Merged in bugfix/default_ind_postprocess (pull request #887)

Bugfix/default ind postprocess

* Add logic to standardize UNIT_OF_MEASURE for flat-rate reimbursement methods

- Implemented functionality in `standardize_reimb_method_and_fee_schedule` to set UNIT_OF_MEASURE to blank for rows where DEFAULT_IND is 'Y' and AARETE_DERIVED_REIMB_METHOD is 'flat rate'.
- Added unit tests to verify behavior for various scenarios, including case insensitivity and non-default conditions.
- Ensured that UNIT_OF_MEASURE remains unchanged for non-flat rate methods.

* Enhance child rank handling and ensure column consistency in parent-child mapping

- Added initialization for the `child_rank` column in both parents and children DataFrames to prevent KeyError during concatenation when no children exist.
- Updated `cols_to_keep` in `parent_child_mapping` to filter out columns not present in `pc_df`, ensuring robustness in data processing.

* Ran Black

* made a small change in code_last_check, fixed so it returns string and not single char

* Made changes to make sure that default_ind postprocess only happens to the cc output and not dashboard

* Merged DEV into bugfix/default_ind_postprocess

* Restore deleted AARETE_DERIVED_PAYER_NAME functions

Functions were removed during previous commit. Restored from DEV to fix
AttributeError in prompt_calls.py.

* Simplify code_last_check return logic and add error logging

- Simplified return to single line with fallback
- Added error logging for failed LLM response parsing


Approved-by: Siddhant Medar

src/tests/test_postprocess.py

@@ -7,6 +7,7 @@ from unittest.mock import MagicMock, patch
 import pandas as pd
 import pytest
 from src.pipelines.shared.postprocessing.postprocessing_funcs import (
+    blank_uom_for_default_flat_rate_cc,
     clean_na_values,
     deduplicate_provider_columns,
     fill_claim_type_from_title,
@@ -21,6 +22,7 @@ from src.pipelines.shared.postprocessing.postprocessing_funcs import (
     remove_hyphens,
     remove_redundant_reimb_info,
     rename_columns,
+    standardize_reimb_method_and_fee_schedule,
     validate_and_reformat_date,
 )
 from src.pipelines.shared.postprocessing.postprocess import standard_postprocess
@@ -920,6 +922,82 @@ class TestPostprocessFunctions(unittest.TestCase):
         self.assertEqual(result_df.loc[1, "CONTRACT_TITLE"], "Another Valid")
 
 
+class TestStandardizeReimbMethodAndFeeScheduleUOM(unittest.TestCase):
+    """Tests for UNIT_OF_MEASURE post-processing when DEFAULT_IND='Y' and flat rate."""
+
+    def test_cc_default_flat_rate_uom_blank(self):
+        """CC only: DEFAULT_IND='Y' and Flat Rate -> UNIT_OF_MEASURE blank."""
+        df = pd.DataFrame(
+            {
+                "DEFAULT_IND": ["Y"],
+                "AARETE_DERIVED_REIMB_METHOD": ["Flat Rate"],
+                "UNIT_OF_MEASURE": ["Per Unit"],
+            }
+        )
+        result = blank_uom_for_default_flat_rate_cc(df)
+        self.assertEqual(result.loc[0, "UNIT_OF_MEASURE"], "")
+
+    def test_cc_default_flat_rate_case_insensitive(self):
+        """CC only: DEFAULT_IND='Y' and 'flat rate' (lowercase) -> UNIT_OF_MEASURE blank."""
+        df = pd.DataFrame(
+            {
+                "DEFAULT_IND": ["Y"],
+                "AARETE_DERIVED_REIMB_METHOD": ["flat rate"],
+                "UNIT_OF_MEASURE": ["Per Visit"],
+            }
+        )
+        result = blank_uom_for_default_flat_rate_cc(df)
+        self.assertEqual(result.loc[0, "UNIT_OF_MEASURE"], "")
+
+    def test_standardize_does_not_blank_default_flat_rate(self):
+        """Shared path: default flat rate keeps UOM (blanking is CC-only)."""
+        constants = Constants()
+        df = pd.DataFrame(
+            {
+                "DEFAULT_IND": ["Y"],
+                "AARETE_DERIVED_REIMB_METHOD": ["Flat Rate"],
+                "UNIT_OF_MEASURE": ["Per Unit"],
+                "REIMB_TERM": [""],
+            }
+        )
+        result = standardize_reimb_method_and_fee_schedule(
+            df, constants.VALID_UNIT_OF_MEASURE
+        )
+        self.assertEqual(result.loc[0, "UNIT_OF_MEASURE"], "Per Unit")
+
+    def test_non_default_flat_rate_uom_per_unit(self):
+        """DEFAULT_IND='N', flat rate, empty UOM -> UNIT_OF_MEASURE becomes Per Unit."""
+        constants = Constants()
+        df = pd.DataFrame(
+            {
+                "DEFAULT_IND": ["N"],
+                "AARETE_DERIVED_REIMB_METHOD": ["Flat Rate"],
+                "UNIT_OF_MEASURE": [""],
+                "REIMB_TERM": [""],
+            }
+        )
+        result = standardize_reimb_method_and_fee_schedule(
+            df, constants.VALID_UNIT_OF_MEASURE
+        )
+        self.assertEqual(result.loc[0, "UNIT_OF_MEASURE"], "Per Unit")
+
+    def test_default_non_flat_rate_uom_unchanged(self):
+        """DEFAULT_IND='Y' and Fee Schedule -> UNIT_OF_MEASURE unchanged."""
+        constants = Constants()
+        df = pd.DataFrame(
+            {
+                "DEFAULT_IND": ["Y"],
+                "AARETE_DERIVED_REIMB_METHOD": ["Fee Schedule"],
+                "UNIT_OF_MEASURE": ["Per Visit"],
+                "REIMB_TERM": [""],
+            }
+        )
+        result = standardize_reimb_method_and_fee_schedule(
+            df, constants.VALID_UNIT_OF_MEASURE
+        )
+        self.assertEqual(result.loc[0, "UNIT_OF_MEASURE"], "Per Visit")
+
+
 class TestOutputFileStructure(unittest.TestCase):
     """Test that the new output file structure is generated correctly."""