Merge branch 'main' into session-info2

.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:

docs/release-notes/3393.bugfix.md

@@ -0,0 +1 @@
+Upper-bound {mod}`sklearn` `<1.6.0` due to {issue}`dask/dask-ml#1002` {smaller}`Ilan Gold`

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

@@ -54,7 +54,7 @@ dependencies = [
     "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",

src/scanpy/_settings.py

@@ -82,9 +82,7 @@ def _type_check(var: Any, varname: str, types: type | tuple[type, ...]):
         possible_types_str = types.__name__
     else:
         type_names = [t.__name__ for t in types]
-        possible_types_str = "{} or {}".format(
-            ", ".join(type_names[:-1]), type_names[-1]
-        )
+        possible_types_str = f"{', '.join(type_names[:-1])} or {type_names[-1]}"
     raise TypeError(f"{varname} must be of type {possible_types_str}")
 
 

src/scanpy/external/exporting.py

@@ -345,8 +345,8 @@ def _write_color_tracks(ctracks, fname):
 
 
 def _frac_to_hex(frac):
-    rgb = tuple(np.array(np.array(plt.cm.jet(frac)[:3]) * 255, dtype=int))
-    return "#{:02x}{:02x}{:02x}".format(*rgb)
+    r, g, b = tuple(np.array(np.array(plt.cm.jet(frac)[:3]) * 255, dtype=int))
+    return f"#{r:02x}{g:02x}{b:02x}"
 
 
 def _get_color_stats_genes(color_stats, E, gene_list):

src/scanpy/external/tl/_phenograph.py

@@ -244,8 +244,8 @@ def phenograph(
     comm_key = (
         f"pheno_{clustering_algo}" if clustering_algo in ["louvain", "leiden"] else ""
     )
-    ig_key = "pheno_{}_ig".format("jaccard" if jaccard else "gaussian")
-    q_key = "pheno_{}_q".format("jaccard" if jaccard else "gaussian")
+    ig_key = f"pheno_{'jaccard' if jaccard else 'gaussian'}_ig"
+    q_key = f"pheno_{'jaccard' if jaccard else 'gaussian'}_q"
 
     communities, graph, Q = phenograph.cluster(
         data=data,

src/scanpy/plotting/_tools/paga.py

@@ -702,11 +702,11 @@ def _paga_graph(
         and isinstance(node_labels, str)
         and node_labels != adata.uns["paga"]["groups"]
     ):
-        raise ValueError(
-            "Provide a list of group labels for the PAGA groups {}, not {}.".format(
-                adata.uns["paga"]["groups"], node_labels
-            )
+        msg = (
+            "Provide a list of group labels for the PAGA groups "
+            f"{adata.uns['paga']['groups']}, not {node_labels}."
         )
+        raise ValueError(msg)
     groups_key = adata.uns["paga"]["groups"]
     if node_labels is None:
         node_labels = adata.obs[groups_key].cat.categories

src/scanpy/preprocessing/_qc.py

@@ -194,26 +194,21 @@ def describe_var(
         if issparse(X):
             X.eliminate_zeros()
     var_metrics = pd.DataFrame(index=adata.var_names)
-    var_metrics["n_cells_by_{expr_type}"], var_metrics["mean_{expr_type}"] = (
+    var_metrics[f"n_cells_by_{expr_type}"], var_metrics[f"mean_{expr_type}"] = (
         materialize_as_ndarray((axis_nnz(X, axis=0), _get_mean_var(X, axis=0)[0]))
     )
     if log1p:
-        var_metrics["log1p_mean_{expr_type}"] = np.log1p(
-            var_metrics["mean_{expr_type}"]
+        var_metrics[f"log1p_mean_{expr_type}"] = np.log1p(
+            var_metrics[f"mean_{expr_type}"]
         )
-    var_metrics["pct_dropout_by_{expr_type}"] = (
-        1 - var_metrics["n_cells_by_{expr_type}"] / X.shape[0]
+    var_metrics[f"pct_dropout_by_{expr_type}"] = (
+        1 - var_metrics[f"n_cells_by_{expr_type}"] / X.shape[0]
     ) * 100
-    var_metrics["total_{expr_type}"] = np.ravel(axis_sum(X, axis=0))
+    var_metrics[f"total_{expr_type}"] = np.ravel(axis_sum(X, axis=0))
     if log1p:
-        var_metrics["log1p_total_{expr_type}"] = np.log1p(
-            var_metrics["total_{expr_type}"]
+        var_metrics[f"log1p_total_{expr_type}"] = np.log1p(
+            var_metrics[f"total_{expr_type}"]
         )
-    # Relabel
-    new_colnames = []
-    for col in var_metrics.columns:
-        new_colnames.append(col.format(**locals()))
-    var_metrics.columns = new_colnames
     if inplace:
         adata.var[var_metrics.columns] = var_metrics
         return None

src/scanpy/tools/_rank_genes_groups.py

@@ -124,10 +124,11 @@ def __init__(
         )
 
         if len(invalid_groups_selected) > 0:
-            raise ValueError(
-                "Could not calculate statistics for groups {} since they only "
-                "contain one sample.".format(", ".join(invalid_groups_selected))
+            msg = (
+                f"Could not calculate statistics for groups {', '.join(invalid_groups_selected)} "
+                "since they only contain one sample."
             )
+            raise ValueError(msg)
 
         adata_comp = adata
         if layer is not None:

tests/notebooks/test_paga_paul15_subsampled.py

@@ -138,6 +138,6 @@ def test_paga_paul15_subsampled(image_comparer, plt):
             show=False,
         )
         # add a test for this at some point
-        # data.to_csv('./write/paga_path_{}.csv'.format(descr))
+        # data.to_csv(f"./write/paga_path_{descr}.csv")
 
     save_and_compare_images("paga_path")