def intersection(self, other, sort=False):
self._validate_sort_keyword(sort)
self._assert_can_do_setop(other)
if self.equals(other):
return self._get_reconciled_name_object(other)
if len(self) == 0:
return self.copy()
if len(other) == 0:
return other.copy()
if not isinstance(other, type(self)):
result = Index.intersection(self, other, sort=sort)
if isinstance(result, type(self)):
if result.freq is None:
result.freq = to_offset(result.inferred_freq)
return result
elif (
other.freq is None
or self.freq is None
or other.freq != self.freq
or not other.freq.isAnchored()
or (not self.is_monotonic or not other.is_monotonic)
):
result = Index.intersection(self, other, sort=sort)
# Invalidate the freq of `result`, which may not be correct at
# this point, depending on the values.
result.freq = None
if hasattr(self, "tz"):
result = self._shallow_copy(
result._values, name=result.name, tz=result.tz, freq=None
)
else:
result = self._shallow_copy(result._values, name=result.name, freq=None)
if result.freq is None:
result.freq = to_offset(result.inferred_freq)
return result
# to make our life easier, "sort" the two ranges
if self[0] <= other[0]:
left, right = self, other
else:
left, right = other, self
# after sorting, the intersection always starts with the right index
# and ends with the index of which the last elements is smallest
end = min(left[-1], right[-1])
start = right[0]
if end < start:
return type(self)(data=[])
else:
lslice = slice(*left.slice_locs(start, end))
left_chunk = left.values[lslice]
return self._shallow_copy(left_chunk)
def intersection(self, other, sort=False):
self._validate_sort_keyword(sort)
self._assert_can_do_setop(other)
if self.equals(other):
return self._get_reconciled_name_object(other)
if len(self) == 0:
return self.copy()
if len(other) == 0:
return other.copy()
if not isinstance(other, type(self)):
result = Index.intersection(self, other, sort=sort)
if isinstance(result, type(self)):
if result.freq is None:
result.freq = to_offset(result.inferred_freq)
return result
elif (other.freq is None or self.freq is None or
other.freq != self.freq or
not other.freq.isAnchored() or
(not self.is_monotonic or not other.is_monotonic)):
result = Index.intersection(self, other, sort=sort)
# Invalidate the freq of `result`, which may not be correct at
# this point, depending on the values.
result.freq = None
if hasattr(self, 'tz'):
result = self._shallow_copy(result._values, name=result.name,
tz=result.tz, freq=None)
else:
result = self._shallow_copy(result._values, name=result.name,
freq=None)
if result.freq is None:
result.freq = to_offset(result.inferred_freq)
return result
# to make our life easier, "sort" the two ranges
if self[0] <= other[0]:
left, right = self, other
else:
left, right = other, self
# after sorting, the intersection always starts with the right index
# and ends with the index of which the last elements is smallest
end = min(left[-1], right[-1])
start = right[0]
if end < start:
return type(self)(data=[])
else:
lslice = slice(*left.slice_locs(start, end))
left_chunk = left.values[lslice]
return self._shallow_copy(left_chunk)
def _get_combined_index(
indexes: List[Index],
intersect: bool = False,
sort: bool = False,
copy: bool = False,
) -> Index:
"""
Return the union or intersection of indexes.
Parameters
----------
indexes : list of Index or list objects
When intersect=True, do not accept list of lists.
intersect : bool, default False
If True, calculate the intersection between indexes. Otherwise,
calculate the union.
sort : bool, default False
Whether the result index should come out sorted or not.
copy : bool, default False
If True, return a copy of the combined index.
Returns
-------
Index
"""
# TODO: handle index names!
indexes = _get_distinct_objs(indexes)
if len(indexes) == 0:
index = Index([])
elif len(indexes) == 1:
index = indexes[0]
elif intersect:
index = indexes[0]
for other in indexes[1:]:
index = index.intersection(other)
else:
index = union_indexes(indexes, sort=sort)
index = ensure_index(index)
if sort:
try:
index = index.sort_values()
except TypeError:
pass
# GH 29879
if copy:
index = index.copy()
return index
def _intersection(self, other: Index, sort=False) -> Index:
"""
intersection specialized to the case with matching dtypes.
