[BUG] sr.dt.tz_localize(...) fails on timezone-aware dask-cuDF series
#13602
Assignees
Labels
bug
Something isn't working
Comments
charlesbluca
added
bug
|
Thanks @charlesbluca -- the following patch fixes this particular issue for me, but are you able to try it out with some other tests to see if things more or less work? If so, I'll go ahead and make a PR: diff --git a/python/dask_cudf/dask_cudf/backends.py b/python/dask_cudf/dask_cudf/backends.py
index 378f46de22..e926911364 100644
--- a/python/dask_cudf/dask_cudf/backends.py
+++ b/python/dask_cudf/dask_cudf/backends.py
@@ -6,6 +6,7 @@ from collections.abc import Iterator
import cupy as cp
import numpy as np
import pandas as pd
+from pandas.core.tools.datetimes import is_datetime64tz_dtype
import pyarrow as pa
from pandas.api.types import is_scalar
@@ -122,6 +123,11 @@ def _get_non_empty_data(s):
data = cudf.core.column.as_column(data, dtype=s.dtype)
elif is_string_dtype(s.dtype):
data = pa.array(["cat", "dog"])
+ elif is_datetime64tz_dtype(s.dtype):
+ from cudf.utils.dtypes import get_time_unit
+
+ data = cudf.date_range("2001-01-01", periods=2, freq=get_time_unit(s))
+ data = data.tz_localize(str(s.dtype.tz))._column
else:
if pd.api.types.is_numeric_dtype(s.dtype):
data = cudf.core.column.as_column( |
rapids-bot bot
pushed a commit
that referenced
this issue
Jun 26, 2023
Closes #13602 Authors: - Ashwin Srinath (https://github.com/shwina) Approvers: - GALI PREM SAGAR (https://github.com/galipremsagar) URL: #13610
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Describe the bug
We currently get a
TypeErrorduring meta construction when attemptingsr.dt.tz_localize(...)on a timezone-aware dask-cuDF series:File /datasets/charlesb/micromamba/envs/dask-sql-gpuci-py39/lib/python3.9/site-packages/dask/dataframe/accessor.py:14, in _bind_method.<locals>.func(self, *args, **kwargs) 13 def func(self, *args, **kwargs): ---> 14 return self._function_map(attr, *args, **kwargs) File /datasets/charlesb/micromamba/envs/dask-sql-gpuci-py39/lib/python3.9/site-packages/dask/dataframe/accessor.py:111, in Accessor._function_map(self, attr, *args, **kwargs) 108 meta = kwargs.pop("meta") 109 else: 110 meta = self._delegate_method( --> 111 self._series._meta_nonempty, self._accessor_name, attr, args, kwargs 112 ) 113 token = f"{self._accessor_name}-{attr}" 114 return self._series.map_partitions( 115 self._delegate_method, 116 self._accessor_name, (...) 122 token=token, 123 ) File /datasets/charlesb/micromamba/envs/dask-sql-gpuci-py39/lib/python3.9/site-packages/dask/dataframe/core.py:566, in _Frame._meta_nonempty(self) 563 @property 564 def _meta_nonempty(self): 565 """A non-empty version of `_meta` with fake data.""" --> 566 return meta_nonempty(self._meta) File /datasets/charlesb/micromamba/envs/dask-sql-gpuci-py39/lib/python3.9/site-packages/dask/utils.py:642, in Dispatch.__call__(self, arg, *args, **kwargs) 638 """ 639 Call the corresponding method based on type of argument. 640 """ 641 meth = self.dispatch(type(arg)) --> 642 return meth(arg, *args, **kwargs) File /datasets/charlesb/micromamba/envs/dask-sql-gpuci-py39/lib/python3.9/site-packages/nvtx/nvtx.py:101, in annotate.__call__.<locals>.inner(*args, **kwargs) 98 @wraps(func) 99 def inner(*args, **kwargs): 100 libnvtx_push_range(self.attributes, self.domain.handle) --> 101 result = func(*args, **kwargs) 102 libnvtx_pop_range(self.domain.handle) 103 return result File /datasets/charlesb/micromamba/envs/dask-sql-gpuci-py39/lib/python3.9/site-packages/dask_cudf/backends.py:142, in _nonempty_series(s, idx) 140 if idx is None: 141 idx = _nonempty_index(s.index) --> 142 data = _get_non_empty_data(s._column) 144 return cudf.Series(data, name=s.name, index=idx) File /datasets/charlesb/micromamba/envs/dask-sql-gpuci-py39/lib/python3.9/site-packages/nvtx/nvtx.py:101, in annotate.__call__.<locals>.inner(*args, **kwargs) 98 @wraps(func) 99 def inner(*args, **kwargs): 100 libnvtx_push_range(self.attributes, self.domain.handle) --> 101 result = func(*args, **kwargs) 102 libnvtx_pop_range(self.domain.handle) 103 return result File /datasets/charlesb/micromamba/envs/dask-sql-gpuci-py39/lib/python3.9/site-packages/dask_cudf/backends.py:131, in _get_non_empty_data(s) 127 data = cudf.core.column.as_column( 128 cp.arange(start=0, stop=2, dtype=s.dtype) 129 ) 130 else: --> 131 data = cudf.core.column.as_column( 132 cp.arange(start=0, stop=2, dtype="int64") 133 ).astype(s.dtype) 134 return data File /datasets/charlesb/micromamba/envs/dask-sql-gpuci-py39/lib/python3.9/site-packages/cudf/core/column/column.py:987, in ColumnBase.astype(self, dtype, **kwargs) 985 elif is_decimal_dtype(dtype): 986 return self.as_decimal_column(dtype, **kwargs) --> 987 elif np.issubdtype(cast(Any, dtype), np.datetime64): 988 return self.as_datetime_column(dtype, **kwargs) 989 elif np.issubdtype(cast(Any, dtype), np.timedelta64): File /datasets/charlesb/micromamba/envs/dask-sql-gpuci-py39/lib/python3.9/site-packages/numpy/core/numerictypes.py:416, in issubdtype(arg1, arg2) 358 r""" 359 Returns True if first argument is a typecode lower/equal in type hierarchy. 360 (...) 413 414 """ 415 if not issubclass_(arg1, generic): --> 416 arg1 = dtype(arg1).type 417 if not issubclass_(arg2, generic): 418 arg2 = dtype(arg2).type TypeError: Cannot interpret 'datetime64[ns, UTC]' as a data typeSteps/Code to reproduce bug
Expected behavior
Would expect this operation to pass and change the timezone of the datetime data accordingly.
Environment overview (please complete the following information)
Environment details
Click here to see environment details
The text was updated successfully, but these errors were encountered: