Skip to content

[pre-commit.ci] pre-commit autoupdate #181

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
pre-commit-ci wants to merge 2 commits into
base: main
Choose a base branch
from
Open

[pre-commit.ci] pre-commit autoupdate #181

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5f6e5b8
[pre-commit.ci] pre-commit autoupdate
pre-commit-ci[bot] Jul 6, 2026
5323abd
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Jul 6, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions .pre-commit-config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@ repos:
# Run ruff to lint and format
- repo: https://github.com/astral-sh/ruff-pre-commit
# Ruff version.
rev: v0.15.9
rev: v0.15.20
hooks:
# Run the linter.
- id: ruff
Expand Down Expand Up @@ -50,6 +50,6 @@ repos:

# Format Snakemake rule / workflow files
- repo: https://github.com/snakemake/snakefmt
rev: v1.0.0
rev: v2.0.3
hooks:
- id: snakefmt
6 changes: 2 additions & 4 deletions Snakefile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -262,13 +262,11 @@ rule purge:
"Delete all files in the folders above? [y/N] "
)
if do_purge == "y":

# Remove the directories and recreate them with .gitkeep
for dir_path in ["resources/", "results/"]:
rmtree(dir_path, ignore_errors=True)
Path(dir_path).mkdir(parents=True, exist_ok=True)
(Path(dir_path) / ".gitkeep").touch()

rmtree("doc/_build", ignore_errors=True)
print(
"Purging all generated resources, results and docs. Downloads are kept."
Expand Down Expand Up @@ -303,7 +301,7 @@ rule rulegraph:
r"""
# Generate DOT file using nested snakemake with the dumped final config
echo "[Rule rulegraph] Using final config file: {input.config_file}"
snakemake --rulegraph --configfile {input.config_file} --quiet | sed -n "/digraph/,\$p" > {output.dot}
snakemake --rulegraph --configfile {input.config_file} --quiet | sed -n "/digraph/,\$p" >{output.dot}

# Generate visualizations from the DOT file
if [ -s {output.dot} ]; then
Expand Down Expand Up @@ -340,7 +338,7 @@ rule filegraph:
r"""
# Generate DOT file using nested snakemake with the dumped final config
echo "[Rule filegraph] Using final config file: {input.config_file}"
snakemake --filegraph all --configfile {input.config_file} --quiet | sed -n "/digraph/,\$p" > {output.dot}
snakemake --filegraph all --configfile {input.config_file} --quiet | sed -n "/digraph/,\$p" >{output.dot}

# Generate visualizations from the DOT file
if [ -s {output.dot} ]; then
Expand Down
31 changes: 0 additions & 31 deletions rules/retrieve.smk
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -177,7 +177,6 @@ if (POPULATION_COUNT_DATASET := dataset_version("population_count"))["source"] i
"Retrieving population count data"
run:
copy2(input["tif"], output["tif"])

if POPULATION_COUNT_DATASET["source"] == "primary":
import xarray as xr
import rioxarray as rio
Expand All @@ -188,7 +187,6 @@ if (POPULATION_COUNT_DATASET := dataset_version("population_count"))["source"] i
ds_reqd.rio.to_raster(file_path)



if (GHG_EMISSIONS_DATASET := dataset_version("ghg_emissions"))["source"] in [
"archive",
"primary",
Expand Down Expand Up @@ -220,7 +218,6 @@ if (GHG_EMISSIONS_DATASET := dataset_version("ghg_emissions"))["source"] in [
copy2(input["ghg"], output["csv"])



if (GEBCO_DATASET := dataset_version("gebco"))["source"] in ["archive", "primary"]:

rule retrieve_gebco:
Expand All @@ -240,10 +237,8 @@ if (GEBCO_DATASET := dataset_version("gebco"))["source"] in ["archive", "primary
import xarray as xr

copy2(input[0], output["zip_file"])

output_folder = Path(output["zip_file"]).parent
unpack_archive(output["zip_file"], output_folder)

# Limit extent to Europe to reduce file size
ds = xr.open_dataset(output["gebco"])
ds = ds.sel(lat=slice(32, 73), lon=slice(-21, 45))
Expand All @@ -252,7 +247,6 @@ if (GEBCO_DATASET := dataset_version("gebco"))["source"] in ["archive", "primary
copy2(input[0], output["gebco"])



if (ATTRIBUTED_PORTS_DATASET := dataset_version("attributed_ports"))["source"] in [
"archive",
"primary",
Expand Down Expand Up @@ -386,13 +380,10 @@ if (BIDDING_ZONES_ENTSOEPY_DATASET := dataset_version("bidding_zones_entsoepy"))
except (URLError, TimeoutError) as e:
raise Exception(f"Network error retrieving {name}: {e}")
shapes = pd.concat(gdfs, ignore_index=True) # type: ignore

logger.info("Downloading entsoe-py zones... Done")

shapes.to_file(output.geojson)



if (CUTOUT_DATASET := dataset_version("cutout"))["source"] in [
"archive",
]:
Expand Down Expand Up @@ -700,7 +691,6 @@ if (ENERGY_ATLAS_DATASET := dataset_version("jrc_energy_atlas"))["source"] in [
f.write(response.content)



if (
DESNZ_ELECTRICITY_CONSUMPTION_DATASET := dataset_version(
"desnz_electricity_consumption"
Expand All @@ -722,7 +712,6 @@ if (
f.write(response.content)



if (ONS_LAD_DATASET := dataset_version("ons_lad"))["source"] in ["archive"]:

rule retrieve_ons_lad:
Expand Down Expand Up @@ -756,7 +745,6 @@ elif ONS_LAD_DATASET["source"] in ["primary"]:
f.write(response.content)



