BUG: FloatingArray.__contains__(nan) (pandas-dev#52840)

* BUG: FloatingArray.__contains__(nan)

* GH ref

* mypy fixup

* mypy fixup

---------

Co-authored-by: Patrick Hoefler <[email protected]>

Author: 2 people

doc/source/whatsnew/v2.1.0.rst

@@ -432,6 +432,7 @@ Metadata
 
 Other
 ^^^^^
+- Bug in :class:`FloatingArray.__contains__` with ``NaN`` item incorrectly returning ``False`` when ``NaN`` values are presnet (:issue:`52840`)
 - Bug in :func:`assert_almost_equal` now throwing assertion error for two unequal sets (:issue:`51727`)
 - Bug in :func:`assert_frame_equal` checks category dtypes even when asked not to check index type (:issue:`52126`)
 - Bug in :meth:`DataFrame.reindex` with a ``fill_value`` that should be inferred with a :class:`ExtensionDtype` incorrectly inferring ``object`` dtype (:issue:`52586`)

pandas/core/arrays/arrow/array.py

@@ -578,7 +578,7 @@ def __len__(self) -> int:
     def __contains__(self, key) -> bool:
         # https://github.com/pandas-dev/pandas/pull/51307#issuecomment-1426372604
         if isna(key) and key is not self.dtype.na_value:
-            if self.dtype.kind == "f" and lib.is_float(key) and isna(key):
+            if self.dtype.kind == "f" and lib.is_float(key):
                 return pc.any(pc.is_nan(self._pa_array)).as_py()
 
             # e.g. date or timestamp types we do not allow None here to match pd.NA

pandas/core/arrays/masked.py

@@ -236,6 +236,14 @@ def __setitem__(self, key, value) -> None:
         self._data[key] = value
         self._mask[key] = mask
 
+    def __contains__(self, key) -> bool:
+        if isna(key) and key is not self.dtype.na_value:
+            # GH#52840
+            if self._data.dtype.kind == "f" and lib.is_float(key):
+                return bool((np.isnan(self._data) & ~self._mask).any())
+
+        return bool(super().__contains__(key))
+
     def __iter__(self) -> Iterator:
         if self.ndim == 1:
             if not self._hasna:

pandas/tests/arrays/floating/test_contains.py

@@ -0,0 +1,12 @@
+import numpy as np
+
+import pandas as pd
+
+
+def test_contains_nan():
+    # GH#52840
+    arr = pd.array(range(5)) / 0
+
+    assert np.isnan(arr._data[0])
+    assert not arr.isna()[0]
+    assert np.nan in arr