def factorize(
self,
sort: bool = False,
na_sentinel: int | lib.NoDefault = lib.no_default,
use_na_sentinel: bool | lib.NoDefault = lib.no_default,
) -> tuple[npt.NDArray[np.intp], RangeIndex]:
# resolve to emit warning if appropriate
resolve_na_sentinel(na_sentinel, use_na_sentinel)
codes = np.arange(len(self), dtype=np.intp)
uniques = self
if sort and self.step < 0:
codes = codes[::-1]
uniques = uniques[::-1]
return codes, uniques
def factorize(
self,
na_sentinel: int | lib.NoDefault = lib.no_default,
use_na_sentinel: bool | lib.NoDefault = lib.no_default,
) -> tuple[np.ndarray, ExtensionArray]:
resolved_na_sentinel = resolve_na_sentinel(na_sentinel,
use_na_sentinel)
if resolved_na_sentinel is None:
raise NotImplementedError(
"Encoding NaN values is not yet implemented")
else:
na_sentinel = resolved_na_sentinel
encoded = self._data.dictionary_encode()
indices = pa.chunked_array([c.indices for c in encoded.chunks],
type=encoded.type.index_type).to_pandas()
if indices.dtype.kind == "f":
indices[np.isnan(indices)] = na_sentinel
indices = indices.astype(np.int64, copy=False)
if encoded.num_chunks:
uniques = type(self)(encoded.chunk(0).dictionary)
else:
uniques = type(self)(pa.array([], type=encoded.type.value_type))
return indices.values, uniques
def factorize(
self,
na_sentinel: int | lib.NoDefault = lib.no_default,
use_na_sentinel: bool | lib.NoDefault = lib.no_default,
) -> tuple[np.ndarray, ExtensionArray]:
resolved_na_sentinel = algos.resolve_na_sentinel(
na_sentinel, use_na_sentinel)
if resolved_na_sentinel is None:
raise NotImplementedError(
"Encoding NaN values is not yet implemented")
else:
na_sentinel = resolved_na_sentinel
arr = self._data
mask = self._mask
codes, uniques = factorize_array(arr,
na_sentinel=na_sentinel,
mask=mask)
# check that factorize_array correctly preserves dtype.
assert uniques.dtype == self.dtype.numpy_dtype, (uniques.dtype,
self.dtype)
uniques_ea = type(self)(uniques, np.zeros(len(uniques), dtype=bool))
return codes, uniques_ea