Skip to content

CLN: de-duplicate dispatch_to_series calls #34386

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 2 commits into from
May 26, 2020
Merged

CLN: de-duplicate dispatch_to_series calls #34386

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
997b5f3
CLN: de-duplicate dispatch_to_series calls
jbrockmendel May 26, 2020
1a072de
blackify
jbrockmendel May 26, 2020
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
60 changes: 21 additions & 39 deletions pandas/core/ops/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -78,14 +78,7 @@
}


COMPARISON_BINOPS: Set[str] = {
"eq",
"ne",
"lt",
"gt",
"le",
"ge",
}
COMPARISON_BINOPS: Set[str] = {"eq", "ne", "lt", "gt", "le", "ge"}

# -----------------------------------------------------------------------------
# Ops Wrapping Utilities
Expand Down Expand Up @@ -246,17 +239,17 @@ def fill_binop(left, right, fill_value):
# Dispatch logic


def dispatch_to_series(left, right, func, axis=None):
def dispatch_to_series(left, right, func, axis: Optional[int] = None):
"""
Evaluate the frame operation func(left, right) by evaluating
column-by-column, dispatching to the Series implementation.

Parameters
----------
left : DataFrame
right : scalar or DataFrame
right : scalar, Series, or DataFrame
func : arithmetic or comparison operator
axis : {None, 0, 1, "index", "columns"}
axis : {None, 0, 1}

Returns
-------
Expand All @@ -266,7 +259,8 @@ def dispatch_to_series(left, right, func, axis=None):
array_op = get_array_op(func)

right = lib.item_from_zerodim(right)
if lib.is_scalar(right) or np.ndim(right) == 0:
if not is_list_like(right):
# i.e. scalar, faster than checking np.ndim(right) == 0
bm = left._mgr.apply(array_op, right=right)
return type(left)(bm)

Expand All @@ -284,15 +278,9 @@ def dispatch_to_series(left, right, func, axis=None):
# axis=1 means we want to operate row-by-row
assert right.index.equals(left.columns)

if right.dtype == "timedelta64[ns]":
# ensure we treat NaT values as the correct dtype
# Note: we do not do this unconditionally as it may be lossy or
# expensive for EA dtypes.
right = np.asarray(right)
else:
right = right._values
# maybe_align_as_frame ensures we do not have an ndarray here
assert not isinstance(right, np.ndarray)
right = right._values
# maybe_align_as_frame ensures we do not have an ndarray here
assert not isinstance(right, np.ndarray)

arrays = [array_op(l, r) for l, r in zip(left._iter_column_arrays(), right)]

Expand All @@ -315,7 +303,7 @@ def dispatch_to_series(left, right, func, axis=None):
# Series


def _align_method_SERIES(left, right, align_asobject=False):
def _align_method_SERIES(left: "Series", right, align_asobject: bool = False):
""" align lhs and rhs Series """
# ToDo: Different from _align_method_FRAME, list, tuple and ndarray
# are not coerced here
Expand Down Expand Up @@ -596,7 +584,11 @@ def _maybe_align_series_as_frame(frame: "DataFrame", series: "Series", axis: int
rvalues = series._values
if not isinstance(rvalues, np.ndarray):
# TODO(EA2D): no need to special-case with 2D EAs
return series
if rvalues.dtype == "datetime64[ns]" or rvalues.dtype == "timedelta64[ns]":
# We can losslessly+cheaply cast to ndarray
rvalues = np.asarray(rvalues)
else:
return series

if axis == 0:
rvalues = rvalues.reshape(-1, 1)
Expand Down Expand Up @@ -633,6 +625,8 @@ def f(self, other, axis=default_axis, level=None, fill_value=None):
# through the DataFrame path
raise NotImplementedError(f"fill_value {fill_value} not supported.")

axis = self._get_axis_number(axis) if axis is not None else 1

# TODO: why are we passing flex=True instead of flex=not special?
# 15 tests fail if we pass flex=not special instead
self, other = _align_method_FRAME(self, other, axis, flex=True, level=level)
Expand All @@ -642,7 +636,6 @@ def f(self, other, axis=default_axis, level=None, fill_value=None):
new_data = self._combine_frame(other, na_op, fill_value)

elif isinstance(other, ABCSeries):
axis = self._get_axis_number(axis) if axis is not None else 1
new_data = dispatch_to_series(self, other, op, axis=axis)
else:
# in this case we always have `np.ndim(other) == 0`
Expand Down Expand Up @@ -670,20 +663,11 @@ def _flex_comp_method_FRAME(cls: Type["DataFrame"], op, special: bool):

@Appender(doc)
def f(self, other, axis=default_axis, level=None):
axis = self._get_axis_number(axis) if axis is not None else 1

self, other = _align_method_FRAME(self, other, axis, flex=True, level=level)

if isinstance(other, ABCDataFrame):
# Another DataFrame
new_data = dispatch_to_series(self, other, op)

elif isinstance(other, ABCSeries):
axis = self._get_axis_number(axis) if axis is not None else 1
new_data = dispatch_to_series(self, other, op, axis=axis)
else:
# in this case we always have `np.ndim(other) == 0`
new_data = dispatch_to_series(self, other, op)

new_data = dispatch_to_series(self, other, op, axis=axis)
return self._construct_result(new_data)

f.__name__ = op_name
Expand All @@ -697,12 +681,10 @@ def _comp_method_FRAME(cls: Type["DataFrame"], op, special: bool):

@Appender(f"Wrapper for comparison method {op_name}")
def f(self, other):
axis = 1 # only relevant for Series other case

self, other = _align_method_FRAME(
self, other, axis=None, level=None, flex=False
)
self, other = _align_method_FRAME(self, other, axis, level=None, flex=False)

axis = 1 # only relevant for Series other case
# See GH#4537 for discussion of scalar op behavior
new_data = dispatch_to_series(self, other, op, axis=axis)
return self._construct_result(new_data)
Expand Down