Add comments

Author: treigerm

src/climatebenchpress/data_loader/datasets/cams.py

@@ -35,6 +35,8 @@ def download(download_path: Path, progress: bool = True):
     def open(download_path: Path) -> xr.Dataset:
         ds = xr.open_dataset(download_path / Path(NO2_FILE).name)
 
+        # Restrict data to a single day.
+        # The specific day is arbitrary.
         ds = ds.sel(valid_time=slice("2023-06-15", "2023-06-15"))
         # Needed to make the dataset CF-compliant.
         ds.longitude.attrs["axis"] = "X"

src/climatebenchpress/data_loader/datasets/cmip6/abc.py

@@ -48,7 +48,8 @@ def download_with(
         zstore = zstore.replace("gs://", "https://storage.googleapis.com/")
 
         ds = xr.open_zarr(fsspec.get_mapper(zstore), consolidated=True)
-        # Only select the year 2020 for the dataset.
+        # Only select the year 2020 for the dataset. The exact choice of this
+        # year is arbitrary,
         # .chunk(-1) ensures that we only use a single chunk for the entire dataset.
         ds = ds.sel(time=slice("2020", "2020")).chunk(-1)
         if variable_selector is not None:

src/climatebenchpress/data_loader/datasets/era5.py

@@ -26,6 +26,8 @@ def download(download_path: Path, progress: bool = True):
 
         era5 = xr.open_zarr(ERA5_GCP_PATH, chunks={"time": 48}, consolidated=True)
 
+        # Restrict data to a single day.
+        # The specific day is arbitrary.
         ds = era5.sel(time=slice("2020-03-01", "2020-03-01"))[
             [
                 "mean_sea_level_pressure",

src/climatebenchpress/data_loader/datasets/esa_biomass_cci.py

@@ -44,6 +44,10 @@ def open(download_path: Path) -> xr.Dataset:
         # Needed to make the dataset CF-compliant.
         ds.lon.attrs["axis"] = "X"
         ds.lat.attrs["axis"] = "Y"
+        # We are constraining the dataset to mainland France to reduce its overall size.
+        # The global snapshot would be around 20 GB, which is too large for our use case.
+        # We chose France because it should have a fairly diverse set of biomass estimates
+        # but the choice is overall somewhat arbitrary.
         ds = ds.sel(
             lon=slice(FRANCE_BBOX[0], FRANCE_BBOX[2]),
             lat=slice(FRANCE_BBOX[3], FRANCE_BBOX[1]),

src/climatebenchpress/data_loader/datasets/nextgems.py

@@ -44,6 +44,8 @@ def download(download_path: Path, progress: bool = True):
             zoom=ZOOM, time=TIME_RESOLUTION, chunks=dict()
         ).to_dask()
 
+        # Restrict data to a single day.
+        # The specific day is arbitrary.
         ds = icon[[PRECIP_KEY, OLR_KEY]].sel(time=slice("2020-03-01", "2020-03-01"))
         # Regrid the data to 0.125 degree resolution.
         # NOTE: