Skip to content
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

Observations: Fix the variables and units in the CSV header #238

Merged
merged 1 commit into from
Nov 18, 2024
Merged

Observations: Fix the variables and units in the CSV header #238

Show file tree
Hide file tree
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
14 changes: 8 additions & 6 deletions cads_adaptors/adaptors/cadsobs/csv.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,6 @@
import logging
from pathlib import Path

import dask
import xarray

from cads_adaptors.adaptors.cadsobs.models import RetrieveArgs
Expand Down Expand Up @@ -66,11 +65,14 @@ def get_csv_header(
time_end = "{:%Y%m%d}".format(
cdm_lite_dataset.report_timestamp[-1].compute().dt.date
)
vars_and_units = zip(
dask.array.unique(cdm_lite_dataset.observed_variable.data)
.compute()
.astype("U"),
dask.array.unique(cdm_lite_dataset.units.data).compute().astype("U"),
# Subset the dataset to get variables and units, drop duplicates, encode and convert
# to tuples.
vars_and_units = list(
cdm_lite_dataset[["observed_variable", "units"]]
.to_dataframe()
.drop_duplicates()
.astype("U")
.itertuples(index=False, name=None)
)
varstr = "\n".join([f"# {v} [{u}]" for v, u in vars_and_units])
header_params = dict(
Expand Down
22 changes: 21 additions & 1 deletion tests/test_cadsobs_adaptor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -126,7 +126,7 @@ def _send_request(self, endpoint, method, payload):
TEST_REQUEST = {
"time_aggregation": "daily",
"format": "netCDF",
"variable": ["maximum_air_temperature"],
"variable": ["maximum_air_temperature", "maximum_relative_humidity"],
"year": ["2007"],
"month": ["11"],
"day": [
Expand Down Expand Up @@ -185,6 +185,26 @@ def test_adaptor(tmp_path, monkeypatch):
assert actual.dimensions["index"].size > 0


def test_adaptor_csv(tmp_path, monkeypatch):
monkeypatch.setattr(
"cads_adaptors.adaptors.cadsobs.adaptor.CadsobsApiClient",
MockerCadsobsApiClient,
)
test_form = {}

adaptor = ObservationsAdaptor(test_form, **TEST_ADAPTOR_CONFIG)
test_request_csv = TEST_REQUEST.copy()
test_request_csv["format"] = "csv"
result = adaptor.retrieve(test_request_csv)
tempfile = Path(tmp_path, "test_adaptor.csv")
with tempfile.open("wb") as tmpf:
tmpf.write(result.read())
assert tempfile.stat().st_size > 0
file_lines = tempfile.read_text().split("\n")
assert "# daily_maximum_air_temperature [K]" in file_lines
assert "# daily_maximum_relative_humidity [%]" in file_lines


def test_adaptor_error(tmp_path, monkeypatch):
monkeypatch.setattr(
"cads_adaptors.adaptors.cadsobs.adaptor.CadsobsApiClient",
Expand Down