one place to have df_has_single_uprn

CLAUDE.md

@@ -62,6 +62,7 @@ bash .devcontainer/backend/install-claude-skills.sh
 ## Type Safety
 
 All new code must pass `pyright` with zero errors under `typeCheckingMode = strict`.
+Use Optional over | None
 Annotate all function return types. Use `dict[str, Any]` for untyped external API
 payloads — never bare `dict`. Add `pandas-stubs` when introducing pandas to a module.
 

backend/address2UPRN/main.py

@@ -17,9 +17,8 @@ from datetime import datetime
 from backend.utils.addressMatch import (
     AddressMatch,
     get_uprn_candidates,
-    df_has_single_uprn,
-    score_addresses,
 )
+from backend.address2UPRN.scoring import df_has_single_uprn
 from datatypes.epc.domain.historic_epc_matching import (
     match_addresses_for_postcode,
 )

backend/utils/addressMatch.py

@@ -259,13 +259,3 @@ def get_uprn_candidates(
     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:
-        return False
-    uprns = df[column].dropna().astype(str).str.strip().unique()
-    if len(uprns) == 0:
-        return False
-    return len(uprns) == 1 and uprns[0] == str(uprn)