Backport PR #32242: BUG: Fixed bug, where pandas._libs.lib.maybe_convert_objects function improperly handled arrays with bools and NaNs (#32552)

Co-authored-by: Anna Daglis <[email protected]>

Author: meeseeksmachine

doc/source/whatsnew/v1.0.2.rst

@@ -24,6 +24,7 @@ Fixed regressions
 - Fixed regression in :class:`DataFrame` arithmetic operations with mis-matched columns (:issue:`31623`)
 - Fixed regression in :meth:`GroupBy.agg` calling a user-provided function an extra time on an empty input (:issue:`31760`)
 - Joining on :class:`DatetimeIndex` or :class:`TimedeltaIndex` will preserve ``freq`` in simple cases (:issue:`32166`)
+- Fixed bug in the repr of an object-dtype ``Index`` with bools and missing values (:issue:`32146`)
 -
 
 .. ---------------------------------------------------------------------------

pandas/_libs/lib.pyx

@@ -2235,7 +2235,7 @@ def maybe_convert_objects(ndarray[object] objects, bint try_float=0,
                                 return uints
                             else:
                                 return ints
-                elif seen.is_bool:
+                elif seen.is_bool and not seen.nan_:
                     return bools.view(np.bool_)
 
     return objects

pandas/tests/dtypes/test_inference.py

@@ -568,6 +568,13 @@ def test_maybe_convert_objects_nullable_integer(self, exp):
 
         tm.assert_extension_array_equal(result, exp)
 
+    def test_maybe_convert_objects_bool_nan(self):
+        # GH32146
+        ind = pd.Index([True, False, np.nan], dtype=object)
+        exp = np.array([True, False, np.nan], dtype=object)
+        out = lib.maybe_convert_objects(ind.values, safe=1)
+        tm.assert_numpy_array_equal(out, exp)
+
     def test_mixed_dtypes_remain_object_array(self):
         # GH14956
         array = np.array([datetime(2015, 1, 1, tzinfo=pytz.utc), 1], dtype=object)

pandas/tests/indexes/test_base.py

@@ -2697,6 +2697,17 @@ def test_intersect_str_dates(self):
         expected = Index([], dtype=object)
         tm.assert_index_equal(result, expected)
 
+    def test_index_repr_bool_nan(self):
+        # GH32146
+        arr = Index([True, False, np.nan], dtype=object)
+        exp1 = arr.format()
+        out1 = ["True", "False", "NaN"]
+        assert out1 == exp1
+
+        exp2 = repr(arr)
+        out2 = "Index([True, False, nan], dtype='object')"
+        assert out2 == exp2
+
 
 class TestIndexUtils:
     @pytest.mark.parametrize(

pandas/tests/series/methods/test_value_counts.py

@@ -1,4 +1,5 @@
 import numpy as np
+import pytest
 
 import pandas as pd
 from pandas import Categorical, CategoricalIndex, Series
@@ -177,3 +178,28 @@ def test_value_counts_categorical_with_nan(self):
             exp = Series([2, 1, 3], index=CategoricalIndex(["a", "b", np.nan]))
             res = ser.value_counts(dropna=False, sort=False)
             tm.assert_series_equal(res, exp)
+
+    @pytest.mark.parametrize(
+        "ser, dropna, exp",
+        [
+            (
+                pd.Series([False, True, True, pd.NA]),
+                False,
+                pd.Series([2, 1, 1], index=[True, False, pd.NA]),
+            ),
+            (
+                pd.Series([False, True, True, pd.NA]),
+                True,
+                pd.Series([2, 1], index=[True, False]),
+            ),
+            (
+                pd.Series(range(3), index=[True, False, np.nan]).index,
+                False,
+                pd.Series([1, 1, 1], index=[True, False, pd.NA]),
+            ),
+        ],
+    )
+    def test_value_counts_bool_with_nan(self, ser, dropna, exp):
+        # GH32146
+        out = ser.value_counts(dropna=dropna)
+        tm.assert_series_equal(out, exp)