Merge branch 'main' into durbonas/docstring_validation_fixes

d-urbonas · web-flow · commit 178ef9990f4b · 2024-10-05T13:49:44.000-04:00
diff --git a/ci/code_checks.sh b/ci/code_checks.sh
@@ -179,17 +179,14 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.errors.ValueLabelTypeMismatch SA01" \
         -i "pandas.infer_freq SA01" \
         -i "pandas.io.json.build_table_schema PR07,RT03,SA01" \
-        -i "pandas.io.stata.StataReader.data_label SA01" \
         -i "pandas.io.stata.StataReader.value_labels RT03,SA01" \
         -i "pandas.io.stata.StataReader.variable_labels RT03,SA01" \
         -i "pandas.io.stata.StataWriter.write_file SA01" \
         -i "pandas.json_normalize RT03,SA01" \
-        -i "pandas.period_range RT03,SA01" \
         -i "pandas.plotting.andrews_curves RT03,SA01" \
         -i "pandas.plotting.lag_plot RT03,SA01" \
         -i "pandas.plotting.scatter_matrix PR07,SA01" \
         -i "pandas.set_eng_float_format RT03,SA01" \
-        -i "pandas.testing.assert_extension_array_equal SA01" \
         -i "pandas.tseries.offsets.BDay PR02,SA01" \
         -i "pandas.tseries.offsets.BQuarterBegin.is_on_offset GL08" \
         -i "pandas.tseries.offsets.BQuarterBegin.n GL08" \
diff --git a/doc/source/whatsnew/v3.0.0.rst b/doc/source/whatsnew/v3.0.0.rst
@@ -544,7 +544,7 @@ Bug fixes
 
 Categorical
 ^^^^^^^^^^^
--
+- Bug in :func:`Series.apply` where ``nan`` was ignored for :class:`CategoricalDtype` (:issue:`59938`)
 -
 
 Datetimelike
@@ -682,6 +682,7 @@ Sparse
 ^^^^^^
 - Bug in :class:`SparseDtype` for equal comparison with na fill value. (:issue:`54770`)
 - Bug in :meth:`DataFrame.sparse.from_spmatrix` which hard coded an invalid ``fill_value`` for certain subtypes. (:issue:`59063`)
+- Bug in :meth:`DataFrame.sparse.to_dense` which ignored subclassing and always returned an instance of :class:`DataFrame` (:issue:`59913`)
 
 ExtensionArray
 ^^^^^^^^^^^^^^
@@ -700,6 +701,7 @@ Other
 - Bug in :func:`eval` on :class:`ExtensionArray` on including division ``/`` failed with a ``TypeError``. (:issue:`58748`)
 - Bug in :func:`eval` where the names of the :class:`Series` were not preserved when using ``engine="numexpr"``. (:issue:`10239`)
 - Bug in :func:`eval` with ``engine="numexpr"`` returning unexpected result for float division. (:issue:`59736`)
+- Bug in :func:`to_numeric` raising ``TypeError`` when ``arg`` is a :class:`Timedelta` or :class:`Timestamp` scalar. (:issue:`59944`)
 - Bug in :func:`unique` on :class:`Index` not always returning :class:`Index` (:issue:`57043`)
 - Bug in :meth:`DataFrame.apply` where passing ``engine="numba"`` ignored ``args`` passed to the applied function (:issue:`58712`)
 - Bug in :meth:`DataFrame.eval` and :meth:`DataFrame.query` which caused an exception when using NumPy attributes via ``@`` notation, e.g., ``df.eval("@np.floor(a)")``. (:issue:`58041`)
diff --git a/pandas/_testing/asserters.py b/pandas/_testing/asserters.py
@@ -701,6 +701,10 @@ def assert_extension_array_equal(
     """
     Check that left and right ExtensionArrays are equal.
 
+    This method compares two ``ExtensionArray`` instances for equality,
+    including checks for missing values, the dtype of the arrays, and
+    the exactness of the comparison (or tolerance when comparing floats).
+
     Parameters
     ----------
     left, right : ExtensionArray
@@ -726,6 +730,12 @@ def assert_extension_array_equal(
 
         .. versionadded:: 2.0.0
 
+    See Also
+    --------
+    testing.assert_series_equal : Check that left and right ``Series`` are equal.
+    testing.assert_frame_equal : Check that left and right ``DataFrame`` are equal.
+    testing.assert_index_equal : Check that left and right ``Index`` are equal.
+
     Notes
     -----
     Missing values are checked separately from valid values.
diff --git a/pandas/core/apply.py b/pandas/core/apply.py
@@ -38,10 +38,7 @@
     is_numeric_dtype,
     is_sequence,
 )
-from pandas.core.dtypes.dtypes import (
-    CategoricalDtype,
-    ExtensionDtype,
-)
+from pandas.core.dtypes.dtypes import ExtensionDtype
 from pandas.core.dtypes.generic import (
     ABCDataFrame,
     ABCNDFrame,
@@ -1465,14 +1462,7 @@ def curried(x):
 
