Add warning for large numbers of datapoints

pysr/sr.py

@@ -11,6 +11,7 @@ import tempfile
 import shutil
 from pathlib import Path
 from datetime import datetime
+import warnings
 
 
 global_equation_file = 'hall_of_fame.csv'
@@ -221,6 +222,10 @@ def pysr(X=None, y=None, weights=None,
     if use_custom_variable_names:
         assert len(variable_names) == X.shape[1]
 
+
+    if len(X) > 10000 and not batching:
+        warnings.warn("Note: you are running with more than 10,000 datapoints. You should consider turning on batching (https://pysr.readthedocs.io/en/latest/docs/options/#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 select_k_features is not None:
         selection = run_feature_selection(X, y, select_k_features)
         print(f"Using features {selection}")

setup.py

@@ -5,7 +5,7 @@ with open("README.md", "r") as fh:
 
 setuptools.setup(
     name="pysr", # Replace with your own username
-    version="0.3.36",
+    version="0.3.37",
     author="Miles Cranmer",
     author_email="miles.cranmer@gmail.com",
     description="Simple and efficient symbolic regression",