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.

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

Support dask arrays in datetime_to_numeric #6556

Merged
merged 8 commits into from
May 31, 2022
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
22 changes: 19 additions & 3 deletions xarray/core/duck_array_ops.py
Original file line number Diff line number Diff line change
Expand Up @@ -431,7 +431,14 @@ def datetime_to_numeric(array, offset=None, datetime_unit=None, dtype=float):
# Compute timedelta object.
# For np.datetime64, this can silently yield garbage due to overflow.
# One option is to enforce 1970-01-01 as the universal offset.
array = array - offset

# This map_blocks call is for backwards compatibility.
# dask == 2021.04.1 does not support subtracting object arrays
# which is required for cftime
if is_duck_dask_array(array) and np.issubdtype(array.dtype, np.object):
array = array.map_blocks(lambda a, b: a - b, offset, meta=array._meta)
else:
array = array - offset

# Scalar is converted to 0d-array
if not hasattr(array, "dtype"):
Expand Down Expand Up @@ -517,10 +524,19 @@ def pd_timedelta_to_float(value, datetime_unit):
return np_timedelta64_to_float(value, datetime_unit)


def _timedelta_to_seconds(array):
return np.reshape([a.total_seconds() for a in array.ravel()], array.shape) * 1e6


def py_timedelta_to_float(array, datetime_unit):
"""Convert a timedelta object to a float, possibly at a loss of resolution."""
array = np.asarray(array)
array = np.reshape([a.total_seconds() for a in array.ravel()], array.shape) * 1e6
array = asarray(array)
if is_duck_dask_array(array):
array = array.map_blocks(
_timedelta_to_seconds, meta=np.array([], dtype=np.float64)
)
else:
array = _timedelta_to_seconds(array)
conversion_factor = np.timedelta64(1, "us") / np.timedelta64(1, datetime_unit)
return conversion_factor * array

Expand Down
49 changes: 39 additions & 10 deletions xarray/tests/test_duck_array_ops.py
Original file line number Diff line number Diff line change
Expand Up @@ -675,39 +675,68 @@ def test_multiple_dims(dtype, dask, skipna, func):
assert_allclose(actual, expected)


def test_datetime_to_numeric_datetime64():
@pytest.mark.parametrize("dask", [True, False])
def test_datetime_to_numeric_datetime64(dask):
if dask and not has_dask:
pytest.skip("requires dask")

times = pd.date_range("2000", periods=5, freq="7D").values
result = duck_array_ops.datetime_to_numeric(times, datetime_unit="h")
if dask:
import dask.array

times = dask.array.from_array(times, chunks=-1)

with raise_if_dask_computes():
result = duck_array_ops.datetime_to_numeric(times, datetime_unit="h")
expected = 24 * np.arange(0, 35, 7)
np.testing.assert_array_equal(result, expected)

offset = times[1]
result = duck_array_ops.datetime_to_numeric(times, offset=offset, datetime_unit="h")
with raise_if_dask_computes():
result = duck_array_ops.datetime_to_numeric(
times, offset=offset, datetime_unit="h"
)
expected = 24 * np.arange(-7, 28, 7)
np.testing.assert_array_equal(result, expected)

dtype = np.float32
result = duck_array_ops.datetime_to_numeric(times, datetime_unit="h", dtype=dtype)
with raise_if_dask_computes():
result = duck_array_ops.datetime_to_numeric(
times, datetime_unit="h", dtype=dtype
)
expected = 24 * np.arange(0, 35, 7).astype(dtype)
np.testing.assert_array_equal(result, expected)


@requires_cftime
def test_datetime_to_numeric_cftime():
@pytest.mark.parametrize("dask", [True, False])
def test_datetime_to_numeric_cftime(dask):
if dask and not has_dask:
pytest.skip("requires dask")

times = cftime_range("2000", periods=5, freq="7D", calendar="standard").values
result = duck_array_ops.datetime_to_numeric(times, datetime_unit="h", dtype=int)
if dask:
import dask.array

times = dask.array.from_array(times, chunks=-1)
with raise_if_dask_computes():
result = duck_array_ops.datetime_to_numeric(times, datetime_unit="h", dtype=int)
expected = 24 * np.arange(0, 35, 7)
np.testing.assert_array_equal(result, expected)

offset = times[1]
result = duck_array_ops.datetime_to_numeric(
times, offset=offset, datetime_unit="h", dtype=int
)
with raise_if_dask_computes():
result = duck_array_ops.datetime_to_numeric(
times, offset=offset, datetime_unit="h", dtype=int
)
expected = 24 * np.arange(-7, 28, 7)
np.testing.assert_array_equal(result, expected)

dtype = np.float32
result = duck_array_ops.datetime_to_numeric(times, datetime_unit="h", dtype=dtype)
with raise_if_dask_computes():
result = duck_array_ops.datetime_to_numeric(
times, datetime_unit="h", dtype=dtype
)
expected = 24 * np.arange(0, 35, 7).astype(dtype)
np.testing.assert_array_equal(result, expected)

Expand Down