def func(self, other, sort=True):
other = self._as_like_interval_index(other)
# GH 19016: ensure set op will not return a prohibited dtype
subtypes = [self.dtype.subtype, other.dtype.subtype]
common_subtype = find_common_type(subtypes)
if is_object_dtype(common_subtype):
msg = ('can only do {op} between two IntervalIndex '
'objects that have compatible dtypes')
raise TypeError(msg.format(op=op_name))
if op_name == 'difference':
result = getattr(self._multiindex, op_name)(other._multiindex,
sort)
else:
result = getattr(self._multiindex, op_name)(other._multiindex)
result_name = get_op_result_name(self, other)
# GH 19101: ensure empty results have correct dtype
if result.empty:
result = result.values.astype(self.dtype.subtype)
else:
result = result.values
return type(self).from_tuples(result, closed=self.closed,
name=result_name)
def func(self, other, sort=sort):
self._assert_can_do_setop(other)
other = ensure_index(other)
if not isinstance(other, IntervalIndex):
result = getattr(self.astype(object), op_name)(other)
if op_name in ('difference',):
result = result.astype(self.dtype)
return result
elif self.closed != other.closed:
msg = ('can only do set operations between two IntervalIndex '
'objects that are closed on the same side')
raise ValueError(msg)
# GH 19016: ensure set op will not return a prohibited dtype
subtypes = [self.dtype.subtype, other.dtype.subtype]
common_subtype = find_common_type(subtypes)
if is_object_dtype(common_subtype):
msg = ('can only do {op} between two IntervalIndex '
'objects that have compatible dtypes')
raise TypeError(msg.format(op=op_name))
result = getattr(self._multiindex, op_name)(other._multiindex,
sort=sort)
result_name = get_op_result_name(self, other)
# GH 19101: ensure empty results have correct dtype
if result.empty:
result = result.values.astype(self.dtype.subtype)
else:
result = result.values
return type(self).from_tuples(result, closed=self.closed,
name=result_name)
def _wrap_joined_index(self, joined, other):
name = get_op_result_name(self, other)
if (isinstance(other, TimedeltaIndex) and self.freq == other.freq and
self._can_fast_union(other)):
joined = self._shallow_copy(joined, name=name)
return joined
else:
return self._simple_new(joined, name)
def __sub__(self, other):
from pandas import Index
other = lib.item_from_zerodim(other)
if isinstance(other, (ABCSeries, ABCDataFrame)):
return NotImplemented
# scalar others
elif other is NaT:
result = self._sub_nat()
elif isinstance(other, (Tick, timedelta, np.timedelta64)):
result = self._add_delta(-other)
elif isinstance(other, DateOffset):
# specifically _not_ a Tick
result = self._add_offset(-other)
elif isinstance(other, (datetime, np.datetime64)):
result = self._sub_datelike(other)
elif is_integer(other):
# This check must come after the check for np.timedelta64
# as is_integer returns True for these
result = self.shift(-other)
elif isinstance(other, Period):
result = self._sub_period(other)
# array-like others
elif is_timedelta64_dtype(other):
# TimedeltaIndex, ndarray[timedelta64]
result = self._add_delta(-other)
elif is_offsetlike(other):
# Array/Index of DateOffset objects
result = self._addsub_offset_array(other, operator.sub)
elif is_datetime64_dtype(other) or is_datetime64tz_dtype(other):
# DatetimeIndex, ndarray[datetime64]
result = self._sub_datelike(other)
elif isinstance(other, Index):
raise TypeError("cannot subtract {cls} and {typ}"
.format(cls=type(self).__name__,
typ=type(other).__name__))
elif is_integer_dtype(other) and self.freq is None:
# GH#19123
raise NullFrequencyError("Cannot shift with no freq")
elif is_float_dtype(other):
# Explicitly catch invalid dtypes
raise TypeError("cannot subtract {dtype}-dtype from {cls}"
.format(dtype=other.dtype,
cls=type(self).__name__))
else: # pragma: no cover
return NotImplemented
if result is NotImplemented:
return NotImplemented
elif not isinstance(result, Index):
