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.

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

Jump to bottom

FEAT-#1838: Lazy map evaluation at Pandas backend #1940

Merged
merged 2 commits into from
Aug 28, 2020
Merged

FEAT-#1838: Lazy map evaluation at Pandas backend #1940

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
090cab6
FEAT-#1838: Lazy functions applying added
dchigarev Aug 20, 2020
d8fa78f
FEAT-#1838: reverted some lazy calls
dchigarev Aug 27, 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
8 changes: 5 additions & 3 deletions modin/engines/base/frame/data.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -706,7 +706,9 @@ def astype(self, col_dtypes):
def astype_builder(df):
return df.astype({k: v for k, v in col_dtypes.items() if k in df})

new_frame = self._frame_mgr_cls.map_partitions(self._partitions, astype_builder)
new_frame = self._frame_mgr_cls.lazy_map_partitions(
self._partitions, astype_builder
)
return self.__constructor__(
new_frame,
self.index,
Expand Down Expand Up @@ -1041,7 +1043,7 @@ def _map_reduce(self, axis, map_func, reduce_func=None, preserve_index=True):
else:
reduce_func = self._build_mapreduce_func(axis, reduce_func)

map_parts = self._frame_mgr_cls.map_partitions(self._partitions, map_func)
map_parts = self._frame_mgr_cls.lazy_map_partitions(self._partitions, map_func)
reduce_parts = self._frame_mgr_cls.map_axis_partitions(
axis, map_parts, reduce_func
)
Expand Down Expand Up @@ -1079,7 +1081,7 @@ def _map(self, func, dtypes=None, validate_index=False, validate_columns=False):
-------
A new dataframe.
"""
new_partitions = self._frame_mgr_cls.map_partitions(self._partitions, func)
new_partitions = self._frame_mgr_cls.lazy_map_partitions(self._partitions, func)
if dtypes == "copy":
dtypes = self._dtypes
elif dtypes is not None:
Expand Down
12 changes: 8 additions & 4 deletions modin/engines/base/frame/partition_manager.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -83,7 +83,7 @@ def groupby_reduce(cls, axis, partitions, by, map_func, reduce_func):
new_partitions = np.array(
[
[
part.apply(
part.add_to_apply_calls(
map_func,
other=by_parts[col_idx].get()
if axis
Expand Down Expand Up @@ -191,7 +191,7 @@ def broadcast_apply(cls, axis, apply_func, left, right):
return np.array(
[
[
part.apply(
part.add_to_apply_calls(
dchigarev marked this conversation as resolved.
Show resolved Hide resolved
apply_func,
r=right_parts[col_idx].get()
if axis
Expand Down Expand Up @@ -451,7 +451,9 @@ def _apply_func_to_list_of_partitions_broadcast(
):
preprocessed_func = cls.preprocess_func(func)
return [
obj.apply(preprocessed_func, other=[o.get() for o in broadcasted], **kwargs)
obj.add_to_apply_calls(
preprocessed_func, other=[o.get() for o in broadcasted], **kwargs
)
for obj, broadcasted in zip(partitions, other.T)
]

Expand All @@ -469,7 +471,9 @@ def _apply_func_to_list_of_partitions(cls, func, partitions, **kwargs):
A list of BaseFramePartition objects.
"""
preprocessed_func = cls.preprocess_func(func)
return [obj.apply(preprocessed_func, **kwargs) for obj in partitions]
return [
obj.add_to_apply_calls(preprocessed_func, **kwargs) for obj in partitions
]

@classmethod
def apply_func_to_select_indices(
Expand Down