Merge pull request #85 from pandas-dev/master

Sync Fork from Upstream Repo

Author: sthagen

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`)
 -
 
 .. ---------------------------------------------------------------------------

doc/source/whatsnew/v1.1.0.rst

@@ -231,7 +231,7 @@ Timezones
 Numeric
 ^^^^^^^
 - Bug in :meth:`DataFrame.floordiv` with ``axis=0`` not treating division-by-zero like :meth:`Series.floordiv` (:issue:`31271`)
--
+- Bug in :meth:`to_numeric` with string argument ``"uint64"`` and ``errors="coerce"`` silently fails (:issue:`32394`)
 -
 
 Conversion

pandas/_libs/lib.pyx

@@ -2024,8 +2024,6 @@ def maybe_convert_numeric(ndarray[object] values, set na_values,
             except (TypeError, ValueError) as err:
                 if not seen.coerce_numeric:
                     raise type(err)(f"{err} at position {i}")
-                elif "uint64" in str(err):  # Exception from check functions.
-                    raise
 
                 seen.saw_null()
                 floats[i] = NaN
@@ -2298,7 +2296,7 @@ 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/core/arrays/categorical.py

@@ -1728,7 +1728,8 @@ def fillna(self, value=None, method=None, limit=None):
         # pad / bfill
         if method is not None:
 
-            values = self.to_dense().reshape(-1, len(self))
+            # TODO: dispatch when self.categories is EA-dtype
+            values = np.asarray(self).reshape(-1, len(self))
             values = interpolate_2d(values, method, 0, None, value).astype(
                 self.categories.dtype
             )[0]

pandas/tests/dtypes/test_inference.py

@@ -507,6 +507,13 @@ def test_convert_numeric_int64_uint64(self, case, coerce):
         result = lib.maybe_convert_numeric(case, set(), coerce_numeric=coerce)
         tm.assert_almost_equal(result, expected)
 
+    def test_convert_numeric_string_uint64(self):
+        # GH32394
+        result = lib.maybe_convert_numeric(
+            np.array(["uint64"], dtype=object), set(), coerce_numeric=True
+        )
+        assert np.isnan(result)
+
     @pytest.mark.parametrize("value", [-(2 ** 63) - 1, 2 ** 64])
     def test_convert_int_overflow(self, value):
         # see gh-18584
@@ -568,6 +575,13 @@ 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

@@ -2458,6 +2458,17 @@ 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)