# Index.__new__ will choose appropriate subclass for dtype
result = Index(result)
res_name = ops.get_op_result_name(self, other)
result.name = res_name
return result
def wrap_arithmetic_op(self, other, result):
if result is NotImplemented:
return NotImplemented
if not isinstance(result, Index):
# Index.__new__ will choose appropriate subclass for dtype
result = Index(result)
res_name = ops.get_op_result_name(self, other)
result.name = res_name
return result
def func(self, other, sort=sort):
result = getattr(self._multiindex, op_name)(other._multiindex,
sort=sort)
result_name = get_op_result_name(self, other)
# GH 19101: ensure empty results have correct dtype
if result.empty:
result = result.values.astype(self.dtype.subtype)
else:
result = result.values
return type(self).from_tuples(result, closed=self.closed,
name=result_name)
def __add__(self, other):
other = lib.item_from_zerodim(other)
if isinstance(other, (ABCSeries, ABCDataFrame)):
return NotImplemented
# scalar others
elif other is NaT:
result = self._add_nat()
elif isinstance(other, (Tick, timedelta, np.timedelta64)):
result = self._add_delta(other)
elif isinstance(other, DateOffset):
# specifically _not_ a Tick
result = self._add_offset(other)
elif isinstance(other, (datetime, np.datetime64)):
result = self._add_datelike(other)
elif is_integer(other):
# This check must come after the check for np.timedelta64
# as is_integer returns True for these
result = self.shift(other)
# array-like others
elif is_timedelta64_dtype(other):
# TimedeltaIndex, ndarray[timedelta64]
result = self._add_delta(other)
elif is_offsetlike(other):
# Array/Index of DateOffset objects
result = self._addsub_offset_array(other, operator.add)
elif is_datetime64_dtype(other) or is_datetime64tz_dtype(other):
# DatetimeIndex, ndarray[datetime64]
return self._add_datelike(other)
elif is_integer_dtype(other):
result = self._addsub_int_array(other, operator.add)
elif is_float_dtype(other) or is_period_dtype(other):
# Explicitly catch invalid dtypes
raise TypeError("cannot add {dtype}-dtype to {cls}"
.format(dtype=other.dtype,
cls=type(self).__name__))
elif is_categorical_dtype(other):
# Categorical op will raise; defer explicitly
return NotImplemented
else: # pragma: no cover
return NotImplemented
if result is NotImplemented:
return NotImplemented
elif not isinstance(result, Index):
# Index.__new__ will choose appropriate subclass for dtype
result = Index(result)
res_name = ops.get_op_result_name(self, other)
result.name = res_name
return result
def wrap_arithmetic_op(self, other, result):
if result is NotImplemented:
return NotImplemented
if isinstance(result, tuple):
# divmod, rdivmod
assert len(result) == 2
return (wrap_arithmetic_op(self, other, result[0]),
wrap_arithmetic_op(self, other, result[1]))
if not isinstance(result, Index):
# Index.__new__ will choose appropriate subclass for dtype
result = Index(result)
res_name = ops.get_op_result_name(self, other)
result.name = res_name
return result
def __sub__(self, other):
from pandas.core.index import Index
from pandas.core.indexes.datetimes import DatetimeIndex
from pandas.core.indexes.timedeltas import TimedeltaIndex
from pandas.tseries.offsets import DateOffset
other = lib.item_from_zerodim(other)
if isinstance(other, ABCSeries):
return NotImplemented
elif is_timedelta64_dtype(other):
result = self._add_delta(-other)
elif isinstance(other, (DateOffset, timedelta)):
result = self._add_delta(-other)
elif is_offsetlike(other):
# Array/Index of DateOffset objects
result = self._sub_offset_array(other)
elif isinstance(self, TimedeltaIndex) and isinstance(other, Index):
if not isinstance(other, TimedeltaIndex):
raise TypeError("cannot subtract TimedeltaIndex and {typ}"
.format(typ=type(other).__name__))
result = self._add_delta(-other)
elif isinstance(other, DatetimeIndex):
result = self._sub_datelike(other)
elif is_integer(other):
