just making them no diff

reggie/configs/data/pennsylvania.yaml

@@ -331,5 +331,5 @@ county_names:
   - York
 
 # Columns added to the end of the file
-additional_columns:
+no_diff_columns:
   - registration_method

reggie/ingestion/preprocessor/pennsylvania_preprocessor.py

@@ -82,7 +82,7 @@ def execute(self):
 
         # PA Added a new column for registration_method on June 18, 2024
         if date_from_str(self.raw_s3_file) > "2024-06-17":
-            dfcols.extend(config["additional_columns"])
+            dfcols.extend(config["no_diff_columns"])
 
         # create a mapping that returns a series based on the values across rows (voters) of cells (election info).
         # consolidates the non nan values into one string that can be appended as a column later for the all_history and
@@ -93,16 +93,10 @@ def mapping(li, zone_dict=zone_dict):
                     li = [x for x in li if x != "nan"]
                     return li
                 else:
-                    li = [
-                        zone_dict[x]
-                        for x in li
-                        if x != "nan" and x in zone_dict
-                    ]
+                    li = [zone_dict[x] for x in li if x != "nan" and x in zone_dict]
                     return li
 
-            return pd.Series(
-                map(mapping, df_sub[columns].values.astype(str).tolist())
-            )
+            return pd.Series(map(mapping, df_sub[columns].values.astype(str).tolist()))
 
         sorted_codes = []
         sorted_code_dict = defaultdict(defaultdict)
@@ -111,12 +105,8 @@ def mapping(li, zone_dict=zone_dict):
             logging.info("Processing {} {}/{}".format(c, idx, len(counties)))
             c = format_column_name(c)
             try:
-                voter_file = next(
-                    f for f in voter_files if c in f["name"].lower()
-                )
-                election_map = next(
-                    f for f in election_maps if c in f["name"].lower()
-                )
+                voter_file = next(f for f in voter_files if c in f["name"].lower())
+                election_map = next(f for f in election_maps if c in f["name"].lower())
                 zones = next(f for f in zone_codes if c in f["name"].lower())
                 types = next(f for f in zone_types if c in f["name"].lower())
             except StopIteration:
@@ -190,9 +180,7 @@ def mapping(li, zone_dict=zone_dict):
 
             # Gather the pairs of election columns to iterate over both at the same time to collect the information
             # contained in both of the columns per election
-            vote_column_list = list(
-                zip(df.columns[70:150:2], df.columns[71:150:2])
-            )
+            vote_column_list = list(zip(df.columns[70:150:2], df.columns[71:150:2]))
 
             # get the value from the eleciton map key for the election name,
             # then combine it with the value in the party and vote type cells for the full election information
@@ -201,11 +189,7 @@ def mapping(li, zone_dict=zone_dict):
             # The columns are all named election_#_vote_type but the cells contain the relevant information
             vote_hist_df = pd.DataFrame(
                 {
-                    i: election_map[i.split("_")[1]]
-                    + " "
-                    + df[i]
-                    + " "
-                    + df[j]
+                    i: election_map[i.split("_")[1]] + " " + df[i] + " " + df[j]
                     for i, j in vote_column_list
                     if i.split("_")[1] in election_map
                 }
@@ -230,9 +214,7 @@ def mapping(li, zone_dict=zone_dict):
                     sorted_code_dict[current_key] = new_dict_entry
             # converts the dataframe to a series that contains the list of elections participate in indexed on position
             vote_hist_df = list_map(vote_hist_df, vote_hist_df.columns)
-            districts = list_map(
-                df[district_columns], district_columns, zone_dict
-            )
+            districts = list_map(df[district_columns], district_columns, zone_dict)
 
             df["all_history"] = vote_hist_df
             df["districts"] = districts
@@ -265,9 +247,7 @@ def mapping(li, zone_dict=zone_dict):
 
         logging.info("coercing")
         main_df = config.coerce_dates(main_df)
-        main_df = self.config.coerce_strings(
-            main_df, exclude=["county", "gender"]
-        )
+        main_df = self.config.coerce_strings(main_df, exclude=["county", "gender"])
         main_df = config.coerce_numeric(
             main_df,
             extra_cols=[