Fix pre-commit

pyproject.toml

@@ -86,7 +86,7 @@ filterwarnings = [
 [tool.ruff]
 src = ["src"]
 line-length = 120
-extent-include = ["*.ipynb"]
+extend-include = ["*.ipynb"]
 
 [tool.ruff.format]
 docstring-code-format = true

src/infercnvpy/io/_genepos.py

@@ -1,5 +1,5 @@
 from pathlib import Path
-from typing import Literal, Union
+from typing import Literal
 
 import gtfparse
 import numpy as np
@@ -9,13 +9,13 @@
 
 
 def genomic_position_from_gtf(
-    gtf_file: Union[Path, str],
-    adata: Union[AnnData, None] = None,
+    gtf_file: Path | str,
+    adata: AnnData | None = None,
     *,
     gtf_gene_id: Literal["gene_id", "gene_name"] = "gene_name",
-    adata_gene_id: Union[str, None] = None,
+    adata_gene_id: str | None = None,
     inplace: bool = True,
-) -> Union[pd.DataFrame, None]:
+) -> pd.DataFrame | None:
     """Get genomic gene positions from a GTF file.
 
     The GTF file needs to match the genome annotation used for your single cell dataset.

src/infercnvpy/io/_scevan.py

@@ -1,7 +1,6 @@
 """Read in result files from scevan."""
 
 from pathlib import Path
-from typing import Optional, Union
 
 import numpy as np
 import pandas as pd
@@ -26,14 +25,14 @@ def _get_chr_pos_from_array(chr_pos_array):
 
 def read_scevan(
     adata: AnnData,
-    scevan_res_dir: Union[str, Path],
-    scevan_res_table: Optional[Union[str, Path]] = None,
+    scevan_res_dir: str | Path,
+    scevan_res_table: str | Path | None = None,
     *,
     subclones: bool = True,
     inplace: bool = True,
     subset: bool = True,
     key_added: str = "scevan",
-) -> Optional[AnnData]:
+) -> AnnData | None:
     """Load results from SCEVAN :cite:`DeFalco2021` for downstream analysis with infercnvpy.
 
     Requires that the cell barcodes used for SCEVAN and `adata.obs_names` match,

src/infercnvpy/pl/_chromosome_heatmap.py

@@ -1,5 +1,3 @@
-from typing import Optional, Union
-
 import matplotlib.axes
 import numpy as np
 import pandas as pd
@@ -15,12 +13,12 @@ def chromosome_heatmap(
     *,
     groupby: str = "cnv_leiden",
     use_rep: str = "cnv",
-    cmap: Union[str, Colormap] = "bwr",
+    cmap: str | Colormap = "bwr",
     figsize: tuple[int, int] = (16, 10),
-    show: Optional[bool] = None,
-    save: Union[str, bool, None] = None,
+    show: bool | None = None,
+    save: str | bool | None = None,
     **kwargs,
-) -> Optional[dict[str, matplotlib.axes.Axes]]:
+) -> dict[str, matplotlib.axes.Axes] | None:
     """Plot a heatmap of smoothed gene expression by chromosome.
 
     Wrapper around :func:`scanpy.pl.heatmap`.
@@ -71,7 +69,7 @@ def chromosome_heatmap(
     kwargs["norm"] = TwoSlopeNorm(0, vmin=vmin, vmax=vmax)
 
     # add chromosome annotations
-    var_group_positions = list(zip(chr_pos, chr_pos[1:] + [tmp_adata.shape[1]]))
+    var_group_positions = list(zip(chr_pos, chr_pos[1:] + [tmp_adata.shape[1]], strict=False))
 
     return_ax_dic = sc.pl.heatmap(
         tmp_adata,
@@ -99,12 +97,12 @@ def chromosome_heatmap_summary(
     *,
     groupby: str = "cnv_leiden",
     use_rep: str = "cnv",
-    cmap: Union[str, Colormap] = "bwr",
+    cmap: str | Colormap = "bwr",
     figsize: tuple[int, int] = (16, 10),
-    show: Optional[bool] = None,
-    save: Union[str, bool, None] = None,
+    show: bool | None = None,
+    save: str | bool | None = None,
     **kwargs,
-) -> Optional[dict[str, matplotlib.axes.Axes]]:
+) -> dict[str, matplotlib.axes.Axes] | None:
     """Plot a heatmap of average of the smoothed gene expression by chromosome per category in groupby.
 
     Wrapper around :func:`scanpy.pl.heatmap`.
@@ -172,7 +170,7 @@ def _get_group_mean(group):
     kwargs["norm"] = TwoSlopeNorm(0, vmin=vmin, vmax=vmax)
 
     # add chromosome annotations
-    var_group_positions = list(zip(chr_pos, chr_pos[1:] + [tmp_adata.shape[1]]))
+    var_group_positions = list(zip(chr_pos, chr_pos[1:] + [tmp_adata.shape[1]], strict=False))
 
     return_ax_dic = sc.pl.heatmap(
         tmp_adata,

src/infercnvpy/tl/__init__.py

@@ -38,7 +38,7 @@ def pca(
     use_rep: str = "cnv",
     key_added: str = "cnv_pca",
     **kwargs,
-) -> Union[np.ndarray, None]:
+) -> np.ndarray | None:
     """Compute the PCA on the result of :func:`infercnvpy.tl.infercnv`.
 
