Skip to content
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.

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

REF: implement _get_engine_target #32611

Merged
merged 1 commit into from
Mar 12, 2020
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
25 changes: 16 additions & 9 deletions pandas/core/indexes/base.py
Original file line number Diff line number Diff line change
Expand Up @@ -567,10 +567,10 @@ def _cleanup(self):
def _engine(self):
# property, for now, slow to look up

# to avoid a reference cycle, bind `_ndarray_values` to a local variable, so
# to avoid a reference cycle, bind `target_values` to a local variable, so
# `self` is not passed into the lambda.
_ndarray_values = self._ndarray_values
return self._engine_type(lambda: _ndarray_values, len(self))
target_values = self._get_engine_target()
return self._engine_type(lambda: target_values, len(self))

# --------------------------------------------------------------------
# Array-Like Methods
Expand Down Expand Up @@ -2972,7 +2972,7 @@ def get_indexer(
"backfill or nearest reindexing"
)

indexer = self._engine.get_indexer(target._ndarray_values)
indexer = self._engine.get_indexer(target._get_engine_target())

return ensure_platform_int(indexer)

Expand All @@ -2986,19 +2986,20 @@ def _convert_tolerance(self, tolerance, target):
def _get_fill_indexer(
self, target: "Index", method: str_t, limit=None, tolerance=None
) -> np.ndarray:

target_values = target._get_engine_target()

if self.is_monotonic_increasing and target.is_monotonic_increasing:
engine_method = (
self._engine.get_pad_indexer
if method == "pad"
else self._engine.get_backfill_indexer
)
indexer = engine_method(target._ndarray_values, limit)
indexer = engine_method(target_values, limit)
else:
indexer = self._get_fill_indexer_searchsorted(target, method, limit)
if tolerance is not None:
indexer = self._filter_indexer_tolerance(
target._ndarray_values, indexer, tolerance
)
indexer = self._filter_indexer_tolerance(target_values, indexer, tolerance)
return indexer

def _get_fill_indexer_searchsorted(
Expand Down Expand Up @@ -3911,6 +3912,12 @@ def _internal_get_values(self) -> np.ndarray:
"""
return self.values

def _get_engine_target(self) -> np.ndarray:
"""
Get the ndarray that we can pass to the IndexEngine constructor.
"""
return self._values

@Appender(IndexOpsMixin.memory_usage.__doc__)
def memory_usage(self, deep: bool = False) -> int:
result = super().memory_usage(deep=deep)
Expand Down Expand Up @@ -4653,7 +4660,7 @@ def get_indexer_non_unique(self, target):
elif self.is_all_dates and target.is_all_dates: # GH 30399
tgt_values = target.asi8
else:
tgt_values = target._ndarray_values
tgt_values = target._get_engine_target()

indexer, missing = self._engine.get_indexer_non_unique(tgt_values)
return ensure_platform_int(indexer), missing
Expand Down
3 changes: 3 additions & 0 deletions pandas/core/indexes/extension.py
Original file line number Diff line number Diff line change
Expand Up @@ -231,6 +231,9 @@ def __array__(self, dtype=None) -> np.ndarray:
def _ndarray_values(self) -> np.ndarray:
return self._data._ndarray_values

def _get_engine_target(self) -> np.ndarray:
return self._data._values_for_argsort()

@Appender(Index.dropna.__doc__)
def dropna(self, how="any"):
if how not in ("any", "all"):
Expand Down