Skip to content

REF: de-duplicate IntervalIndex._intersection #41929

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
Jun 10, 2021
Merged

REF: de-duplicate IntervalIndex._intersection #41929

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
50 changes: 0 additions & 50 deletions pandas/core/indexes/interval.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -802,56 +802,6 @@ def _format_data(self, name=None) -> str:
# name argument is unused here; just for compat with base / categorical
return self._data._format_data() + "," + self._format_space()

# --------------------------------------------------------------------
# Set Operations

def _intersection(self, other, sort):
"""
intersection specialized to the case with matching dtypes.
"""
# For IntervalIndex we also know other.closed == self.closed
if self.left.is_unique and self.right.is_unique:
return super()._intersection(other, sort=sort)
elif other.left.is_unique and other.right.is_unique and self.isna().sum() <= 1:
# Swap other/self if other is unique and self does not have
# multiple NaNs
return super()._intersection(other, sort=sort)
else:
# duplicates
taken = self._intersection_non_unique(other)

if sort is None:
taken = taken.sort_values()

return taken

def _intersection_non_unique(self, other: IntervalIndex) -> IntervalIndex:
"""
Used when the IntervalIndex does have some common endpoints,
on either sides.
Return the intersection with another IntervalIndex.

Parameters
----------
other : IntervalIndex

Returns
-------
IntervalIndex
"""
mask = np.zeros(len(self), dtype=bool)

if self.hasnans and other.hasnans:
first_nan_loc = np.arange(len(self))[self.isna()][0]
mask[first_nan_loc] = True

other_tups = set(zip(other.left, other.right))
for i, tup in enumerate(zip(self.left, self.right)):
if tup in other_tups:
mask[i] = True

return self[mask]

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

@property
Expand Down