Merged in feature/rename-proc-cd (pull request #645)

rename columns function

* rename columns function

* update columns


Approved-by: Alex Galarce

fieldExtraction/src/constants/investment_columns.py

@@ -84,8 +84,8 @@ COLUMN_ORDER = [
     "FEE_SCHEDULE_VERSION",
     "AARETE_DERIVED_FEE_SCHEDULE_VERSION",
     "SERVICE_TERM",
-    "PROCEDURE_CD",
-    "PROCEDURE_CD_DESC",
+    "CPT4_PROC_CD",
+    "CPT4_PROC_CD_DESC",
     "CPT4_PROC_MOD",
     "CPT4_PROC_MOD_DESC",
     "REVENUE_CD",

fieldExtraction/src/investment/investment_postprocessing_funcs.py

@@ -20,6 +20,26 @@ BASE_DIR = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__fil
 MAPPINGS_DIR = os.path.join(BASE_DIR, 'crosswalk', 'mappings')
 
 
+def rename_columns(df):
+    """
+    Use the provided mapping to rename columns in the data
+
+    Args:
+        df (pd.DataFrame): The input DataFrame with columns to be renamed.
+    Returns:
+        pd.DataFrame: The DataFrame with renamed columns.
+    """
+    # Check if the DataFrame is empty, return it as is if it is
+    if df.empty:
+        return df
+        
+    # If not empty, proceed with column renaming
+    rename_map = {"PROCEDURE_CD" : "CPT4_PROC_CD",
+                  "PROCEDURE_CD_DESC" : "CPT4_PROC_CD_DESC"}
+    # Rename columns using the mapping
+    df = df.rename(columns=rename_map)
+    return df
+
 
 def normalize_indicator_field(value: str) -> str:
     """

fieldExtraction/src/investment/postprocess.py

@@ -8,16 +8,18 @@ from src.prompts.investment_prompts import FieldSet, invoke_derived_term_date
 
 def postprocess(df):
     if df.shape[0] > 0:
-        # Add postprocessing here
+        
         df['CLIENT_NAME'] = config.CLIENT_NAME
 
+        # Rename columns
+        df = investment_postprocessing_funcs.rename_columns(df)
+
         # Sort to ensure consistent ordering
         sort_columns = ['FILE_NAME']
         if 'EXHIBIT_PAGE' in df.columns:
             sort_columns.append('EXHIBIT_PAGE')
         if 'REIMB_LESSER_OF_ID' in df.columns:
             sort_columns.append('REIMB_LESSER_OF_ID')
-
         df = df.sort_values(by=sort_columns).reset_index(drop=True)
 
         # Postprocess date fields

fieldExtraction/tests/investment_postprocess_test.py

@@ -15,6 +15,7 @@ from src.investment.investment_postprocessing_funcs import (
     process_patient_age_range,
     remove_redundant_reimb_info,
     deduplicate_provider_columns,
+    rename_columns
 )
 
 
@@ -47,6 +48,59 @@ class TestPostprocessFunctions(unittest.TestCase):
         self.assertEqual(flatten_singleton_string_list("invalid"), "invalid")
         self.assertEqual(flatten_singleton_string_list(None), "")
 
+    def test_rename_columns(self):
+        """Tests the rename_columns function to ensure it correctly renames specified columns.
+        
+        Tests:
+        1. Basic column renaming from PROCEDURE_CD to CPT4_PROC_CD
+        2. Multiple columns being renamed
+        3. Handling of columns not in the rename map
+        4. Empty DataFrame
+        """
+        # Test case 1: Basic column renaming
+        input_df1 = pd.DataFrame({
+            "PROCEDURE_CD": ["12345", "67890"],
+            "PROCEDURE_CD_DESC": ["Test Procedure", "Another Procedure"],
+            "OTHER_COLUMN": ["value1", "value2"]
+        })
+        
+        expected_df1 = pd.DataFrame({
+            "CPT4_PROC_CD": ["12345", "67890"],
+            "CPT4_PROC_CD_DESC": ["Test Procedure", "Another Procedure"],
+            "OTHER_COLUMN": ["value1", "value2"]
+        })
+        
+        result_df1 = rename_columns(input_df1)
+        pd.testing.assert_frame_equal(result_df1, expected_df1)
+        
+        # Test case 2: Only some columns need renaming
+        input_df2 = pd.DataFrame({
+            "PROCEDURE_CD": ["12345", "67890"],
+            "OTHER_COLUMN": ["value1", "value2"]
+        })
+        
+        expected_df2 = pd.DataFrame({
+            "CPT4_PROC_CD": ["12345", "67890"],
+            "OTHER_COLUMN": ["value1", "value2"]
+        })
+        
+        result_df2 = rename_columns(input_df2)
+        pd.testing.assert_frame_equal(result_df2, expected_df2)
+        
+        # Test case 3: None of the columns need renaming
+        input_df3 = pd.DataFrame({
+            "COLUMN_A": ["a", "b"],
+            "COLUMN_B": ["c", "d"]
+        })
+        
+        result_df3 = rename_columns(input_df3)
+        pd.testing.assert_frame_equal(result_df3, input_df3)  # Should be unchanged
+        
+        # Test case 4: Empty DataFrame
+        empty_df = pd.DataFrame()
+        result_empty_df = rename_columns(empty_df)
+        pd.testing.assert_frame_equal(result_empty_df, empty_df)  # Should be unchanged
+
 
     @patch("src.utils.llm_utils.invoke_claude")
     @patch("src.investment.investment_postprocessing_funcs.invoke_derived_term_date")