Add RUF lints (#3582)

Author: flying-sheep

benchmarks/benchmarks/preprocessing_counts.py

@@ -81,7 +81,7 @@ class FastSuite:
         ["pbmc3k", "pbmc68k_reduced", "bmmc", "lung93k"],
         ["counts", "counts-off-axis"],
     )
-    param_names = ["dataset", "layer"]
+    param_names = ("dataset", "layer")
 
     def time_calculate_qc_metrics(self, *_):
         sc.pp.calculate_qc_metrics(

benchmarks/benchmarks/preprocessing_log.py

@@ -84,7 +84,7 @@ class FastSuite:
         ["pbmc3k", "pbmc68k_reduced", "bmmc", "lung93k"],
         [None, "off-axis"],
     )
-    param_names = ["dataset", "layer"]
+    param_names = ("dataset", "layer")
 
     def time_mean_var(self, *_):
         _get_mean_var(adata.X)

pyproject.toml

@@ -243,7 +243,7 @@ select = [
     "PT",     # Pytest style
     "PTH",    # Pathlib instead of os.path
     "PYI",    # Typing
-    "RUF100", # Unused noqa
+    "RUF",    # Miscellaneous Ruff-only lints
     "SIM",    # Simplify control flow
     "TC",     # Manage type checking blocks
     "UP",     # Update legacy syntax
@@ -252,27 +252,18 @@ select = [
 ]
 external = [ "PLR0917" ] # preview lint that we use
 ignore = [
-    # dict() syntax is preferrable when creating dicts for kwargs
-    "C408",
-    # E266 too many leading '#' for block comment -> Scanpy allows them for comments into sections
-    "E262",
-    # module level import not at top of file -> required to circumvent circular imports for Scanpys API
-    "E402",
-    # line too long -> we accept long comment lines; black gets rid of long code lines
-    "E501",
-    # allow I, O, l as variable names -> I is the identity matrix, i, j, k, l is reasonable indexing notation
-    "E741",
-    # We ban blank lines before docstrings instead of the opposite
-    "D203",
-    # We want multiline summaries to start on the first line, not the second
-    "D213",
-    # TODO: replace our current param docs reuse with this and remove it here:
-    "D417",
-    # Numbers like “2” aren’t that “magic”.
-    "PLR2004",
-    # `Literal["..."] | str` is useful for autocompletion
-    "PYI051",
+    "C408",    # dict() syntax is preferrable when creating dicts for kwargs
+    "E262",    # E266 too many leading '#' for block comment -> Scanpy allows them for comments into sections
+    "E402",    # module level import not at top of file -> required to circumvent circular imports for Scanpys API
+    "E501",    # line too long -> we accept long comment lines; black gets rid of long code lines
+    "E741",    # allow I, O, l as variable names -> I is the identity matrix, i, j, k, l is reasonable indexing notation
+    "D203",    # We ban blank lines before docstrings instead of the opposite
+    "D213",    # We want multiline summaries to start on the first line, not the second
+    "D417",    # TODO: replace our current param docs reuse with this and remove it here:
+    "PLR2004", # Numbers like “2” aren’t that “magic”.
+    "PYI051",  # `Literal["..."] | str` is useful for autocompletion
 ]
+allowed-confusables = [ "×", "’", "–", "α" ]
 [tool.ruff.lint.per-file-ignores]
 # Do not assign a lambda expression, use a def
 "src/scanpy/tools/_rank_genes_groups.py" = [ "E731" ]

src/scanpy/__init__.py

@@ -60,9 +60,23 @@
 del sys, annotate_doc_types
 
 __all__ = [
-    "__version__",
     "AnnData",
+    "Neighbors",
+    "Verbosity",
+    "__version__",
     "concat",
+    "datasets",
+    "experimental",
+    "external",
+    "get",
+    "logging",
+    "metrics",
+    "pl",
+    "pp",
+    "queries",
+    "read",
+    "read_10x_h5",
+    "read_10x_mtx",
     "read_csv",
     "read_excel",
     "read_h5ad",
@@ -71,23 +85,9 @@
     "read_mtx",
     "read_text",
     "read_umi_tools",
-    "read",
-    "read_10x_h5",
-    "read_10x_mtx",
     "read_visium",
-    "write",
-    "datasets",
-    "experimental",
-    "external",
-    "get",
-    "logging",
-    "metrics",
-    "queries",
-    "pl",
-    "pp",
-    "tl",
-    "Verbosity",
-    "settings",
-    "Neighbors",
     "set_figure_params",
+    "settings",
+    "tl",
+    "write",
 ]

src/scanpy/_compat.py

@@ -49,13 +49,13 @@
 __all__ = [
     "DaskArray",
     "ZappyArray",
+    "_numba_threading_layer",
+    "deprecated",
     "fullname",
+    "njit",
+    "old_positionals",
     "pkg_metadata",
     "pkg_version",
-    "old_positionals",
-    "deprecated",
-    "njit",
-    "_numba_threading_layer",
 ]
 
 

src/scanpy/datasets/__init__.py

@@ -19,6 +19,7 @@
 __all__ = [
     "blobs",
     "burczynski06",
+    "ebi_expression_atlas",
     "krumsiek11",
     "moignard15",
     "paul15",
@@ -27,5 +28,4 @@
     "pbmc68k_reduced",
     "toggleswitch",
     "visium_sge",
-    "ebi_expression_atlas",
 ]

src/scanpy/external/exporting.py

@@ -22,7 +22,7 @@
 
     from anndata import AnnData
 
-__all__ = ["spring_project", "cellbrowser"]
+__all__ = ["cellbrowser", "spring_project"]
 
 
 @old_positionals(

src/scanpy/external/pl.py

@@ -7,8 +7,8 @@
 
 import matplotlib.pyplot as plt
 import numpy as np
-from anndata import AnnData  # noqa: TCH002
-from matplotlib.axes import Axes  # noqa: TCH002
+from anndata import AnnData  # noqa: TC002
+from matplotlib.axes import Axes  # noqa: TC002
 from sklearn.utils import deprecated
 
 from .._compat import old_positionals
@@ -30,10 +30,10 @@
 
 
 __all__ = [
-    "phate",
-    "trimap",
     "harmony_timeseries",
+    "phate",
     "sam",
+    "trimap",
     "wishbone_marker_trajectory",
 ]
 

src/scanpy/external/pp/_harmony_integrate.py

@@ -2,7 +2,7 @@
 
 from __future__ import annotations
 
-from collections.abc import Sequence  # noqa: TCH003
+from collections.abc import Sequence  # noqa: TC003
 from typing import TYPE_CHECKING
 
 import numpy as np

src/scanpy/external/tl/__init__.py

@@ -12,14 +12,14 @@
 from ._wishbone import wishbone
 
 __all__ = [
+    "cyclone",
     "harmony_timeseries",
     "palantir",
     "palantir_results",
     "phate",
     "phenograph",
-    "cyclone",
-    "sandbag",
     "sam",
+    "sandbag",
     "trimap",
     "wishbone",
 ]

src/scanpy/metrics/__init__.py

@@ -6,4 +6,4 @@
 from ._metrics import confusion_matrix
 from ._morans_i import morans_i
 
-__all__ = ["gearys_c", "morans_i", "confusion_matrix"]
+__all__ = ["confusion_matrix", "gearys_c", "morans_i"]

src/scanpy/metrics/_common.py

@@ -24,7 +24,7 @@
     _Vals = NDArray | SpBase | DaskArray | pd.DataFrame | pd.Series
 
 
-__all__ = ["_get_graph", "_SparseMetric"]
+__all__ = ["_SparseMetric", "_get_graph"]
 
 
 @dataclass

src/scanpy/neighbors/__init__.py

@@ -704,8 +704,8 @@ def _handle_transformer(
                 # Use defaults from UMAP’s `nearest_neighbors` function
                 kwds.update(
                     n_jobs=settings.n_jobs,
-                    n_trees=min(64, 5 + int(round((self._adata.n_obs) ** 0.5 / 20.0))),
-                    n_iters=max(5, int(round(np.log2(self._adata.n_obs)))),
+                    n_trees=min(64, 5 + round((self._adata.n_obs) ** 0.5 / 20.0)),
+                    n_iters=max(5, round(np.log2(self._adata.n_obs))),
                 )
             transformer = PyNNDescentTransformer(**kwds)
         elif transformer == "rapids":

src/scanpy/plotting/__init__.py

@@ -55,30 +55,30 @@
 from ._utils import matrix, timeseries, timeseries_as_heatmap, timeseries_subplot
 