"""
if len(self) == 0:
return self.copy()._get_reconciled_name_object(other)
if len(other) == 0:
return other.copy()._get_reconciled_name_object(self)
if not isinstance(other, type(self)):
result = Index.intersection(self, other, sort=sort)
if isinstance(result, type(self)):
if result.freq is None:
# TODO: no tests rely on this; needed?
result = result._with_freq("infer")
return result
elif not self._can_fast_intersect(other):
result = Index._intersection(self, other, sort=sort)
# We need to invalidate the freq because Index._intersection
# uses _shallow_copy on a view of self._data, which will preserve
# self.freq if we're not careful.
result = self._wrap_setop_result(other, result)
return result._with_freq(None)._with_freq("infer")
# to make our life easier, "sort" the two ranges
if self[0] <= other[0]:
left, right = self, other
else:
left, right = other, self
# after sorting, the intersection always starts with the right index
# and ends with the index of which the last elements is smallest
end = min(left[-1], right[-1])
start = right[0]
if end < start:
result = self[:0]
else:
lslice = slice(*left.slice_locs(start, end))
left_chunk = left._values[lslice]
# error: Argument 1 to "_simple_new" of "DatetimeIndexOpsMixin" has
# incompatible type "Union[ExtensionArray, Any]"; expected
# "Union[DatetimeArray, TimedeltaArray, PeriodArray]" [arg-type]
result = type(self)._simple_new(left_chunk) # type: ignore[arg-type]
return self._wrap_setop_result(other, result)
def intersection(self, other):
"""
Specialized intersection for TimedeltaIndex objects. May be much faster
than Index.intersection
Parameters
----------
other : TimedeltaIndex or array-like
Returns
-------
y : Index or TimedeltaIndex
"""
self._assert_can_do_setop(other)
if self.equals(other):
return self._get_reconciled_name_object(other)
if not isinstance(other, TimedeltaIndex):
try:
other = TimedeltaIndex(other)
except (TypeError, ValueError):
pass
result = Index.intersection(self, other)
return result
if len(self) == 0:
return self
if len(other) == 0:
return other
# to make our life easier, "sort" the two ranges
if self[0] <= other[0]:
left, right = self, other
else:
left, right = other, self
end = min(left[-1], right[-1])
start = right[0]
if end < start:
return type(self)(data=[])
else:
lslice = slice(*left.slice_locs(start, end))
left_chunk = left.values[lslice]
return self._shallow_copy(left_chunk)
def intersection(self, other):
"""
Specialized intersection for TimedeltaIndex objects. May be much faster
than Index.intersection
Parameters
----------
other : TimedeltaIndex or array-like
Returns
-------
y : Index or TimedeltaIndex
"""
self._assert_can_do_setop(other)
if self.equals(other):
return self._get_reconciled_name_object(other)
if not isinstance(other, TimedeltaIndex):
try:
other = TimedeltaIndex(other)
except (TypeError, ValueError):
pass
result = Index.intersection(self, other)
return result
if len(self) == 0:
return self
if len(other) == 0:
return other
# to make our life easier, "sort" the two ranges
if self[0] <= other[0]:
left, right = self, other
else:
left, right = other, self
end = min(left[-1], right[-1])
start = right[0]
if end < start:
return type(self)(data=[])
else:
lslice = slice(*left.slice_locs(start, end))
left_chunk = left.values[lslice]
return self._shallow_copy(left_chunk)
def _get_combined_index(indexes, intersect=False, sort=False):
# TODO: handle index names!
indexes = _get_distinct_objs(indexes)
if len(indexes) == 0:
index = Index([])
elif len(indexes) == 1:
index = indexes[0]
elif intersect:
index = indexes[0]
for other in indexes[1:]:
index = index.intersection(other)
else:
index = _union_indexes(indexes, sort=sort)
index = ensure_index(index)
if sort:
try:
index = index.sort_values()
except TypeError:
pass
return index
def _get_combined_index(indexes, intersect=False, sort=False):
# TODO: handle index names!
indexes = com.get_distinct_objs(indexes)
if len(indexes) == 0:
index = Index([])
elif len(indexes) == 1:
index = indexes[0]
elif intersect:
index = indexes[0]
for other in indexes[1:]:
index = index.intersection(other)
else:
index = _union_indexes(indexes, sort=sort)
index = ensure_index(index)
if sort:
try:
index = index.sort_values()
except TypeError:
pass
return index
def _get_combined_index(indexes, intersect=False, sort=False):
"""
Return the union or intersection of indexes.
