def test_google_cmip_col():
try:
import intake
except ImportError:
intake = None
if intake is None:
with pytest.raises(ImportError):
col = google_cmip_col(catalog="main")
else:
col = google_cmip_col(catalog="main")
assert (col.catalog_file ==
"https://storage.googleapis.com/cmip6/pangeo-cmip6.csv")
with pytest.raises(ValueError):
col = google_cmip_col(catalog="wrong")
def data(source_id,
variable_id,
experiment_id,
grid_label,
use_intake_esm,
catalog="main"):
zarr_kwargs = {
"consolidated": True,
# "decode_times": False,
"decode_times": True,
"use_cftime": True,
}
cat = google_cmip_col(catalog=catalog).search(
source_id=source_id,
experiment_id=experiment_id,
variable_id=variable_id,
# member_id="r1i1p1f1",
table_id="Omon",
grid_label=grid_label,
)
if len(cat.df["zstore"]) > 0:
if use_intake_esm:
ddict = cat.to_dataset_dict(
zarr_kwargs=zarr_kwargs,
preprocess=combined_preprocessing,
storage_options={"token": "anon"},
)
_, ds = ddict.popitem()
else:
##### debugging options
# @charlesbluca suggested this to make this work in GHA
# https://github.com/jbusecke/cmip6_preprocessing/pull/62#issuecomment-741928365
mm = fsspec.get_mapper(
cat.df["zstore"]
[0]) # think you can pass in storage options here as well?
ds_raw = xr.open_zarr(mm, **zarr_kwargs)
ds = combined_preprocessing(ds_raw)
else:
ds = None
return ds, cat
def test_google_cmip_col():
col = google_cmip_col(catalog="main")
assert col.catalog_file == "https://storage.googleapis.com/cmip6/pangeo-cmip6.csv"
def all_models():
df = google_cmip_col().df
all_models = df["source_id"].unique()
all_models = tuple(np.sort(all_models))
# all_models = tuple(["EC-Earth3"])
return all_models