def wrapper(self, other):
if isinstance(other, str):
try:
other = self._scalar_from_string(other)
except ValueError:
# failed to parse as timedelta
return invalid_comparison(self, other, op)
if isinstance(other, self._recognized_scalars) or other is NaT:
other = self._scalar_type(other)
self._check_compatible_with(other)
other_i8 = self._unbox_scalar(other)
result = op(self.view("i8"), other_i8)
if isna(other):
result.fill(nat_result)
elif not is_list_like(other):
return invalid_comparison(self, other, op)
elif len(other) != len(self):
raise ValueError("Lengths must match")
else:
if isinstance(other, list):
other = np.array(other)
if not isinstance(other, (np.ndarray, cls)):
return invalid_comparison(self, other, op)
if is_object_dtype(other):
with np.errstate(all="ignore"):
result = ops.comp_method_OBJECT_ARRAY(
op, self.astype(object), other
)
o_mask = isna(other)
elif not cls._is_recognized_dtype(other.dtype):
# e.g. other is datetimearray
return invalid_comparison(self, other, op)
else:
other = type(self)._from_sequence(other)
self._check_compatible_with(other)
result = op(self.view("i8"), other.view("i8"))
o_mask = other._isnan
if o_mask.any():
result[o_mask] = nat_result
if self._hasnans:
result[self._isnan] = nat_result
return result
def comparison_op(left: Union[np.ndarray, ABCExtensionArray], right: Any,
op) -> Union[np.ndarray, ABCExtensionArray]:
"""
Evaluate a comparison operation `=`, `!=`, `>=`, `>`, `<=`, or `<`.
Parameters
----------
left : np.ndarray or ExtensionArray
right : object
Cannot be a DataFrame, Series, or Index.
op : {operator.eq, operator.ne, operator.gt, operator.ge, operator.lt, operator.le}
Returns
-------
ndarrray or ExtensionArray
"""
from pandas.core.ops import should_extension_dispatch, dispatch_to_extension_op
# NB: We assume extract_array has already been called on left and right
lvalues = left
rvalues = right
rvalues = lib.item_from_zerodim(rvalues)
if isinstance(rvalues, list):
# TODO: same for tuples?
rvalues = np.asarray(rvalues)
if isinstance(rvalues, (np.ndarray, ABCExtensionArray, ABCIndexClass)):
# TODO: make this treatment consistent across ops and classes.
# We are not catching all listlikes here (e.g. frozenset, tuple)
# The ambiguous case is object-dtype. See GH#27803
if len(lvalues) != len(rvalues):
raise ValueError("Lengths must match to compare")
if should_extension_dispatch(lvalues, rvalues):
res_values = dispatch_to_extension_op(op, lvalues, rvalues)
elif is_scalar(rvalues) and isna(rvalues):
# numpy does not like comparisons vs None
if op is operator.ne:
res_values = np.ones(len(lvalues), dtype=bool)
else:
res_values = np.zeros(len(lvalues), dtype=bool)
elif is_object_dtype(lvalues.dtype):
res_values = comp_method_OBJECT_ARRAY(op, lvalues, rvalues)
else:
op_name = "__{op}__".format(op=op.__name__)
method = getattr(lvalues, op_name)
with np.errstate(all="ignore"):
res_values = method(rvalues)
if res_values is NotImplemented:
res_values = invalid_comparison(lvalues, rvalues, op)
if is_scalar(res_values):
raise TypeError("Could not compare {typ} type with Series".format(
typ=type(rvalues)))
return res_values
def comparison_op(left: ArrayLike, right: Any, op) -> ArrayLike:
"""
Evaluate a comparison operation `=`, `!=`, `>=`, `>`, `<=`, or `<`.
Note: the caller is responsible for ensuring that numpy warnings are
suppressed (with np.errstate(all="ignore")) if needed.
