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

Merged in feature/pc-functionality (pull request #835)

Browse Source 
bug fix for pc module

* bug fix for pc module


Approved-by: Katon Minhas
This commit is contained in:
Karan Desai
2026-01-12 21:29:53 +00:00
committed by Katon Minhas
parent 87f3d2f4f0
commit 6679bf7f47
1 changed files with 10 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
fieldExtraction/src/investment/main.py
+10 -4
View File
@@ -228,7 +228,8 @@ def main(testing=False, test_params={}):
if config.WRITE_TO_S3: if config.WRITE_TO_S3:
doczy_output_for_pc = io_utils.write_s3(FINAL_RESULT_DF, "", run_timestamp, "final") doczy_output_for_pc = io_utils.write_s3(FINAL_RESULT_DF, "", run_timestamp, "final")
if not ERROR_RESULT_DF.empty: if not ERROR_RESULT_DF.empty:
doczy_output_for_pc = io_utils.write_s3(ERROR_RESULT_DF, "", run_timestamp, "error") io_utils.write_s3(ERROR_RESULT_DF, "", run_timestamp, "error")
logging.warning(f"{len(ERROR_RESULT_DF)} files failed processing - error results written to S3")
# Export usage and cost tracking data to S3 only if both dataframes have data # Export usage and cost tracking data to S3 only if both dataframes have data
if not per_file_usage_df.empty and not batch_summary_df.empty: if not per_file_usage_df.empty and not batch_summary_df.empty:
@@ -238,11 +239,16 @@ def main(testing=False, test_params={}):
else: else:
doczy_output_for_pc = io_utils.write_local(FINAL_RESULT_DF, "", run_timestamp, "final") doczy_output_for_pc = io_utils.write_local(FINAL_RESULT_DF, "", run_timestamp, "final")
if not ERROR_RESULT_DF.empty: if not ERROR_RESULT_DF.empty:
doczy_output_for_pc = io_utils.write_local(ERROR_RESULT_DF, "", run_timestamp, "error") io_utils.write_local(ERROR_RESULT_DF, "", run_timestamp, "error")
logging.warning(f"{len(ERROR_RESULT_DF)} files failed processing - error results written locally")
if config.PERFORM_PARENT_CHILD_MAPPING: if config.PERFORM_PARENT_CHILD_MAPPING:
with timing_utils.timed_block("parent_child_mapping", log_level="INFO"): if FINAL_RESULT_DF.empty:
parent_child_main.main(doczy_output_for_pc) logging.warning("Skipping Parent-Child mapping: No successful results to process (FINAL_RESULT_DF is empty)")
else:
logging.info(f"Starting Parent-Child mapping with {len(FINAL_RESULT_DF)} records from: {doczy_output_for_pc}")
with timing_utils.timed_block("parent_child_mapping", log_level="INFO"):
parent_child_main.main(doczy_output_for_pc)
# Export usage and cost tracking data locally only if both dataframes have data # Export usage and cost tracking data locally only if both dataframes have data
if not per_file_usage_df.empty and not batch_summary_df.empty: if not per_file_usage_df.empty and not batch_summary_df.empty: