FIX Param validation Interval error for large integers (#26648)

naoise-h · jeremiedbb · web-flow · commit 38a1e64bbe42 · 2023-09-27T16:07:49.000Z
Co-authored-by: jeremie du boisberranger &lt;jeremiedbb@yahoo.fr&gt;
diff --git a/doc/whats_new/v1.4.rst b/doc/whats_new/v1.4.rst
@@ -29,6 +29,10 @@ Changes impacting all modules
   to work with our estimators and functions.
   :pr:`26464` by `Thomas Fan`_.
 
+- |Fix| Fixed a bug in most estimators and functions where setting a parameter to
+  a large integer would cause a `TypeError`.
+  :pr:`26648` by :user:`Naoise Holohan <naoise-h>`.
+
 Metadata Routing
 ----------------
 
diff --git a/sklearn/utils/__init__.py b/sklearn/utils/__init__.py
@@ -1094,7 +1094,11 @@ def is_scalar_nan(x):
     >>> is_scalar_nan([np.nan])
     False
     """
-    return isinstance(x, numbers.Real) and math.isnan(x)
+    return (
+        not isinstance(x, numbers.Integral)
+        and isinstance(x, numbers.Real)
+        and math.isnan(x)
+    )
 
 
 def _approximate_mode(class_counts, n_draws, rng):
diff --git a/sklearn/utils/_param_validation.py b/sklearn/utils/_param_validation.py
@@ -311,7 +311,9 @@ class _NanConstraint(_Constraint):
     """Constraint representing the indicator `np.nan`."""
 
     def is_satisfied_by(self, val):
-        return isinstance(val, Real) and math.isnan(val)
+        return (
+            not isinstance(val, Integral) and isinstance(val, Real) and math.isnan(val)
+        )
 
     def __str__(self):
         return "numpy.nan"
@@ -475,7 +477,7 @@ def _check_params(self):
             )
 
     def __contains__(self, val):
-        if np.isnan(val):
+        if not isinstance(val, Integral) and np.isnan(val):
             return False
 
         left_cmp = operator.lt if self.closed in ("left", "both") else operator.le
diff --git a/sklearn/utils/tests/test_param_validation.py b/sklearn/utils/tests/test_param_validation.py
@@ -74,16 +74,41 @@ def fit(self, X=None, y=None):
 def test_interval_range(interval_type):
     """Check the range of values depending on closed."""
     interval = Interval(interval_type, -2, 2, closed="left")
-    assert -2 in interval and 2 not in interval
+    assert -2 in interval
+    assert 2 not in interval
 
     interval = Interval(interval_type, -2, 2, closed="right")
-    assert -2 not in interval and 2 in interval
+    assert -2 not in interval
+    assert 2 in interval
 
     interval = Interval(interval_type, -2, 2, closed="both")
-    assert -2 in interval and 2 in interval
+    assert -2 in interval
+    assert 2 in interval
 
     interval = Interval(interval_type, -2, 2, closed="neither")
-    assert -2 not in interval and 2 not in interval
+    assert -2 not in interval
+    assert 2 not in interval
+
+
+@pytest.mark.parametrize("interval_type", [Integral, Real])
+def test_interval_large_integers(interval_type):
+    """Check that Interval constraint work with large integers.
+
+    non-regression test for #26648.
+    """
+    interval = Interval(interval_type, 0, 2, closed="neither")
+    assert 2**65 not in interval
+    assert 2**128 not in interval
+    assert float(2**65) not in interval
+    assert float(2**128) not in interval
+
+    interval = Interval(interval_type, 0, 2**128, closed="neither")
+    assert 2**65 in interval
+    assert 2**128 not in interval
+    assert float(2**65) in interval
+    assert float(2**128) not in interval
+
+    assert 2**1024 not in interval
 
 
 def test_interval_inf_in_bounds():
@@ -389,6 +414,7 @@ def test_generate_valid_param(constraint):
         ("verbose", 1),
         (MissingValues(), -1),
         (MissingValues(), -1.0),
+        (MissingValues(), 2**1028),
         (MissingValues(), None),
         (MissingValues(), float("nan")),
         (MissingValues(), np.nan),
