yujunjun/unstructured
1
0
Fork 0
mirror of https://github.com/Unstructured-IO/unstructured.git synced 2025-09-28 01:40:23 +00:00
Code Issues Packages Projects Releases Wiki Activity

refactor: get_mean_grouping command takes in export_name (#2677)

Browse Source 
The `get_mean_grouping_command` currently does not take `export_name` as
param. Add the param for better naming use case.
This commit is contained in:
Klaijan 2024-03-20 17:09:02 -07:00 committed by GitHub
parent 31bef433ad
commit 469f878d14
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 11 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
CHANGELOG.md
View File

@ -1,6 +1,6 @@
## 0.12.7-dev8 ## 0.12.7-dev8
### Enhancements ### Enhancements
* **Add `.metadata.is_continuation` to text-split chunks.** `.metadata.is_continuation=True` is added to second-and-later chunks formed by text-splitting an oversized `Table` element but not to their counterpart `Text` element splits. Add this indicator for `CompositeElement` to allow text-split continuation chunks to be identified for downstream processes that may wish to skip intentionally redundant metadata values in continuation chunks. * **Add `.metadata.is_continuation` to text-split chunks.** `.metadata.is_continuation=True` is added to second-and-later chunks formed by text-splitting an oversized `Table` element but not to their counterpart `Text` element splits. Add this indicator for `CompositeElement` to allow text-split continuation chunks to be identified for downstream processes that may wish to skip intentionally redundant metadata values in continuation chunks.
* **Add `compound_structure_acc` metric to table eval.** Add a new property to `unstructured.metrics.table_eval.TableEvaluation`: `composite_structure_acc`, which is computed from the element level row and column index and content accuracy scores * **Add `compound_structure_acc` metric to table eval.** Add a new property to `unstructured.metrics.table_eval.TableEvaluation`: `composite_structure_acc`, which is computed from the element level row and column index and content accuracy scores

15
unstructured/ingest/evaluate.py
View File

@ -42,7 +42,7 @@ def main():
help="Directory to save the output evaluation metrics to. Default to \ help="Directory to save the output evaluation metrics to. Default to \
your/working/dir/metrics/", your/working/dir/metrics/",
) )
@click.option("--grouping", type=str, help="Input field for aggregration, or leave blank if none.") @click.option("--group_by", type=str, help="Input field for aggregration, or leave blank if none.")
@click.option( @click.option(
"--weights", "--weights",
type=(int, int, int), type=(int, int, int),
@ -74,7 +74,7 @@ def measure_text_extraction_accuracy_command(
output_type: str, output_type: str,
output_list: Optional[List[str]] = None, output_list: Optional[List[str]] = None,
source_list: Optional[List[str]] = None, source_list: Optional[List[str]] = None,
grouping: Optional[str] = None, group_by: Optional[str] = None,
): ):
return measure_text_extraction_accuracy( return measure_text_extraction_accuracy(
output_dir, output_dir,
@ -82,7 +82,7 @@ def measure_text_extraction_accuracy_command(
output_list, output_list,
source_list, source_list,
export_dir, export_dir,
grouping, group_by,
weights, weights,
visualize, visualize,
output_type, output_type,
@ -158,8 +158,13 @@ def measure_element_type_accuracy_command(
type=str, type=str,
help="Evaluated metric. Expecting one of 'text_extraction' or 'element_type'", help="Evaluated metric. Expecting one of 'text_extraction' or 'element_type'",
) )
def get_mean_grouping_command(group_by: str, data_input: str, export_dir: str, eval_name: str): @click.option(
return get_mean_grouping(group_by, data_input, export_dir, eval_name) "--export_name", type=str, help="Optional. Define your file name for the output here."
)
def get_mean_grouping_command(
group_by: str, data_input: str, export_dir: str, eval_name: str, export_name: str
):
return get_mean_grouping(group_by, data_input, export_dir, eval_name, export_name)
@main.command() @main.command()