Merge branch 'main' of https://github.com/sanchit-misra/scanpy into s…

…cale-mean-variance

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -1,8 +1,8 @@
 name: Bug report
 description: Scanpy doesn’t do what it should? Please help us fix it!
 #title: ...
+type: Bug
 labels:
-- Bug 🐛
 - Triage 🩺
 #assignees: []
 body:

.github/ISSUE_TEMPLATE/config.yml

@@ -1,4 +1,4 @@
-blank_issues_enabled: true
+blank_issues_enabled: false
 contact_links:
   - name: Scanpy Community Forum
     url: https://discourse.scverse.org/

.github/ISSUE_TEMPLATE/enhancement-request.yml

@@ -1,8 +1,8 @@
 name: Enhancement request
 description: Anything you’d like to see in scanpy?
 #title: ...
+type: Enhancement
 labels:
-- Enhancement ✨
 - Triage 🩺
 #assignees: []
 body:
@@ -14,6 +14,7 @@ body:
     - 'Additional function parameters / changed functionality / changed defaults?'
     - 'New analysis tool: A simple analysis tool you have been using and are missing in `sc.tools`?'
     - 'New plotting function: A kind of plot you would like to seein `sc.pl`?'
+    - 'Improved documentation or error message?'
     - 'Other?'
   validations:
     required: true

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.7.4
+    rev: v0.8.2
     hooks:
     -   id: ruff
         types_or: [python, pyi, jupyter]

ci/scripts/min-deps.py

@@ -12,6 +12,7 @@
 import sys
 from collections import deque
 from contextlib import ExitStack
+from functools import cached_property
 from pathlib import Path
 from typing import TYPE_CHECKING
 
@@ -25,6 +26,8 @@
 
 if TYPE_CHECKING:
     from collections.abc import Generator, Iterable, Sequence
+    from collections.abc import Set as AbstractSet
+    from typing import Any, Self
 
 
 def min_dep(req: Requirement) -> Requirement:
@@ -77,48 +80,86 @@ def extract_min_deps(
 
 
 class Args(argparse.Namespace):
-    path: Path
+    """\
+    Parse a pyproject.toml file and output a list of minimum dependencies.
+    Output is optimized for `[uv] pip install` (see `-o`/`--output` for details).
+    """
+
+    _path: Path
     output: Path | None
-    extras: list[str]
+    _extras: list[str]
+    _all_extras: bool
+
+    @classmethod
+    def parse(cls, argv: Sequence[str] | None = None) -> Self:
+        return cls.parser().parse_args(argv, cls())
+
+    @classmethod
+    def parser(cls) -> argparse.ArgumentParser:
+        parser = argparse.ArgumentParser(
+            prog="min-deps",
+            description=cls.__doc__,
+            usage="pip install `python min-deps.py pyproject.toml`",
+        )
+        parser.add_argument(
+            "_path",
+            metavar="pyproject.toml",
+            type=Path,
+            help="Path to pyproject.toml to parse minimum dependencies from",
+        )
+        parser.add_argument(
+            "--extras",
+            dest="_extras",
+            metavar="EXTRA",
+            type=str,
+            nargs="*",
+            default=(),
+            help="extras to install",
+        )
+        parser.add_argument(
+            "--all-extras",
+            dest="_all_extras",
+            action="store_true",
+            help="get all extras",
+        )
+        parser.add_argument(
+            *("--output", "-o"),
+            metavar="FILE",
+            type=Path,
+            default=None,
+            help=(
+                "output file (default: stdout). "
+                "Without this option, output is space-separated for direct passing to `pip install`. "
+                "With this option, output written to a file newline-separated file usable as `requirements.txt` or `constraints.txt`."
+            ),
+        )
+        return parser
+
+    @cached_property
+    def pyproject(self) -> dict[str, Any]:
+        return tomllib.loads(self._path.read_text())
+
+    @cached_property
+    def extras(self) -> AbstractSet[str]:
+        if self._extras:
+            if self._all_extras:
+                sys.exit("Cannot specify both --extras and --all-extras")
+            return dict.fromkeys(self._extras).keys()
+        if not self._all_extras:
+            return set()
+        return self.pyproject["project"]["optional-dependencies"].keys()
 
