Merge branch 'main' into pandas-devGH-24537/parr-fillna-test

Author: phofl

doc/source/whatsnew/v2.0.0.rst

@@ -572,9 +572,11 @@ Other API changes
 Deprecations
 ~~~~~~~~~~~~
 - Deprecated argument ``infer_datetime_format`` in :func:`to_datetime` and :func:`read_csv`, as a strict version of it is now the default (:issue:`48621`)
-- Deprecated :func:`pandas.io.sql.execute`(:issue:`50185`)
+- Deprecated :func:`pandas.io.sql.execute` (:issue:`50185`)
+- :meth:`Index.is_boolean` has been deprecated. Use :func:`pandas.api.types.is_bool_dtype` instead (:issue:`50042`)
 - :meth:`Index.is_integer` has been deprecated. Use :func:`pandas.api.types.is_integer_dtype` instead (:issue:`50042`)
 - :meth:`Index.is_floating` has been deprecated. Use :func:`pandas.api.types.is_float_dtype` instead (:issue:`50042`)
+- :meth:`Index.holds_integer` has been deprecated. Use :func:`pandas.api.types.infer_dtype` instead (:issue:`50243`)
 
 .. ---------------------------------------------------------------------------
 .. _whatsnew_200.prior_deprecations:

pandas/core/arrays/categorical.py

@@ -47,6 +47,7 @@
 from pandas.core.dtypes.common import (
     ensure_int64,
     ensure_platform_int,
+    is_bool_dtype,
     is_categorical_dtype,
     is_datetime64_dtype,
     is_dict_like,
@@ -600,7 +601,7 @@ def _from_inferred_categories(
                 cats = to_datetime(inferred_categories, errors="coerce")
             elif is_timedelta64_dtype(dtype.categories):
                 cats = to_timedelta(inferred_categories, errors="coerce")
-            elif dtype.categories.is_boolean():
+            elif is_bool_dtype(dtype.categories):
                 if true_values is None:
                     true_values = ["True", "TRUE", "true"]
 

pandas/core/indexes/base.py

@@ -2192,6 +2192,9 @@ def is_boolean(self) -> bool:
         """
         Check if the Index only consists of booleans.
 
+        .. deprecated:: 2.0.0
+            Use `pandas.api.types.is_bool_dtype` instead.
+
         Returns
         -------
         bool
@@ -2220,6 +2223,12 @@ def is_boolean(self) -> bool:
         >>> idx.is_boolean()
         False
         """
+        warnings.warn(
+            f"{type(self).__name__}.is_boolean is deprecated. "
+            "Use pandas.api.types.is_bool_type instead.",
+            FutureWarning,
+            stacklevel=find_stack_level(),
+        )
         return self.inferred_type in ["boolean"]
 
     @final
@@ -2237,7 +2246,7 @@ def is_integer(self) -> bool:
 
         See Also
         --------
-        is_boolean : Check if the Index only consists of booleans.
+        is_boolean : Check if the Index only consists of booleans (deprecated).
         is_floating : Check if the Index is a floating type (deprecated).
         is_numeric : Check if the Index only consists of numeric data.
         is_object : Check if the Index is of the object dtype.
@@ -2285,7 +2294,7 @@ def is_floating(self) -> bool:
 
         See Also
         --------
-        is_boolean : Check if the Index only consists of booleans.
+        is_boolean : Check if the Index only consists of booleans (deprecated).
         is_integer : Check if the Index only consists of integers (deprecated).
         is_numeric : Check if the Index only consists of numeric data.
         is_object : Check if the Index is of the object dtype.
@@ -2311,8 +2320,8 @@ def is_floating(self) -> bool:
         False
         """
         warnings.warn(
-            f"{type(self).__name__}.is_floating is deprecated."
-            "Use pandas.api.types.is_float_dtype instead",
+            f"{type(self).__name__}.is_floating is deprecated. "
+            "Use pandas.api.types.is_float_dtype instead.",
             FutureWarning,
             stacklevel=find_stack_level(),
         )
@@ -2330,7 +2339,7 @@ def is_numeric(self) -> bool:
 
         See Also
         --------
-        is_boolean : Check if the Index only consists of booleans.
+        is_boolean : Check if the Index only consists of booleans (deprecated).
         is_integer : Check if the Index only consists of integers (deprecated).
         is_floating : Check if the Index is a floating type (deprecated).
         is_object : Check if the Index is of the object dtype.
@@ -2373,7 +2382,7 @@ def is_object(self) -> bool:
 
         See Also
         --------
-        is_boolean : Check if the Index only consists of booleans.
+        is_boolean : Check if the Index only consists of booleans (deprecated).
         is_integer : Check if the Index only consists of integers (deprecated).
         is_floating : Check if the Index is a floating type (deprecated).
         is_numeric : Check if the Index only consists of numeric data.
@@ -2414,7 +2423,7 @@ def is_categorical(self) -> bool:
         See Also
         --------
         CategoricalIndex : Index for categorical data.
-        is_boolean : Check if the Index only consists of booleans.
+        is_boolean : Check if the Index only consists of booleans (deprecated).
         is_integer : Check if the Index only consists of integers (deprecated).
         is_floating : Check if the Index is a floating type (deprecated).
         is_numeric : Check if the Index only consists of numeric data.
@@ -2457,7 +2466,7 @@ def is_interval(self) -> bool:
         See Also
         --------
         IntervalIndex : Index for Interval objects.
-        is_boolean : Check if the Index only consists of booleans.
+        is_boolean : Check if the Index only consists of booleans (deprecated).
         is_integer : Check if the Index only consists of integers (deprecated).
         is_floating : Check if the Index is a floating type (deprecated).
         is_numeric : Check if the Index only consists of numeric data.
@@ -2478,12 +2487,28 @@ def is_interval(self) -> bool:
         return self.inferred_type in ["interval"]
 
     @final
-    def holds_integer(self) -> bool:
+    def _holds_integer(self) -> bool:
         """
         Whether the type is an integer type.
         """
         return self.inferred_type in ["integer", "mixed-integer"]
 
+    @final
+    def holds_integer(self) -> bool:
+        """
+        Whether the type is an integer type.
+
+        .. deprecated:: 2.0.0
+            Use `pandas.api.types.infer_dtype` instead
+        """
+        warnings.warn(
+            f"{type(self).__name__}.holds_integer is deprecated. "
+            "Use pandas.api.types.infer_dtype instead.",
+            FutureWarning,
+            stacklevel=find_stack_level(),
+        )
+        return self._holds_integer()
+
     @cache_readonly
     def inferred_type(self) -> str_t:
         """
@@ -5528,7 +5553,7 @@ def _should_fallback_to_positional(self) -> bool:
         """
         Should an integer key be treated as positional?
         """
-        return not self.holds_integer()
+        return not self._holds_integer()
 
     _index_shared_docs[
         "get_indexer_non_unique"
@@ -5874,8 +5899,8 @@ def _should_compare(self, other: Index) -> bool:
         Check if `self == other` can ever have non-False entries.
         """
 
-        if (other.is_boolean() and self.is_numeric()) or (
-            self.is_boolean() and other.is_numeric()
+        if (is_bool_dtype(other) and self.is_numeric()) or (
+            is_bool_dtype(self) and other.is_numeric()
         ):
             # GH#16877 Treat boolean labels passed to a numeric index as not
             #  found. Without this fix False and True would be treated as 0 and 1

pandas/plotting/_core.py

@@ -940,15 +940,15 @@ def __call__(self, *args, **kwargs):
                         f"{kind} requires either y column or 'subplots=True'"
                     )
                 if y is not None:
-                    if is_integer(y) and not data.columns.holds_integer():
+                    if is_integer(y) and not data.columns._holds_integer():
                         y = data.columns[y]
                     # converted to series actually. copy to not modify
                     data = data[y].copy()
                     data.index.name = y
         elif isinstance(data, ABCDataFrame):
             data_cols = data.columns
             if x is not None:
-                if is_integer(x) and not data.columns.holds_integer():
+                if is_integer(x) and not data.columns._holds_integer():
                     x = data_cols[x]
                 elif not isinstance(data[x], ABCSeries):
                     raise ValueError("x must be a label or position")
@@ -957,7 +957,7 @@ def __call__(self, *args, **kwargs):
                 # check if we have y as int or list of ints
                 int_ylist = is_list_like(y) and all(is_integer(c) for c in y)
                 int_y_arg = is_integer(y) or int_ylist
-                if int_y_arg and not data.columns.holds_integer():
+                if int_y_arg and not data.columns._holds_integer():
                     y = data_cols[y]
 
                 label_kw = kwargs["label"] if "label" in kwargs else False

pandas/plotting/_matplotlib/core.py

@@ -1137,9 +1137,9 @@ def __init__(self, data, x, y, **kwargs) -> None:
         MPLPlot.__init__(self, data, **kwargs)
         if x is None or y is None:
             raise ValueError(self._kind + " requires an x and y column")
-        if is_integer(x) and not self.data.columns.holds_integer():
+        if is_integer(x) and not self.data.columns._holds_integer():
             x = self.data.columns[x]
-        if is_integer(y) and not self.data.columns.holds_integer():
+        if is_integer(y) and not self.data.columns._holds_integer():
             y = self.data.columns[y]
 
         # Scatter plot allows to plot objects data
@@ -1196,7 +1196,7 @@ def __init__(self, data, x, y, s=None, c=None, **kwargs) -> None:
         elif is_hashable(s) and s in data.columns:
             s = data[s]
         super().__init__(data, x, y, s=s, **kwargs)
