Skip to content

⚡️ Speed up function get_default_pandas_dtypes by 5,005% #266

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

Open
codeflash-ai wants to merge 1 commit into
base: main
Choose a base branch
from
Open

⚡️ Speed up function get_default_pandas_dtypes by 5,005% #266

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
95 changes: 51 additions & 44 deletions unstructured/staging/base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -381,50 +381,57 @@ def convert_to_csv(elements: Iterable[Element]) -> str:

@requires_dependencies(["pandas"])
def get_default_pandas_dtypes() -> dict[str, Any]:
return {
"text": pd.StringDtype(), # type: ignore
"type": pd.StringDtype(), # type: ignore
"element_id": pd.StringDtype(), # type: ignore
"filename": pd.StringDtype(), # Optional[str] # type: ignore
"filetype": pd.StringDtype(), # Optional[str] # type: ignore
"file_directory": pd.StringDtype(), # Optional[str] # type: ignore
"last_modified": pd.StringDtype(), # Optional[str] # type: ignore
"attached_to_filename": pd.StringDtype(), # Optional[str] # type: ignore
"parent_id": pd.StringDtype(), # Optional[str], # type: ignore
"category_depth": "Int64", # Optional[int]
"image_path": pd.StringDtype(), # Optional[str] # type: ignore
"languages": object, # Optional[list[str]]
"page_number": "Int64", # Optional[int]
"page_name": pd.StringDtype(), # Optional[str] # type: ignore
"url": pd.StringDtype(), # Optional[str] # type: ignore
"link_urls": pd.StringDtype(), # Optional[str] # type: ignore
"link_texts": object, # Optional[list[str]]
"links": object,
"sent_from": object, # Optional[list[str]],
"sent_to": object, # Optional[list[str]]
"subject": pd.StringDtype(), # Optional[str] # type: ignore
"section": pd.StringDtype(), # Optional[str] # type: ignore
"header_footer_type": pd.StringDtype(), # Optional[str] # type: ignore
"emphasized_text_contents": object, # Optional[list[str]]
"emphasized_text_tags": object, # Optional[list[str]]
"text_as_html": pd.StringDtype(), # Optional[str] # type: ignore
"max_characters": "Int64", # Optional[int]
"is_continuation": "boolean", # Optional[bool]
"detection_class_prob": float, # Optional[float],
"sender": pd.StringDtype(), # type: ignore
"coordinates_points": object,
"coordinates_system": pd.StringDtype(), # type: ignore
"coordinates_layout_width": float,
"coordinates_layout_height": float,
"data_source_url": pd.StringDtype(), # Optional[str] # type: ignore
"data_source_version": pd.StringDtype(), # Optional[str] # type: ignore
"data_source_record_locator": object,
"data_source_date_created": pd.StringDtype(), # Optional[str] # type: ignore
"data_source_date_modified": pd.StringDtype(), # Optional[str] # type: ignore
"data_source_date_processed": pd.StringDtype(), # Optional[str] # type: ignore
"data_source_permissions_data": object,
"embeddings": object,
}
cached = getattr(get_default_pandas_dtypes, "_cached_template", None)
if cached is None:
pd_string = pd.StringDtype() # type: ignore
cached = {
"text": pd_string, # type: ignore
"type": pd_string, # type: ignore
"element_id": pd_string, # type: ignore
"filename": pd_string, # Optional[str] # type: ignore
"filetype": pd_string, # Optional[str] # type: ignore
"file_directory": pd_string, # Optional[str] # type: ignore
"last_modified": pd_string, # Optional[str] # type: ignore
"attached_to_filename": pd_string, # Optional[str] # type: ignore
"parent_id": pd_string, # Optional[str], # type: ignore
"category_depth": "Int64", # Optional[int]
"image_path": pd_string, # Optional[str] # type: ignore
"languages": object, # Optional[list[str]]
"page_number": "Int64", # Optional[int]
"page_name": pd_string, # Optional[str] # type: ignore
"url": pd_string, # Optional[str] # type: ignore
"link_urls": pd_string, # Optional[str] # type: ignore
"link_texts": object, # Optional[list[str]]
"links": object,
"sent_from": object, # Optional[list[str]],
"sent_to": object, # Optional[list[str]]
"subject": pd_string, # Optional[str] # type: ignore
"section": pd_string, # Optional[str] # type: ignore
"header_footer_type": pd_string, # Optional[str] # type: ignore
"emphasized_text_contents": object, # Optional[list[str]]
"emphasized_text_tags": object, # Optional[list[str]]
"text_as_html": pd_string, # Optional[str] # type: ignore
"max_characters": "Int64", # Optional[int]
"is_continuation": "boolean", # Optional[bool]
"detection_class_prob": float, # Optional[float],
"sender": pd_string, # type: ignore
"coordinates_points": object,
"coordinates_system": pd_string, # type: ignore
"coordinates_layout_width": float,
"coordinates_layout_height": float,
"data_source_url": pd_string, # Optional[str] # type: ignore
"data_source_version": pd_string, # Optional[str] # type: ignore
"data_source_record_locator": object,
"data_source_date_created": pd_string, # Optional[str] # type: ignore
"data_source_date_modified": pd_string, # Optional[str] # type: ignore
"data_source_date_processed": pd_string, # Optional[str] # type: ignore
"data_source_permissions_data": object,
"embeddings": object,
}
# cache the template dict to avoid recreating dtype instances repeatedly
get_default_pandas_dtypes._cached_template = cached
# return a shallow copy to preserve original behavior (fresh dict each call)
return dict(cached)


@requires_dependencies(["pandas"])
Expand Down