if (SHIP_RASTER_DATASET := dataset_version("ship_raster"))["source"] in [
"archive",
"primary",
Expand Down Expand Up @@ -881,7 +869,6 @@ if (EEZ_DATASET := dataset_version("eez"))["source"] in ["primary"]:

name = str(uuid4())[:8]
org = str(uuid4())[:8]

response = requests.post(
f"{EEZ_DATASET['url']}",
params={"name": f"World_EEZ_{EEZ_DATASET['version']}_LR.zip"},
Expand All @@ -895,13 +882,11 @@ if (EEZ_DATASET := dataset_version("eez"))["source"] in ["primary"]:
"agree": "1",
},
)

with open(output["zip_file"], "wb") as f:
f.write(response.content)
output_folder = Path(output["zip_file"]).parent
unpack_archive(output["zip_file"], output_folder)


elif (EEZ_DATASET := dataset_version("eez"))["source"] in ["archive"]:

rule retrieve_eez:
Expand Down Expand Up @@ -936,7 +921,6 @@ if (WB_URB_POP_DATASET := dataset_version("worldbank_urban_population"))["source
run:
copy2(input["zip"], output["zip"])
unpack_archive(output["zip"], WB_URB_POP_DATASET["folder"])

# Filename contains some added numbers when downloaded,
# remove them to have a consistent filename across versions
target_filename = Path(output["csv"])
Expand Down Expand Up @@ -1115,13 +1099,11 @@ if (WDPA_DATASET := dataset_version("wdpa"))["source"] in [
output_folder = Path(output["zip_file"]).parent
copy2(input["zip_file"], output["zip_file"])
unpack_archive(output["zip_file"], output_folder)

# Extract {bYYYY} from the input file / URL
bYYYY = re.search(
r"WDPA_(\w{3}\d{4})_Public_shp.zip",
input["zip_file"],
).group(1)

for i in range(3):
# vsizip is special driver for directly working with zipped shapefiles in ogr2ogr
layer_path = (
Expand All @@ -1131,7 +1113,6 @@ if (WDPA_DATASET := dataset_version("wdpa"))["source"] in [
shell("ogr2ogr -f gpkg -update -append {output.gpkg} {layer_path}")



if (WDPA_MARINE_DATASET := dataset_version("wdpa_marine"))["source"] in [
"primary",
"archive",
Expand All @@ -1152,21 +1133,18 @@ if (WDPA_MARINE_DATASET := dataset_version("wdpa_marine"))["source"] in [
output_folder = Path(output["zip_file"]).parent
copy2(input["zip_file"], output["zip_file"])
unpack_archive(output["zip_file"], output_folder)

# Extract {bYYYY} from the input file / URL
bYYYY = re.search(
r"WDPA_WDOECM_(\w{3}\d{4})_Public_marine_shp.zip",
input["zip_file"],
).group(1)

for i in range(3):
# vsizip is special driver for directly working with zipped shapefiles in ogr2ogr
layer_path = f"/vsizip/{output_folder}/WDPA_WDOECM_{bYYYY}_Public_marine_shp_{i}.zip"
print(f"Adding layer {i+1} of 3 to combined output file.")
shell("ogr2ogr -f gpkg -update -append {output.gpkg} {layer_path}")



if (INSTRAT_CO2_PRICES_DATASET := dataset_version("instrat_co2_prices"))["source"] in [
"primary",
]:
Expand All @@ -1190,10 +1168,8 @@ if (INSTRAT_CO2_PRICES_DATASET := dataset_version("instrat_co2_prices"))["source
"Accept": "application/json",
"Referer": "https://energy.instrat.pl/",
}

r = requests.get(url, headers=headers)
r.raise_for_status()

df = pd.read_json(r.text)
df.to_csv(output["csv"], index=False)

Expand Down Expand Up @@ -1232,17 +1208,14 @@ if (TYDNP_DATASET := dataset_version("tyndp"))["source"] in ["primary", "archive
for key in input.keys():
# Keep zip file
copy2(input[key], output[f"{key}_zip"])

# unzip
output_folder = Path(output[f"{key}_zip"]).parent
unpack_archive(output[f"{key}_zip"], output_folder)

# Remove __MACOSX directory if it exists
macosx_dir = output_folder / "__MACOSX"
rmtree(macosx_dir, ignore_errors=True)



def get_osm_archive_files(version):
return [
"buses.csv",
Expand Down Expand Up @@ -1320,7 +1293,6 @@ if OSM_DATASET["source"] in ["archive"]:
copy2(input[key], output[key])



# Only create incumbent rule if it points to a different folder
OSM_DATASET_INCUMBENT = get_osm_network_incumbent(
version=config.get("osm_network_release", {})
Expand Down Expand Up @@ -1362,7 +1334,6 @@ if OSM_DATASET_INCUMBENT["source"] in ["archive"] and OSM_DATASET_INCUMBENT[
copy2(input[key], output[key])



if OSM_DATASET["source"] == "build":
OSM_RAW_JSON = [
"cables_way.json",
Expand Down Expand Up @@ -1594,7 +1565,6 @@ if (JRC_ARDECO_DATASET := dataset_version("jrc_ardeco"))["source"] in [
for key in input.keys():
copy2(input[key], output[key])


elif (JRC_ARDECO_DATASET := dataset_version("jrc_ardeco"))["source"] in ["archive"]:

rule retrieve_jrc_ardeco:
Expand All @@ -1615,7 +1585,6 @@ elif (JRC_ARDECO_DATASET := dataset_version("jrc_ardeco"))["source"] in ["archiv
copy2(input[key], output[key])



if (AQUIFER_DATA_DATASET := dataset_version("aquifer_data"))["source"] in [
"primary",
"archive",
Expand Down