Parameters
----------
left : np.ndarray or ExtensionArray
right : object
Cannot be a DataFrame, Series, or Index.
op : {operator.eq, operator.ne, operator.gt, operator.ge, operator.lt, operator.le}
Returns
-------
ndarray or ExtensionArray
"""
# NB: We assume extract_array has already been called on left and right
lvalues = ensure_wrapped_if_datetimelike(left)
rvalues = ensure_wrapped_if_datetimelike(right)
rvalues = lib.item_from_zerodim(rvalues)
if isinstance(rvalues, list):
# TODO: same for tuples?
rvalues = np.asarray(rvalues)
if isinstance(rvalues, (np.ndarray, ABCExtensionArray)):
# TODO: make this treatment consistent across ops and classes.
# We are not catching all listlikes here (e.g. frozenset, tuple)
# The ambiguous case is object-dtype. See GH#27803
if len(lvalues) != len(rvalues):
raise ValueError("Lengths must match to compare", lvalues.shape,
rvalues.shape)
if should_extension_dispatch(lvalues, rvalues) or (
(isinstance(rvalues,
(Timedelta, BaseOffset, Timestamp)) or right is NaT)
and not is_object_dtype(lvalues.dtype)):
# Call the method on lvalues
res_values = op(lvalues, rvalues)
elif is_scalar(rvalues) and isna(rvalues):
# numpy does not like comparisons vs None
if op is operator.ne:
res_values = np.ones(lvalues.shape, dtype=bool)
else:
res_values = np.zeros(lvalues.shape, dtype=bool)
elif is_numeric_v_string_like(lvalues, rvalues):
# GH#36377 going through the numexpr path would incorrectly raise
return invalid_comparison(lvalues, rvalues, op)
elif is_object_dtype(lvalues.dtype) or isinstance(rvalues, str):
res_values = comp_method_OBJECT_ARRAY(op, lvalues, rvalues)
else:
res_values = _na_arithmetic_op(lvalues, rvalues, op, is_cmp=True)
return res_values
def na_op(x, y):
# TODO:
# should have guarantess on what x, y can be type-wise
# Extension Dtypes are not called here
# Checking that cases that were once handled here are no longer
# reachable.
assert not (is_categorical_dtype(y) and not is_scalar(y))
if is_object_dtype(x.dtype):
result = _comp_method_OBJECT_ARRAY(op, x, y)
elif is_datetimelike_v_numeric(x, y):
return invalid_comparison(x, y, op)
else:
# we want to compare like types
# we only want to convert to integer like if
# we are not NotImplemented, otherwise
# we would allow datetime64 (but viewed as i8) against
# integer comparisons
# we have a datetime/timedelta and may need to convert
assert not needs_i8_conversion(x)
mask = None
if not is_scalar(y) and needs_i8_conversion(y):
mask = isna(x) | isna(y)
y = y.view("i8")
x = x.view("i8")
method = getattr(x, op_name, None)
if method is not None:
with np.errstate(all="ignore"):
result = method(y)
if result is NotImplemented:
return invalid_comparison(x, y, op)
else:
result = op(x, y)
if mask is not None and mask.any():
result[mask] = masker
return result
def na_op(x, y):
# TODO:
# should have guarantees on what x, y can be type-wise
# Extension Dtypes are not called here
if is_object_dtype(x.dtype):
result = comp_method_OBJECT_ARRAY(op, x, y)
elif is_datetimelike_v_numeric(x, y):
return invalid_comparison(x, y, op)
else:
method = getattr(x, op_name)
with np.errstate(all="ignore"):
result = method(y)
if result is NotImplemented:
return invalid_comparison(x, y, op)
return result
def wrapper(self, other):
ordinal_op = getattr(self.asi8, opname)
if is_list_like(other) and len(other) != len(self):
raise ValueError("Lengths must match")
if isinstance(other, str):
try:
other = self._scalar_from_string(other)
except ValueError:
# string that can't be parsed as Period
return invalid_comparison(self, other, op)
elif isinstance(other, int):
# TODO: sure we want to allow this? we dont for DTA/TDA
# 2 tests rely on this
other = Period(other, freq=self.freq)
result = ordinal_op(other.ordinal)
if isinstance(other, Period):
self._check_compatible_with(other)
result = ordinal_op(other.ordinal)
elif isinstance(other, cls):
self._check_compatible_with(other)
result = ordinal_op(other.asi8)
mask = self._isnan | other._isnan
if mask.any():
result[mask] = nat_result
return result
elif other is NaT:
result = np.empty(len(self.asi8), dtype=bool)
result.fill(nat_result)
else:
return invalid_comparison(self, other, op)
if self._hasnans:
result[self._isnan] = nat_result
return result
def wrapper(self, other):
other = lib.item_from_zerodim(other)
if isinstance(other, (ABCDataFrame, ABCSeries, ABCIndexClass)):
return NotImplemented
if _is_convertible_to_td(other) or other is NaT:
try:
other = Timedelta(other)
except ValueError:
# failed to parse as timedelta
return invalid_comparison(self, other, op)
result = op(self.view("i8"), other.value)
if isna(other):
result.fill(nat_result)
elif not is_list_like(other):
return invalid_comparison(self, other, op)
elif len(other) != len(self):
raise ValueError("Lengths must match")
else:
try:
other = type(self)._from_sequence(other)._data
except (ValueError, TypeError):
return invalid_comparison(self, other, op)
result = op(self.view("i8"), other.view("i8"))
result = com.values_from_object(result)
o_mask = np.array(isna(other))
if o_mask.any():
result[o_mask] = nat_result
if self._hasnans:
result[self._isnan] = nat_result
return result
def wrapper(self, other):
if isinstance(other, str):
try:
other = self._scalar_from_string(other)
except ValueError:
# failed to parse as timedelta
return invalid_comparison(self, other, op)
if _is_convertible_to_td(other) or other is NaT:
other = Timedelta(other)
result = op(self.view("i8"), other.value)
if isna(other):
result.fill(nat_result)
elif not is_list_like(other):
return invalid_comparison(self, other, op)
elif len(other) != len(self):
raise ValueError("Lengths must match")
else:
try:
other = type(self)._from_sequence(other)._data
except (ValueError, TypeError):
return invalid_comparison(self, other, op)
result = op(self.view("i8"), other.view("i8"))
result = com.values_from_object(result)
o_mask = np.array(isna(other))
if o_mask.any():
result[o_mask] = nat_result
if self._hasnans:
result[self._isnan] = nat_result
return result
def _na_arithmetic_op(left: np.ndarray, right, op, is_cmp: bool = False):
"""
Return the result of evaluating op on the passed in values.
If native types are not compatible, try coercion to object dtype.
Parameters
----------
left : np.ndarray
right : np.ndarray or scalar
Excludes DataFrame, Series, Index, ExtensionArray.
is_cmp : bool, default False
If this a comparison operation.
Returns
-------
array-like
Raises
------
TypeError : invalid operation
"""
if isinstance(right, str):
# can never use numexpr
func = op
else:
func = partial(expressions.evaluate, op)
try:
result = func(left, right)
except TypeError:
if not is_cmp and (is_object_dtype(left.dtype)
or is_object_dtype(right)):
# For object dtype, fallback to a masked operation (only operating
# on the non-missing values)
# Don't do this for comparisons, as that will handle complex numbers
# incorrectly, see GH#32047
result = _masked_arith_op(left, right, op)
else:
raise
if is_cmp and (is_scalar(result) or result is NotImplemented):
# numpy returned a scalar instead of operating element-wise
# e.g. numeric array vs str
# TODO: can remove this after dropping some future numpy version?
return invalid_comparison(left, right, op)
return missing.dispatch_fill_zeros(op, left, right, result)
def na_arithmetic_op(left,
right,
op,
str_rep: Optional[str],
is_cmp: bool = False):
"""
Return the result of evaluating op on the passed in values.
If native types are not compatible, try coersion to object dtype.
Parameters
----------
left : np.ndarray
right : np.ndarray or scalar
str_rep : str or None
is_cmp : bool, default False
If this a comparison operation.
Returns
-------
array-like
Raises
------
TypeError : invalid operation
"""
import pandas.core.computation.expressions as expressions
try:
result = expressions.evaluate(op, str_rep, left, right)
except TypeError:
if is_cmp:
# numexpr failed on comparison op, e.g. ndarray[float] > datetime
# In this case we do not fall back to the masked op, as that
# will handle complex numbers incorrectly, see GH#32047
raise
result = masked_arith_op(left, right, op)
if is_cmp and (is_scalar(result) or result is NotImplemented):
# numpy returned a scalar instead of operating element-wise
# e.g. numeric array vs str
return invalid_comparison(left, right, op)
return missing.dispatch_fill_zeros(op, left, right, result)
def _na_arithmetic_op(left, right, op, is_cmp: bool = False):
"""
Return the result of evaluating op on the passed in values.
If native types are not compatible, try coercion to object dtype.
Parameters
----------
left : np.ndarray
right : np.ndarray or scalar
is_cmp : bool, default False
If this a comparison operation.