-        if is_integer(c) and not self.data.columns.holds_integer():
+        if is_integer(c) and not self.data.columns._holds_integer():
             c = self.data.columns[c]
         self.c = c
 
@@ -1291,7 +1291,7 @@ def _kind(self) -> Literal["hexbin"]:
 
     def __init__(self, data, x, y, C=None, **kwargs) -> None:
         super().__init__(data, x, y, **kwargs)
-        if is_integer(C) and not self.data.columns.holds_integer():
+        if is_integer(C) and not self.data.columns._holds_integer():
             C = self.data.columns[C]
         self.C = C
 

pandas/tests/base/common.py

@@ -1,9 +1,10 @@
 from typing import Any
 
 from pandas import Index
+from pandas.api.types import is_bool_dtype
 
 
 def allow_na_ops(obj: Any) -> bool:
     """Whether to skip test cases including NaN"""
-    is_bool_index = isinstance(obj, Index) and obj.is_boolean()
+    is_bool_index = isinstance(obj, Index) and is_bool_dtype(obj)
     return not is_bool_index and obj._can_hold_na

pandas/tests/extension/test_arrow.py

@@ -528,6 +528,7 @@ def test_groupby_extension_transform(self, data_for_grouping, request):
     def test_groupby_extension_apply(
         self, data_for_grouping, groupby_apply_op, request
     ):
+        pa_dtype = data_for_grouping.dtype.pyarrow_dtype
         with tm.maybe_produces_warning(
             PerformanceWarning,
             pa_version_under7p0 and not pa.types.is_duration(pa_dtype),
@@ -770,6 +771,7 @@ def test_value_counts(self, all_data, dropna, request):
         super().test_value_counts(all_data, dropna)
 
     def test_value_counts_with_normalize(self, data, request):
+        pa_dtype = data.dtype.pyarrow_dtype
         with tm.maybe_produces_warning(
             PerformanceWarning,
             pa_version_under7p0 and not pa.types.is_duration(pa_dtype),
@@ -869,6 +871,7 @@ def test_sort_values_missing(
 
     @pytest.mark.parametrize("ascending", [True, False])
     def test_sort_values_frame(self, data_for_sorting, ascending, request):
+        pa_dtype = data_for_sorting.dtype.pyarrow_dtype
         with tm.maybe_produces_warning(
             PerformanceWarning,
             pa_version_under7p0 and not pa.types.is_duration(pa_dtype),

pandas/tests/indexes/common.py

@@ -797,6 +797,12 @@ def test_inv(self, simple_index):
             with pytest.raises(TypeError, match=msg):
                 ~Series(idx)
 
+    def test_is_boolean_is_deprecated(self, simple_index):
+        # GH50042
+        idx = simple_index
+        with tm.assert_produces_warning(FutureWarning):
+            idx.is_boolean()
+
     def test_is_floating_is_deprecated(self, simple_index):
         # GH50042
         idx = simple_index
@@ -809,6 +815,13 @@ def test_is_integer_is_deprecated(self, simple_index):
         with tm.assert_produces_warning(FutureWarning):
             idx.is_integer()
 
+    def test_holds_integer_deprecated(self, simple_index):
+        # GH50243
+        idx = simple_index
+        msg = f"{type(idx).__name__}.holds_integer is deprecated. "
+        with tm.assert_produces_warning(FutureWarning, match=msg):
+            idx.holds_integer()
+
 
 class NumericBase(Base):
     """

pandas/tests/indexes/test_setops.py

@@ -25,6 +25,7 @@
 )
 import pandas._testing as tm
 from pandas.api.types import (
+    is_bool_dtype,
     is_datetime64tz_dtype,
     is_signed_integer_dtype,
     pandas_dtype,
@@ -271,7 +272,7 @@ def test_union_base(self, index):
     def test_difference_base(self, sort, index):
         first = index[2:]
         second = index[:4]
-        if index.is_boolean():
+        if is_bool_dtype(index):
             # i think (TODO: be sure) there assumptions baked in about
             #  the index fixture that don't hold here?
             answer = set(first).difference(set(second))

pandas/tests/indexing/test_loc.py

@@ -37,7 +37,10 @@
     to_timedelta,
 )
 import pandas._testing as tm
-from pandas.api.types import is_scalar
+from pandas.api.types import (
+    is_bool_dtype,
+    is_scalar,
+)
 from pandas.core.api import Float64Index
 from pandas.core.indexing import _one_ellipsis_message
 from pandas.tests.indexing.common import check_indexing_smoketest_or_raises
@@ -1658,7 +1661,7 @@ def test_loc_iloc_getitem_leading_ellipses(self, series_with_simple_index, index
         obj = series_with_simple_index
         key = 0 if (indexer is tm.iloc or len(obj) == 0) else obj.index[0]
 
-        if indexer is tm.loc and obj.index.is_boolean():
+        if indexer is tm.loc and is_bool_dtype(obj.index):
             # passing [False] will get interpreted as a boolean mask
             # TODO: should it?  unambiguous when lengths dont match?
             return

pyproject.toml

@@ -356,7 +356,7 @@ disable = [
 
 [tool.pytest.ini_options]
 # sync minversion with pyproject.toml & install.rst
-minversion =  "6.0"
+minversion = "7.0"
 addopts = "--strict-data-files --strict-markers --strict-config --capture=no --durations=30 --junitxml=test-data.xml"
 empty_parameter_set_mark = "fail_at_collect"
 xfail_strict = true