def dtype(self):
dtype = self._col.dtype
if is_categorical_dtype(dtype):
codes = self._col.values.codes
(
_,
bitwidth,
c_arrow_dtype_f_str,
_,
) = self._dtype_from_pandasdtype(codes.dtype)
return (
DtypeKind.CATEGORICAL,
bitwidth,
c_arrow_dtype_f_str,
Endianness.NATIVE,
)
elif is_string_dtype(dtype):
if infer_dtype(self._col) == "string":
return (
DtypeKind.STRING,
8,
dtype_to_arrow_c_fmt(dtype),
Endianness.NATIVE,
)
raise NotImplementedError(
"Non-string object dtypes are not supported yet")
else:
return self._dtype_from_pandasdtype(dtype)
def _dtype_from_pandasdtype(self, dtype) -> Tuple[DtypeKind, int, str, str]:
"""
See `self.dtype` for details.
"""
# Note: 'c' (complex) not handled yet (not in array spec v1).
# 'b', 'B' (bytes), 'S', 'a', (old-style string) 'V' (void) not handled
# datetime and timedelta both map to datetime (is timedelta handled?)
kind = _NP_KINDS.get(dtype.kind, None)
if kind is None:
# Not a NumPy dtype. Check if it's a categorical maybe
raise ValueError(f"Data type {dtype} not supported by exchange protocol")
return (kind, dtype.itemsize * 8, dtype_to_arrow_c_fmt(dtype), dtype.byteorder)
def test_dtype_to_arrow_c_fmt(pandas_dtype, c_string): # PR01
"""Test ``dtype_to_arrow_c_fmt`` utility function."""
assert dtype_to_arrow_c_fmt(pandas_dtype) == c_string