[pre-commit.ci] pre-commit autoupdate

.pre-commit-config.yaml

@@ -14,7 +14,7 @@ repos:
   - id: check-yaml
     exclude: .gitlab-ci.yml
 - repo: https://github.com/astral-sh/ruff-pre-commit
-  rev: v0.15.11
+  rev: v0.16.6
   hooks:
   - id: ruff-check
     args:
@@ -23,7 +23,7 @@ repos:
     - --target-version=py310
     - --extend-select=UP,I
 - repo: https://github.com/psf/black-pre-commit-mirror
-  rev: 26.3.1
+  rev: 26.5.1
   hooks:
   - id: black
     args:
@@ -43,7 +43,7 @@ repos:
     additional_dependencies:
     - tomli
 - repo: https://github.com/jsh9/pydoclint
-  rev: 0.8.3
+  rev: 0.9.1
   hooks:
   - id: pydoclint
     args:
@@ -52,7 +52,7 @@ repos:
     - -athd=False
     - -crt=False
 - repo: https://github.com/igorshubovych/markdownlint-cli
-  rev: v0.48.0
+  rev: v0.49.1
   hooks:
   - id: markdownlint
     args:
@@ -65,5 +65,5 @@ repos:
   hooks:
   - id: blackdoc
     additional_dependencies:
-    - black==26.3.1
+    - black==26.5.1
   - id: blackdoc-autoupdate-black

docs/notebooks/1_demo_dataset.ipynb

@@ -1944,7 +1944,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "new_label_map = {**COCO_pascal.label_map, **{1: \"something else\"}}\n",
+    "new_label_map = {**COCO_pascal.label_map, 1: \"something else\"}\n",
     "COCO_incompatible = COCO_pascal.from_template(label_map=new_label_map)"
    ]
   },

lours/cli/caipy_to_fiftyone.py

@@ -1,6 +1,5 @@
 import socketserver
 from argparse import ArgumentParser
-from logging import warn
 from pathlib import Path
 from time import sleep
 from typing import TYPE_CHECKING
@@ -256,7 +255,7 @@
     args = parser.parse_args()
 
     if not args.launch_app and not args.persistent:
-        warn(
+        warning(
             "App won't be launched and dataset is not persistent, this command will not"
             " do anything",
             RuntimeWarning,

lours/dataset/__init__.py

@@ -15,17 +15,17 @@
 
 __all__ = [
     "Dataset",
-    "from_folder",
-    "from_files",
     "from_caipy",
     "from_caipy_generic",
     "from_coco",
     "from_coco_keypoints",
+    "from_crowd_human",
     "from_darknet",
-    "from_darknet_yolov5",
     "from_darknet_generic",
     "from_darknet_json",
-    "from_crowd_human",
+    "from_darknet_yolov5",
+    "from_files",
+    "from_folder",
     "from_mot",
     "from_parquet",
     "from_pascalVOC_detection",

lours/dataset/dataset.py

@@ -41,7 +41,7 @@ class Dataset:
           for a complete explanation of main principles.
         - :ref:`Dataset demo notebook </notebooks/1_demo_dataset.ipynb>`
 
-    """  # noqa: E501
+    """
 
     dataset_name: str | None
     images_root: Path
@@ -3535,12 +3535,12 @@ class mapping. Otherwise, keep them as is (with potential class fusion).
             Index: []
             Label map :
             {1: 'interview'}
-        """  # noqa: E501
+        """
         if not remove_not_mapped:
             not_mapped = {
                 category_id: category_id
                 for category_id in self.label_map.keys()
-                if category_id not in class_mapping.keys()
+                if category_id not in class_mapping
             }
             class_mapping = {**class_mapping, **not_mapped}
         new_label_map = {
@@ -3726,7 +3726,7 @@ class mapping. Otherwise, keep them as is (with potential class fusion).
             [2 rows x 8 columns]
             Label map :
             {0: 'new_listen', 1: 'new_reach'}
-        """  # noqa: E501
+        """
         if df.index.name == "input_category_id":
             mapping_df = df
         else:
@@ -3785,7 +3785,7 @@ class mapping. Otherwise, keep them as is (with potential class fusion).
             - :meth:`.remap_from_other`
             - :meth:`.remove_classes`
             - :meth:`.keep_classes`
-        """  # noqa: E501
+        """
         mapping_df = pd.read_csv(csv).set_index("input_category_id")
         return self.remap_from_dataframe(
             mapping_df, remove_not_mapped, remove_emptied_images
@@ -4965,7 +4965,7 @@ def to_caipy(
         See Also:
             - :mod:`lours.dataset.io.caipy`
             - :meth:`to_caipy_generic`
-        """  # noqa: E501
+        """
         from .io.caipy import dataset_to_caipy
 
