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

Merged in bugfix/postprocessing_date_fix (pull request #996)

Browse Source 
Date formatting changes

* Date formatting changes

* Merged dev into bugfix/postprocessing_date_fix


Approved-by: Katon Minhas
This commit is contained in:
Praneel Panchigar
2026-05-08 16:02:53 +00:00
committed by Katon Minhas
parent 2da639e59b
commit fc49f8627e
1 changed files with 11 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/scripts/postprocess_existing_output.py
+11 -2
View File
@@ -27,8 +27,17 @@ else:
df = pd.read_csv(input_path, dtype=str, keep_default_na=False) df = pd.read_csv(input_path, dtype=str, keep_default_na=False)
print(f"Loaded {len(df)} rows, {len(df.columns)} columns") print(f"Loaded {len(df)} rows, {len(df.columns)} columns")
# Format date columns to YYYY/MM/DD # Format CC-team-facing date columns to YYYY/MM/DD.
date_cols = [c for c in df.columns if "_DT" in c or "DATE" in c] # Raw 1:1 extracted dates (EFFECTIVE_DT, TERMINATION_DT) and obscure date
# fields (OUTLIER_DT, DISCOUNT_*_DT, PREMIUM_*_DT, SEQUESTRATION_*_DT) are
# preserved as-is.
DATE_COLS_TO_FORMAT = (
"AARETE_DERIVED_EFFECTIVE_DT",
"AARETE_DERIVED_TERMINATION_DT",
"REIMB_EFFECTIVE_DT",
"REIMB_TERMINATION_DT",
)
date_cols = [c for c in df.columns if c in DATE_COLS_TO_FORMAT]
print(f"Formatting {len(date_cols)} date columns: {date_cols}") print(f"Formatting {len(date_cols)} date columns: {date_cols}")
for col in date_cols: for col in date_cols:
df[col] = df[col].apply(validate_and_reformat_date) df[col] = df[col].apply(validate_and_reformat_date)