     Thin wrapper around :func:`scanpy.pp.pca`.

src/infercnvpy/tl/_copykat.py

@@ -1,6 +1,5 @@
 import os
 from multiprocessing import cpu_count
-from typing import Optional
 
 import pandas as pd
 from anndata import AnnData
@@ -18,8 +17,8 @@ def copykat(
     min_genes_chr: int = 5,
     key_added: str = "cnv",
     inplace: bool = True,
-    layer: Optional[str] = None,
-    n_jobs: Optional[int] = None,
+    layer: str | None = None,
+    n_jobs: int | None = None,
     norm_cell_names: str = "",
     cell_line="no",
     window_size=25,
@@ -172,7 +171,7 @@ def copykat(
 
     if inplace:
         adata.uns[key_added] = chrom_pos
-        adata.obsm["X_%s" % key_added] = new_cpkat_trans
+        adata.obsm[f"X_{key_added}"] = new_cpkat_trans
         adata.obs[key_added] = copyKAT_pred
     else:
         return new_cpkat_trans, copyKAT_pred

src/infercnvpy/tl/_infercnv.py

@@ -2,7 +2,6 @@
 import re
 from collections.abc import Sequence
 from multiprocessing import cpu_count
-from typing import Union
 
 import numpy as np
 import scipy.ndimage
@@ -18,20 +17,20 @@
 def infercnv(
     adata: AnnData,
     *,
-    reference_key: Union[str, None] = None,
-    reference_cat: Union[None, str, Sequence[str]] = None,
-    reference: Union[np.ndarray, None] = None,
+    reference_key: str | None = None,
+    reference_cat: None | str | Sequence[str] = None,
+    reference: np.ndarray | None = None,
     lfc_clip: float = 3,
     window_size: int = 100,
     step: int = 10,
-    dynamic_threshold: Union[float, None] = 1.5,
-    exclude_chromosomes: Union[Sequence[str], None] = ("chrX", "chrY"),
+    dynamic_threshold: float | None = 1.5,
+    exclude_chromosomes: Sequence[str] | None = ("chrX", "chrY"),
     chunksize: int = 5000,
-    n_jobs: Union[int, None] = None,
+    n_jobs: int | None = None,
     inplace: bool = True,
-    layer: Union[str, None] = None,
+    layer: str | None = None,
     key_added: str = "cnv",
-) -> Union[None, tuple[dict, scipy.sparse.csr_matrix]]:
+) -> None | tuple[dict, scipy.sparse.csr_matrix]:
     """Infer Copy Number Variation (CNV) by averaging gene expression over genomic regions.
 
     This method is heavily inspired by `infercnv <https://github.com/broadinstitute/inferCNV/>`_
@@ -121,7 +120,8 @@ def infercnv(
             itertools.repeat(dynamic_threshold),
             tqdm_class=tqdm,
             max_workers=cpu_count() if n_jobs is None else n_jobs,
-        )
+        ),
+        strict=False,
     )
     res = scipy.sparse.vstack(chunks)
 
@@ -148,7 +148,7 @@ def alphanum_key(key):
     return sorted(l, key=alphanum_key)
 
 
-def _running_mean(x: Union[np.ndarray, scipy.sparse.spmatrix], n: int = 50, step: int = 10) -> np.ndarray:
+def _running_mean(x: np.ndarray | scipy.sparse.spmatrix, n: int = 50, step: int = 10) -> np.ndarray:
     """Compute a pyramidially weighted running mean.
 
     Densifies the matrix. Use `step` and `chunksize` to save memory.
@@ -213,16 +213,16 @@ def _running_mean_for_chromosome(chr):
 
     running_means = [_running_mean_for_chromosome(chr) for chr in chromosomes]
 
-    chr_start_pos = dict(zip(chromosomes, np.cumsum([0] + [x.shape[1] for x in running_means])))
+    chr_start_pos = dict(zip(chromosomes, np.cumsum([0] + [x.shape[1] for x in running_means]), strict=False))
 
     return chr_start_pos, np.hstack(running_means)
 
 
 def _get_reference(
     adata: AnnData,
-    reference_key: Union[str, None],
-    reference_cat: Union[None, str, Sequence[str]],
-    reference: Union[np.ndarray, None],
+    reference_key: str | None,
+    reference_cat: None | str | Sequence[str],
+    reference: np.ndarray | None,
 ) -> np.ndarray:
     """Parameter validation extraction of reference gene expression.
 

src/infercnvpy/tl/_scores.py

@@ -2,7 +2,7 @@
 
 import warnings
 from collections.abc import Mapping
-from typing import Any, Optional
+from typing import Any
 
 import numpy as np
 import scipy.sparse as sp
@@ -19,7 +19,7 @@ def cnv_score(
     key_added: str = "cnv_score",
     inplace: bool = True,
     obs_key=None,
-) -> Optional[Mapping[Any, np.number]]:
+) -> Mapping[Any, np.number] | None:
     """Assign each cnv cluster a CNV score.
 
     Clusters with a high score are likely affected by copy number abberations.
@@ -78,11 +78,11 @@ def ithgex(
     adata: AnnData,
     groupby: str,
     *,
-    use_raw: Optional[bool] = None,
-    layer: Optional[str] = None,
+    use_raw: bool | None = None,
+    layer: str | None = None,
     inplace: bool = True,
     key_added: str = "ithgex",
-) -> Optional[Mapping[str, float]]:
+) -> Mapping[str, float] | None:
     """Compute the ITHGEX diversity score based on gene expression cite:`Wu2021`.
 
     A high score indicates a high diversity of gene expression profiles of cells
@@ -158,7 +158,7 @@ def ithcna(
     use_rep: str = "X_cnv",
     key_added: str = "ithcna",
     inplace: bool = True,
-) -> Optional[Mapping[str, float]]:
+) -> Mapping[str, float] | None:
     """Compute the ITHCNA diversity score based on copy number variation :cite:`Wu2021`.
 
     A high score indicates a high diversity of CNV profiles of cells