         return dataset_to_caipy(
@@ -5033,7 +5033,7 @@ def to_caipy_generic(
             - :mod:`lours.dataset.io.caipy`
             - :meth:`to_caipy`
 
-        """  # noqa: E501
+        """
         from .io.caipy import dataset_to_caipy_generic
 
         return dataset_to_caipy_generic(

lours/dataset/io/caipy.py

@@ -208,7 +208,7 @@ def from_caipy(
         - :ref:`Tutorial on schemas </notebooks/6_demo_schemas.ipynb>`
         - :ref:`Tutorial on booleanization </notebooks/7_demo_booleanize.ipynb>`
         - `cAIpy specifications <UPDATE-ME>`_
-    """  # noqa: E501
+    """
     dataset_path = Path(dataset_path)
     annotations_folder = dataset_path / "Annotations"
     images_folder = dataset_path / "Images"
@@ -285,7 +285,7 @@ def from_caipy_generic(
         - :ref:`Tutorial on schemas </notebooks/6_demo_schemas.ipynb>`
         - :ref:`Tutorial on booleanization </notebooks/7_demo_booleanize.ipynb>`
         - `cAIpy specifications <UPDATE-ME>`_
-    """  # noqa: E501
+    """
     if use_schema and json_schema is not None:
         if isinstance(json_schema, dict):
             schema = json_schema

lours/dataset/io/darknet.py

@@ -112,8 +112,7 @@ def write_data_file(data: dict[str, str | int], data_file: Path) -> None:
     """
     keys = ["classes", "train", "valid", "names", "backup"]
     with open(data_file, "w") as f:
-        for key in keys:
-            f.write(f"{key} = {data.get(key, '')}\n")
+        f.writelines(f"{key} = {data.get(key, '')}\n" for key in keys)
 
 
 def yolov5_img_path_to_label_path(img_path: Path) -> Path:
@@ -129,7 +128,7 @@ def yolov5_img_path_to_label_path(img_path: Path) -> Path:
 
     Returns:
         corresponding label file as it would have been searched for by yolov5
-    """  # noqa: E501
+    """
     annotation_path = img_path.with_suffix(".txt")
     folder_parts = list(annotation_path.parts)
     if "images" in folder_parts:

lours/dataset/io/schema_util/__init__.py

@@ -10,12 +10,12 @@
 )
 
 __all__ = [
+    "fill_with_dtypes_and_default_value",
+    "flatten_schema",
     "get_dtypes_and_default_values",
     "get_enums",
     "get_remapping_dict_from_names",
     "get_remapping_dict_from_schema",
-    "flatten_schema",
     "load_json_schema",
-    "fill_with_dtypes_and_default_value",
     "remap_dict",
 ]

lours/dataset/io/schema_util/schema_util_functions.py

@@ -321,6 +321,5 @@ def remap_dict(flattened_dict: dict, mapping_tree: dict | None = None) -> dict:
                     # is clearly not na
                     if isna.any():  # pyright: ignore
                         raise ValueError(f"value contains nan : {output_value}")
-                    pass
             output_dict[k] = output_value
     return output_dict

lours/dataset/remap_presets/__init__.py

@@ -9,7 +9,7 @@
 
 import pandas as pd
 
-__all__ = ["presets", "list_available_presets"]
+__all__ = ["list_available_presets", "presets"]
 
 presets = {}
 presets_folder = files("lours") / "dataset" / "remap_presets"

lours/dataset/split/balanced_groups.py

@@ -114,7 +114,6 @@ def check_groups(
         "category and continuous group must be a "
         "perfect partition of the histogram index"
     )
-    return
 
 
 def hist_distance(

lours/evaluation/__init__.py

@@ -1,4 +1,4 @@
 from .detection import CrowdDetectionEvaluator, DetectionEvaluator
 from .evaluator import Evaluator
 