# This check must come after the check for timedelta64_dtype
# or else it will incorrectly catch np.timedelta64 objects
result = self.shift(-other)
elif isinstance(other, (datetime, np.datetime64)):
result = self._sub_datelike(other)
elif isinstance(other, Period):
result = self._sub_period(other)
elif isinstance(other, Index):
raise TypeError("cannot subtract {typ1} and {typ2}"
.format(typ1=type(self).__name__,
typ2=type(other).__name__))
elif is_integer_dtype(other) and self.freq is None:
# GH#19123
raise NullFrequencyError("Cannot shift with no freq")
else: # pragma: no cover
return NotImplemented
if result is not NotImplemented:
res_name = ops.get_op_result_name(self, other)
result.name = res_name
return result
def __add__(self, other):
from pandas import DateOffset
other = lib.item_from_zerodim(other)
if isinstance(other, ABCSeries):
return NotImplemented
# scalar others
elif other is NaT:
result = self._add_nat()
elif isinstance(other, (DateOffset, timedelta, np.timedelta64)):
result = self._add_delta(other)
elif isinstance(other, (datetime, np.datetime64)):
result = self._add_datelike(other)
elif is_integer(other):
# This check must come after the check for np.timedelta64
# as is_integer returns True for these
result = self.shift(other)
# array-like others
elif is_timedelta64_dtype(other):
# TimedeltaIndex, ndarray[timedelta64]
result = self._add_delta(other)
elif is_offsetlike(other):
# Array/Index of DateOffset objects
result = self._addsub_offset_array(other, operator.add)
elif is_datetime64_dtype(other) or is_datetime64tz_dtype(other):
# DatetimeIndex, ndarray[datetime64]
return self._add_datelike(other)
elif is_integer_dtype(other) and self.freq is None:
# GH#19123
raise NullFrequencyError("Cannot shift with no freq")
else: # pragma: no cover
return NotImplemented
if result is NotImplemented:
return NotImplemented
elif not isinstance(result, Index):
# Index.__new__ will choose appropriate subclass for dtype
result = Index(result)
res_name = ops.get_op_result_name(self, other)
result.name = res_name
return result
def _wrap_setop_result(self, other, result):
name = get_op_result_name(self, other)
result = self._apply_meta(result)
result.name = name
return result
def __sub__(self, other):
from pandas import Index
other = lib.item_from_zerodim(other)
if isinstance(other, (ABCSeries, ABCDataFrame)):
return NotImplemented
# scalar others
elif other is NaT:
result = self._sub_nat()
elif isinstance(other, (Tick, timedelta, np.timedelta64)):
result = self._add_delta(-other)
elif isinstance(other, DateOffset):
# specifically _not_ a Tick
result = self._add_offset(-other)
elif isinstance(other, (datetime, np.datetime64)):
result = self._sub_datelike(other)
elif is_integer(other):
# This check must come after the check for np.timedelta64
# as is_integer returns True for these
result = self.shift(-other)
elif isinstance(other, Period):
result = self._sub_period(other)
# array-like others
elif is_timedelta64_dtype(other):
# TimedeltaIndex, ndarray[timedelta64]
result = self._add_delta(-other)
elif is_offsetlike(other):
# Array/Index of DateOffset objects
result = self._addsub_offset_array(other, operator.sub)
elif is_datetime64_dtype(other) or is_datetime64tz_dtype(other):
# DatetimeIndex, ndarray[datetime64]
result = self._sub_datelike(other)
elif is_period_dtype(other):
# PeriodIndex
result = self._sub_period_array(other)
elif is_integer_dtype(other):
result = self._addsub_int_array(other, operator.sub)
elif isinstance(other, Index):
raise TypeError("cannot subtract {cls} and {typ}"
.format(cls=type(self).__name__,
typ=type(other).__name__))
elif is_float_dtype(other):
# Explicitly catch invalid dtypes
raise TypeError("cannot subtract {dtype}-dtype from {cls}"
.format(dtype=other.dtype,
cls=type(self).__name__))
elif is_categorical_dtype(other):
# Categorical op will raise; defer explicitly
return NotImplemented
else: # pragma: no cover
return NotImplemented
if result is NotImplemented:
