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

Jump to bottom

Fix and add test for groupby_bins() isnan TypeError. #3405

Merged
merged 3 commits into from
Oct 17, 2019
Merged

Fix and add test for groupby_bins() isnan TypeError. #3405

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
f5db2f0
Fix and add test for groupby_bins() isnan TypeError.
dnowacki-usgs Oct 15, 2019
8eec204
Better testing
dnowacki-usgs Oct 16, 2019
99fac7f
black
dnowacki-usgs Oct 16, 2019
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
2 changes: 1 addition & 1 deletion xarray/core/groupby.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -321,7 +321,7 @@ def __init__(
full_index = None

if bins is not None:
if np.isnan(bins).all():
if duck_array_ops.isnull(bins).all():
raise ValueError("All bin edges are NaN.")
binned = pd.cut(group.values, bins, **cut_kwargs)
new_dim_name = group.name + "_bins"
Expand Down
16 changes: 16 additions & 0 deletions xarray/tests/test_groupby.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -276,4 +276,20 @@ def test_groupby_grouping_errors():
dataset.to_array().groupby(dataset.foo * np.nan)


def test_groupby_bins_timeseries():
ds = xr.Dataset()
dnowacki-usgs marked this conversation as resolved.
Show resolved Hide resolved
ds["time"] = xr.DataArray(
pd.date_range("2010-08-01", "2010-08-15", freq="15min"), dims="time"
)
ds["val"] = xr.DataArray(np.ones(*ds["time"].shape), dims="time")
time_bins = pd.date_range(start="2010-08-01", end="2010-08-15", freq="24H")
actual = ds.groupby_bins("time", time_bins).sum()
expected = xr.DataArray(
96 * np.ones((14,)),
dims=["time_bins"],
coords={"time_bins": pd.cut(time_bins, time_bins).categories},
).to_dataset(name="val")
assert_identical(actual, expected)


# TODO: move other groupby tests from test_dataset and test_dataarray over here