-__all__ = ["Evaluator", "DetectionEvaluator", "CrowdDetectionEvaluator"]
+__all__ = ["CrowdDetectionEvaluator", "DetectionEvaluator", "Evaluator"]

lours/evaluation/detection/__init__.py

@@ -4,4 +4,4 @@
 from .crowd_detection_evaluator import CrowdDetectionEvaluator
 from .detection_evaluator import DetectionEvaluator
 
-__all__ = ["DetectionEvaluator", "CrowdDetectionEvaluator", "util"]
+__all__ = ["CrowdDetectionEvaluator", "DetectionEvaluator", "util"]

lours/evaluation/detection/crowd_detection_evaluator.py

@@ -1,6 +1,5 @@
 from collections.abc import Iterable
 from functools import partial
-from typing import TYPE_CHECKING
 
 import numpy as np
 import pandas as pd
@@ -15,9 +14,6 @@
 from .detection_evaluator_base import DetectionEvaluatorBase
 from .util import resample_count
 
-if TYPE_CHECKING:
-    pass
-
 
 class CrowdDetectionEvaluator(DetectionEvaluatorBase):
     """Class specialization for crowd detection and counting tasks.

lours/evaluation/detection/detection_evaluator.py

@@ -1,6 +1,5 @@
 from collections.abc import Iterable
 from functools import partial
-from typing import TYPE_CHECKING
 
 import numpy as np
 import pandas as pd
@@ -17,9 +16,6 @@
     pr_curve,
 )
 
-if TYPE_CHECKING:
-    pass
-
 
 class DetectionEvaluator(DetectionEvaluatorBase):
     """Class specialization for detection tasks Note that the constructor is the

lours/utils/doc_utils.py

@@ -64,9 +64,7 @@ def construct_attribute_column(
     int
     | Sequence[str]
     | Sequence[int | Sequence[float] | Sequence[str] | dict[str, float]]
-    | dict[
-        str, int | Sequence[float] | Sequence[str] | Sequence[float] | dict[str, float]
-    ]
+    | dict[str, int | Sequence[float] | Sequence[str] | dict[str, float]]
 )
 """The random attribute columns type is a way to design a column with random
 attributes.

lours/utils/label_map_merger.py

@@ -3,8 +3,6 @@ class IncompatibleLabelMapsError(ValueError):
     from other ValueError exceptions
     """
 
-    pass
-
 
 def merge_label_maps(
     left: dict[int, str], right: dict[int, str], method: str = "inner"

test_lours/test_dataset/test_io.py

@@ -93,13 +93,10 @@ def test_caipy_io():
         assert max(map(len, subfolders)) == 0
 
     # Save to caipy generic and reload, ensure they are the same
-    with TemporaryDirectory() as t_images:
-        with TemporaryDirectory() as t_annotations:
-            dataset.to_caipy_generic(
-                t_images, t_annotations, copy_images=True, to_jpg=True
-            )
-            dataset2 = from_caipy_generic(t_images, t_annotations)
-            assert_dataset_equal(dataset, dataset2)
+    with TemporaryDirectory() as t_images, TemporaryDirectory() as t_annotations:
+        dataset.to_caipy_generic(t_images, t_annotations, copy_images=True, to_jpg=True)
+        dataset2 = from_caipy_generic(t_images, t_annotations)
+        assert_dataset_equal(dataset, dataset2)
 
     # Save to coco and reload, ensure they are the same
     with TemporaryDirectory() as t:

test_lours/test_dataset/test_split/test_balanced_groups.py

@@ -60,7 +60,6 @@ def test_dataset_share1():
     assert same_share_cost == 0
     share_cost = balanced_groups.dataset_share_distance(test_share1, test_share2)
     assert share_cost == 1
-    return
 
 
 def test_dataset_share2():
@@ -71,7 +70,6 @@ def test_dataset_share2():
     share_cost = balanced_groups.dataset_share_distance(test_share1, test_share2)
     print(share_cost)
     assert share_cost == 5 / 7
-    return
 
 
 def test_check_group():