Returns
-------
array-like
Raises
------
TypeError : invalid operation
"""
try:
result = expressions.evaluate(op, left, right)
except TypeError:
if is_object_dtype(left) or is_object_dtype(right) and not is_cmp:
# For object dtype, fallback to a masked operation (only operating
# on the non-missing values)
# Don't do this for comparisons, as that will handle complex numbers
# incorrectly, see GH#32047
result = _masked_arith_op(left, right, op)
else:
raise
if is_cmp and (is_scalar(result) or result is NotImplemented):
# numpy returned a scalar instead of operating element-wise
# e.g. numeric array vs str
return invalid_comparison(left, right, op)
return missing.dispatch_fill_zeros(op, left, right, result)
def wrapper(self, other):
res_name = get_op_result_name(self, other)
# TODO: shouldn't we be applying finalize whenever
# not isinstance(other, ABCSeries)?
finalizer = (lambda x: x.__finalize__(self)
if isinstance(other, (np.ndarray, ABCIndexClass)) else x)
if isinstance(other, ABCDataFrame): # pragma: no cover
# Defer to DataFrame implementation; fail early
return NotImplemented
if isinstance(other, ABCSeries) and not self._indexed_same(other):
raise ValueError(
"Can only compare identically-labeled Series objects")
other = lib.item_from_zerodim(other)
if isinstance(other, list):
# TODO: same for tuples?
other = np.asarray(other)
if isinstance(other, (np.ndarray, ABCExtensionArray, ABCIndexClass)):
# TODO: make this treatment consistent across ops and classes.
# We are not catching all listlikes here (e.g. frozenset, tuple)
# The ambiguous case is object-dtype. See GH#27803
if len(self) != len(other):
raise ValueError("Lengths must match to compare")
lvalues = extract_array(self, extract_numpy=True)
rvalues = extract_array(other, extract_numpy=True)
if should_extension_dispatch(lvalues, rvalues):
res_values = dispatch_to_extension_op(op, lvalues, rvalues)
elif is_scalar(rvalues) and isna(rvalues):
# numpy does not like comparisons vs None
if op is operator.ne:
res_values = np.ones(len(lvalues), dtype=bool)
else:
res_values = np.zeros(len(lvalues), dtype=bool)
elif is_object_dtype(lvalues.dtype):
res_values = comp_method_OBJECT_ARRAY(op, lvalues, rvalues)
else:
op_name = "__{op}__".format(op=op.__name__)
method = getattr(lvalues, op_name)
with np.errstate(all="ignore"):
res_values = method(rvalues)
if res_values is NotImplemented:
res_values = invalid_comparison(lvalues, rvalues, op)
if is_scalar(res_values):
raise TypeError(
"Could not compare {typ} type with Series".format(
typ=type(rvalues)))
result = self._constructor(res_values, index=self.index)
result = finalizer(result)
# Set the result's name after finalizer is called because finalizer
# would set it back to self.name
result.name = res_name
return result
def wrapper(self, other):
ordinal_op = getattr(self.asi8, opname)
if is_list_like(other) and len(other) != len(self):
raise ValueError("Lengths must match")
if isinstance(other, str):
try:
other = self._scalar_from_string(other)
except ValueError:
# string that can't be parsed as Period
return invalid_comparison(self, other, op)
elif isinstance(other, int):
# TODO: sure we want to allow this? we dont for DTA/TDA
# 2 tests rely on this
other = Period(other, freq=self.freq)
result = ordinal_op(other.ordinal)
if isinstance(other, Period):
self._check_compatible_with(other)
result = ordinal_op(other.ordinal)
elif other is NaT:
result = np.empty(len(self.asi8), dtype=bool)
result.fill(nat_result)
elif not is_list_like(other):
return invalid_comparison(self, other, op)
else:
if isinstance(other, list):
# TODO: could use pd.Index to do inference?
other = np.array(other)
if not isinstance(other, (np.ndarray, cls)):
return invalid_comparison(self, other, op)
if is_object_dtype(other):
with np.errstate(all="ignore"):
result = ops.comp_method_OBJECT_ARRAY(
op, self.astype(object), other
)
o_mask = isna(other)
elif not is_period_dtype(other):
# e.g. is_timedelta64_dtype(other)
return invalid_comparison(self, other, op)
else:
assert isinstance(other, cls), type(other)
self._check_compatible_with(other)
result = ordinal_op(other.asi8)
o_mask = other._isnan
if o_mask.any():
result[o_mask] = nat_result
if self._hasnans:
result[self._isnan] = nat_result
return result
