def test_init_hourly(self, tmp_path):
ERA5HourlyPreprocessor(tmp_path)
assert (
tmp_path / "interim/reanalysis-era5-single-levels_preprocessed"
).exists()
assert (tmp_path / "interim/reanalysis-era5-single-levels_interim").exists()
def preprocess_era5_hourly():
data_path = get_data_path()
regrid_path = data_path / "interim/VCI_preprocessed/data_kenya.nc"
assert regrid_path.exists(), f"{regrid_path} not available"
processor = ERA5HourlyPreprocessor(data_path)
# W-MON is weekly each monday (the same as the NDVI data from Atzberger)
processor.preprocess(subset_str="kenya", resample_time="W-MON")
def preprocess_era5_hourly(subset_str: str = "kenya"):
data_path = get_data_path()
regrid_path = (
data_path /
f"interim/reanalysis-era5-land_preprocessed/data_{subset_str}.nc")
assert regrid_path.exists(), f"{regrid_path} not available"
processor = ERA5HourlyPreprocessor(data_path)
# W-MON is weekly each monday (the same as the NDVI data from Atzberger)
processor.preprocess(subset_str=subset_str, resample_time="W-MON")
def test_make_filename(tmp_path, granularity):
if granularity == "monthly":
basename = "reanalysis-era5-single-levels-monthly-means"
processor = ERA5MonthlyMeanPreprocessor(tmp_path)
elif granularity == "hourly":
basename = "reanalysis-era5-single-levels"
processor = ERA5HourlyPreprocessor(tmp_path)
path = Path(basename + "/2m_temperature/1979_2019/01_12.nc")
name = processor.create_filename(path, "kenya")
expected_name = "1979_2019_01_12_2m_temperature_kenya.nc"
assert name == expected_name, f"{name} generated, expected {expected_name}"
def test_get_filenames(tmp_path, granularity):
if granularity == "monthly":
basename = "reanalysis-era5-single-levels-monthly-means"
processor = ERA5MonthlyMeanPreprocessor(tmp_path)
elif granularity == "hourly":
basename = "reanalysis-era5-single-levels"
processor = ERA5HourlyPreprocessor(tmp_path)
(tmp_path / f"raw/{basename}/" "2m_temperature/1979_2019").mkdir(parents=True)
test_file = tmp_path / f"raw/{basename}/" "/2m_temperature/1979_2019.01_12.nc"
test_file.touch()
files = processor.get_filepaths()
assert files[0] == test_file, f"Expected {test_file} to be retrieved"
def test_preprocess(self, tmp_path, granularity):
if granularity == "monthly":
basename = "reanalysis-era5-single-levels-monthly-means"
processor = ERA5MonthlyMeanPreprocessor(tmp_path)
elif granularity == "hourly":
basename = "reanalysis-era5-single-levels"
processor = ERA5HourlyPreprocessor(tmp_path)
(tmp_path / f"raw/{basename}/" "2m_temperature/1979_2019").mkdir(parents=True)
data_path = tmp_path / f"raw/{basename}/" "2m_temperature/1979_2019/01_12.nc"
if granularity == "hourly":
dataset = self._make_era5_dataset(size=(100, 100), monthly=False)
else:
dataset = self._make_era5_dataset(size=(100, 100), monthly=True)
dataset.to_netcdf(path=data_path)
kenya = get_kenya()
regrid_dataset, _, _ = _make_dataset(
size=(20, 20),
latmin=kenya.latmin,
latmax=kenya.latmax,
lonmin=kenya.lonmin,
lonmax=kenya.lonmax,
)
regrid_path = tmp_path / "regridder.nc"
regrid_dataset.to_netcdf(regrid_path)
processor.preprocess(subset_str="kenya", regrid=regrid_path, parallel=False)
expected_out_path = (
tmp_path / f"interim/{basename}" "_preprocessed/data_kenya.nc"
)
assert (
expected_out_path.exists()
), f"Expected processed file to be saved to {expected_out_path}"
# check the subsetting happened correctly
out_data = xr.open_dataset(expected_out_path)
expected_dims = ["lat", "lon", "time"]
assert len(list(out_data.dims)) == len(expected_dims)
for dim in expected_dims:
assert dim in list(
out_data.dims
), f"Expected {dim} to be in the processed dataset dims"
lons = out_data.lon.values
assert (lons.min() >= kenya.lonmin) and (
lons.max() <= kenya.lonmax
), "Longitudes not correctly subset"
lats = out_data.lat.values
assert (lats.min() >= kenya.latmin) and (
lats.max() <= kenya.latmax
), "Latitudes not correctly subset"
assert out_data.t2m.values.shape[1:] == (20, 20)
assert (
not processor.interim.exists()
), f"Interim era5 folder should have been deleted"