python: Debug Test",
+            "type": "debugpy",
+            "request": "launch",
+            "program": "${file}",
+            "purpose": ["debug-test"],
+            "console": "internalConsole",
+            "justMyCode": false,
+            "env": { "PYTEST_ADDOPTS": "--color=yes" },
+            "presentation": { "hidden": true },
+        },
+    ],
+}

.vscode/settings.json

@@ -0,0 +1,22 @@
+{
+    "[python][toml][json][jsonc]": {
+        "editor.formatOnSave": true,
+        "editor.codeActionsOnSave": {
+            "source.organizeImports": "explicit",
+            "source.fixAll": "explicit",
+        },
+    },
+    "[python]": {
+        "editor.defaultFormatter": "charliermarsh.ruff",
+    },
+    "[toml]": {
+        "editor.defaultFormatter": "tamasfe.even-better-toml",
+    },
+    "[json][jsonc]": {
+        "editor.defaultFormatter": "biomejs.biome",
+    },
+    "python.analysis.typeCheckingMode": "basic",
+    "python.testing.pytestArgs": ["-vv", "--color=yes"],
+    "python.testing.pytestEnabled": true,
+    "python.terminal.activateEnvironment": true,
+}

benchmarks/asv.conf.json

@@ -78,7 +78,7 @@
         "natsort": [""],
         "pandas": [""],
         "memory_profiler": [""],
-        "zarr": [""],
+        "zarr": ["2.18.4"],
         "pytest": [""],
         "scanpy": [""],
         "python-igraph": [""],

biome.jsonc

@@ -0,0 +1,21 @@
+{
+    "$schema": "https://biomejs.dev/schemas/1.9.4/schema.json",
+    "formatter": {
+        "indentStyle": "space",
+        "indentWidth": 4,
+    },
+    "overrides": [
+        {
+            "include": ["./.vscode/*.json", "**/*.jsonc", "**/asv.conf.json"],
+            "json": {
+                "formatter": {
+                    "trailingCommas": "all",
+                },
+                "parser": {
+                    "allowComments": true,
+                    "allowTrailingCommas": true,
+                },
+            },
+        },
+    ],
+}

ci/scripts/min-deps.py

@@ -71,7 +71,9 @@ def extract_min_deps(
 
         # If we are referring to other optional dependency lists, resolve them
         if req.name == project_name:
-            assert req.extras, f"Project included itself as dependency, without specifying extras: {req}"
+            assert req.extras, (
+                f"Project included itself as dependency, without specifying extras: {req}"
+            )
             for extra in req.extras:
                 extra_deps = pyproject["project"]["optional-dependencies"][extra]
                 dependencies += map(Requirement, extra_deps)

ci/scripts/towncrier_automation.py

@@ -92,7 +92,11 @@ def main(argv: Sequence[str] | None = None) -> None:
             f"--base={base_branch}",
             f"--title={pr_title}",
             f"--body={pr_description}",
-            *(["--label=no milestone"] if base_branch == "main" else []),
+            *(
+                ["--label=no milestone", "--label=Development Process 🚀"]
+                if base_branch == "main"
+                else []
+            ),
             *(["--dry-run"] if args.dry_run else []),
         ],
         check=True,

docs/api/deprecated.md

@@ -11,4 +11,5 @@
 
    pp.filter_genes_dispersion
    pp.normalize_per_cell
+   pp.subsample
 ```

docs/api/preprocessing.md

@@ -31,7 +31,7 @@ For visual quality control, see {func}`~scanpy.pl.highest_expr_genes` and
    pp.normalize_total
    pp.regress_out
    pp.scale
-   pp.subsample
+   pp.sample
    pp.downsample_counts
 ```
 
@@ -49,7 +49,7 @@ For visual quality control, see {func}`~scanpy.pl.highest_expr_genes` and
 
 ### Batch effect correction
 
-Also see [Data integration]. Note that a simple batch correction method is available via {func}`pp.regress_out`. Checkout {mod}`scanpy.external` for more.
+Also see {ref}`data-integration`. Note that a simple batch correction method is available via {func}`pp.regress_out`. Checkout {mod}`scanpy.external` for more.
 
 ```{eval-rst}
 .. autosummary::

docs/api/tools.md

@@ -48,6 +48,8 @@ Compute densities on embeddings.
    tl.paga
 ```
 
