def _cast_to_common_type(arr: ArrayLike, dtype: DtypeObj) -> ArrayLike:
"""
Helper function for `arr.astype(common_dtype)` but handling all special
cases.
"""
if (is_categorical_dtype(arr.dtype) and isinstance(dtype, np.dtype)
and np.issubdtype(dtype, np.integer)):
# problem case: categorical of int -> gives int as result dtype,
# but categorical can contain NAs -> fall back to object dtype
try:
return arr.astype(dtype, copy=False)
except ValueError:
return arr.astype(object, copy=False)
if is_sparse(arr) and not is_sparse(dtype):
# problem case: SparseArray.astype(dtype) doesn't follow the specified
# dtype exactly, but converts this to Sparse[dtype] -> first manually
# convert to dense array
arr = cast(SparseArray, arr)
return arr.to_dense().astype(dtype, copy=False)
if (isinstance(arr, np.ndarray) and arr.dtype.kind in ["m", "M"]
and dtype is np.dtype("object")):
# wrap datetime-likes in EA to ensure astype(object) gives Timestamp/Timedelta
# this can happen when concat_compat is called directly on arrays (when arrays
# are not coming from Index/Series._values), eg in BlockManager.quantile
arr = array(arr)
if is_extension_array_dtype(dtype):
if isinstance(arr, np.ndarray):
# numpy's astype cannot handle ExtensionDtypes
return array(arr, dtype=dtype, copy=False)
return arr.astype(dtype, copy=False)
def dispatch_to_extension_op(
op, left: Union[ABCExtensionArray, np.ndarray], right: Any,
):
"""
Assume that left or right is a Series backed by an ExtensionArray,
apply the operator defined by op.
Parameters
----------
op : binary operator
left : ExtensionArray or np.ndarray
right : object
Returns
-------
ExtensionArray or np.ndarray
2-tuple of these if op is divmod or rdivmod
"""
# NB: left and right should already be unboxed, so neither should be
# a Series or Index.
if left.dtype.kind in "mM" and isinstance(left, np.ndarray):
# We need to cast datetime64 and timedelta64 ndarrays to
# DatetimeArray/TimedeltaArray. But we avoid wrapping others in
# PandasArray as that behaves poorly with e.g. IntegerArray.
left = array(left)
# The op calls will raise TypeError if the op is not defined
# on the ExtensionArray
res_values = op(left, right)
return res_values
def dispatch_to_extension_op(op, left, right):
"""
Assume that left or right is a Series backed by an ExtensionArray,
apply the operator defined by op.
"""
if left.dtype.kind in "mM":
# We need to cast datetime64 and timedelta64 ndarrays to
# DatetimeArray/TimedeltaArray. But we avoid wrapping others in
# PandasArray as that behaves poorly with e.g. IntegerArray.
left = array(left)
# The op calls will raise TypeError if the op is not defined
# on the ExtensionArray
# unbox Series and Index to arrays
new_left = extract_array(left, extract_numpy=True)
new_right = extract_array(right, extract_numpy=True)
try:
res_values = op(new_left, new_right)
except NullFrequencyError:
# DatetimeIndex and TimedeltaIndex with freq == None raise ValueError
# on add/sub of integers (or int-like). We re-raise as a TypeError.
raise TypeError(
"incompatible type for a datetime/timedelta "
"operation [{name}]".format(name=op.__name__)
)
return res_values
def dispatch_to_extension_op(
op,
left: Union[ABCExtensionArray, np.ndarray],
right: Any,
keep_null_freq: bool = False,
):
"""
Assume that left or right is a Series backed by an ExtensionArray,
apply the operator defined by op.
Parameters
----------
op : binary operator
left : ExtensionArray or np.ndarray
right : object
keep_null_freq : bool, default False
Whether to re-raise a NullFrequencyError unchanged, as opposed to
catching and raising TypeError.
