get rid of duplicate function and make better sensible variable name

backend/address2UPRN/main.py

@@ -14,11 +14,8 @@ from utils.s3 import (
 )
 from datetime import datetime
 
-from backend.utils.addressMatch import (
-    AddressMatch,
-    get_uprn_candidates,
-)
-from backend.address2UPRN.scoring import all_uprns_match
+from backend.utils.addressMatch import AddressMatch
+from backend.address2UPRN.scoring import all_uprns_match, rank_by_address_similarity
 from datatypes.epc.domain.historic_epc_matching import (
     match_addresses_for_postcode,
 )
@@ -82,7 +79,7 @@ def get_uprn_with_epc_df(
     if epc_df.empty:
         return None
 
-    scored_df = get_uprn_candidates(
+    scored_df = rank_by_address_similarity(
         epc_df,
         user_address=user_inputed_address,
     )
@@ -174,7 +171,7 @@ def resolve_uprns_for_postcode_group(
     for _, row in group_df.iterrows():
         user_address = str(row[address_col]).strip()
 
-        scored_df = get_uprn_candidates(
+        scored_df = rank_by_address_similarity(
             epc_df,
             user_address=user_address,
         )

backend/address2UPRN/scoring.py

@@ -19,7 +19,7 @@ def all_uprns_match(
     return len(uprns) == 1 and uprns[0] == str(target_uprn)
 
 
-def get_uprn_candidates(
+def rank_by_address_similarity(
     df: pd.DataFrame,
     user_address: str,
     address_column: str = "address",

backend/utils/addressMatch.py

@@ -242,31 +242,6 @@ def score_addresses(
     return df[address_column].apply(lambda x: AddressMatch.score(user_address, x))
 
 
-def get_uprn_candidates(
-    df: pd.DataFrame,
-    user_address: str,
-    address_column: str = "address",
-    uprn_column: str = "uprn",
-) -> pd.DataFrame:
-    """
-    Annotate EPC results with lexicographical similarity scores and ranks.
-    Returns a DataFrame sorted by descending lexiscore.
-    """
-    if address_column not in df.columns:
-        raise ValueError(f"Missing column: {address_column}")
-    if uprn_column not in df.columns:
-        raise ValueError(f"Missing column: {uprn_column}")
-
-    out = df.copy()
-    user_norm = AddressMatch.normalise_address(user_address)
-    out["lexiscore"] = out[address_column].apply(
-        lambda x: AddressMatch.levenshtein(user_norm, x)
-    )
-    out[uprn_column] = out[uprn_column].astype(str).str.replace(r"\.0$", "", regex=True)
-    out["lexirank"] = out["lexiscore"].rank(method="dense", ascending=False).astype(int)
-    return out.sort_values(["lexirank", "lexiscore"], ascending=[True, False])
-
-
 def df_has_single_uprn(df: pd.DataFrame, uprn: str, column: str = "uprn") -> bool:
     """Returns True if all non-null UPRNs in df match the given uprn."""
     if column not in df.columns:

datatypes/epc/domain/historic_epc_matching.py

@@ -4,7 +4,7 @@ from typing import Optional
 import pandas as pd
 from botocore.exceptions import ClientError
 
-from backend.address2UPRN.scoring import get_uprn_candidates
+from backend.address2UPRN.scoring import rank_by_address_similarity
 from backend.utils.addressMatch import AddressMatch
 from datatypes.epc.domain.historic_epc import HistoricEpc
 from utils.pandas_utils import pandas_cell_to_str
@@ -85,7 +85,7 @@ def match_addresses_for_postcode(
             ) from e
         raise
 
-    scored = get_uprn_candidates(
+    scored = rank_by_address_similarity(
         df,
         user_address=user_address,
         address_column=address_column,