+(data-integration)=
+
 ### Data integration
 
 ```{eval-rst}

docs/conf.py

@@ -142,6 +142,8 @@
     rapids_singlecell=("https://rapids-singlecell.readthedocs.io/en/latest/", None),
     scipy=("https://docs.scipy.org/doc/scipy/", None),
     seaborn=("https://seaborn.pydata.org/", None),
+    session_info2=("https://session-info2.readthedocs.io/en/stable/", None),
+    squidpy=("https://squidpy.readthedocs.io/en/stable/", None),
     sklearn=("https://scikit-learn.org/stable/", None),
 )
 
@@ -225,9 +227,6 @@ def setup(app: Sphinx):
     ("py:class", "scanpy._utils.Empty"),
     ("py:class", "numpy.random.mtrand.RandomState"),
     ("py:class", "scanpy.neighbors._types.KnnTransformerLike"),
-    # Will work once scipy 1.8 is released
-    ("py:class", "scipy.sparse.base.spmatrix"),
-    ("py:class", "scipy.sparse.csr.csr_matrix"),
 ]
 
 # Options for plot examples

docs/contributors.md

@@ -1,22 +1,25 @@
 # Contributors
 
 [anndata graph](https://github.com/scverse/anndata/graphs/contributors>) | [scanpy graph](https://github.com/scverse/scanpy/graphs/contributors)| ☀ = maintainer
+
 ## Current developers
 
-- [Isaac Virshup](https://github.com/ivirshup), lead developer since 2019 ☀
-- [Gökcen Eraslan](https://twitter.com/gokcen), developer, diverse contributions ☀
-- [Sergei Rybakov](https://github.com/Koncopd), developer, diverse contributions ☀
-- [Fidel Ramirez](https://github.com/fidelram) developer, plotting ☀
-- [Giovanni Palla](https://twitter.com/g_palla1), developer, spatial data
-- [Malte Luecken](https://twitter.com/MDLuecken), developer, community & forum
+- [Philipp Angerer](https://github.com/flying-sheep), lead developer since 2023, software quality, initial anndata conception ☀
+- [Ilan Gold](https://github.com/ilan-gold), developer, Dask ☀
+- [Severin Dicks](https://github.com/SeverinDicks), developer, performance ☀
 - [Lukas Heumos](https://twitter.com/LukasHeumos), developer, diverse contributions
-- [Philipp Angerer](https://github.com/flying-sheep), developer, software quality, initial anndata conception ☀
 
 ## Other roles
 
+- [Isaac Virshup](https://github.com/ivirshup), lead developer 2019-2023
 - [Alex Wolf](https://twitter.com/falexwolf): lead developer 2016-2019, initial anndata & scanpy conception
 - [Fabian Theis](https://twitter.com/fabian_theis) & lab: enabling guidance, support and environment
 
 ## Former developers
 
-- Tom White: developer 2018-2019, distributed computing
+- [Tom White](https://github.com/tomwhite): developer 2018-2019, distributed computing
+- [Gökcen Eraslan](https://twitter.com/gokcen), developer, diverse contributions
+- [Sergei Rybakov](https://github.com/Koncopd), developer, diverse contributions
+- [Fidel Ramirez](https://github.com/fidelram) developer, plotting
+- [Giovanni Palla](https://twitter.com/g_palla1), developer, spatial data
+- [Malte Luecken](https://twitter.com/MDLuecken), developer, community & forum

docs/dev/code.md

@@ -9,6 +9,7 @@
 5. {ref}`Make sure all tests are passing <tests>`
 6. {ref}`Build and visually check any changed documentation <building-the-docs>`
 7. {ref}`Open a PR back to the main repository <open-a-pr>`
+8. {ref}`Add a release note to your PR <adding-to-the-docs>`
 
 ## Code style
 

docs/dev/documentation.md

@@ -12,10 +12,12 @@ Sometimes these caches are not invalidated when you've updated the docs.
 If docs are not updating the way you expect, first try "force reloading" your browser page – e.g. reload the page without using the cache.
 Next, if problems persist, clear the sphinx cache (`hatch run docs:clean`) and try building them again.
 
+(adding-to-the-docs)=
+
 ## Adding to the docs
 
 For any user-visible changes, please make sure a note has been added to the release notes using [`hatch run towncrier:create`][towncrier create].
-We recommend waiting on this until your PR is close to done since this can often causes merge conflicts.
+When asked for “Issue number (`+` if none)”, enter the *PR number* instead.
 
 Once you've added a new function to the documentation, you'll need to make sure there is a link somewhere in the documentation site pointing to it.
 This should be added to `docs/api.md` under a relevant heading.

docs/extensions/param_police.py

@@ -37,7 +37,8 @@ def show_param_warnings(app, exception):
             line,
         )
