def _preprocess_host_value(self, value, dtype):
value = to_cudf_compatible_scalar(value, dtype=dtype)
valid = not _is_null_host_scalar(value)
if dtype is None:
if not valid:
if isinstance(value, (np.datetime64, np.timedelta64)):
unit, _ = np.datetime_data(value)
if unit == "generic":
raise TypeError(
"Cant convert generic NaT to null scalar")
else:
dtype = value.dtype
else:
raise TypeError(
"dtype required when constructing a null scalar")
else:
dtype = value.dtype
dtype = np.dtype(dtype)
# temporary
dtype = np.dtype("object") if dtype.char == "U" else dtype
if not valid:
value = NA
return value, dtype
def _preprocess_host_value(self, value, dtype):
valid = not _is_null_host_scalar(value)
if isinstance(dtype, Decimal64Dtype):
value = pa.scalar(value,
type=pa.decimal128(dtype.precision,
dtype.scale)).as_py()
if isinstance(value, decimal.Decimal) and dtype is None:
dtype = Decimal64Dtype._from_decimal(value)
value = to_cudf_compatible_scalar(value, dtype=dtype)
if dtype is None:
if not valid:
if isinstance(value, (np.datetime64, np.timedelta64)):
unit, _ = np.datetime_data(value)
if unit == "generic":
raise TypeError(
"Cant convert generic NaT to null scalar")
else:
dtype = value.dtype
else:
raise TypeError(
"dtype required when constructing a null scalar")
else:
dtype = value.dtype
if not isinstance(dtype, Decimal64Dtype):
dtype = np.dtype(dtype)
if not valid:
value = NA
return value, dtype
def __getitem__(self, arg):
if isinstance(arg, tuple):
arg = list(arg)
data = self._sr._column[arg]
if is_scalar(data) or _is_null_host_scalar(data):
return data
index = self._sr.index.take(arg)
return self._sr._copy_construct(data=data, index=index)
def __getitem__(self, arg):
if isinstance(arg, tuple):
arg = list(arg)
data = self._sr._column[arg]
if (isinstance(data, (dict, list)) or _is_scalar_or_zero_d_array(data)
or _is_null_host_scalar(data)):
return data
return self._sr._from_data({self._sr.name: data},
index=cudf.Index(self._sr.index.take(arg)))
def to_cudf_compatible_scalar(val, dtype=None):
"""
Converts the value `val` to a numpy/Pandas scalar,
optionally casting to `dtype`.
If `val` is None, returns None.
"""
if _is_null_host_scalar(val) or isinstance(val, cudf.Scalar):
return val
if not is_scalar(val):
raise ValueError(
f"Cannot convert value of type {type(val).__name__} "
" to cudf scalar"
)
if isinstance(val, (np.ndarray, cp.ndarray)) and val.ndim == 0:
val = val.item()
if ((dtype is None) and isinstance(val, str)) or is_string_dtype(dtype):
dtype = "str"
if isinstance(val, dt.datetime):
val = np.datetime64(val)
elif isinstance(val, dt.timedelta):
val = np.timedelta64(val)
elif isinstance(val, pd.Timestamp):
val = val.to_datetime64()
elif isinstance(val, pd.Timedelta):
val = val.to_timedelta64()
val = pd.api.types.pandas_dtype(type(val)).type(val)
if dtype is not None:
val = val.astype(dtype)
if val.dtype.type is np.datetime64:
time_unit, _ = np.datetime_data(val.dtype)
if time_unit in ("D", "W", "M", "Y"):
val = val.astype("datetime64[s]")
elif val.dtype.type is np.timedelta64:
time_unit, _ = np.datetime_data(val.dtype)
if time_unit in ("D", "W", "M", "Y"):
val = val.astype("timedelta64[ns]")
return val
def _preprocess_host_value(self, value, dtype):
if isinstance(dtype, Decimal64Dtype):
# TODO: Support coercion from decimal.Decimal to different dtype
# TODO: Support coercion from integer to Decimal64Dtype
raise NotImplementedError(
"dtype as cudf.Decimal64Dtype is not supported. Pass a "
"decimal.Decimal to construct a DecimalScalar.")
if isinstance(value, decimal.Decimal) and dtype is not None:
raise TypeError(f"Can not coerce decimal to {dtype}")
value = to_cudf_compatible_scalar(value, dtype=dtype)
valid = not _is_null_host_scalar(value)
if isinstance(value, decimal.Decimal):
# 0.0042 -> Decimal64Dtype(2, 4)
dtype = Decimal64Dtype._from_decimal(value)
else:
if dtype is None:
if not valid:
if isinstance(value, (np.datetime64, np.timedelta64)):
unit, _ = np.datetime_data(value)
if unit == "generic":
raise TypeError(
"Cant convert generic NaT to null scalar")
else:
dtype = value.dtype
else:
raise TypeError(
"dtype required when constructing a null scalar")
else:
dtype = value.dtype
dtype = np.dtype(dtype)
# temporary
dtype = np.dtype("object") if dtype.char == "U" else dtype
if not valid:
value = NA
return value, dtype
def is_valid(self):
if not self._is_host_value_current:
self._device_value_to_host()
return not _is_null_host_scalar(self._host_value)
