scikit-learn · thomasjpfan · Mar 2, 2021 · Mar 1, 2021
diff --git a/doc/whats_new/v0.24.rst b/doc/whats_new/v0.24.rst
@@ -48,6 +48,16 @@ Changelog
  :class:`~sklearn.semi_supervised.LabelPropagation`.
  :pr:`19271` by :user:`Zhaowei Wang <ThuWangzw>`.

+:mod:`sklearn.tree`
+.......................
+
+- |Fix| Fix a bug in `fit` of :class:`tree.BaseDecisionTree` that caused
+  segmentation faults under certain conditions. `fit` now deep copies the
+  `Criterion` object to prevent shared concurrent accesses.
+  :pr:`19580` by :user:`Samuel Brice <samdbrice>` and
+  :user:`Alex Adamson <aadamson>` and
+  :user:`Wil Yegelwel <wyegelwel>`.
+
 :mod:`sklearn.utils`
 ....................


diff --git a/sklearn/ensemble/tests/test_forest.py b/sklearn/ensemble/tests/test_forest.py
@@ -1494,3 +1494,21 @@ def test_n_features_deprecation(Estimator):

    with pytest.warns(FutureWarning, match="n_features_ was deprecated"):
        est.n_features_
+
+
+@pytest.mark.parametrize('Forest', FOREST_REGRESSORS)
+def test_mse_criterion_object_segfault_smoke_test(Forest):
+    # This is a smoke test to ensure that passing a mutable criterion
+    # does not cause a segfault when fitting with concurrent threads.
+    # Non-regression test for:
+    # https://github.com/scikit-learn/scikit-learn/issues/12623
+    from sklearn.tree._criterion import MSE
+
+    y = y_reg.reshape(-1, 1)
+    n_samples, n_outputs = y.shape
+    mse_criterion = MSE(n_outputs, n_samples)
+    est = FOREST_REGRESSORS[Forest](
+        n_estimators=2, n_jobs=2, criterion=mse_criterion
+    )
+
+    est.fit(X_reg, y)
diff --git a/sklearn/tree/_classes.py b/sklearn/tree/_classes.py
@@ -16,6 +16,7 @@

 import numbers
 import warnings
+import copy
 from abc import ABCMeta
 from abc import abstractmethod
 from math import ceil
@@ -349,6 +350,10 @@ def fit(self, X, y, sample_weight=None, check_input=True,
            else:
                criterion = CRITERIA_REG[self.criterion](self.n_outputs_,
                                                         n_samples)
+        else:
+            # Make a deepcopy in case the criterion has mutable attributes that
+            # might be shared and modified concurrently during parallel fitting
+            criterion = copy.deepcopy(criterion)

        SPLITTERS = SPARSE_SPLITTERS if issparse(X) else DENSE_SPLITTERS