Skip to content

[bot] Merge master/17dfca8f into rel/dev #1126

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
yenkins-admin merged 2 commits into from
Sep 2, 2025
Merged

[bot] Merge master/17dfca8f into rel/dev #1126

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
ac0189f
feat: optimize memory allocation when converting execution response t…
Martozar Sep 2, 2025
17dfca8
Merge pull request #1125 from Martozar/c.mze-CQ-1579
Martozar Sep 2, 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
2 changes: 1 addition & 1 deletion CONTRIBUTING.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,7 +66,7 @@ One logical change is done in one commit.

### Documenting new features

To document a new feature, you need to create a new `.md` file in one of the subsections. These subsections reresent the left navigation menu and are in a hierarchical directories.
To document a new feature, you need to create a new `.md` file in one of the subsections. These subsections represent the left navigation menu and are in a hierarchical directories.

e.g.:

Expand Down
18 changes: 18 additions & 0 deletions gooddata-pandas/gooddata_pandas/dataframe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -238,6 +238,7 @@ def for_created_visualization(
created_visualizations_response: dict,
on_execution_submitted: Optional[Callable[[Execution], None]] = None,
is_cancellable: bool = False,
optimized: bool = False,
) -> tuple[pandas.DataFrame, DataFrameMetadata]:
"""
Creates a data frame using a created visualization.
Expand All @@ -247,6 +248,10 @@ def for_created_visualization(
on_execution_submitted (Optional[Callable[[Execution], None]]): Callback to call when the execution was
submitted to the backend.
is_cancellable (bool, optional): Whether the execution should be cancelled when the connection is interrupted.
optimized (bool, default=False): Use memory optimized accumulator if True; by default, the accumulator stores
headers in memory as lists of dicts, which can consume a lot of memory for large results.
Optimized accumulator stores only unique values and story only reference to them in the list,
which can significantly reduce memory usage.

Returns:
pandas.DataFrame: A DataFrame instance.
Expand All @@ -257,6 +262,7 @@ def for_created_visualization(
return self.for_exec_def(
exec_def=execution_definition,
on_execution_submitted=on_execution_submitted,
optimized=optimized,
)

def result_cache_metadata_for_exec_result_id(self, result_id: str) -> ResultCacheMetadata:
Expand All @@ -279,6 +285,7 @@ def for_exec_def(
result_size_bytes_limit: Optional[int] = None,
page_size: int = _DEFAULT_PAGE_SIZE,
on_execution_submitted: Optional[Callable[[Execution], None]] = None,
optimized: bool = False,
) -> tuple[pandas.DataFrame, DataFrameMetadata]:
"""
Creates a data frame using an execution definition.
Expand Down Expand Up @@ -311,6 +318,10 @@ def for_exec_def(
page_size (int): Number of records per page.
on_execution_submitted (Optional[Callable[[Execution], None]]): Callback to call when the execution was
submitted to the backend.
optimized (bool, default=False): Use memory optimized accumulator if True; by default, the accumulator stores
headers in memory as lists of dicts, which can consume a lot of memory for large results.
Optimized accumulator stores only unique values and story only reference to them in the list,
which can significantly reduce memory usage.

Returns:
Tuple[pandas.DataFrame, DataFrameMetadata]: Tuple holding DataFrame and DataFrame metadata.
Expand All @@ -331,6 +342,7 @@ def for_exec_def(
result_size_dimensions_limits=result_size_dimensions_limits,
result_size_bytes_limit=result_size_bytes_limit,
page_size=page_size,
optimized=optimized,
)

def for_exec_result_id(
Expand All @@ -343,6 +355,7 @@ def for_exec_result_id(
use_local_ids_in_headers: bool = False,
use_primary_labels_in_attributes: bool = False,
page_size: int = _DEFAULT_PAGE_SIZE,
optimized: bool = False,
) -> tuple[pandas.DataFrame, DataFrameMetadata]:
"""
Retrieves a DataFrame and DataFrame metadata for a given execution result identifier.
Expand Down Expand Up @@ -373,6 +386,10 @@ def for_exec_result_id(
use_local_ids_in_headers (bool): Use local identifier in headers.
use_primary_labels_in_attributes (bool): Use primary labels in attributes.
page_size (int): Number of records per page.
optimized (bool, default=False): Use memory optimized accumulator if True; by default, the accumulator stores
headers in memory as lists of dicts, which can consume a lot of memory for large results.
Optimized accumulator stores only unique values and story only reference to them in the list,
which can significantly reduce memory usage.

Returns:
Tuple[pandas.DataFrame, DataFrameMetadata]: Tuple holding DataFrame and DataFrame metadata.
Expand All @@ -398,4 +415,5 @@ def for_exec_result_id(
use_local_ids_in_headers=use_local_ids_in_headers,
use_primary_labels_in_attributes=use_primary_labels_in_attributes,
page_size=page_size,
optimized=optimized,
)
Loading
Loading