Skip to content

feat: apply unit conversion during zarr build #78

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

Closed
turban wants to merge 1 commit into from
Closed

feat: apply unit conversion during zarr build #78

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
27 changes: 27 additions & 0 deletions src/climate_api/data_manager/services/downloader.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -143,6 +143,7 @@ def build_dataset_zarr(dataset: dict[str, Any], *, start: str | None = None, end
dims = [lon_dim, lat_dim]

ds = _select_time_range(ds, dataset=dataset, start=start, end=end)
ds = _apply_unit_conversion(ds, dataset)

xmin = ds[lon_dim].min().item()
xmax = ds[lon_dim].max().item()
Expand Down Expand Up @@ -243,6 +244,32 @@ def _select_time_range(
return selected


_UNIT_CONVERSIONS: dict[tuple[str, str], tuple[str, float, float]] = {
# (from, to): (display_label, scale, offset) — applied as: value * scale + offset
("kelvin", "degc"): ("degC", 1.0, -273.15),
("m", "mm"): ("mm", 1000.0, 0.0),
}


def _apply_unit_conversion(ds: xr.Dataset, dataset: dict[str, Any]) -> xr.Dataset:
convert_to = dataset.get("convert_units")
if not convert_to:
return ds
units = dataset.get("units", "")
key = (units.lower(), convert_to.lower())
conversion = _UNIT_CONVERSIONS.get(key)
if conversion is None:
logger.warning("No unit conversion defined for %s -> %s; skipping", units, convert_to)
return ds
label, scale, offset = conversion
varname = dataset["variable"]
logger.info("Converting %s from %s to %s", varname, units, label)
da = ds[varname]
converted = da * scale + offset if scale != 1.0 else da + offset
ds = ds.assign({varname: converted.assign_attrs({**da.attrs, "units": label})})
return ds


def _compute_time_space_chunks(
ds: xr.Dataset,
dataset: dict[str, Any],
Expand Down
Loading