DEPR: deprecate get_values

pandas/_libs/lib.pyx

@@ -76,7 +76,10 @@ def values_from_object(obj: object):
     """ return my values or the object if we are say an ndarray """
     func: object
 
-    func = getattr(obj, 'get_values', None)
+    if getattr(obj, '_typ', '') == 'dataframe':
+        return obj.values
+
+    func = getattr(obj, '_internal_get_values', None)
     if func is not None:
         obj = func()
 

pandas/_libs/src/ujson/python/objToJSON.c

@@ -269,9 +269,19 @@ static PyObject *get_values(PyObject *obj) {
         }
     }
 
-    if (!values && PyObject_HasAttrString(obj, "get_values")) {
+    if (!values && PyObject_HasAttrString(obj, "_internal_get_values")) {
         PRINTMARK();
-        values = PyObject_CallMethod(obj, "get_values", NULL);
+        values = PyObject_CallMethod(obj, "_internal_get_values", NULL);
+        if (values && !PyArray_CheckExact(values)) {
+            PRINTMARK();
+            Py_DECREF(values);
+            values = NULL;
+        }
+    }
+
+    if (!values && PyObject_HasAttrString(obj, "get_block_values")) {
+        PRINTMARK();
+        values = PyObject_CallMethod(obj, "get_block_values", NULL);
         if (values && !PyArray_CheckExact(values)) {
             PRINTMARK();
             Py_DECREF(values);

pandas/core/algorithms.py

@@ -1582,7 +1582,7 @@ def take_nd(arr, indexer, axis=0, out=None, fill_value=np.nan, mask_info=None,
         return arr.take(indexer, fill_value=fill_value, allow_fill=allow_fill)
 
     if is_sparse(arr):
-        arr = arr.get_values()
+        arr = arr.to_dense()
     elif isinstance(arr, (ABCIndexClass, ABCSeries)):
         arr = arr.values
 

pandas/core/arrays/categorical.py

@@ -1505,6 +1505,9 @@ def get_values(self):
             A numpy array of the same dtype as categorical.categories.dtype or
             Index if datetime / periods.
         """
+        raise Exception("USING GET_VALUES")
+
+    def _internal_get_values(self):
         # if we are a datetime and period index, return Index to keep metadata
         if is_datetimelike(self.categories):
             return self.categories.take(self._codes, fill_value=np.nan)
@@ -1937,7 +1940,7 @@ def __iter__(self):
         """
         Returns an Iterator over the values of this Categorical.
         """
-        return iter(self.get_values().tolist())
+        return iter(self._internal_get_values().tolist())
 
     def __contains__(self, key):
         """

pandas/core/arrays/sparse.py

@@ -454,7 +454,7 @@ def _sparse_array_op(
 
     if left.sp_index.ngaps == 0 or right.sp_index.ngaps == 0:
         with np.errstate(all='ignore'):
-            result = op(left.get_values(), right.get_values())
+            result = op(left.to_dense(), right.to_dense())
             fill = op(_get_fill(left), _get_fill(right))
 
         if left.sp_index.ngaps == 0:
@@ -1473,7 +1473,12 @@ def to_dense(self):
         return np.asarray(self, dtype=self.sp_values.dtype)
 
     # TODO: Look into deprecating this in favor of `to_dense`.
-    get_values = to_dense
+    # get_values = to_dense
+
+    def get_values(self):
+        raise Exception("USING GET_VALUES")
+
+    _internal_get_values = to_dense
 
     # ------------------------------------------------------------------------
     # IO

pandas/core/dtypes/concat.py

@@ -197,7 +197,7 @@ def _concat_categorical(to_concat, axis=0):
             return union_categoricals(categoricals)
 
     # extract the categoricals & coerce to object if needed
-    to_concat = [x.get_values() if is_categorical_dtype(x.dtype)
+    to_concat = [x._internal_get_values() if is_categorical_dtype(x.dtype)
                  else np.asarray(x).ravel() if not is_datetime64tz_dtype(x)
                  else np.asarray(x.astype(object)) for x in to_concat]
     result = _concat_compat(to_concat)

pandas/core/frame.py

@@ -1648,7 +1648,7 @@ def to_records(self, index=True, convert_datetime64=None,
                 else:
                     ix_vals = [self.index.values]
 
-            arrays = ix_vals + [self[c].get_values() for c in self.columns]
+            arrays = ix_vals + [self[c]._internal_get_values() for c in self.columns]
 
             count = 0
             index_names = list(self.index.names)
@@ -1664,7 +1664,7 @@ def to_records(self, index=True, convert_datetime64=None,
             names = [str(name) for name in itertools.chain(index_names,
                                                            self.columns)]
         else:
-            arrays = [self[c].get_values() for c in self.columns]
+            arrays = [self[c]._internal_get_values() for c in self.columns]
             names = [str(c) for c in self.columns]
             index_names = []
 

pandas/core/generic.py

@@ -5368,6 +5368,9 @@ def get_values(self):
                [nan,  2.],
                [nan,  3.]])
         """
+        raise Exception("USING GET_VALUES")
+
+    def _internal_get_values(self):
         return self.values
 
     def get_dtype_counts(self):

pandas/core/groupby/generic.py

@@ -1111,7 +1111,7 @@ def nunique(self, dropna=True):
         """
         ids, _, _ = self.grouper.group_info
 
-        val = self.obj.get_values()
+        val = self.obj._internal_get_values()
 
         try:
             sorter = np.lexsort((val, ids))
@@ -1185,7 +1185,7 @@ def value_counts(self, normalize=False, sort=True, ascending=False,
                               bins=bins)
 
         ids, _, _ = self.grouper.group_info
-        val = self.obj.get_values()
+        val = self.obj._internal_get_values()
 
