jacob-mathison/doczyai-pipelines
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Activity

Merged in hotfix/irs_tweak (pull request #303)

Browse Source 
returning None instead on str(N/A)

* returning None instead on str(N/A)


Approved-by: Katon Minhas
This commit is contained in:
Karan Desai
2024-11-27 15:29:39 +00:00
committed by Katon Minhas
parent 56e3fdd1f8
commit 2458f8cddc
2 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
fieldExtraction/src/hotfix_helper_funcs.py
+4 -4
View File
@@ -72,10 +72,10 @@ def clean_output_postprocess(merged_df):
merged_df['dummy_other'] = merged_df['dummy_other'].apply(lambda lst: [x for x in [remove_alphabets(x) for x in lst] if x is not None])
merged_df['dummy_other_signatory'] = merged_df['dummy_other_signatory'].apply(lambda lst: [x for x in [remove_alphabets(x) for x in lst] if x is not None])
merged_df['dummy'] = merged_df['dummy'].apply(lambda lst: [add_hyphen_if_needed(x) for x in lst])
merged_df['dummy_other'] = merged_df['dummy_other'].apply(lambda lst: [add_hyphen_if_needed(x) for x in lst])
merged_df['dummy_other_signatory'] = merged_df['dummy_other_signatory'].apply(lambda lst: [add_hyphen_if_needed(x) for x in lst])
merged_df['dummy'] = merged_df['dummy'].apply(lambda lst: [x for x in [add_hyphen_if_needed(x) for x in lst] if x is not None])
merged_df['dummy_other'] = merged_df['dummy_other'].apply(lambda lst: [x for x in [add_hyphen_if_needed(x) for x in lst] if x is not None])
merged_df['dummy_other_signatory'] = merged_df['dummy_other_signatory'].apply(lambda lst: [x for x in [add_hyphen_if_needed(x) for x in lst] if x is not None])
merged_df['dummy'] = merged_df['dummy'].apply(list_to_string)
merged_df['dummy_other'] = merged_df['dummy_other'].apply(list_to_string)
merged_df['dummy_other_signatory'] = merged_df['dummy_other_signatory'].apply(list_to_string)
fieldExtraction/src/utils.py
+1 -1
View File
@@ -352,6 +352,6 @@ def add_hyphen_if_needed(input_str):
# Ensure the output is in the format 'xx-xxxxxxx'
if not bool(re.fullmatch(r"\b\d{2}-\d{7}\b", input_str)):
input_str = 'N/A'
input_str = None
return input_str