MAINT: update pre-commit, ruff rules (#207)

<!--pre-commit.ci start-->
updates:
- [github.com/astral-sh/ruff-pre-commit: v0.12.8 →
v0.14.6](astral-sh/ruff-pre-commit@v0.12.8...v0.14.6)
- [github.com/pre-commit/mirrors-mypy: v1.17.1 →
v1.18.2](pre-commit/mirrors-mypy@v1.17.1...v1.18.2)
<!--pre-commit.ci end-->

Also:
+ update ruff rules
+ fix ruff issues

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Pieter Roggemans <pieter.roggemans@gmail.com>

Author: pre-commit-ci[bot]

.pre-commit-config.yaml

@@ -4,13 +4,13 @@ ci:
 
 repos:
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: "v0.12.8"
+    rev: "v0.14.6"
     hooks:
       - id: ruff-format
       - id: ruff
-        # args: [ --fix ]
+        args: [ --fix ]
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: "v1.17.1"
+    rev: "v1.18.2"
     hooks:
       - id: mypy
         additional_dependencies: [pandas-stubs<2.3, types-python-dateutil, types-requests]

cropclassification/calc_cover.py

@@ -23,8 +23,8 @@
 def run_cover(
     config_paths: list[Path],
     default_basedir: Path,
-    config_overrules: list[str] = [],
-):
+    config_overrules: list[str] | None = None,
+) -> None:
     """Run a the cover marker using the setting in the config_paths.
 
     Args:
@@ -43,7 +43,7 @@ def run_cover(
     # Main initialisation of the logging
     log_level = conf.general.get("log_level")
     log_dir = conf.paths.getpath("log_dir")
-    global logger
+    global logger  # noqa: PLW0603
     logger = log_helper.main_log_init(log_dir, __name__, log_level)
 
     logger.warning("This is a POC for a cover marker, so not for operational use!")
@@ -274,7 +274,7 @@ def run_cover(
     logging.shutdown()
 
 
-def _categorize_pred(x):
+def _categorize_pred(x: float | str) -> str:
     if pd.isna(x):
         return "NODATA"
     try:
@@ -290,16 +290,16 @@ def _categorize_pred(x):
 
 
 def _calc_cover(
-    input_parcel_path,
-    timeseries_periodic_dir,
-    images_to_use,
+    input_parcel_path: Path,
+    timeseries_periodic_dir: Path,
+    images_to_use: dict[str, conf.ImageConfig],
     start_date: datetime,
     end_date: datetime,
     parcel_columns: list[str] | None,
     output_path: Path,
     output_geo_path: Path | None = None,
     force: bool = False,
-):
+) -> None:
     logger.info(f"start processing {output_path}")
 
     if output_path.exists():
@@ -490,7 +490,9 @@ def _calc_cover(
     shutil.rmtree(tmp_dir)
 
 
-def _select_parcels_BMG_MEG_MEV_EEF(input_geo_path, output_geo_path):
+def _select_parcels_BMG_MEG_MEV_EEF(
+    input_geo_path: Path, output_geo_path: Path
+) -> None:
     """Select parcels based on the cover marker."""
     # Select the relevant parcels based on the cover marker
     info = gfo.get_layerinfo(input_geo_path)
@@ -539,7 +541,7 @@ def _select_parcels_BMG_MEG_MEV_EEF(input_geo_path, output_geo_path):
     gfo.copy_layer(input_geo_path, output_geo_path, where=where)
 
 
-def _select_parcels_EEF(input_geo_path, output_geo_path):
+def _select_parcels_EEF(input_geo_path: Path, output_geo_path: Path) -> None:
     """Select parcels based on the cover marker."""
     # Select the relevant parcels based on the cover marker
     info = gfo.get_layerinfo(input_geo_path)
@@ -566,7 +568,7 @@ def _select_parcels_EEF(input_geo_path, output_geo_path):
     gfo.copy_layer(input_geo_path, output_geo_path, where=where)
 
 
-def _select_parcels(input_geo_path, output_geo_path):
+def _select_parcels(input_geo_path: Path, output_geo_path: Path) -> None:
     """Select parcels based on the cover marker."""
     # Select the relevant parcels based on the cover marker
     info = gfo.get_layerinfo(input_geo_path)
@@ -593,7 +595,7 @@ def _select_parcels(input_geo_path, output_geo_path):
     gfo.copy_layer(input_geo_path, output_geo_path, where=where)
 
 
-def report():
+def report() -> None:
     """Create a report for the cover marker."""
     # Read parcels selected to be controlled for the cover marker
     prc_selectie_path = Path(

cropclassification/calc_cropclass.py

@@ -23,8 +23,8 @@
 def run_cropclass(
     config_paths: list[Path],
     default_basedir: Path,
-    config_overrules: list[str] = [],
-):
+    config_overrules: list[str] | None = None,
+) -> None:
     """Runs a crop classification marker using the setting in the config_paths.
 
