diff --git a/pipeline/plugins/extractors/tap-uk-ees/tap_uk_ees/tap.py b/pipeline/plugins/extractors/tap-uk-ees/tap_uk_ees/tap.py index 7b81fac..cbf26d3 100644 --- a/pipeline/plugins/extractors/tap-uk-ees/tap_uk_ees/tap.py +++ b/pipeline/plugins/extractors/tap-uk-ees/tap_uk_ees/tap.py @@ -592,7 +592,11 @@ class LegacyKS2Stream(Stream): for _, row in df.iterrows(): record = {"year": year_code} for old_col, new_col in _LEGACY_KS2_COLUMN_MAP.items(): - record[new_col] = row.get(old_col, "") + val = row.get(old_col, "") + # Strip % suffix — old DfE CSVs use "57%" not "57" + if isinstance(val, str) and val.endswith("%"): + val = val[:-1] + record[new_col] = val yield record