Skip to content

DO NOT MERGE - WIP - NativeQueryCompiler performance improvements #7632

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

Draft
wants to merge 2 commits into
base: main
Choose a base branch
from
Draft

DO NOT MERGE - WIP - NativeQueryCompiler performance improvements #7632

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2689541
NativeQueryCompiler performance improvements
sfc-gh-jkew Jul 25, 2025
e9da120
re-add metrics
sfc-gh-jkew Jul 25, 2025
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
13 changes: 9 additions & 4 deletions modin/core/storage_formats/pandas/native_query_compiler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -102,7 +102,7 @@ class NativeQueryCompiler(BaseQueryCompiler):
_modin_frame: pandas.DataFrame
_should_warn_on_default_to_pandas: bool = False

def __init__(self, pandas_frame):
def __init__(self, pandas_frame, in_place=False):
if hasattr(pandas_frame, "_to_pandas"):
pandas_frame = pandas_frame._to_pandas()
if is_scalar(pandas_frame):
Expand All @@ -112,10 +112,10 @@ def __init__(self, pandas_frame):
# so that we don't modify it.
# TODO(https://github.com/modin-project/modin/issues/7435): Look
# into avoiding this copy.
pandas_frame = pandas_frame.copy()
if not in_place:
pandas_frame = pandas_frame.copy()
else:
pandas_frame = pandas.DataFrame(pandas_frame)

self._modin_frame = pandas_frame

storage_format = property(
Expand All @@ -126,6 +126,11 @@ def __init__(self, pandas_frame):
def execute(self):
pass


def default_to_pandas(self, pandas_op, *args, **kwargs):
#print("new default to pandas")
return type(self)(pandas_op(self._modin_frame, *args, **kwargs), in_place=True)

@property
def frame_has_materialized_dtypes(self) -> bool:
"""
Expand Down Expand Up @@ -202,7 +207,7 @@ def to_pandas(self):

@classmethod
def from_pandas(cls, df, data_cls):
return cls(df)
return cls(df, in_place=True)

@classmethod
def from_arrow(cls, at, data_cls):
Expand Down
Loading