     if param_warnings:
-        raise RuntimeError("Encountered text parameter type. Use annotations.")
+        msg = "Encountered text parameter type. Use annotations."
+        raise RuntimeError(msg)
 
 
 def setup(app: Sphinx):

docs/release-notes/1.11.0.md

@@ -0,0 +1,38 @@
+(v1.11.0)=
+### 1.11.0rc1 {small}`2024-12-20`
+
+### Features
+
+- {func}`~scanpy.pp.sample` supports both upsampling and downsampling of observations and variables. {func}`~scanpy.pp.subsample` is now deprecated. {smaller}`G Eraslan & P Angerer` ({pr}`943`)
+- Add `layer` argument to {func}`scanpy.tl.score_genes` and {func}`scanpy.tl.score_genes_cell_cycle` {smaller}`L Zappia` ({pr}`2921`)
+- Prevent `raw` conflict with `layer` in {func}`~scanpy.tl.score_genes` {smaller}`S Dicks` ({pr}`3155`)
+- Add support for `median` as an aggregation function to {func}`~scanpy.get.aggregate`. This allows for median-based aggregation of data (e.g., pseudobulk), complementing existing methods like mean- and sum-based aggregation {smaller}`M Dehkordi (Farhad)` ({pr}`3180`)
+- Add `key_added` argument to {func}`~scanpy.pp.pca`, {func}`~scanpy.tl.tsne` and {func}`~scanpy.tl.umap` {smaller}`P Angerer` ({pr}`3184`)
+- Support running {func}`scanpy.pp.pca` on sparse Dask arrays with the `'covariance_eigh'` solver {smaller}`P Angerer` ({pr}`3263`)
+- Use upstreamed {class}`~sklearn.decomposition.PCA` implementation for {class}`~scipy.sparse.csr_array` and {class}`~scipy.sparse.csr_matrix` (see scikit-learn {ref}`sklearn:changes_1_4`) {smaller}`P Angerer` ({pr}`3267`)
+- Add explicit support to {func}`scanpy.pp.pca` for `svd_solver='covariance_eigh'` {smaller}`P Angerer` ({pr}`3296`)
+- Add support for {class}`dask.array.Array` to {func}`scanpy.pp.calculate_qc_metrics` {smaller}`I Gold` ({pr}`3307`)
+- Support `layer` parameter in {func}`scanpy.pl.highest_expr_genes` {smaller}`P Angerer` ({pr}`3324`)
+- Run numba functions single-threaded when called from inside of a {class}`~multiprocessing.pool.ThreadPool` {smaller}`P Angerer` ({pr}`3335`)
+- Switch {func}`~scanpy.logging.print_header` and {func}`~scanpy.logging.print_versions` to {mod}`session_info2` {smaller}`P Angerer` ({pr}`3384`)
+- Add sampling probabilities/mask parameter `p` to {func}`~scanpy.pp.sample` {smaller}`P Angerer` ({pr}`3410`)
+
+### Performance
+
+- Speed up {func}`~scanpy.pp.regress_out` {smaller}`P Ashish, P Angerer & S Dicks` ({pr}`3284`)
+
+### Documentation
+
+- Improve {func}`~scanpy.external.pp.harmony_integrate` docs {smaller}`D Kühl` ({pr}`3362`)
+- Raise {exc}`FutureWarning` when calling deprecated {mod}`scanpy.pp` functions {smaller}`P Angerer` ({pr}`3380`)
+- | Deprecate … | in favor of … |
+  | --- | --- |
+  | {func}`scanpy.read_visium` | {func}`squidpy.read.visium` |
+  | {func}`scanpy.datasets.visium_sge` | {func}`squidpy.datasets.visium` |
+  | {func}`scanpy.pl.spatial` | {func}`squidpy.pl.spatial_scatter` |
+
+  {smaller}`P Angerer` ({pr}`3407`)
+
+### Bug fixes
+
+- Upper-bound {mod}`sklearn` `<1.6.0` due to {issue}`dask/dask-ml#1002` {smaller}`Ilan Gold` ({pr}`3393`)

docs/release-notes/1.5.0.md

@@ -5,7 +5,7 @@ The `1.5.0` release adds a lot of new functionality, much of which takes advanta
 
 #### Spatial data support
 
-- Basic analysis {doc}`/tutorials/spatial/basic-analysis` and integration with single cell data {doc}`/tutorials/spatial/integration-scanorama` {smaller}`G Palla`
+- Tutorials for basic analysis and integration with single cell data {smaller}`G Palla`
 - {func}`~scanpy.read_visium` read 10x Visium data {pr}`1034` {smaller}`G Palla, P Angerer, I Virshup`
 - {func}`~scanpy.datasets.visium_sge` load Visium data directly from 10x Genomics {pr}`1013` {smaller}`M Mirkazemi, G Palla, P Angerer`
 - {func}`~scanpy.pl.spatial` plot spatial data {pr}`1012` {smaller}`G Palla, P Angerer`

docs/release-notes/3418.doc.md

@@ -0,0 +1 @@
+Fix reference in {mod}`scanpy.pp` page {smaller}`D Kazemi`

docs/release-notes/3426.bugfix.md

@@ -0,0 +1 @@
+Fix {func}`~scanpy.tl.rank_genes_groups` compatibility with data >10M cells {smaller}`P Angerer`

docs/release-notes/3428.bugfix.md

@@ -0,0 +1 @@
+Fix {func}`scanpy.pl.rank_genes_groups`’s `ax` parameter {smaller}`P Angerer`

docs/release-notes/3441.dev.md

@@ -0,0 +1 @@
+Fix version number inference in development environments (CI and local) {smaller}`P Angerer`