Parameters
----------
indexes : list of Index or list objects
When intersect=True, do not accept list of lists.
intersect : bool, default False
If True, calculate the intersection between indexes. Otherwise,
calculate the union.
sort : bool, default False
Whether the result index should come out sorted or not.
Returns
-------
Index
"""
# TODO: handle index names!
indexes = _get_distinct_objs(indexes)
if len(indexes) == 0:
index = Index([])
elif len(indexes) == 1:
index = indexes[0]
elif intersect:
index = indexes[0]
for other in indexes[1:]:
index = index.intersection(other)
else:
index = _union_indexes(indexes, sort=sort)
index = ensure_index(index)
if sort:
try:
index = index.sort_values()
except TypeError:
pass
return index
def intersection(self, other, sort=False):
"""
Specialized intersection for DatetimeIndex/TimedeltaIndex.
May be much faster than Index.intersection
Parameters
----------
other : Same type as self or array-like
sort : False or None, default False
Sort the resulting index if possible.
.. versionadded:: 0.24.0
.. versionchanged:: 0.24.1
Changed the default to ``False`` to match the behaviour
from before 0.24.0.
.. versionchanged:: 0.25.0
The `sort` keyword is added
Returns
-------
y : Index or same type as self
"""
self._validate_sort_keyword(sort)
self._assert_can_do_setop(other)
if self.equals(other):
return self._get_reconciled_name_object(other)
if len(self) == 0:
return self.copy()
if len(other) == 0:
return other.copy()
if not isinstance(other, type(self)):
result = Index.intersection(self, other, sort=sort)
if isinstance(result, type(self)):
if result.freq is None:
result._set_freq("infer")
return result
elif (
other.freq is None
or self.freq is None
or other.freq != self.freq
or not other.freq.is_anchored()
or (not self.is_monotonic or not other.is_monotonic)
):
result = Index.intersection(self, other, sort=sort)
# Invalidate the freq of `result`, which may not be correct at
# this point, depending on the values.
result._set_freq(None)
result = self._shallow_copy(result._data, name=result.name)
if result.freq is None:
result._set_freq("infer")
return result
# to make our life easier, "sort" the two ranges
if self[0] <= other[0]:
left, right = self, other
else:
left, right = other, self
# after sorting, the intersection always starts with the right index
# and ends with the index of which the last elements is smallest
end = min(left[-1], right[-1])
start = right[0]
if end < start:
return type(self)(data=[])
else:
lslice = slice(*left.slice_locs(start, end))
left_chunk = left.values[lslice]
return self._shallow_copy(left_chunk)
def intersection(self, other, sort=False):
"""
Specialized intersection for DatetimeIndex/TimedeltaIndex.
May be much faster than Index.intersection
Parameters
----------
other : Same type as self or array-like
sort : False or None, default False
Sort the resulting index if possible.
.. versionadded:: 0.24.0
.. versionchanged:: 0.24.1
Changed the default to ``False`` to match the behaviour
from before 0.24.0.
.. versionchanged:: 0.25.0
The `sort` keyword is added
Returns
-------
y : Index or same type as self
"""
self._validate_sort_keyword(sort)
self._assert_can_do_setop(other)
if self.equals(other):
return self._get_reconciled_name_object(other)
if len(self) == 0:
return self.copy()._get_reconciled_name_object(other)
if len(other) == 0:
return other.copy()._get_reconciled_name_object(self)
if not isinstance(other, type(self)):
result = Index.intersection(self, other, sort=sort)
if isinstance(result, type(self)):
if result.freq is None:
# TODO: no tests rely on this; needed?
result = result._with_freq("infer")
return result
elif not self._can_fast_intersect(other):
result = Index.intersection(self, other, sort=sort)
# We need to invalidate the freq because Index.intersection
# uses _shallow_copy on a view of self._data, which will preserve
# self.freq if we're not careful.
return result._with_freq(None)._with_freq("infer")
# to make our life easier, "sort" the two ranges
if self[0] <= other[0]:
left, right = self, other
else:
left, right = other, self
# after sorting, the intersection always starts with the right index
# and ends with the index of which the last elements is smallest
end = min(left[-1], right[-1])
start = right[0]
if end < start:
result = type(self)(data=[], dtype=self.dtype, freq=self.freq)
else:
lslice = slice(*left.slice_locs(start, end))
left_chunk = left._values[lslice]
result = type(self)._simple_new(left_chunk)
return self._wrap_setop_result(other, result)
