Add more helpful warnings

pysr/sr.py

@@ -691,7 +691,7 @@ class PySRRegressor(BaseEstimator, RegressorMixin):
 
         if maxsize > 40:
             warnings.warn(
-                "Note: Using a large maxsize for the equation search will be exponentially slower and use significant memory. You should consider turning `use_frequency` to False, and perhaps use `warmup_maxsize_by`."
+                "Note: Using a large maxsize for the equation search will be exponentially slower and use significant memory."
             )
         elif maxsize < 7:
             raise NotImplementedError("PySR requires a maxsize of at least 7")
@@ -1147,6 +1147,20 @@ class PySRRegressor(BaseEstimator, RegressorMixin):
                 "Note: you are running with more than 10,000 datapoints. You should consider turning on batching (https://astroautomata.com/PySR/#/options?id=batching). You should also reconsider if you need that many datapoints. Unless you have a large amount of noise (in which case you should smooth your dataset first), generally < 10,000 datapoints is enough to find a functional form with symbolic regression. More datapoints will lower the search speed."
             )
 
+        if self.n_features >= 10 and not select_k_features:
+            warnings.warn(
+                "Note: you are running with 10 features or more. "
+                "Genetic algorithms like used in PySR scale poorly with large numbers of features. "
+                "Consider using feature selection techniques to select the most important features "
+                "(you can do this automatically with the `select_k_features` parameter), "
+                "or, alternatively, doing a dimensionality reduction beforehand. "
+                "For example, `X = PCA(n_components=6).fit_transform(X)`, "
+                "using scikit-learn's `PCA` class, "
+                "will reduce the number of features to 6 in an interpretable way, "
+                "as each resultant feature "
+                "will be a linear combination of the original features. "
+            )
+
         X, selection = _handle_feature_selection(
             X, select_k_features, y, variable_names
         )

test/test.py

@@ -7,6 +7,7 @@ from pysr.sr import run_feature_selection, _handle_feature_selection
 import sympy
 from sympy import lambdify
 import pandas as pd
+import warnings
 
 
 class TestPipeline(unittest.TestCase):
@@ -275,11 +276,36 @@ class TestMiscellaneous(unittest.TestCase):
     """Test miscellaneous functions."""
 
     def test_deprecation(self):
-        # Ensure that deprecation works as expected, with a warning,
-        # and sets the correct value.
+        """Ensure that deprecation works as expected.
+
+        This should give a warning, and sets the correct value.
+        """
         with self.assertWarns(UserWarning):
             model = PySRRegressor(fractionReplaced=0.2)
         # This is a deprecated parameter, so we should get a warning.
 
         # The correct value should be set:
         self.assertEqual(model.params["fraction_replaced"], 0.2)
+
+    def test_size_warning(self):
+        """Ensure that a warning is given for a large input size."""
+        model = PySRRegressor()
+        X = np.random.randn(10001, 2)
+        y = np.random.randn(10001)
+        with warnings.catch_warnings():
+            warnings.simplefilter("error")
+            with self.assertRaises(Exception) as context:
+                model.fit(X, y)
+            self.assertIn("more than 10,000", str(context.exception))
+
+    def test_feature_warning(self):
+        """Ensure that a warning is given for large number of features."""
+        model = PySRRegressor()
+        X = np.random.randn(100, 10)
+        y = np.random.randn(100)
+        with warnings.catch_warnings():
+            warnings.simplefilter("error")
+            with self.assertRaises(Exception) as context:
+                model.fit(X, y)
+            self.assertIn("with 10 features or more", str(context.exception))
+