fix TypeError when a variable name matches a builtin python function

pysr/export_sympy.py

@@ -57,17 +57,29 @@
 }
 
 
+def create_sympy_symbols_map(
+    feature_names_in: List[str],
+) -> Dict[str, sympy.Symbol]:
+    return {variable: sympy.Symbol(variable) for variable in feature_names_in}
+
+
 def create_sympy_symbols(
     feature_names_in: List[str],
 ) -> List[sympy.Symbol]:
     return [sympy.Symbol(variable) for variable in feature_names_in]
 
 
 def pysr2sympy(
-    equation: str, *, extra_sympy_mappings: Optional[Dict[str, Callable]] = None
+    equation: str,
+    *,
+    feature_names_in: Optional[List[str]] = None,
+    extra_sympy_mappings: Optional[Dict[str, Callable]] = None,
 ):
+    if feature_names_in is None:
+        feature_names_in = []
     local_sympy_mappings = {
-        **(extra_sympy_mappings if extra_sympy_mappings else {}),
+        **create_sympy_symbols_map(feature_names_in),
+        **(extra_sympy_mappings if extra_sympy_mappings is not None else {}),
         **sympy_mappings,
     }
 

pysr/sr.py

@@ -2226,6 +2226,7 @@ def get_hof(self):
             for _, eqn_row in output.iterrows():
                 eqn = pysr2sympy(
                     eqn_row["equation"],
+                    feature_names_in=self.feature_names_in_,
                     extra_sympy_mappings=self.extra_sympy_mappings,
                 )
                 sympy_format.append(eqn)

pysr/test/test.py

@@ -272,7 +272,7 @@ def test_warm_start_set_at_init(self):
         regressor = PySRRegressor(warm_start=True, max_evals=10)
         regressor.fit(self.X, y)
 
-    def test_noisy(self):
+    def test_noisy_builtin_variable_names(self):
         y = self.X[:, [0, 1]] ** 2 + self.rstate.randn(self.X.shape[0], 1) * 0.05
         model = PySRRegressor(
             # Test that passing a single operator works:
@@ -289,9 +289,12 @@ def test_noisy(self):
         model.set_params(model_selection="best")
         # Also try without a temp equation file:
         model.set_params(temp_equation_file=False)
-        model.fit(self.X, y)
+        # We also test builtin variable names
+        model.fit(self.X, y, variable_names=["exec", "hash", "x3", "x4", "x5"])
         self.assertLessEqual(model.get_best()[1]["loss"], 1e-2)
         self.assertLessEqual(model.get_best()[1]["loss"], 1e-2)
+        self.assertIn("exec", model.latex()[0])
+        self.assertIn("hash", model.latex()[1])
 
     def test_pandas_resample_with_nested_constraints(self):
         X = pd.DataFrame(