     Args:
@@ -80,7 +80,7 @@ def run_cropclass(
         logger.info(
             "Write new config_used.ini, because some parameters might have been added"
         )
-        with open(config_used_path, "w") as config_used_file:
+        with config_used_path.open("w") as config_used_file:
             conf.config.write(config_used_file)
     else:
         # Copy the config files to a config dir for later notice
@@ -101,7 +101,7 @@ def run_cropclass(
 
             # Write the resolved complete config, so it can be reused
             logger.info("Write config_used.ini, so it can be reused later on")
-            with open(config_used_path, "w") as config_used_file:
+            with config_used_path.open("w") as config_used_file:
                 conf.config.write(config_used_file)
 
     # Read the info about the run

cropclassification/calc_periodic_mosaic.py

@@ -8,7 +8,7 @@
 from cropclassification.util import mosaic_util
 
 
-def calc_periodic_mosaic_task(config_paths: list[Path], default_basedir: Path):
+def calc_periodic_mosaic_task(config_paths: list[Path], default_basedir: Path) -> None:
     """Runs a periodic mosaic using the setting in the config_paths.
 
     Args:

cropclassification/helpers/config_helper.py

@@ -39,7 +39,7 @@ def __init__(
         imageprofile_name: str,
         imageprofile: ImageProfile | None = None,
         bands: list[str] | None = None,
-    ):
+    ) -> None:
         """Constructor for ImageConfig.
 
         Args:
@@ -62,9 +62,9 @@ def __init__(
 def read_config(
     config_paths: list[Path] | Path | None,
     default_basedir: Path | None = None,
-    overrules: list[str] = [],
+    overrules: list[str] | None = None,
     preload_defaults: bool = True,
-):
+) -> None:
     """Read cropclassification configuration file(s).
 
     Args:
@@ -102,10 +102,13 @@ def read_config(
         if not config_path.exists():
             raise ValueError(f"Config file doesn't exist: {config_path}")
 
+    if overrules is None:
+        overrules = []
+
     # If there are overrules, write them to a temporary configuration file.
-    global config_overrules
+    global config_overrules  # noqa: PLW0603
     config_overrules = overrules
-    global config_overrules_path
+    global config_overrules_path  # noqa: PLW0603
     config_overrules_path = None
     if len(config_overrules) > 0:
         tmp_dir = Path(tempfile.gettempdir())
@@ -131,12 +134,12 @@ def read_config(
             overrules_parser[section][parameter] = value
 
         # Write to temp file and add file to config_paths
-        with open(config_overrules_path, "w") as overrules_file:
+        with config_overrules_path.open("w") as overrules_file:
             overrules_parser.write(overrules_file)
         config_paths.append(config_overrules_path)
 
     # Read and parse the config files
-    global config
+    global config  # noqa: PLW0603
     config = configparser.ConfigParser(
         interpolation=configparser.ExtendedInterpolation(),
         converters={
@@ -195,40 +198,40 @@ def read_config(
         tmp_dir=tmp_dir_str
     )
 
-    global config_paths_used
+    global config_paths_used  # noqa: PLW0603
     config_paths_used = config_paths
 
     # Now set global variables to each section as shortcuts
-    global general
+    global general  # noqa: PLW0603
     general = config["general"]
-    global calc_timeseries_params
+    global calc_timeseries_params  # noqa: PLW0603
     calc_timeseries_params = config["calc_timeseries_params"]
-    global calc_marker_params
+    global calc_marker_params  # noqa: PLW0603
     calc_marker_params = config["calc_marker_params"]
-    global calc_periodic_mosaic_params
+    global calc_periodic_mosaic_params  # noqa: PLW0603
     if "calc_periodic_mosaic_params" in config:
         calc_periodic_mosaic_params = config["calc_periodic_mosaic_params"]
     else:
         calc_periodic_mosaic_params = None
-    global roi
+    global roi  # noqa: PLW0603
     roi = config["roi"]
-    global period
+    global period  # noqa: PLW0603
     period = config["period"]
-    global images
+    global images  # noqa: PLW0603
     images = config["images"]
-    global marker
+    global marker  # noqa: PLW0603
     marker = config["marker"]
-    global timeseries
+    global timeseries  # noqa: PLW0603
     timeseries = config["timeseries"]
-    global preprocess
+    global preprocess  # noqa: PLW0603
     preprocess = config["preprocess"]
-    global classifier
+    global classifier  # noqa: PLW0603
     classifier = config["classifier"]
-    global postprocess
+    global postprocess  # noqa: PLW0603
     postprocess = config["postprocess"]
-    global columns
+    global columns  # noqa: PLW0603
     columns = config["columns"]
-    global paths
+    global paths  # noqa: PLW0603
     paths = config["paths"]
 
