Formatting

pyproject.toml

@@ -138,12 +138,11 @@ exclude = [
 # If you need to ignore something for some specific module,
 # add overrides for them. Avoid changing the global config!
 # For example:
-# [[tool.mypy.overrides]]
-# module = [
-#  "my_unpyted_dependency1.*",
-#  "my_unpyted_dependency2.*"
-# ]
-# ignore_missing_imports = true
+ [[tool.mypy.overrides]]
+ module = [
+     "cdsapi.*",
+ ]
+ ignore_missing_imports = true
 
 # [[tool.mypy.overrides]]
 # module = [

src/climate_downscale/cli.py

@@ -6,26 +6,24 @@
 @click.group()
 def cdrun() -> None:
     """Entry point for running climate downscale workflows."""
-    pass
 
 
 @click.group()
 def cdtask() -> None:
     """Entry point for running climate downscale tasks."""
-    pass
 
 
 for module in [extract]:
-    runners = getattr(module, 'RUNNERS', {})
-    task_runners = getattr(module, 'TASK_RUNNERS', {})
+    runners = getattr(module, "RUNNERS", {})
+    task_runners = getattr(module, "TASK_RUNNERS", {})
 
     if not runners or not task_runners:
         continue
 
-    command_name = module.__name__.split('.')[-1]
+    command_name = module.__name__.split(".")[-1]
 
     @click.group(name=command_name)
-    def workflow_runner():
+    def workflow_runner() -> None:
         pass
 
     for name, runner in runners.items():
@@ -34,7 +32,7 @@ def workflow_runner():
     cdrun.add_command(workflow_runner)
 
     @click.group(name=command_name)
-    def task_runner():
+    def task_runner() -> None:
         pass
 
     for name, runner in task_runners.items():

src/climate_downscale/data.py

@@ -1,11 +1,9 @@
 from pathlib import Path
 
-
 DEFAULT_ROOT = "/mnt/share/erf/ERA5/"
 
 
 class ClimateDownscaleData:
-
     def __init__(self, root: str | Path) -> None:
         self._root = Path(root)
         self._credentials_root = self._root / ".credentials"

src/climate_downscale/extract/README.md

@@ -4,36 +4,36 @@
 
 ### [ERA5](https://cds.climate.copernicus.eu/cdsapp#!/dataset/reanalysis-era5-land?tab=overview)
 
-ERA5-Land is a reanalysis dataset providing a consistent view of the evolution of land 
-variables over several decades at an enhanced resolution compared to ERA5. ERA5-Land 
-has been produced by replaying the land component of the ECMWF ERA5 climate reanalysis. 
-Reanalysis combines model data with observations from across the world into a globally 
-complete and consistent dataset using the laws of physics. Reanalysis produces data 
-that goes several decades back in time, providing an accurate description of the 
+ERA5-Land is a reanalysis dataset providing a consistent view of the evolution of land
+variables over several decades at an enhanced resolution compared to ERA5. ERA5-Land
+has been produced by replaying the land component of the ECMWF ERA5 climate reanalysis.
+Reanalysis combines model data with observations from across the world into a globally
+complete and consistent dataset using the laws of physics. Reanalysis produces data
+that goes several decades back in time, providing an accurate description of the
 climate of the past.
 
-ERA5-Land uses as input to control the simulated land fields ERA5 atmospheric 
-variables, such as air temperature and air humidity. This is called the atmospheric 
-forcing. Without the constraint of the atmospheric forcing, the model-based estimates 
-can rapidly deviate from reality. Therefore, while observations are not directly used 
-in the production of ERA5-Land, they have an indirect influence through the atmospheric 
-forcing used to run the simulation. In addition, the input air temperature, air 
-humidity and pressure used to run ERA5-Land are corrected to account for the altitude 
-difference between the grid of the forcing and the higher resolution grid of ERA5-Land. 
+ERA5-Land uses as input to control the simulated land fields ERA5 atmospheric
+variables, such as air temperature and air humidity. This is called the atmospheric
+forcing. Without the constraint of the atmospheric forcing, the model-based estimates
+can rapidly deviate from reality. Therefore, while observations are not directly used
+in the production of ERA5-Land, they have an indirect influence through the atmospheric
+forcing used to run the simulation. In addition, the input air temperature, air
+humidity and pressure used to run ERA5-Land are corrected to account for the altitude
+difference between the grid of the forcing and the higher resolution grid of ERA5-Land.
 This correction is called 'lapse rate correction'.
 
