Handle percent/decimal convention in Number-Match

evaluations/evaluations/numbers.py

@@ -47,6 +47,10 @@ def extract_numbers(text: str) -> list[float]:
         value = _to_float(token)
         if value is not None:
             numbers.append(value)
+            if "%" in token:
+                # Gold answers store ratios as either a percent (24.69) or a
+                # decimal (0.935); offer both readings of a percent figure.
+                numbers.append(value / 100)
     for number, scale in _SCALED_RE.findall(text):
         value = _to_float(number)
         if value is not None:

evaluations/tests/test_evaluators.py

@@ -82,6 +82,14 @@ class TestNumberMatchEvaluator:
         ctx = self._make_ctx("50.3", "In 2008 it grew from 27.0 to 50.3 percent")
         assert self.evaluator.evaluate(ctx) == 1.0
 
+    def test_percent_answer_matches_decimal_gold(self) -> None:
+        ctx = self._make_ctx("0.935", "the cumulative total return was 93.5%")
+        assert self.evaluator.evaluate(ctx) == 1.0
+
+    def test_percent_answer_matches_percent_gold(self) -> None:
+        ctx = self._make_ctx("24.691358024691358", "approximately 24.69% of production")
+        assert self.evaluator.evaluate(ctx) == 1.0
+
     def test_non_numeric_prediction(self) -> None:
         ctx = self._make_ctx("127.4", "I cannot determine the value")
         assert self.evaluator.evaluate(ctx) == 0.0

evaluations/tests/test_numbers.py

@@ -8,8 +8,8 @@ class TestExtractNumbers:
     def test_currency_and_thousands(self) -> None:
         assert extract_numbers("$1,234.5") == [1234.5]
 
-    def test_percent_stripped(self) -> None:
+    def test_percent_yields_both_readings(self) -> None:
-        assert extract_numbers("margin was 50.3%") == [50.3]
+        assert extract_numbers("margin was 50.3%") == [50.3, 0.503]
 
     def test_parenthesised_negative(self) -> None:
         assert extract_numbers("loss of (123)") == [-123.0]