Raise error for more cases when timezone-aware data is passed to `a…

…s_column` (#13835)

Fixes: #13834 

This PR raises `NotImplementedError` for more types of data that are timezone-aware passed to `as_column`.

Authors:
  - GALI PREM SAGAR (https://github.com/galipremsagar)

Approvers:
  - Matthew Roeschke (https://github.com/mroeschke)
  - Bradley Dice (https://github.com/bdice)

URL: #13835

python/cudf/cudf/api/types.py

@@ -454,17 +454,23 @@ def is_any_real_numeric_dtype(arr_or_dtype) -> bool:
 # TODO: Evaluate which of the datetime types need special handling for cudf.
 is_datetime_dtype = _wrap_pandas_is_dtype_api(pd_types.is_datetime64_dtype)
 is_datetime64_any_dtype = pd_types.is_datetime64_any_dtype
-is_datetime64_dtype = pd_types.is_datetime64_dtype
-is_datetime64_ns_dtype = pd_types.is_datetime64_ns_dtype
-is_datetime64tz_dtype = pd_types.is_datetime64tz_dtype
+is_datetime64_dtype = _wrap_pandas_is_dtype_api(pd_types.is_datetime64_dtype)
+is_datetime64_ns_dtype = _wrap_pandas_is_dtype_api(
+    pd_types.is_datetime64_ns_dtype
+)
+is_datetime64tz_dtype = _wrap_pandas_is_dtype_api(
+    pd_types.is_datetime64tz_dtype
+)
 is_extension_type = pd_types.is_extension_type
 is_extension_array_dtype = pd_types.is_extension_array_dtype
 is_int64_dtype = pd_types.is_int64_dtype
 is_period_dtype = pd_types.is_period_dtype
 is_signed_integer_dtype = pd_types.is_signed_integer_dtype
 is_timedelta_dtype = _wrap_pandas_is_dtype_api(pd_types.is_timedelta64_dtype)
-is_timedelta64_dtype = pd_types.is_timedelta64_dtype
-is_timedelta64_ns_dtype = pd_types.is_timedelta64_ns_dtype
+is_timedelta64_dtype = _wrap_pandas_is_dtype_api(pd_types.is_timedelta64_dtype)
+is_timedelta64_ns_dtype = _wrap_pandas_is_dtype_api(
+    pd_types.is_timedelta64_ns_dtype
+)
 is_unsigned_integer_dtype = pd_types.is_unsigned_integer_dtype
 is_sparse = pd_types.is_sparse
 # is_list_like = pd_types.is_list_like

python/cudf/cudf/core/column/column.py

@@ -53,6 +53,7 @@
     infer_dtype,
     is_bool_dtype,
     is_categorical_dtype,
+    is_datetime64_dtype,
     is_datetime64tz_dtype,
     is_decimal32_dtype,
     is_decimal64_dtype,
@@ -2230,6 +2231,12 @@ def as_column(
         data = ColumnBase.from_scalar(arbitrary, length if length else 1)
     elif isinstance(arbitrary, pd.core.arrays.masked.BaseMaskedArray):
         data = as_column(pa.Array.from_pandas(arbitrary), dtype=dtype)
+    elif isinstance(arbitrary, pd.DatetimeIndex) and isinstance(
+        arbitrary.dtype, pd.DatetimeTZDtype
+    ):
+        raise NotImplementedError(
+            "cuDF does not yet support timezone-aware datetimes"
+        )
     else:
         try:
             data = as_column(
@@ -2279,6 +2286,18 @@ def as_column(
                             "Use `tz_localize()` to construct "
                             "timezone aware data."
                         )
+                    elif is_datetime64_dtype(dtype):
+                        # Error checking only, actual construction happens
+                        # below.
+                        pa_array = pa.array(arbitrary)
+                        if (
+                            isinstance(pa_array.type, pa.TimestampType)
+                            and pa_array.type.tz is not None
+                        ):
+                            raise NotImplementedError(
+                                "cuDF does not yet support timezone-aware "
+                                "datetimes"
+                            )
                     if is_list_dtype(dtype):
                         data = pa.array(arbitrary)
                         if type(data) not in (pa.ListArray, pa.NullArray):

python/cudf/cudf/tests/test_datetime.py

@@ -2093,6 +2093,8 @@ def test_construction_from_tz_timestamps(data):
         _ = cudf.Series(data)
     with pytest.raises(NotImplementedError):
         _ = cudf.Index(data)
+    with pytest.raises(NotImplementedError):
+        _ = cudf.DatetimeIndex(data)
 
 
 @pytest.mark.parametrize("op", _cmpops)