[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

docs/_ext/edit_on_github.py

@@ -20,7 +20,7 @@ def get_github_repo(app: Sphinx, path: str) -> str:
 
 
 def _html_page_context(
-    app: Sphinx, _pagename: str, templatename: str, context: dict[str, Any], doctree: Optional[Any]
+    app: Sphinx, _pagename: str, templatename: str, context: dict[str, Any], doctree: Any | None
 ) -> None:
     # doctree is None - otherwise viewcode fails
     if templatename != "page.html" or doctree is None:

ehrapy/_utils_doc.py

@@ -1,9 +1,10 @@
 import inspect
+from collections.abc import Callable
 from textwrap import dedent
-from typing import Callable, Optional, Union
+from typing import Optional, Union
 
 
-def getdoc(c_or_f: Union[Callable, type]) -> Optional[str]:  # pragma: no cover
+def getdoc(c_or_f: Callable | type) -> str | None:  # pragma: no cover
     if getattr(c_or_f, "__doc__", None) is None:
         return None
     doc = inspect.getdoc(c_or_f)

ehrapy/data/_datasets.py

@@ -743,7 +743,7 @@ def synthea_1k_sample(
 
     df = anndata_to_df(adata)
     df.drop(
-        columns=[col for col in df.columns if any(isinstance(x, (list, dict)) for x in df[col].dropna())], inplace=True
+        columns=[col for col in df.columns if any(isinstance(x, list | dict) for x in df[col].dropna())], inplace=True
     )
     df.drop(columns=df.columns[df.isna().all()], inplace=True)
     adata = df_to_anndata(df, index_column="id")

ehrapy/plot/_scanpy_pl_api.py

@@ -1,10 +1,10 @@
 from __future__ import annotations
 
-from collections.abc import Collection, Iterable, Mapping, Sequence
+from collections.abc import Callable, Collection, Iterable, Mapping, Sequence
 from enum import Enum
 from functools import partial
 from types import MappingProxyType
-from typing import TYPE_CHECKING, Any, Callable, Literal, Union
+from typing import TYPE_CHECKING, Any, Literal, Union
 
 import scanpy as sc
 from scanpy.plotting import DotPlot, MatrixPlot, StackedViolin

ehrapy/preprocessing/_encoding.py

@@ -73,7 +73,7 @@ def encode(
 
     if isinstance(encodings, str) and not autodetect:
         raise ValueError("Passing a string for parameter encodings is only possible when using autodetect=True!")
-    elif autodetect and not isinstance(encodings, (str, type(None))):
+    elif autodetect and not isinstance(encodings, str | type(None)):
         raise ValueError(
             f"Setting encode mode with autodetect=True only works by passing a string (encode mode name) or None not {type(encodings)}!"
         )

ehrapy/preprocessing/_imputation.py

@@ -63,7 +63,7 @@ def explicit_impute(
         _warn_imputation_threshold(adata, var_names=replacement.keys(), threshold=warning_threshold)  # type: ignore
 
     # 1: Replace all missing values with the specified value
-    if isinstance(replacement, (int, str)):
+    if isinstance(replacement, int | str):
         _replace_explicit(adata.X, replacement, impute_empty_strings)
 
     # 2: Replace all missing values in a subset of columns with a specified value per column or a default value, when the column is not explicitly named

ehrapy/preprocessing/_normalization.py

@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Callable
+from typing import TYPE_CHECKING
 
 import numpy as np
 import sklearn.preprocessing as sklearn_pp
@@ -20,7 +20,7 @@
 )
 
 if TYPE_CHECKING:
-    from collections.abc import Sequence
+    from collections.abc import Callable, Sequence
 
     import pandas as pd
     from anndata import AnnData

ehrapy/preprocessing/_scanpy_pp_api.py

@@ -1,7 +1,8 @@
 from __future__ import annotations
 
+from collections.abc import Callable
 from types import MappingProxyType
-from typing import TYPE_CHECKING, Any, Callable, Literal, Union
+from typing import TYPE_CHECKING, Any, Literal, Union
 
 import numpy as np
 import scanpy as sc

ehrapy/tools/_scanpy_tl_api.py

@@ -14,16 +14,16 @@
 
 def tsne(
     adata: AnnData,
-    n_pcs: Optional[int] = None,
-    use_rep: Optional[str] = None,
-    perplexity: Union[float, int] = 30,
-    early_exaggeration: Union[float, int] = 12,
-    learning_rate: Union[float, int] = 1000,
+    n_pcs: int | None = None,
+    use_rep: str | None = None,
+    perplexity: float | int = 30,
+    early_exaggeration: float | int = 12,
+    learning_rate: float | int = 1000,
     random_state: AnyRandom = 0,
-    n_jobs: Optional[int] = None,
+    n_jobs: int | None = None,
     copy: bool = False,
     metric: str = "euclidean",
-) -> Optional[AnnData]:  # pragma: no cover
+) -> AnnData | None:  # pragma: no cover
     """Calculates t-SNE [Maaten08]_ [Amir13]_ [Pedregosa11]_.
 
     t-distributed stochastic neighborhood embedding (tSNE) [Maaten08]_ has been
@@ -83,18 +83,18 @@ def umap(
     min_dist: float = 0.5,
     spread: float = 1.0,
     n_components: int = 2,
-    maxiter: Optional[int] = None,
+    maxiter: int | None = None,
     alpha: float = 1.0,
     gamma: float = 1.0,
     negative_sample_rate: int = 5,
-    init_pos: Union[_method_options._InitPos, np.ndarray, None] = "spectral",
+    init_pos: _method_options._InitPos | np.ndarray | None = "spectral",
     random_state: AnyRandom = 0,
-    a: Optional[float] = None,
-    b: Optional[float] = None,
+    a: float | None = None,
+    b: float | None = None,
     copy: bool = False,
     method: Literal["umap", "rapids"] = "umap",
-    neighbors_key: Optional[str] = None,
-) -> Optional[AnnData]:  # pragma: no cover
+    neighbors_key: str | None = None,
+) -> AnnData | None:  # pragma: no cover
     """Embed the neighborhood graph using UMAP [McInnes18]_.
 
     UMAP (Uniform Manifold Approximation and Projection) is a manifold learning
@@ -186,17 +186,17 @@ def umap(
 def draw_graph(
     adata: AnnData,
     layout: _method_options._Layout = "fa",
-    init_pos: Union[str, bool, None] = None,
-    root: Optional[int] = None,
+    init_pos: str | bool | None = None,
+    root: int | None = None,
     random_state: AnyRandom = 0,
-    n_jobs: Optional[int] = None,
-    adjacency: Optional[spmatrix] = None,
-    key_added_ext: Optional[str] = None,
-    neighbors_key: Optional[str] = None,
-    obsp: Optional[str] = None,
+    n_jobs: int | None = None,
+    adjacency: spmatrix | None = None,
+    key_added_ext: str | None = None,
+    neighbors_key: str | None = None,
+    obsp: str | None = None,
     copy: bool = False,
     **kwds,
-) -> Optional[AnnData]:  # pragma: no cover
+) -> AnnData | None:  # pragma: no cover
     """Force-directed graph drawing [Islam11]_ [Jacomy14]_ [Chippada18]_.
 
     .. _fa2: https://github.com/bhargavchippada/forceatlas2
@@ -264,10 +264,10 @@ def draw_graph(
 def diffmap(
     adata: AnnData,
     n_comps: int = 15,
-    neighbors_key: Optional[str] = None,
+    neighbors_key: str | None = None,
     random_state: AnyRandom = 0,
     copy: bool = False,
-) -> Optional[AnnData]:  # pragma: no cover
+) -> AnnData | None:  # pragma: no cover
     """Diffusion Maps [Coifman05]_ [Haghverdi15]_ [Wolf18]_.
 
     Diffusion maps [Coifman05]_ has been proposed for visualizing single-cell
@@ -309,9 +309,9 @@ def diffmap(
 def embedding_density(
     adata: AnnData,
     basis: str = "umap",  # was positional before 1.4.5
-    groupby: Optional[str] = None,
-    key_added: Optional[str] = None,
-    components: Union[str, Sequence[str]] = None,
+    groupby: str | None = None,
+    key_added: str | None = None,
+    components: str | Sequence[str] = None,
 ) -> None:  # pragma: no cover
     """Calculate the density of observation in an embedding (per condition).
 
@@ -353,19 +353,19 @@ def embedding_density(
 def leiden(
     adata: AnnData,
     resolution: float = 1,
-    restrict_to: Optional[tuple[str, Sequence[str]]] = None,
+    restrict_to: tuple[str, Sequence[str]] | None = None,
     random_state: AnyRandom = 0,
     key_added: str = "leiden",
-    adjacency: Optional[spmatrix] = None,
+    adjacency: spmatrix | None = None,
     directed: bool = True,
     use_weights: bool = True,
     n_iterations: int = -1,
-    partition_type: Optional[type[MutableVertexPartition]] = None,
-    neighbors_key: Optional[str] = None,
-    obsp: Optional[str] = None,
+    partition_type: type[MutableVertexPartition] | None = None,
+    neighbors_key: str | None = None,
+    obsp: str | None = None,
     copy: bool = False,
     **partition_kwargs,
-) -> Optional[AnnData]:  # pragma: no cover
+) -> AnnData | None:  # pragma: no cover
     """Cluster observations into subgroups [Traag18]_.
 
     Cluster observations using the Leiden algorithm [Traag18]_,
@@ -429,15 +429,15 @@ def leiden(
 def dendrogram(
     adata: AnnData,
     groupby: str,
-    n_pcs: Optional[int] = None,
-    use_rep: Optional[str] = None,
-    var_names: Optional[Sequence[str]] = None,
+    n_pcs: int | None = None,
+    use_rep: str | None = None,
+    var_names: Sequence[str] | None = None,
     cor_method: str = "pearson",
     linkage_method: str = "complete",
     optimal_ordering: bool = False,
-    key_added: Optional[str] = None,
+    key_added: str | None = None,
     inplace: bool = True,
-) -> Optional[dict[str, Any]]:  # pragma: no cover
+) -> dict[str, Any] | None:  # pragma: no cover
     """Computes a hierarchical clustering for the given `groupby` categories.
 
     By default, the PCA representation is used unless `.X` has less than 50 variables.
@@ -505,9 +505,9 @@ def dpt(
     n_branchings: int = 0,
     min_group_size: float = 0.01,
     allow_kendall_tau_shift: bool = True,
-    neighbors_key: Optional[str] = None,
+    neighbors_key: str | None = None,
     copy: bool = False,
-) -> Optional[AnnData]:  # pragma: no cover
+) -> AnnData | None:  # pragma: no cover
     """Infer progression of observations through geodesic distance along the graph [Haghverdi16]_ [Wolf19]_.
 
     Reconstruct the progression of a biological process from snapshot
@@ -562,12 +562,12 @@ def dpt(
 
 def paga(
     adata: AnnData,
-    groups: Optional[str] = None,
+    groups: str | None = None,
     use_rna_velocity: bool = False,
     model: Literal["v1.2", "v1.0"] = "v1.2",
-    neighbors_key: Optional[str] = None,
+    neighbors_key: str | None = None,
     copy: bool = False,
-) -> Optional[AnnData]:  # pragma: no cover
+) -> AnnData | None:  # pragma: no cover
     """Mapping out the coarse-grained connectivity structures of complex manifolds [Wolf19]_.
 
     By quantifying the connectivity of partitions (groups, clusters),
@@ -626,13 +626,13 @@ def paga(
 def ingest(
     adata: AnnData,
     adata_ref: AnnData,
-    obs: Optional[Union[str, Iterable[str]]] = None,
-    embedding_method: Union[str, Iterable[str]] = ("umap", "pca"),
+    obs: str | Iterable[str] | None = None,
+    embedding_method: str | Iterable[str] = ("umap", "pca"),
     labeling_method: str = "knn",
-    neighbors_key: Optional[str] = None,
+    neighbors_key: str | None = None,
     inplace: bool = True,
     **kwargs,
-) -> Optional[AnnData]:  # pragma: no cover
+) -> AnnData | None:  # pragma: no cover
     """Map labels and embeddings from reference data to new data.
 
     Integrates embeddings and annotations of an `adata` with a reference dataset

ehrapy/tools/causal/_dowhy.py

@@ -244,7 +244,7 @@ def causal_inference(
                     pval = "Not applicable"
 
                 # Format effect, can be list when refuter is "add_unobserved_common_cause"
-                if isinstance(refute.new_effect, (list, tuple)):
+                if isinstance(refute.new_effect, list | tuple):
                     new_effect = ", ".join([str(np.round(x, 2)) for x in refute.new_effect])
                 else:
                     new_effect = f"{refute.new_effect:.3f}"

ehrapy/tools/cohort_tracking/_cohort_tracker.py

@@ -390,7 +390,7 @@ def create_legend_with_subtitles(patches_list, subtitles_list, tot_legend_kwargs
             # there can be empty lists which distort the logic of matching patches to subtitles
             patches_list = [patch for patch in patches_list if patch]
 
-            for patches, subtitle in zip(patches_list, subtitles_list):
+            for patches, subtitle in zip(patches_list, subtitles_list, strict=False):
                 handles.append(Line2D([], [], linestyle="none", marker="", alpha=0))  # Placeholder for title
                 labels.append(subtitle)
 
@@ -494,7 +494,7 @@ def plot_flowchart(
         tot_bbox_kwargs = {"boxstyle": "round,pad=0.3", "fc": "lightblue", "alpha": 0.5}
         if bbox_kwargs is not None:
             tot_bbox_kwargs.update(bbox_kwargs)
-        for _, (y, label) in enumerate(zip(y_positions, node_labels)):
+        for _, (y, label) in enumerate(zip(y_positions, node_labels, strict=False)):
             axes.annotate(
                 label,
                 xy=(0, y),

ehrapy/tools/feature_ranking/_rank_features_groups.py

@@ -107,7 +107,7 @@ def _save_rank_features_result(
     fields = (names, scores, pvals, pvals_adj, logfoldchanges, pts)
     field_names = ("names", "scores", "pvals", "pvals_adj", "logfoldchanges", "pts")
 
-    for values, key in zip(fields, field_names):
+    for values, key in zip(fields, field_names, strict=False):
         if values is None or not len(values):
             continue
 
@@ -139,7 +139,7 @@ def _get_groups_order(groups_subset, group_names, reference):
     """
     if groups_subset == "all":
         groups_order = group_names
-    elif isinstance(groups_subset, (str, int)):
+    elif isinstance(groups_subset, str | int):
         raise ValueError("Specify a sequence of groups")
     else:
         groups_order = list(groups_subset)