blade
/
dc-ml-emea-ar
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

a little change

This commit is contained in:
Blade He 2025-01-22 09:57:42 -06:00
parent 350550d1b0
commit d9b0bed39a
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
main.py
View File

@ -1015,9 +1015,9 @@ def batch_run_documents(
page_filter_ground_truth_file = (
r"/data/emea_ar/ground_truth/page_filter/datapoint_page_info_88_documents.xlsx"
)
re_run_extract_data = False
re_run_extract_data = True
re_run_mapping_data = True
force_save_total_data = True
force_save_total_data = False
calculate_metrics = False
extract_way = "text"
@ -1348,7 +1348,7 @@ if __name__ == "__main__":
# special_doc_id_list = ["553242411"]
doc_source = "aus_prospectus"
doc_source = "emea_ar"
if doc_source == "aus_prospectus":
document_sample_file = r"./sample_documents/aus_prospectus_100_documents_multi_fund_sample.txt"
with open(document_sample_file, "r", encoding="utf-8") as f: