Merged in chore/health_plan_state (pull request #304)

refactored code to add recent health plan state hotfixes into the existing postprocessing pipeline

* refactored code to add recent health plan state hotfixes into the existing postprocessing pipeline

* Merged main into chore/health_plan_state

* Merged main into chore/health_plan_state

* add debug print statement

* debug print statements

* more debug print statements

* print df columns for debug

* move health plan state hotfix functionality to postprocessing_funcs.py

* add better error printing

* add error message for parent agreement code

* remove dots in state abbreviations

* remove unused import

* also look for state abbreviations

* Merged main into chore/health_plan_state

* remove print statements

* Merged main into chore/health_plan_state


Approved-by: Katon Minhas

fieldExtraction/src/postprocessing_funcs.py

@@ -9,6 +9,7 @@ import valid
 from valid import DERIVED_INDICATOR_FIELDS
 import claude_funcs
 from utils import is_empty
+from hotfix_helper_funcs import state_check
 
 import logging
 
@@ -142,10 +143,10 @@ def get_parent_agreement_code(filename):
         filename = re.sub(r"\([^)]*\)", "", filename)
 
         match = re.search(r"([^\sa-zA-Z]+)(?=\.\w+$|$)", filename)
-        end = [i for i in match.group(1).split("_") if i]
+        end = [i for i in match.group(1).split("_") if i] # an error is happening here.  This function needs a docstring.
         return end[0]
     except Exception as e:
-        print(f"Error: {e}")
+        print(f"Error in `get_parent_agreement_code`: {e}; returning `N/A`")
         return "N/A"
 
 
@@ -399,6 +400,35 @@ def clean_health_plan_state(final_df):
         final_df["HEALTH_PLAN_STATE"] = final_df["HEALTH_PLAN_STATE"].str.title()
     return final_df
 
+def clean_health_plan_state_from_hotfix(
+    df: pd.DataFrame,
+    contract_name: str,
+    text_dict: dict[str, str],
+) -> pd.DataFrame:
+
+    if not isinstance(df, pd.DataFrame):
+        # raise TypeError(f"Expected a dataframe, got {type(df).__name__}")
+        return df
+
+    if contract_name is None:
+        # raise ValueError(
+        #     f"Expected 'contract_name' parameter, got {contract_name}"
+        # )
+        return df
+
+    if "HEALTH_PLAN_STATE" not in df.columns:
+        # raise KeyError(
+        #     f"Column 'Health Plan State' not found in DataFrame. Available columns are: {list(df.columns)}"
+        # )
+        return df
+
+    health_plan_state = df["HEALTH_PLAN_STATE"].unique().tolist()[0]
+    
+    answer = state_check(health_plan_state, text_dict)
+
+    df["HEALTH_PLAN_STATE"] = answer
+    
+    return df
 
 def clean_notice_provider_name_and_address(final_df):
     if "NOTICE_PROVIDER_NAME" in final_df and "NOTICE_PROVIDER_ADDRESS" in final_df: