Skip to content

REF: de-duplicate CategoricalIndex._get_indexer #42042

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 2 commits into from
Jun 16, 2021
Merged

REF: de-duplicate CategoricalIndex._get_indexer #42042

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2e5c986
REF: de-duplicate CategoricalIndex._get_indexer
jbrockmendel Jun 13, 2021
79140c2
REF: de-duplicate get_indexer_non_unique
jbrockmendel Jun 13, 2021
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
1 change: 1 addition & 0 deletions pandas/core/indexes/base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5167,6 +5167,7 @@ def set_value(self, arr, key, value):
def get_indexer_non_unique(self, target) -> tuple[np.ndarray, np.ndarray]:
# both returned ndarrays are np.intp
target = ensure_index(target)
target = self._maybe_cast_listlike_indexer(target)

if not self._should_compare(target) and not is_interval_dtype(self.dtype):
# IntervalIndex get special treatment bc numeric scalars can be
Expand Down
49 changes: 7 additions & 42 deletions pandas/core/indexes/category.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,17 +12,12 @@

from pandas._libs import index as libindex
from pandas._typing import (
ArrayLike,
Dtype,
DtypeObj,
)
from pandas.util._decorators import (
Appender,
doc,
)
from pandas.util._decorators import doc

from pandas.core.dtypes.common import (
ensure_platform_int,
is_categorical_dtype,
is_scalar,
)
Expand All @@ -41,7 +36,6 @@
import pandas.core.indexes.base as ibase
from pandas.core.indexes.base import (
Index,
_index_shared_docs,
maybe_extract_name,
)
from pandas.core.indexes.extension import (
Expand Down Expand Up @@ -492,38 +486,9 @@ def _maybe_cast_indexer(self, key) -> int:
return -1
raise

def _get_indexer(
self,
target: Index,
method: str | None = None,
limit: int | None = None,
tolerance=None,
) -> np.ndarray:
# returned ndarray is np.intp

if self.equals(target):
return np.arange(len(self), dtype="intp")

return self._get_indexer_non_unique(target._values)[0]

@Appender(_index_shared_docs["get_indexer_non_unique"] % _index_doc_kwargs)
def get_indexer_non_unique(self, target) -> tuple[np.ndarray, np.ndarray]:
# both returned ndarrays are np.intp
target = ibase.ensure_index(target)
return self._get_indexer_non_unique(target._values)

def _get_indexer_non_unique(
self, values: ArrayLike
) -> tuple[np.ndarray, np.ndarray]:
# both returned ndarrays are np.intp
"""
get_indexer_non_unique but after unrapping the target Index object.
"""
# Note: we use engine.get_indexer_non_unique for get_indexer in addition
# to get_indexer_non_unique because, even if `target` is unique, any
# non-category entries in it will be encoded as -1 so `codes` may
# not be unique.

def _maybe_cast_listlike_indexer(self, values) -> CategoricalIndex:
if isinstance(values, CategoricalIndex):
values = values._data
if isinstance(values, Categorical):
# Indexing on codes is more efficient if categories are the same,
# so we can apply some optimizations based on the degree of
Expand All @@ -532,9 +497,9 @@ def _get_indexer_non_unique(
codes = cat._codes
else:
codes = self.categories.get_indexer(values)

indexer, missing = self._engine.get_indexer_non_unique(codes)
return ensure_platform_int(indexer), ensure_platform_int(missing)
codes = codes.astype(self.codes.dtype, copy=False)
cat = self._data._from_backing_data(codes)
return type(self)._simple_new(cat)

# --------------------------------------------------------------------

Expand Down
8 changes: 7 additions & 1 deletion pandas/core/indexes/datetimelike.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,6 +45,7 @@

from pandas.core.arrays import (
DatetimeArray,
ExtensionArray,
PeriodArray,
TimedeltaArray,
)
Expand Down Expand Up @@ -595,7 +596,12 @@ def _maybe_cast_listlike_indexer(self, keyarr):
try:
res = self._data._validate_listlike(keyarr, allow_object=True)
except (ValueError, TypeError):
res = com.asarray_tuplesafe(keyarr)
if not isinstance(keyarr, ExtensionArray):
# e.g. we don't want to cast DTA to ndarray[object]
res = com.asarray_tuplesafe(keyarr)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

should we just have ExtensionArray pass thru asarray_tuplesafe (would need to change the return signature), not sure if this is used enough to warrant but a thought.

# TODO: com.asarray_tuplesafe shouldn't cast e.g. DatetimeArray
else:
res = keyarr
return Index(res, dtype=res.dtype)


Expand Down