         else:
             curried = func
-
-        # row-wise access
-        # apply doesn't have a `na_action` keyword and for backward compat reasons
-        # we need to give `na_action="ignore"` for categorical data.
-        # TODO: remove the `na_action="ignore"` when that default has been changed in
-        #  Categorical (GH51645).
-        action = "ignore" if isinstance(obj.dtype, CategoricalDtype) else None
-        mapped = obj._map_values(mapper=curried, na_action=action)
+        mapped = obj._map_values(mapper=curried)
 
         if len(mapped) and isinstance(mapped[0], ABCSeries):
             # GH#43986 Need to do list(mapped) in order to get treated as nested
diff --git a/pandas/core/arrays/sparse/accessor.py b/pandas/core/arrays/sparse/accessor.py
@@ -369,10 +369,10 @@ def to_dense(self) -> DataFrame:
         1  1
         2  0
         """
-        from pandas import DataFrame
-
         data = {k: v.array.to_dense() for k, v in self._parent.items()}
-        return DataFrame(data, index=self._parent.index, columns=self._parent.columns)
+        return self._parent._constructor(
+            data, index=self._parent.index, columns=self._parent.columns
+        )
 
     def to_coo(self) -> spmatrix:
         """
diff --git a/pandas/core/indexes/period.py b/pandas/core/indexes/period.py
@@ -563,6 +563,14 @@ def period_range(
     Returns
     -------
     PeriodIndex
+        A PeriodIndex of fixed frequency periods.
+
+    See Also
+    --------
+    date_range : Returns a fixed frequency DatetimeIndex.
+    Period : Represents a period of time.
+    PeriodIndex : Immutable ndarray holding ordinal values indicating regular periods
+        in time.
 
     Notes
     -----
diff --git a/pandas/core/tools/numeric.py b/pandas/core/tools/numeric.py
@@ -11,6 +11,10 @@
     lib,
     missing as libmissing,
 )
+from pandas._libs.tslibs import (
+    Timedelta,
+    Timestamp,
+)
 from pandas.util._validators import check_dtype_backend
 
 from pandas.core.dtypes.cast import maybe_downcast_numeric
@@ -189,6 +193,8 @@ def to_numeric(
             return float(arg)
         if is_number(arg):
             return arg
+        if isinstance(arg, (Timedelta, Timestamp)):
+            return arg._value
         is_scalars = True
         values = np.array([arg], dtype="O")
     elif getattr(arg, "ndim", 1) > 1:
diff --git a/pandas/io/formats/html.py b/pandas/io/formats/html.py
@@ -195,6 +195,8 @@ def _write_cell(
             esc = {}
 
         rs = pprint_thing(s, escape_chars=esc).strip()
+        # replace spaces betweens strings with non-breaking spaces
+        rs = rs.replace("  ", "&nbsp;&nbsp;")
 
         if self.render_links and is_url(rs):
             rs_unescaped = pprint_thing(s, escape_chars={}).strip()
diff --git a/pandas/io/formats/style_render.py b/pandas/io/formats/style_render.py
@@ -906,9 +906,9 @@ def concatenated_visible_rows(obj):
                 row_body_headers = [
                     {
                         **col,
-                        "display_value": col["display_value"]
-                        if col["is_visible"]
-                        else "",
+                        "display_value": (
+                            col["display_value"] if col["is_visible"] else ""
+                        ),
                         "cellstyle": self.ctx_index[r, c],
                     }
                     for c, col in enumerate(row[:index_levels])
@@ -2069,18 +2069,18 @@ def maybe_convert_css_to_tuples(style: CSSProperties) -> CSSList:
                                              ('border','1px solid red')]
     """
     if isinstance(style, str):
-        s = style.split(";")
-        try:
-            return [
-                (x.split(":")[0].strip(), x.split(":")[1].strip())
-                for x in s
-                if x.strip() != ""
-            ]
-        except IndexError as err:
+        if style and ":" not in style:
             raise ValueError(
                 "Styles supplied as string must follow CSS rule formats, "
                 f"for example 'attr: val;'. '{style}' was given."
-            ) from err
+            )
+        s = style.split(";")
+        return [
+            (x.split(":")[0].strip(), ":".join(x.split(":")[1:]).strip())
+            for x in s
+            if x.strip() != ""
+        ]
+
     return style
 
 
diff --git a/pandas/io/stata.py b/pandas/io/stata.py
@@ -2004,6 +2004,16 @@ def data_label(self) -> str:
         """
         Return data label of Stata file.
 