     # Check some parameters that should be overriden to have a valid config
@@ -239,7 +242,7 @@ def read_config(
         raise ValueError("paths.images_periodic_dir must be overridden")
 
     # Load image profiles
-    global image_profiles
+    global image_profiles  # noqa: PLW0603
     image_profiles_config_filepath = paths.getpath("image_profiles_config_filepath")
     if image_profiles_config_filepath is not None:
         image_profiles = _get_image_profiles(
@@ -250,12 +253,12 @@ def read_config(
         image_profiles = {}
 
 
-def parse_image_config(input) -> dict[str, ImageConfig]:
+def parse_image_config(image_config: str) -> dict[str, ImageConfig]:
     """Parses the json input to a dictionary of ImageConfig objects."""
     result = None
     imageconfig_parsed = None
     try:
-        imageconfig_parsed = json.loads(input)
+        imageconfig_parsed = json.loads(image_config)
     except Exception:
         pass
 
@@ -281,7 +284,7 @@ def parse_image_config(input) -> dict[str, ImageConfig]:
                 )
     else:
         # It was no json object, so it must be a list
-        result = {i.strip(): ImageConfig(i.strip()) for i in input.split(",")}
+        result = {i.strip(): ImageConfig(i.strip()) for i in image_config.split(",")}
 
     return result
 
@@ -330,7 +333,7 @@ def _get_image_profiles(image_profiles_path: Path) -> dict[str, ImageProfile]:
     return profiles
 
 
-def _validate_image_profiles(profiles: dict[str, ImageProfile]):
+def _validate_image_profiles(profiles: dict[str, ImageProfile]) -> None:
     # Check that all base_image_profile s are actually existing image profiles.
     for profile in list(profiles):
         base_image_profile = profiles[profile].base_imageprofile
@@ -340,7 +343,7 @@ def _validate_image_profiles(profiles: dict[str, ImageProfile]):
             )
 
 
-def pformat_config():
+def pformat_config() -> str:
     """Formats the config as a pretty string."""
     message = (
         f"Config files used: {pprint.pformat(config_paths_used)} \n"
@@ -351,13 +354,13 @@ def pformat_config():
     return message
 
 
-def as_dict():
+def as_dict() -> dict[str, Any]:
     """Converts the config objects into a dictionary.
 
     The resulting dictionary has sections as keys which point to a dict of the
     sections options as key => value pairs.
     """
-    the_dict = {}
+    the_dict: dict[str, dict[str, Any]] = {}
     for section in config.sections():
         the_dict[section] = {}
         for key, val in config.items(section):

cropclassification/helpers/log_helper.py

@@ -2,7 +2,6 @@
 
 import datetime
 import logging
-import os
 from pathlib import Path
 
 
@@ -21,7 +20,7 @@ def main_log_init(
     """
     # Make sure the log dir exists
     if not log_dir.exists():
-        os.makedirs(log_dir, exist_ok=True)
+        log_dir.mkdir(parents=True, exist_ok=True)
 
     # Get root logger
     logger = logging.getLogger("")

cropclassification/helpers/model_helper.py

@@ -1,8 +1,6 @@
 """Module with helper functions regarding (keras) models."""
 
-import glob
 import logging
-import os
 from pathlib import Path
 
 import pandas as pd
@@ -163,11 +161,9 @@ def get_models(model_dir: Path, model_base_filename: str | None = None) -> pd.Da
     """
     # glob search string
     if model_base_filename is not None:
-        model_weight_paths = glob.glob(
-            f"{model_dir!s}{os.sep}{model_base_filename}_*.hdf5"
-        )
+        model_weight_paths = list(model_dir.glob(f"{model_base_filename}_*.hdf5"))
     else:
-        model_weight_paths = glob.glob(f"{model_dir!s}{os.sep}*.hdf5")
+        model_weight_paths = list(model_dir.glob("*.hdf5"))
 
     # Loop through all models and extract necessary info...
     model_info_list = []
@@ -224,15 +220,15 @@ def save_and_clean_models(
     model_save_dir: Path,
     model_save_base_filename: str,
     acc_metric_mode: str,
-    new_model=None,
+    new_model=None,  # noqa: ANN001
     new_model_acc_train: float | None = None,
     new_model_acc_val: float | None = None,
     new_model_epoch: int | None = None,
     save_weights_only: bool = False,
     verbose: bool = True,
     debug: bool = False,
     only_report: bool = False,
-):
+) -> None:
     """Save the new model if it is good enough.
 
     Existing models are removed if they are worse than the new or other existing models.
@@ -337,7 +333,7 @@ def save_and_clean_models(
                 logger.debug(f"DELETE {model_info['filename']}")
             elif model_info["path"].exists():
                 logger.debug(f"DELETE {model_info['filename']}")
-                os.remove(model_info["path"])
+                model_info["path"].unlink()
 
             if debug:
                 print(f"Better one(s) found for{model_info['filename']}:")