return NotImplemented
elif not isinstance(result, Index):
# Index.__new__ will choose appropriate subclass for dtype
result = Index(result)
res_name = ops.get_op_result_name(self, other)
result.name = res_name
return result
def _arith_method(self, other, op):
"""
Parameters
----------
other : Any
op : callable that accepts 2 params
perform the binary op
"""
if isinstance(other, ABCTimedeltaIndex):
# Defer to TimedeltaIndex implementation
return NotImplemented
elif isinstance(other, (timedelta, np.timedelta64)):
# GH#19333 is_integer evaluated True on timedelta64,
# so we need to catch these explicitly
return super()._arith_method(other, op)
elif is_timedelta64_dtype(other):
# Must be an np.ndarray; GH#22390
return super()._arith_method(other, op)
if op in [
operator.pow,
ops.rpow,
operator.mod,
ops.rmod,
operator.floordiv,
ops.rfloordiv,
divmod,
ops.rdivmod,
]:
return super()._arith_method(other, op)
step: Callable | None = None
if op in [operator.mul, ops.rmul, operator.truediv, ops.rtruediv]:
step = op
# TODO: if other is a RangeIndex we may have more efficient options
right = extract_array(other, extract_numpy=True, extract_range=True)
left = self
try:
# apply if we have an override
if step:
with np.errstate(all="ignore"):
rstep = step(left.step, right)
# we don't have a representable op
# so return a base index
if not is_integer(rstep) or not rstep:
raise ValueError
else:
rstep = left.step
with np.errstate(all="ignore"):
rstart = op(left.start, right)
rstop = op(left.stop, right)
res_name = ops.get_op_result_name(self, other)
result = type(self)(rstart, rstop, rstep, name=res_name)
# for compat with numpy / Int64Index
# even if we can represent as a RangeIndex, return
# as a Float64Index if we have float-like descriptors
if not all(is_integer(x) for x in [rstart, rstop, rstep]):
result = result.astype("float64")
return result
except (ValueError, TypeError, ZeroDivisionError):
# Defer to Int64Index implementation
# test_arithmetic_explicit_conversions
return super()._arith_method(other, op)
def _wrap_joined_index(self, joined, other):
name = get_op_result_name(self, other)
return UInt64Index(joined, name=name)
def _wrap_joined_index(self, joined, other):
name = get_op_result_name(self, other)
return UInt64Index(joined, name=name)
def _wrap_setop_result(self, other, result):
name = get_op_result_name(self, other)
return self._shallow_copy(result, name=name)
def _wrap_joined_index(self, joined: np.ndarray,
other: "CategoricalIndex") -> "CategoricalIndex":
name = get_op_result_name(self, other)
return self._create_from_codes(joined, name=name)
def _wrap_joined_index(self: _T, joined: np.ndarray, other: _T) -> _T:
name = get_op_result_name(self, other)
arr = self._data._from_backing_data(joined)
return type(self)._simple_new(arr, name=name)
def _wrap_joined_index(self, joined: np.ndarray,
other: "CategoricalIndex") -> "CategoricalIndex":
name = get_op_result_name(self, other)
cat = self._data._from_backing_data(joined)
return type(self)._simple_new(cat, name=name)
def _wrap_setop_result(self, other, result):
name = get_op_result_name(self, other)
return self._shallow_copy(result, name=name)
def _wrap_setop_result(self, other, result):
name = get_op_result_name(self, other)
result = self._apply_meta(result)
result.name = name
return result
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)
res_name = get_op_result_name(self, 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:
# TODO: no tests rely on this; needed?
result = result._with_freq("infer")
result.name = res_name
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 = result._with_freq(None)._with_freq("infer")
result.name = res_name
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=[],
dtype=self.dtype,
freq=self.freq,
name=res_name)
else:
lslice = slice(*left.slice_locs(start, end))
left_chunk = left._values[lslice]
return type(self)._simple_new(left_chunk, name=res_name)
