HOUSEKEEPING: Small improvements (#160)

* deps: Add h5py as an extras as it is no longer a dependency

* housekeeping: Add override typing decorator

* deps: Updated pre-commit packages

* housekeeping: Added more override decorators

Author: wong-hl

.pre-commit-config.yaml

@@ -11,7 +11,7 @@ repos:
       - id: mixed-line-ending
   - repo: https://github.com/astral-sh/ruff-pre-commit
     # Ruff version.
-    rev: v0.15.0
+    rev: v0.15.4
     hooks:
       # Run the linter.
       - id: ruff
@@ -20,7 +20,7 @@ repos:
       - id: ruff-format
   - repo: https://github.com/astral-sh/uv-pre-commit
     # uv version.
-    rev: 0.10.0
+    rev: 0.10.7
     hooks:
       - id: uv-lock
   - repo: local

pyproject.toml

@@ -26,7 +26,7 @@ dependencies = [
     "crick", # necessary for dask.percentile method
     "dask",
     "distributed",
-    "h5netcdf",
+    "h5netcdf[h5py]",
     "pydantic",
     "pyproj",
     "pyyaml",

src/rojak/atmosphere/jet_stream.py

@@ -1,5 +1,5 @@
 from abc import ABC, abstractmethod
-from typing import TYPE_CHECKING, ClassVar, assert_never
+from typing import TYPE_CHECKING, ClassVar, assert_never, override
 
 import numpy as np
 import scipy.ndimage as ndi
@@ -60,6 +60,7 @@ def _alpha_vel_field(self) -> xr.DataArray:
             * self._wind_speed.integrate(self._pressure_coord_name).rename("alpha_vel")
         )  # pyright: ignore[reportReturnType]
 
+    @override
     def identify_jet_stream(self) -> "xr.DataArray":
         identified_jet_stream: xr.DataArray = self._alpha_vel_field() > self._ALPHA_VEL_THRESHOLD
         return (
@@ -170,6 +171,7 @@ def _local_maxima(self) -> xr.DataArray:
             kwargs={"threshold": self._MINIMUM_WIND_SPEED_THRESHOLD},
         )
 
+    @override
     def identify_jet_stream(self) -> "xr.DataArray":
         return (self._local_maxima() & (self._u_wind >= 0)).rename("jet_stream_schiemann")
 

src/rojak/datalib/ecmwf/era5.py

@@ -13,7 +13,7 @@
 #  limitations under the License.
 
 import logging
-from typing import TYPE_CHECKING, ClassVar, Literal
+from typing import TYPE_CHECKING, ClassVar, Literal, override
 
 import cdsapi
 from rich.progress import track
@@ -91,6 +91,7 @@ def __init__(
         self.request_dataset_name = reanalysis_dataset_names[dataset_name]
         self.cds_client: cdsapi.Client = cdsapi.Client()
 
+    @override
     def download_files(
         self,
         years: list[int],
@@ -103,6 +104,7 @@ def download_files(
         for date in track(dates):
             self._download_file(date, base_output_dir)
 
+    @override
     def _download_file(self, date: "Date", base_output_dir: "Path") -> None:
         this_request = self.request_body
         this_request["year"] = date.year
@@ -134,6 +136,7 @@ def __init__(self, on_pressure_level: "xr.Dataset") -> None:
         super().__init__()
         self._on_pressure_level = on_pressure_level
 
+    @override
     def to_clear_air_turbulence_data(self, domain: "SpatialDomain") -> CATData:
         logger.debug("Converting data to CATData")
         target_variables: list[DataVarSchema] = [

src/rojak/datalib/madis/amdar.py

@@ -19,7 +19,7 @@
 from collections.abc import Container, Hashable, Iterable
 from ftplib import FTP
 from pathlib import Path
-from typing import TYPE_CHECKING, Any, ClassVar
+from typing import TYPE_CHECKING, Any, ClassVar, override
 
 import dask.array as da
 import dask.dataframe as dd
@@ -226,6 +226,7 @@ def drop_invalid_error_data(self, dataset: xr.Dataset) -> xr.Dataset:
             dataset = self.__mask_invalid_error_var(dataset, str(var))
         return dataset.dropna(self.dimension_name, subset=error_vars_present)
 
+    @override
     def apply_preprocessor(self, output_directory: Path) -> None:
         # Filters and exports data to parquet
         output_directory.mkdir(parents=True, exist_ok=True)
@@ -279,6 +280,7 @@ def __init__(self, file_pattern: str | None = None) -> None:
         else:
             self.file_pattern = file_pattern
 
