Skip to content

REF: Refactor merge array conversions for factorizer #49978

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Dec 1, 2022
Merged

REF: Refactor merge array conversions for factorizer #49978

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
65 changes: 36 additions & 29 deletions pandas/core/reshape/merge.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2364,35 +2364,7 @@ def _factorize_keys(
# "_values_for_factorize"
rk, _ = rk._values_for_factorize() # type: ignore[union-attr]

klass: type[libhashtable.Factorizer]
if is_numeric_dtype(lk.dtype):
if not is_dtype_equal(lk, rk):
dtype = find_common_type([lk.dtype, rk.dtype])
if isinstance(dtype, ExtensionDtype):
cls = dtype.construct_array_type()
if not isinstance(lk, ExtensionArray):
lk = cls._from_sequence(lk, dtype=dtype, copy=False)
else:
lk = lk.astype(dtype)

if not isinstance(rk, ExtensionArray):
rk = cls._from_sequence(rk, dtype=dtype, copy=False)
else:
rk = rk.astype(dtype)
else:
lk = lk.astype(dtype)
rk = rk.astype(dtype)
if isinstance(lk, BaseMaskedArray):
# Invalid index type "type" for "Dict[Type[object], Type[Factorizer]]";
# expected type "Type[object]"
klass = _factorizers[lk.dtype.type] # type: ignore[index]
else:
klass = _factorizers[lk.dtype.type]

else:
klass = libhashtable.ObjectFactorizer
lk = ensure_object(lk)
rk = ensure_object(rk)
klass, lk, rk = _convert_arrays_and_get_rizer_klass(lk, rk)

rizer = klass(max(len(lk), len(rk)))

Expand Down Expand Up @@ -2433,6 +2405,41 @@ def _factorize_keys(
return llab, rlab, count


def _convert_arrays_and_get_rizer_klass(
lk: ArrayLike, rk: ArrayLike
) -> tuple[type[libhashtable.Factorizer], ArrayLike, ArrayLike]:
klass: type[libhashtable.Factorizer]
if is_numeric_dtype(lk.dtype):
if not is_dtype_equal(lk, rk):
dtype = find_common_type([lk.dtype, rk.dtype])
if isinstance(dtype, ExtensionDtype):
cls = dtype.construct_array_type()
if not isinstance(lk, ExtensionArray):
lk = cls._from_sequence(lk, dtype=dtype, copy=False)
else:
lk = lk.astype(dtype)

if not isinstance(rk, ExtensionArray):
rk = cls._from_sequence(rk, dtype=dtype, copy=False)
else:
rk = rk.astype(dtype)
else:
lk = lk.astype(dtype)
rk = rk.astype(dtype)
if isinstance(lk, BaseMaskedArray):
# Invalid index type "type" for "Dict[Type[object], Type[Factorizer]]";
# expected type "Type[object]"
klass = _factorizers[lk.dtype.type] # type: ignore[index]
else:
klass = _factorizers[lk.dtype.type]

else:
klass = libhashtable.ObjectFactorizer
lk = ensure_object(lk)
rk = ensure_object(rk)
return klass, lk, rk


def _sort_labels(
uniques: np.ndarray, left: npt.NDArray[np.intp], right: npt.NDArray[np.intp]
) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]]:
Expand Down