DEPR: remove get_values, SparseArray.values (#29989)

Author: jbrockmendel

doc/redirects.csv

@@ -360,7 +360,6 @@ generated/pandas.DataFrame.from_records,../reference/api/pandas.DataFrame.from_r
 generated/pandas.DataFrame.ge,../reference/api/pandas.DataFrame.ge
 generated/pandas.DataFrame.get,../reference/api/pandas.DataFrame.get
 generated/pandas.DataFrame.get_value,../reference/api/pandas.DataFrame.get_value
-generated/pandas.DataFrame.get_values,../reference/api/pandas.DataFrame.get_values
 generated/pandas.DataFrame.groupby,../reference/api/pandas.DataFrame.groupby
 generated/pandas.DataFrame.gt,../reference/api/pandas.DataFrame.gt
 generated/pandas.DataFrame.head,../reference/api/pandas.DataFrame.head
@@ -643,7 +642,6 @@ generated/pandas.Index.get_level_values,../reference/api/pandas.Index.get_level_
 generated/pandas.Index.get_loc,../reference/api/pandas.Index.get_loc
 generated/pandas.Index.get_slice_bound,../reference/api/pandas.Index.get_slice_bound
 generated/pandas.Index.get_value,../reference/api/pandas.Index.get_value
-generated/pandas.Index.get_values,../reference/api/pandas.Index.get_values
 generated/pandas.Index.groupby,../reference/api/pandas.Index.groupby
 generated/pandas.Index.has_duplicates,../reference/api/pandas.Index.has_duplicates
 generated/pandas.Index.hasnans,../reference/api/pandas.Index.hasnans
@@ -1044,7 +1042,6 @@ generated/pandas.Series.from_csv,../reference/api/pandas.Series.from_csv
 generated/pandas.Series.ge,../reference/api/pandas.Series.ge
 generated/pandas.Series.get,../reference/api/pandas.Series.get
 generated/pandas.Series.get_value,../reference/api/pandas.Series.get_value
-generated/pandas.Series.get_values,../reference/api/pandas.Series.get_values
 generated/pandas.Series.groupby,../reference/api/pandas.Series.groupby
 generated/pandas.Series.gt,../reference/api/pandas.Series.gt
 generated/pandas.Series.hasnans,../reference/api/pandas.Series.hasnans

doc/source/reference/frame.rst

@@ -30,7 +30,6 @@ Attributes and underlying data
    DataFrame.dtypes
    DataFrame.select_dtypes
    DataFrame.values
-   DataFrame.get_values
    DataFrame.axes
    DataFrame.ndim
    DataFrame.size

doc/source/reference/indexing.rst

@@ -159,7 +159,6 @@ Selecting
    Index.get_loc
    Index.get_slice_bound
    Index.get_value
-   Index.get_values
    Index.isin
    Index.slice_indexer
    Index.slice_locs

doc/source/reference/series.rst

@@ -53,7 +53,6 @@ Conversion
    Series.to_period
    Series.to_timestamp
    Series.to_list
-   Series.get_values
    Series.__array__
 
 Indexing, iteration

pandas/_libs/reduction.pyx

@@ -26,14 +26,6 @@ cdef _check_result_array(object obj, Py_ssize_t cnt):
         raise ValueError('Function does not reduce')
 
 
-cdef bint _is_sparse_array(object obj):
-    # TODO can be removed one SparseArray.values is removed (GH26421)
-    if hasattr(obj, '_subtyp'):
-        if obj._subtyp == 'sparse_array':
-            return True
-    return False
-
-
 cdef class Reducer:
     """
     Performs generic reduction operation on a C or Fortran-contiguous ndarray
@@ -404,8 +396,7 @@ cdef class SeriesGrouper(_BaseGrouper):
 cdef inline _extract_result(object res, bint squeeze=True):
     """ extract the result object, it might be a 0-dim ndarray
         or a len-1 0-dim, or a scalar """
-    if (not _is_sparse_array(res) and hasattr(res, 'values')
-            and util.is_array(res.values)):
+    if hasattr(res, 'values') and util.is_array(res.values):
         res = res.values
     if util.is_array(res):
         if res.ndim == 0:

pandas/core/arrays/categorical.py

@@ -302,9 +302,7 @@ class Categorical(ExtensionArray, PandasObject):
     __array_priority__ = 1000
     _dtype = CategoricalDtype(ordered=False)
     # tolist is not actually deprecated, just suppressed in the __dir__
-    _deprecations = PandasObject._deprecations | frozenset(
-        ["tolist", "itemsize", "get_values"]
-    )
+    _deprecations = PandasObject._deprecations | frozenset(["tolist", "itemsize"])
     _typ = "categorical"
 
     def __init__(
@@ -1461,29 +1459,18 @@ def value_counts(self, dropna=True):
 
         return Series(count, index=CategoricalIndex(ix), dtype="int64")
 
-    def get_values(self):
+    def _internal_get_values(self):
         """
         Return the values.
 
-        .. deprecated:: 0.25.0
-
         For internal compatibility with pandas formatting.
 
         Returns
         -------
-        numpy.array
+        np.ndarray or Index
             A numpy array of the same dtype as categorical.categories.dtype or
             Index if datetime / periods.
         """
-        warn(
-            "The 'get_values' method is deprecated and will be removed in a "
-            "future version",
-            FutureWarning,
-            stacklevel=2,
-        )
-        return self._internal_get_values()
-
-    def _internal_get_values(self):
         # if we are a datetime and period index, return Index to keep metadata
         if needs_i8_conversion(self.categories):
             return self.categories.take(self._codes, fill_value=np.nan)

pandas/core/arrays/sparse/array.py

@@ -568,23 +568,6 @@ def npoints(self) -> int:
         """
         return self.sp_index.npoints
 
-    @property
-    def values(self):
-        """
-        Dense values
-
-        .. deprecated:: 0.25.0
-
-            Use ``np.asarray(...)`` or the ``.to_dense()`` method instead.
-        """
-        msg = (
-            "The SparseArray.values attribute is deprecated and will be "
-            "removed in a future version. You can use `np.asarray(...)` or "
-            "the `.to_dense()` method instead."
-        )
-        warnings.warn(msg, FutureWarning, stacklevel=2)
-        return self.to_dense()
-
     def isna(self):
         # If null fill value, we want SparseDtype[bool, true]
         # to preserve the same memory usage.
@@ -1137,22 +1120,6 @@ def to_dense(self):
         """
         return np.asarray(self, dtype=self.sp_values.dtype)
 
-    def get_values(self):
-        """
-        Convert SparseArray to a NumPy array.
-
-        .. deprecated:: 0.25.0
-            Use `to_dense` instead.
-
-        """
-        warnings.warn(
-            "The 'get_values' method is deprecated and will be removed in a "
-            "future version. Use the 'to_dense' method instead.",
-            FutureWarning,
-            stacklevel=2,
-        )
-        return self._internal_get_values()
-
     _internal_get_values = to_dense
 
     # ------------------------------------------------------------------------

pandas/core/generic.py

@@ -5506,13 +5506,10 @@ def _get_values(self):
         # compat
         return self.values
 
-    def get_values(self):
+    def _internal_get_values(self):
         """
         Return an ndarray after converting sparse values to dense.
 
-        .. deprecated:: 0.25.0
-            Use ``np.asarray(..)`` or :meth:`DataFrame.values` instead.
-
         This is the same as ``.values`` for non-sparse data. For sparse
         data contained in a `SparseArray`, the data are first
         converted to a dense representation.
@@ -5526,41 +5523,7 @@ def get_values(self):
         --------
         values : Numpy representation of DataFrame.
         SparseArray : Container for sparse data.
-
-        Examples
-        --------
-        >>> df = pd.DataFrame({'a': [1, 2], 'b': [True, False],
-        ...                    'c': [1.0, 2.0]})
-        >>> df
-           a      b    c
-        0  1   True  1.0
-        1  2  False  2.0
-
-        >>> df.get_values()
-        array([[1, True, 1.0], [2, False, 2.0]], dtype=object)
-
-        >>> df = pd.DataFrame({"a": pd.SparseArray([1, None, None]),
-        ...                    "c": [1.0, 2.0, 3.0]})
-        >>> df
-             a    c
-        0  1.0  1.0
-        1  NaN  2.0
-        2  NaN  3.0
-
-        >>> df.get_values()
-        array([[ 1.,  1.],
-               [nan,  2.],
-               [nan,  3.]])
-        """
-        warnings.warn(
-            "The 'get_values' method is deprecated and will be removed in a "
-            "future version. Use '.values' or 'np.asarray(..)' instead.",
-            FutureWarning,
-            stacklevel=2,
-        )
-        return self._internal_get_values()
-
-    def _internal_get_values(self):
+        """
         return self.values
 
     @property

pandas/core/indexes/base.py

@@ -215,7 +215,7 @@ class Index(IndexOpsMixin, PandasObject):
     _deprecations: FrozenSet[str] = (
         PandasObject._deprecations
         | IndexOpsMixin._deprecations
-        | frozenset(["contains", "get_values", "set_value"])
+        | frozenset(["contains", "set_value"])
     )
 
     # To hand over control to subclasses
@@ -3753,21 +3753,18 @@ def _values(self) -> Union[ExtensionArray, ABCIndexClass, np.ndarray]:
         """
         return self._data
 
-    def get_values(self):
+    def _internal_get_values(self):
         """
         Return `Index` data as an `numpy.ndarray`.
 
-        .. deprecated:: 0.25.0
-            Use :meth:`Index.to_numpy` or :attr:`Index.array` instead.
-
         Returns
         -------
         numpy.ndarray
             A one-dimensional numpy array of the `Index` values.
 
         See Also
         --------
-        Index.values : The attribute that get_values wraps.
+        Index.values : The attribute that _internal_get_values wraps.
 