 __all__ = [
-    "palettes",
+    "DotPlot",
+    "MatrixPlot",
+    "StackedViolin",
     "clustermap",
     "correlation_matrix",
     "dendrogram",
-    "heatmap",
-    "ranking",
-    "scatter",
-    "tracksplot",
-    "violin",
-    "DotPlot",
+    "diffmap",
     "dotplot",
-    "MatrixPlot",
-    "matrixplot",
-    "filter_genes_dispersion",
-    "highly_variable_genes",
-    "highest_expr_genes",
-    "set_rcParams_defaults",
-    "set_rcParams_scanpy",
-    "StackedViolin",
-    "stacked_violin",
-    "scrublet_score_distribution",
     "dpt_groups_pseudotime",
     "dpt_timeseries",
+    "draw_graph",
+    "embedding",
     "embedding_density",
+    "filter_genes_dispersion",
+    "heatmap",
+    "highest_expr_genes",
+    "highly_variable_genes",
+    "matrix",
+    "matrixplot",
+    "paga",
+    "paga_compare",
+    "paga_path",
+    "palettes",
+    "pca",
     "pca_loadings",
     "pca_overview",
     "pca_scatter",
@@ -90,19 +90,19 @@
     "rank_genes_groups_stacked_violin",
     "rank_genes_groups_tracksplot",
     "rank_genes_groups_violin",
+    "ranking",
+    "scatter",
+    "scrublet_score_distribution",
+    "set_rcParams_defaults",
+    "set_rcParams_scanpy",
     "sim",
-    "paga",
-    "paga_compare",
-    "paga_path",
-    "diffmap",
-    "draw_graph",
-    "embedding",
-    "pca",
     "spatial",
-    "tsne",
-    "umap",
-    "matrix",
+    "stacked_violin",
     "timeseries",
     "timeseries_as_heatmap",
     "timeseries_subplot",
+    "tracksplot",
+    "tsne",
+    "umap",
+    "violin",
 ]

src/scanpy/plotting/_anndata.py

@@ -4,7 +4,7 @@
 
 from collections import OrderedDict
 from collections.abc import Collection, Mapping, Sequence
-from itertools import product
+from itertools import pairwise, product
 from types import NoneType
 from typing import TYPE_CHECKING, NamedTuple, TypedDict, cast
 
@@ -885,7 +885,7 @@ def violin(  # noqa: PLR0912, PLR0913, PLR0915
         raise ValueError(msg)
 
     if groupby is not None:
-        obs_df = get.obs_df(adata, keys=[groupby] + keys, layer=layer, use_raw=use_raw)
+        obs_df = get.obs_df(adata, keys=[groupby, *keys], layer=layer, use_raw=use_raw)
         if kwds.get("palette") is None:
             if not isinstance(adata.obs[groupby].dtype, CategoricalDtype):
                 msg = (
@@ -1640,8 +1640,8 @@ def tracksplot(  # noqa: PLR0912, PLR0913, PLR0915
     # obtain the start and end of each category and make
     # a list of ranges that will be used to plot a different
     # color
-    cumsum = [0] + list(np.cumsum(obs_tidy.index.value_counts(sort=False)))
-    x_values = [(x, y) for x, y in zip(cumsum[:-1], cumsum[1:], strict=True)]
+    cumsum = [0, *np.cumsum(obs_tidy.index.value_counts(sort=False)).tolist()]
+    x_values = list(pairwise(cumsum))
 
     dendro_height = 1 if dendrogram else 0
 
@@ -2071,7 +2071,7 @@ def _prepare_dataframe(  # noqa: PLR0912
             # if not a list, turn into a list
             groupby = [groupby]
         for group in groupby:
-            if group not in list(adata.obs_keys()) + [adata.obs.index.name]:
+            if group not in [*adata.obs_keys(), adata.obs.index.name]:
                 if adata.obs.index.name is not None:
                     msg = f' or index name "{adata.obs.index.name}"'
                 else:

src/scanpy/plotting/_tools/__init__.py

@@ -1,5 +1,7 @@
 from __future__ import annotations
 
+import functools
+import operator
 from collections.abc import Mapping, Sequence
 from copy import copy
 from typing import TYPE_CHECKING
@@ -546,7 +548,9 @@ def _rank_genes_groups_plot(  # noqa: PLR0912, PLR0913, PLR0915
     if var_names is not None:
         if isinstance(var_names, Mapping):
             # get a single list of all gene names in the dictionary
-            var_names_list = sum([list(x) for x in var_names.values()], [])
+            var_names_list = functools.reduce(
+                operator.iadd, [list(x) for x in var_names.values()], []
+            )
         elif isinstance(var_names, str):
             var_names_list = [var_names]
         else:

src/scanpy/plotting/_tools/paga.py

@@ -982,14 +982,14 @@ def _paga_graph(  # noqa: PLR0912, PLR0913, PLR0915
 
             cumsum = np.cumsum(fracs)
             cumsum = cumsum / cumsum[-1]
-            cumsum = [0] + cumsum.tolist()
+            cumsum = [0, *cumsum.tolist()]
 
             for r1, r2, color in zip(
                 cumsum[:-1], cumsum[1:], color_single, strict=True
             ):
                 angles = np.linspace(2 * np.pi * r1, 2 * np.pi * r2, 20)
-                x = [0] + np.cos(angles).tolist()
-                y = [0] + np.sin(angles).tolist()
+                x = [0, *np.cos(angles).tolist()]
+                y = [0, *np.sin(angles).tolist()]
 
                 xy = np.column_stack([x, y])
                 s = np.abs(xy).max()