+        The data label is a descriptive string associated with the dataset
+        stored in the Stata file. This property provides access to that
+        label, if one is present.
+
+        See Also
+        --------
+        io.stata.StataReader.variable_labels : Return a dict associating each variable
+            name with corresponding label.
+        DataFrame.to_stata : Export DataFrame object to Stata dta format.
+
         Examples
         --------
         >>> df = pd.DataFrame([(1,)], columns=["variable"])
diff --git a/pandas/tests/apply/test_frame_apply.py b/pandas/tests/apply/test_frame_apply.py
@@ -741,8 +741,9 @@ def test_apply_category_equalness(val):
 
     result = df.a.apply(lambda x: x == val)
     expected = Series(
-        [np.nan if pd.isnull(x) else x == val for x in df_values], name="a"
+        [False if pd.isnull(x) else x == val for x in df_values], name="a"
     )
+    # False since behavior of NaN for categorical dtype has been changed (GH 59966)
     tm.assert_series_equal(result, expected)
 
 
diff --git a/pandas/tests/apply/test_series_apply.py b/pandas/tests/apply/test_series_apply.py
@@ -236,10 +236,10 @@ def test_apply_categorical_with_nan_values(series, by_row):
         with pytest.raises(AttributeError, match=msg):
             s.apply(lambda x: x.split("-")[0], by_row=by_row)
         return
-
-    result = s.apply(lambda x: x.split("-")[0], by_row=by_row)
+    # NaN for cat dtype fixed in (GH 59966)
+    result = s.apply(lambda x: x.split("-")[0] if pd.notna(x) else False, by_row=by_row)
     result = result.astype(object)
-    expected = Series(["1", "1", np.nan], dtype="category")
+    expected = Series(["1", "1", False], dtype="category")
     expected = expected.astype(object)
     tm.assert_series_equal(result, expected)
 
diff --git a/pandas/tests/arrays/sparse/test_accessor.py b/pandas/tests/arrays/sparse/test_accessor.py
@@ -252,3 +252,7 @@ def test_with_column_named_sparse(self):
         # https://github.com/pandas-dev/pandas/issues/30758
         df = pd.DataFrame({"sparse": pd.arrays.SparseArray([1, 2])})
         assert isinstance(df.sparse, pd.core.arrays.sparse.accessor.SparseFrameAccessor)
+
+    def test_subclassing(self):
+        df = tm.SubclassedDataFrame({"sparse": pd.arrays.SparseArray([1, 2])})
+        assert isinstance(df.sparse.to_dense(), tm.SubclassedDataFrame)
diff --git a/pandas/tests/io/formats/style/test_style.py b/pandas/tests/io/formats/style/test_style.py
@@ -886,8 +886,19 @@ def test_maybe_convert_css_to_tuples(self):
         expected = []
         assert maybe_convert_css_to_tuples("") == expected
 
+        # issue #59623
+        expected = [("a", "b"), ("c", "url('data:123')")]
+        assert maybe_convert_css_to_tuples("a:b;c: url('data:123');") == expected
+
+        # if no value, return attr and empty string
+        expected = [("a", ""), ("c", "")]
+        assert maybe_convert_css_to_tuples("a:;c: ") == expected
+
     def test_maybe_convert_css_to_tuples_err(self):
-        msg = "Styles supplied as string must follow CSS rule formats"
+        msg = (
+            "Styles supplied as string must follow CSS rule formats, "
+            "for example 'attr: val;'. 'err' was given."
+        )
         with pytest.raises(ValueError, match=msg):
             maybe_convert_css_to_tuples("err")
 
diff --git a/pandas/tests/io/formats/test_format.py b/pandas/tests/io/formats/test_format.py
@@ -375,12 +375,29 @@ def test_repr_min_rows(self):
             (None, "{:.3f}", "None"),
             ("", "{:.2f}", ""),
             (112345.6789, "{:6.3f}", "112345.679"),
+            ("foo      foo", None, "foo&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;foo"),
+            (" foo", None, "foo"),
+            (
+                "foo foo       foo",
+                None,
+                "foo foo&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; foo",
+            ),  # odd no.of spaces
+            (
+                "foo foo    foo",
+                None,
+                "foo foo&nbsp;&nbsp;&nbsp;&nbsp;foo",
+            ),  # even no.of spaces
         ],
     )
     def test_repr_float_formatting_html_output(
         self, data, format_option, expected_values
     ):
-        with option_context("display.float_format", format_option.format):
+        if format_option is not None:
+            with option_context("display.float_format", format_option.format):
+                df = DataFrame({"A": [data]})
+                html_output = df._repr_html_()
+                assert expected_values in html_output
+        else:
             df = DataFrame({"A": [data]})
             html_output = df._repr_html_()
             assert expected_values in html_output
diff --git a/pandas/tests/tools/test_to_numeric.py b/pandas/tests/tools/test_to_numeric.py
@@ -384,6 +384,21 @@ def test_timedelta(transform_assert_equal):
     assert_equal(result, expected)
 
 
+@pytest.mark.parametrize(
+    "scalar",
+    [
+        pd.Timedelta(1, "D"),
+        pd.Timestamp("2017-01-01T12"),
+        pd.Timestamp("2017-01-01T12", tz="US/Pacific"),
+    ],
+)
+def test_timedelta_timestamp_scalar(scalar):
+    # GH#59944
+    result = to_numeric(scalar)
+    expected = to_numeric(Series(scalar))[0]
+    assert result == expected
+
+
 def test_period(request, transform_assert_equal):
     transform, assert_equal = transform_assert_equal
 