+    @override
     def _download_file(self, date: Date, base_output_dir: Path) -> None:
         output_dir: Path = (base_output_dir / f"{date.year:02d}" / f"{date.month:02d}").resolve()
         output_dir.mkdir(parents=True, exist_ok=True)
@@ -293,6 +295,7 @@ def _download_file(self, date: Date, base_output_dir: Path) -> None:
                 with target_file_path.open(mode="wb") as f_out:
                     ftp.retrbinary(f"RETR {file}", f_out.write)
 
+    @override
     def download_files(
         self,
         years: list[int],
@@ -327,6 +330,7 @@ class AcarsAmdarRepository(AmdarDataRepository):
     def __init__(self, path_to_files: str | list) -> None:
         super().__init__(path_to_files, True)
 
+    @override
     def load(self) -> "dd.DataFrame":
         target_columns: list[str] | None = (
             list(AcarsAmdarRepository._MINIMAL_DATA_VARS) if self._use_min_turbulence_vars else None
@@ -342,20 +346,23 @@ def load(self) -> "dd.DataFrame":
 
         return amdar_data
 
+    @override
     def _call_compute_closest_pressure_level(
         self,
         data_frame: "dd.DataFrame",
         pressure_levels: "np.ndarray[Any, np.dtype[np.float64]]",
     ) -> "dd.Series":
         return self._compute_closest_pressure_level(data_frame, pressure_levels, "altitude")
 
+    @override
     def _instantiate_amdar_turbulence_data_class(
         self,
         data_frame: "dd.DataFrame",
         grid: "dgpd.GeoDataFrame",
     ) -> "AmdarTurbulenceData":
         return AcarsAmdarTurbulenceData(data_frame, grid)
 
+    @override
     def _time_column_rename_mapping(self) -> dict[str, str]:
         return {"timeObs": "datetime"}
 
@@ -364,9 +371,11 @@ class AcarsAmdarTurbulenceData(AmdarTurbulenceData):
     def __init__(self, data_frame: "dd.DataFrame", grid: "dgpd.GeoDataFrame") -> None:
         super().__init__(data_frame, grid)
 
+    @override
     def _minimum_altitude_qc(self, data_frame: "dd.DataFrame") -> "dd.DataFrame":
         return data_frame[data_frame["altitude"] >= self.MINIMUM_ALTITUDE]
 
+    @override
     def _drop_manoeuvre_data_qc(self, data_frame: "dd.DataFrame") -> "dd.DataFrame":
         # Attributes:
         # long_name:  Aircraft roll angle flag

src/rojak/datalib/ukmo/amdar.py

@@ -13,7 +13,7 @@
 #  limitations under the License.
 
 from collections.abc import Iterable
-from typing import TYPE_CHECKING, Any, ClassVar
+from typing import TYPE_CHECKING, Any, ClassVar, override
 
 import dask.dataframe as dd
 import numpy as np
@@ -111,20 +111,23 @@ def load(
 
         return data.optimize()
 
+    @override
     def _call_compute_closest_pressure_level(
         self,
         data_frame: "dd.DataFrame",
         pressure_levels: "np.ndarray[Any, np.dtype[np.float64]]",
     ) -> "dd.Series":
         return self._compute_closest_pressure_level(data_frame, pressure_levels, "altitude")
 
+    @override
     def _instantiate_amdar_turbulence_data_class(
         self,
         data_frame: "dd.DataFrame",
         grid: "dgpd.GeoDataFrame",
     ) -> "AmdarTurbulenceData":
         return UkmoAmdarTurbulenceData(data_frame, grid)
 
+    @override
     def _time_column_rename_mapping(self) -> dict[str, str]:
         return {}
 
@@ -133,9 +136,11 @@ class UkmoAmdarTurbulenceData(AmdarTurbulenceData):
     def __init__(self, data_frame: "dd.DataFrame", grid: "dgpd.GeoDataFrame") -> None:
         super().__init__(data_frame, grid)
 
+    @override
     def _minimum_altitude_qc(self, data_frame: "dd.DataFrame") -> "dd.DataFrame":
         return data_frame[data_frame["altitude"] >= self.MINIMUM_ALTITUDE]
 
+    @override
     def _drop_manoeuvre_data_qc(self, data_frame: "dd.DataFrame") -> "dd.DataFrame":
         # roll_angle is NA in entire month of Jan and May in 2024
         return data_frame