BUG: Trees: minor bug in NaN detection leading to incorrect split. #33113
Description
Describe the bug
The break here is wrong, and in some edge cases it will prevent _any_isnan_axis0 detecting NaNs for some features. Then because of that, the splitter won't considers splits with NaNs on the left (because it's not aware this feature has NaNs).
Steps/Code to Reproduce
import numpy as np
from numpy import nan
from sklearn.tree import DecisionTreeRegressor
X = np.array([
[nan, nan],
[1, 0],
[1, 1]
])
y = np.array([0, 0, 1])
tree = DecisionTreeRegressor(max_depth=1).fit(X, y)
assert (tree.tree_.impurity[1:] == 0).all()Expected Results
The best split is found => No assertion error
The best split: X[:, 1] < 0.5 and missing values to the left node.
Actual Results
Assertion error.
Versions
System:
python: 3.12.11 (main, Aug 18 2025, 19:19:11) [Clang 20.1.4 ]
executable: /home/arthur/dev-perso/scikit-learn/sklearn-env/bin/python
machine: Linux-6.14.0-37-generic-x86_64-with-glibc2.39
Python dependencies:
sklearn: 1.9.dev0
pip: None
setuptools: 80.9.0
numpy: 2.3.5
scipy: 1.16.3
Cython: 3.2.1
pandas: 2.3.3
matplotlib: 3.10.7
joblib: 1.5.2
threadpoolctl: 3.6.0
Built with OpenMP: True
threadpoolctl info:
user_api: blas
internal_api: openblas
num_threads: 16
prefix: libscipy_openblas
filepath: /home/arthur/dev-perso/scikit-learn/sklearn-env/lib/python3.12/site-packages/numpy.libs/libscipy_openblas64_-fdde5778.so
version: 0.3.30
threading_layer: pthreads
architecture: Haswell
user_api: blas
internal_api: openblas
num_threads: 16
prefix: libscipy_openblas
filepath: /home/arthur/dev-perso/scikit-learn/sklearn-env/lib/python3.12/site-packages/scipy.libs/libscipy_openblas-b75cc656.so
version: 0.3.29.dev
threading_layer: pthreads
architecture: Haswell
user_api: openmp
internal_api: openmp
num_threads: 16
prefix: libgomp
filepath: /usr/lib/x86_64-linux-gnu/libgomp.so.1.0.0
version: None