-The ERA5-Land dataset, as any other simulation, provides estimates which have some 
-degree of uncertainty. Numerical models can only provide a more or less accurate 
-representation of the real physical processes governing different components of the 
-Earth System. In general, the uncertainty of model estimates grows as we go back in 
-time, because the number of observations available to create a good quality atmospheric 
-forcing is lower. ERA5-land parameter fields can currently be used in combination with 
+The ERA5-Land dataset, as any other simulation, provides estimates which have some
+degree of uncertainty. Numerical models can only provide a more or less accurate
+representation of the real physical processes governing different components of the
+Earth System. In general, the uncertainty of model estimates grows as we go back in
+time, because the number of observations available to create a good quality atmospheric
+forcing is lower. ERA5-land parameter fields can currently be used in combination with
 the uncertainty of the equivalent ERA5 fields.
 
-The temporal and spatial resolutions of ERA5-Land makes this dataset very useful for 
-all kind of land surface applications such as flood or drought forecasting. The 
-temporal and spatial resolution of this dataset, the period covered in time, as well as 
-the fixed grid used for the data distribution at any period enables decisions makers, 
+The temporal and spatial resolutions of ERA5-Land makes this dataset very useful for
+all kind of land surface applications such as flood or drought forecasting. The
+temporal and spatial resolution of this dataset, the period covered in time, as well as
+the fixed grid used for the data distribution at any period enables decisions makers,
 businesses and individuals to access and use more accurate information on land states.
 
 ### [CMIP6](https://pcmdi.llnl.gov/CMIP6/)
@@ -53,4 +53,3 @@ GSOD dataset is produced by the National Centers for Environmental Information
 ## Downscaling Predictors
 
 ### [Local Climate Zones](https://lcz-generator.rub.de/global-lcz-map)
-

src/climate_downscale/extract/__init__.py

@@ -1,17 +1,17 @@
-from climate_downscale.extract.ncei_climate_stations import (
-    extract_ncei_climate_stations,
-)
 from climate_downscale.extract.era5 import (
     extract_era5,
     extract_era5_task,
 )
+from climate_downscale.extract.ncei_climate_stations import (
+    extract_ncei_climate_stations,
+)
 
 RUNNERS = {
-    'ncei': extract_ncei_climate_stations,
+    "ncei": extract_ncei_climate_stations,
     "era5": extract_era5,
 }
 
 TASK_RUNNERS = {
-    'ncei': extract_ncei_climate_stations,
+    "ncei": extract_ncei_climate_stations,
     "era5": extract_era5_task,
 }

src/climate_downscale/extract/era5.py

@@ -1,12 +1,18 @@
-from typing import TypeVar, ParamSpec
 from pathlib import Path
+from typing import ParamSpec, TypeVar
 
-from climate_downscale.data import ClimateDownscaleData, DEFAULT_ROOT
-from rra_tools.cli_tools import with_output_directory, with_queue, with_choice, ClickOption, RUN_ALL
+import cdsapi
+import click
 from rra_tools import jobmon
+from rra_tools.cli_tools import (
+    RUN_ALL,
+    ClickOption,
+    with_choice,
+    with_output_directory,
+    with_queue,
+)
 
-import click
-import cdsapi
+from climate_downscale.data import DEFAULT_ROOT, ClimateDownscaleData
 
