Merge branch 'master' into recover

.travis.yml

@@ -9,10 +9,6 @@ jobs:
       dist: bionic
       before_install: sudo apt-get -y install python3-pip python3-setuptools
       env: PY=python3 SETUPPREFIX="--user"
-    - name: "macOS"
-      os: osx
-      before_install: python3 --version; pip3 --version; sw_vers
-      env: PY=python3
     - name: "Windows"
       os: windows
       before_install:

README.md

@@ -1,4 +1,4 @@
-# [PySR.jl](https://github.com/MilesCranmer/PySR)
+# [PySR](https://github.com/MilesCranmer/PySR)
 
 (pronounced like *py* as in python, and then *sur* as in surface)
 
@@ -13,6 +13,9 @@ Uses regularized evolution, simulated annealing, and gradient-free optimization.
 
 [Documentation](https://pysr.readthedocs.io/en/latest)
 
+Check out [SymbolicRegression.jl](https://github.com/MilesCranmer/SymbolicRegression.jl) for
+the pure-Julia version of this package.
+
 Symbolic regression is a very interpretable machine learning algorithm
 for low-dimensional problems: these tools search equation space
 to find algebraic relations that approximate a dataset.

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'
@@ -202,9 +203,13 @@ def pysr(X=None, y=None, weights=None,
     if len(X.shape) == 1:
         X = X[:, None]
 
-    check_assertions(X, binary_operators, unary_operators,
+    _check_assertions(X, binary_operators, unary_operators,
                      use_custom_variable_names, variable_names, weights, y)
 
+
+    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.")
+
     X, variable_names = handle_feature_selection(
             X, select_k_features,
             use_custom_variable_names, variable_names, y

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="[email protected]",
     description="Simple and efficient symbolic regression",