Returns
-------
ExtensionArray or np.ndarray
2-tuple of these if op is divmod or rdivmod
"""
# NB: left and right should already be unboxed, so neither should be
# a Series or Index.
if left.dtype.kind in "mM" and isinstance(left, np.ndarray):
# We need to cast datetime64 and timedelta64 ndarrays to
# DatetimeArray/TimedeltaArray. But we avoid wrapping others in
# PandasArray as that behaves poorly with e.g. IntegerArray.
left = array(left)
# The op calls will raise TypeError if the op is not defined
# on the ExtensionArray
try:
res_values = op(left, right)
except NullFrequencyError:
# DatetimeIndex and TimedeltaIndex with freq == None raise ValueError
# on add/sub of integers (or int-like). We re-raise as a TypeError.
if keep_null_freq:
# TODO: remove keep_null_freq after Timestamp+int deprecation
# GH#22535 is enforced
raise
raise TypeError(
"incompatible type for a datetime/timedelta "
"operation [{name}]".format(name=op.__name__)
)
return res_values
def __eq__(self, other):
# ensure pandas array for list-like and eliminate non-interval scalars
if is_list_like(other):
if len(self) != len(other):
raise ValueError("Lengths must match to compare")
other = array(other)
elif not isinstance(other, Interval):
# non-interval scalar -> no matches
return np.zeros(len(self), dtype=bool)
# determine the dtype of the elements we want to compare
if isinstance(other, Interval):
other_dtype = pandas_dtype("interval")
elif not is_categorical_dtype(other.dtype):
other_dtype = other.dtype
else:
# for categorical defer to categories for dtype
other_dtype = other.categories.dtype
# extract intervals if we have interval categories with matching closed
if is_interval_dtype(other_dtype):
if self.closed != other.categories.closed:
return np.zeros(len(self), dtype=bool)
other = other.categories.take(other.codes)
# interval-like -> need same closed and matching endpoints
if is_interval_dtype(other_dtype):
if self.closed != other.closed:
return np.zeros(len(self), dtype=bool)
return (self._left == other.left) & (self._right == other.right)
# non-interval/non-object dtype -> no matches
if not is_object_dtype(other_dtype):
return np.zeros(len(self), dtype=bool)
# object dtype -> iteratively check for intervals
result = np.zeros(len(self), dtype=bool)
for i, obj in enumerate(other):
# need object to be an Interval with same closed and endpoints
if (
isinstance(obj, Interval)
and self.closed == obj.closed
and self._left[i] == obj.left
and self._right[i] == obj.right
):
result[i] = True
return result
def _cmp_method(self, other, op):
# ensure pandas array for list-like and eliminate non-interval scalars
if is_list_like(other):
if len(self) != len(other):
raise ValueError("Lengths must match to compare")
other = array(other)
elif not isinstance(other, Interval):
# non-interval scalar -> no matches
return invalid_comparison(self, other, op)
# determine the dtype of the elements we want to compare
if isinstance(other, Interval):
other_dtype = pandas_dtype("interval")
elif not is_categorical_dtype(other.dtype):
other_dtype = other.dtype
else:
# for categorical defer to categories for dtype
other_dtype = other.categories.dtype
# extract intervals if we have interval categories with matching closed
if is_interval_dtype(other_dtype):
if self.closed != other.categories.closed:
return invalid_comparison(self, other, op)
other = other.categories.take(
other.codes,
allow_fill=True,
fill_value=other.categories._na_value)
# interval-like -> need same closed and matching endpoints
if is_interval_dtype(other_dtype):
if self.closed != other.closed:
return invalid_comparison(self, other, op)
elif not isinstance(other, Interval):
other = type(self)(other)
if op is operator.eq:
return (self._left == other.left) & (self._right
== other.right)
elif op is operator.ne:
return (self._left != other.left) | (self._right !=
other.right)
elif op is operator.gt:
return (self._left > other.left) | (
(self._left == other.left) & (self._right > other.right))
elif op is operator.ge:
return (self == other) | (self > other)
elif op is operator.lt:
return (self._left < other.left) | (
(self._left == other.left) & (self._right < other.right))
else:
# operator.lt
return (self == other) | (self < other)
# non-interval/non-object dtype -> no matches
if not is_object_dtype(other_dtype):
return invalid_comparison(self, other, op)
# object dtype -> iteratively check for intervals
result = np.zeros(len(self), dtype=bool)
for i, obj in enumerate(other):
try:
result[i] = op(self[i], obj)
except TypeError:
if obj is NA:
# comparison with np.nan returns NA
# github.com/pandas-dev/pandas/pull/37124#discussion_r509095092
result[i] = op is operator.ne
else:
raise
return result