 VALID_YEARS = [str(y) for y in range(1990, 2024)]
 VALID_MONTHS = [f"{i:02d}" for i in range(1, 13)]
@@ -65,8 +71,8 @@ def extract_era5_main(
     variable: str,
 ) -> None:
     cddata = ClimateDownscaleData(output_dir)
-    cred_path = cddata.credentials_root / 'copernicus.txt'
-    url, key = cred_path.read_text().strip().split('\n')
+    cred_path = cddata.credentials_root / "copernicus.txt"
+    url, key = cred_path.read_text().strip().split("\n")
 
     copernicus = cdsapi.Client(url=url, key=key)
     kwargs = {
@@ -79,7 +85,7 @@ def extract_era5_main(
         "time_zone": "UTC+00:00",
         "frequency": "1-hourly",
         "grid": "0.1/0.1",
-        "area": {"lat": [-90, 90], "lon": [-180, 180]}
+        "area": {"lat": [-90, 90], "lon": [-180, 180]},
     }
     result = copernicus.service(
         "tool.toolbox.orchestrator.workflow",
@@ -96,7 +102,7 @@ def extract_era5_main(
     copernicus.download(result, [out_path])
 
 
-@click.command()
+@click.command()  # type: ignore[arg-type]
 @with_output_directory(DEFAULT_ROOT)
 @with_year()
 @with_month()
@@ -105,7 +111,7 @@ def extract_era5_task(year: str, month: str, variable: str) -> None:
     extract_era5_main(DEFAULT_ROOT, year, month, variable)
 
 
-@click.command()
+@click.command()  # type: ignore[arg-type]
 @with_output_directory(DEFAULT_ROOT)
 @with_year(allow_all=True)
 @with_variable(allow_all=True)
@@ -135,4 +141,3 @@ def extract_era5(
         },
         runner="cdtask",
     )
-

src/climate_downscale/extract/ncei_climate_stations.py

@@ -1,42 +1,41 @@
-from rra_tools.shell_tools import wget
-from rra_tools.cli_tools import (
-    with_output_directory
-)
 import shutil
 import tempfile
 from pathlib import Path
-import pandas as pd
 
 import click
+import pandas as pd
+from rra_tools.cli_tools import with_output_directory
+from rra_tools.shell_tools import wget
 
-from climate_downscale.data import ClimateDownscaleData, DEFAULT_ROOT
-
+from climate_downscale.data import DEFAULT_ROOT, ClimateDownscaleData
 
 EXTRACTION_YEARS = list(range(1990, 1992))
-URL_TEMPLATE = 'https://www.ncei.noaa.gov/data/global-summary-of-the-day/archive/{year}.tar.gz'
+URL_TEMPLATE = (
+    "https://www.ncei.noaa.gov/data/global-summary-of-the-day/archive/{year}.tar.gz"
+)
 
 
-def extract_ncei_climate_stations_main(output_dir: str | Path):
+def extract_ncei_climate_stations_main(output_dir: str | Path) -> None:
     cd_data = ClimateDownscaleData(output_dir)
 
-    data = []
+    dfs = []
     for year in EXTRACTION_YEARS:
-        with tempfile.NamedTemporaryFile(suffix='.tar.gz') as f:
+        with tempfile.NamedTemporaryFile(suffix=".tar.gz") as f:
             url = URL_TEMPLATE.format(year=year)
 
             wget(url, f.name)
 
             with tempfile.TemporaryDirectory() as outdir:
                 shutil.unpack_archive(f.name, outdir)
-                data.append(
-                    pd.concat([pd.read_csv(f) for f in Path(outdir).glob('*.csv')])
+                dfs.append(
+                    pd.concat([pd.read_csv(f) for f in Path(outdir).glob("*.csv")])
                 )
-    data = pd.concat(data)
+    data = pd.concat(dfs)
 
-    data.to_parquet(cd_data.ncei_climate_stations / 'climate_stations.parquet')
+    data.to_parquet(cd_data.ncei_climate_stations / "climate_stations.parquet")
 
 
-@click.command()
+@click.command()  # type: ignore[arg-type]
 @with_output_directory(DEFAULT_ROOT)
-def extract_ncei_climate_stations(output_dir: str):
+def extract_ncei_climate_stations(output_dir: str) -> None:
     extract_ncei_climate_stations_main(output_dir)

tests/test_climate_downscale.py

@@ -1,3 +1,4 @@
 def test_climate_downscale() -> None:
     from climate_downscale import cli
+
     assert cli