 
 def main(argv: Sequence[str] | None = None) -> None:
-    parser = argparse.ArgumentParser(
-        prog="min-deps",
-        description=(
-            "Parse a pyproject.toml file and output a list of minimum dependencies. "
-            "Output is optimized for `[uv] pip install` (see `-o`/`--output` for details)."
-        ),
-        usage="pip install `python min-deps.py pyproject.toml`",
-    )
-    parser.add_argument(
-        "path", type=Path, help="pyproject.toml to parse minimum dependencies from"
-    )
-    parser.add_argument(
-        "--extras", type=str, nargs="*", default=(), help="extras to install"
-    )
-    parser.add_argument(
-        *("--output", "-o"),
-        type=Path,
-        default=None,
-        help=(
-            "output file (default: stdout). "
-            "Without this option, output is space-separated for direct passing to `pip install`. "
-            "With this option, output written to a file newline-separated file usable as `requirements.txt` or `constraints.txt`."
-        ),
-    )
-
-    args = parser.parse_args(argv, Args())
-
-    pyproject = tomllib.loads(args.path.read_text())
+    args = Args.parse(argv)
 
-    project_name = pyproject["project"]["name"]
+    project_name = args.pyproject["project"]["name"]
     deps = [
-        *map(Requirement, pyproject["project"]["dependencies"]),
+        *map(Requirement, args.pyproject["project"]["dependencies"]),
         *(Requirement(f"{project_name}[{extra}]") for extra in args.extras),
     ]
 
-    min_deps = extract_min_deps(deps, pyproject=pyproject)
+    min_deps = extract_min_deps(deps, pyproject=args.pyproject)
 
     sep = "\n" if args.output else " "
     with ExitStack() as stack:

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
 ```
 

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),
 )
 

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 the `Aggregation` class in `scanpy.get._aggregated.py`. 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 {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 {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 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/tutorials/index.md

@@ -37,19 +37,6 @@ trajectories/index
 
 ## Spatial data
 
-```{seealso}
-For more up-to-date tutorials on working with spatial data, see:
-
-* [SquidPy tutorials](https://squidpy.readthedocs.io/en/stable/notebooks/tutorials/index.html)
-* [SpatialData tutorials](https://spatialdata.scverse.org/en/latest/tutorials/notebooks/notebooks.html)
-* [Scverse ecosystem spatial tutorials](https://scverse.org/learn/)
-```
-
-```{toctree}
-:maxdepth: 2
-
-spatial/index
-```
 
 ## Experimental
 
@@ -64,3 +51,12 @@ experimental/index
 A number of older tutorials can be found at:
 
 * The [`scanpy_usage`](https://github.com/scverse/scanpy_usage) repository
+
+```{seealso}
+Scanpy used to have tutorials for its (now deprecated) spatial data functionality.x
+For up-to-date tutorials on working with spatial data, see:
+
+* SquidPy {doc}`squidpy:notebooks/tutorials/index`
+* [SpatialData tutorials](https://spatialdata.scverse.org/en/latest/tutorials/notebooks/notebooks.html)
+* [Scverse ecosystem spatial tutorials](https://scverse.org/learn/)
+```

hatch.toml

@@ -22,7 +22,7 @@ overrides.matrix.deps.env-vars = [
     { if = ["min"], key = "UV_CONSTRAINT", value = "ci/scanpy-min-deps.txt" },
 ]
 overrides.matrix.deps.pre-install-commands = [
-    { if = ["min"], value = "uv run ci/scripts/min-deps.py pyproject.toml -o ci/scanpy-min-deps.txt" },
+    { if = ["min"], value = "uv run ci/scripts/min-deps.py pyproject.toml --all-extras -o ci/scanpy-min-deps.txt" },
 ]
 overrides.matrix.deps.python = [
     { if = ["min"], value = "3.10" },

pyproject.toml

@@ -47,25 +47,26 @@ classifiers = [
 ]
 dependencies = [
     "anndata>=0.8",
-    "numpy>=1.23",
+    "numpy>=1.24",
     "matplotlib>=3.6",
     "pandas >=1.5",
     "scipy>=1.8",
     "seaborn>=0.13",
     "h5py>=3.7",
     "tqdm",
-    "scikit-learn>=1.1",
+    "scikit-learn>=1.1,<1.6.0",
     "statsmodels>=0.13",
     "patsy!=1.0.0", # https://github.com/pydata/patsy/issues/215
     "networkx>=2.7",
     "natsort",
     "joblib",
-    "numba>=0.56",
+    "numba>=0.57",
     "umap-learn>=0.5,!=0.5.0",
     "pynndescent>=0.5",
     "packaging>=21.3",
-    "session-info",
+    "session-info2",
     "legacy-api-wrap>=1.4",  # for positional API deprecations
+    "typing-extensions; python_version < '3.13'",
 ]
 dynamic = ["version"]