         Examples
         --------
@@ -3780,33 +3777,24 @@ def get_values(self):
         a  1  2  3
         b  4  5  6
         c  7  8  9
-        >>> df.index.get_values()
+        >>> df.index._internal_get_values()
         array(['a', 'b', 'c'], dtype=object)
 
         Standalone `Index` values:
 
         >>> idx = pd.Index(['1', '2', '3'])
-        >>> idx.get_values()
+        >>> idx._internal_get_values()
         array(['1', '2', '3'], dtype=object)
 
         `MultiIndex` arrays also have only one dimension:
 
         >>> midx = pd.MultiIndex.from_arrays([[1, 2, 3], ['a', 'b', 'c']],
         ...                                  names=('number', 'letter'))
-        >>> midx.get_values()
+        >>> midx._internal_get_values()
         array([(1, 'a'), (2, 'b'), (3, 'c')], dtype=object)
-        >>> midx.get_values().ndim
+        >>> midx._internal_get_values().ndim
         1
         """
-        warnings.warn(
-            "The 'get_values' method is deprecated and will be removed in a "
-            "future version. Use '.to_numpy()' or '.array' instead.",
-            FutureWarning,
-            stacklevel=2,
-        )
-        return self._internal_get_values()
-
-    def _internal_get_values(self):
         return self.values
 
     @Appender(IndexOpsMixin.memory_usage.__doc__)

pandas/core/series.py

@@ -465,27 +465,16 @@ def _values(self):
         """
         return self._data.internal_values()
 
-    def get_values(self):
+    def _internal_get_values(self):
         """
         Same as values (but handles sparseness conversions); is a view.
 
-        .. deprecated:: 0.25.0
-            Use :meth:`Series.to_numpy` or :attr:`Series.array` instead.
-
         Returns
         -------
         numpy.ndarray
             Data of the Series.
         """
-        warnings.warn(
-            "The 'get_values' method is deprecated and will be removed in a "
-            "future version. Use '.to_numpy()' or '.array' instead.",
-            FutureWarning,
-            stacklevel=2,
-        )
-        return self._internal_get_values()
 
-    def _internal_get_values(self):
         return self._data.get_values()
 
     # ops

pandas/tests/arrays/categorical/test_api.py

@@ -504,9 +504,3 @@ def test_recode_to_categories_large(self):
         new = Index(expected)
         result = _recode_for_categories(codes, old, new)
         tm.assert_numpy_array_equal(result, expected)
-
-    def test_deprecated_get_values(self):
-        cat = Categorical(["a", "b", "c", "a"])
-        with tm.assert_produces_warning(FutureWarning):
-            res = cat.get_values()
-        tm.assert_numpy_array_equal(res, np.array(cat))

pandas/tests/arrays/sparse/test_array.py

@@ -617,8 +617,7 @@ def test_dense_repr(self, vals, fill_value):
         res = arr.to_dense()
         tm.assert_numpy_array_equal(res, vals)
 
-        with tm.assert_produces_warning(FutureWarning):
-            res2 = arr.get_values()
+        res2 = arr._internal_get_values()
 
         tm.assert_numpy_array_equal(res2, vals)
 
@@ -1244,12 +1243,3 @@ def test_map_missing():
 
     result = arr.map({0: 10, 1: 11})
     tm.assert_sp_array_equal(result, expected)
-
-
-def test_deprecated_values():
-    arr = SparseArray([0, 1, 2])
-
-    with tm.assert_produces_warning(FutureWarning):
-        result = arr.values
-
-    tm.assert_numpy_array_equal(result, arr.to_dense())

pandas/tests/frame/test_api.py

@@ -528,9 +528,3 @@ def test_tab_complete_warning(self, ip):
         with tm.assert_produces_warning(None):
             with provisionalcompleter("ignore"):
                 list(ip.Completer.completions("df.", 1))
-
-    def test_get_values_deprecated(self):
-        df = DataFrame({"a": [1, 2], "b": [0.1, 0.2]})
-        with tm.assert_produces_warning(FutureWarning):
-            res = df.get_values()
-        tm.assert_numpy_array_equal(res, df.values)

pandas/tests/indexes/period/test_period.py

@@ -180,8 +180,7 @@ def test_values(self):
         exp = np.array([], dtype=np.object)
         tm.assert_numpy_array_equal(idx.values, exp)
         tm.assert_numpy_array_equal(idx.to_numpy(), exp)
-        with tm.assert_produces_warning(FutureWarning):
-            tm.assert_numpy_array_equal(idx.get_values(), exp)
+
         exp = np.array([], dtype=np.int64)
         tm.assert_numpy_array_equal(idx._ndarray_values, exp)
 

pandas/tests/series/test_api.py

@@ -498,12 +498,6 @@ def test_integer_series_size(self):
         s = Series(range(9), dtype="Int64")
         assert s.size == 9
 
-    def test_get_values_deprecation(self):
-        s = Series(range(9))
-        with tm.assert_produces_warning(FutureWarning):
-            res = s.get_values()
-        tm.assert_numpy_array_equal(res, s.values)
-
 
 class TestCategoricalSeries:
     @pytest.mark.parametrize(