Skip to content
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.

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

PERF: avoid calling .values to know the result dtype in eval() #44791

Closed
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
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
15 changes: 9 additions & 6 deletions pandas/core/computation/ops.py
Original file line number Diff line number Diff line change
Expand Up @@ -146,15 +146,18 @@ def is_scalar(self) -> bool:
@property
def type(self):
try:
# potentially very slow for large, mixed dtype frames
return self._value.values.dtype
# .values for dataframe would be slow
return self._value._mgr.as_array_dtype()
except AttributeError:
try:
# ndarray
return self._value.dtype
return self._value.values.dtype
except AttributeError:
# scalar
return type(self._value)
try:
# ndarray
return self._value.dtype
except AttributeError:
# scalar
return type(self._value)

return_type = type

Expand Down
9 changes: 9 additions & 0 deletions pandas/core/internals/array_manager.py
Original file line number Diff line number Diff line change
Expand Up @@ -1145,6 +1145,15 @@ def as_array(

return result

def as_array_dtype(self):
"""
The dtype of the np.ndarray when you would convert self to a numpy array
(i.e. calling ``mgr.as_array()`` or ``df.values``).
"""
if len(self.arrays) == 0:
return np.dtype(float)
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

can this be explicitly np.float64? i never know how this will behave on windows or 32bit builds

return interleaved_dtype([arr.dtype for arr in self.arrays])


class SingleArrayManager(BaseArrayManager, SingleDataManager):

Expand Down
16 changes: 16 additions & 0 deletions pandas/core/internals/managers.py
Original file line number Diff line number Diff line change
Expand Up @@ -1549,6 +1549,22 @@ def as_array(

return arr.transpose()

def as_array_dtype(self):
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

could be shared in the base class?

"""
The dtype of the np.ndarray when you would convert self to a numpy array
(i.e. calling ``mgr.as_array()`` or ``df.values``).
"""
if len(self.blocks) == 0:
return np.dtype(float)

if self.is_single_block:
return self.blocks[0].dtype

dtype = interleaved_dtype( # type: ignore[assignment]
[blk.dtype for blk in self.blocks]
)
return dtype

def _interleave(
self,
dtype: np.dtype | None = None,
Expand Down