         # groupby removes null keys from groupings
         mask = ids != -1
@@ -1299,7 +1299,7 @@ def count(self):
             Count of values within each group.
         """
         ids, _, ngroups = self.grouper.group_info
-        val = self.obj.get_values()
+        val = self.obj._internal_get_values()
 
         mask = (ids != -1) & ~isna(val)
         ids = ensure_platform_int(ids)

pandas/core/indexes/base.py

@@ -3804,6 +3804,9 @@ def get_values(self):
         >>> midx.get_values().ndim
         1
         """
+        raise Exception("USING GET_VALUES")
+
+    def _internal_get_values(self):
         return self.values
 
     @Appender(IndexOpsMixin.memory_usage.__doc__)

pandas/core/indexes/category.py

@@ -357,8 +357,12 @@ def _wrap_setop_result(self, other, result):
 
     def get_values(self):
         """ return the underlying data as an ndarray """
+        raise Exception("USING GET_VALUES")
         return self._data.get_values()
 
+    def _internal_get_values(self):
+        return self._data._internal_get_values()
+
     def tolist(self):
         return self._data.tolist()
 

pandas/core/indexes/multi.py

@@ -1216,7 +1216,7 @@ def values(self):
         for i in range(self.nlevels):
             vals = self._get_level_values(i)
             if is_categorical_dtype(vals):
-                vals = vals.get_values()
+                vals = vals._internal_get_values()
             if (isinstance(vals.dtype, ExtensionDtype)
                     or hasattr(vals, '_box_values')):
                 vals = vals.astype(object)

pandas/core/internals/blocks.py

@@ -179,6 +179,9 @@ def get_values(self, dtype=None):
             return self.values.astype(object)
         return self.values
 
+    def get_block_values(self, dtype=None):
+        return self.get_values(dtype=dtype)
+
     def to_dense(self):
         return self.values.view()
 
@@ -2915,7 +2918,7 @@ def to_dense(self):
         # Categorical.get_values returns a DatetimeIndex for datetime
         # categories, so we can't simply use `np.asarray(self.values)` like
         # other types.
-        return self.values.get_values()
+        return self.values._internal_get_values()
 
     def to_native_types(self, slicer=None, na_rep='', quoting=None, **kwargs):
         """ convert to our native types format, slicing if desired """
@@ -3216,6 +3219,7 @@ def _putmask_preserve(nv, n):
     dtype, _ = maybe_promote(n.dtype)
 
     if is_extension_type(v.dtype) and is_object_dtype(dtype):
+        # ?
         v = v.get_values(dtype)
     else:
         v = v.astype(dtype)

pandas/core/ops.py

@@ -1893,7 +1893,7 @@ def wrapper(self, other, axis=None):
                                      name=res_name, dtype='bool')
 
         else:
-            values = self.get_values()
+            values = self.to_numpy()
 
             with np.errstate(all='ignore'):
                 res = na_op(values, other)

pandas/core/series.py

@@ -506,11 +506,17 @@ def get_values(self):
         """
         Same as values (but handles sparseness conversions); is a view.
 
+        .. deprecated:: 0.25.0
+
         Returns
         -------
         numpy.ndarray
             Data of the Series.
         """
+        raise Exception("USING GET_VALUES")
+        #warnings.warn("deprecated", FutureWarning, stacklevel=2)
+
+    def _internal_get_values(self):
         return self._data.get_values()
 
     @property

pandas/core/sparse/frame.py

@@ -493,7 +493,7 @@ def xs(self, key, axis=0, copy=False):
             return data
 
         i = self.index.get_loc(key)
-        data = self.take([i]).get_values()[0]
+        data = self.take([i])._internal_get_values()[0]
         return Series(data, index=self.columns)
 
     # ----------------------------------------------------------------------
@@ -694,7 +694,7 @@ def _reindex_with_indexers(self, reindexers, method=None, fill_value=None,
             if col not in self:
                 continue
             if row_indexer is not None:
-                new_arrays[col] = algos.take_1d(self[col].get_values(),
+                new_arrays[col] = algos.take_1d(self[col]._internal_get_values(),
                                                 row_indexer,
                                                 fill_value=fill_value)
             else:

pandas/core/sparse/series.py

@@ -224,7 +224,7 @@ def __repr__(self):
     def _reduce(self, op, name, axis=0, skipna=True, numeric_only=None,
                 filter_type=None, **kwds):
         """ perform a reduction operation """
-        return op(self.get_values(), skipna=skipna, **kwds)
+        return op(self.array.to_dense(), skipna=skipna, **kwds)
 
     def __getstate__(self):
         # pickling

pandas/io/formats/format.py

@@ -129,7 +129,7 @@ def _get_footer(self):
         return str(footer)
 
     def _get_formatted_values(self):
-        return format_array(self.categorical.get_values(), None,
+        return format_array(self.categorical._internal_get_values(), None,
                             float_format=None, na_rep=self.na_rep)
 
     def to_string(self):
@@ -1195,7 +1195,7 @@ def _format_strings(self):
 
         if is_categorical_dtype(values.dtype):
             # Categorical is special for now, so that we can preserve tzinfo
-            array = values.get_values()
+            array = values._internal_get_values()
         else:
             array = np.asarray(values)
 

pandas/tests/arrays/categorical/test_api.py

@@ -248,7 +248,7 @@ def test_set_categories(self):
         tm.assert_index_equal(c.categories, Index([1, 2, 3, 4]))
 
         exp = np.array([1, 2, 3, 4, 1], dtype=np.int64)
-        tm.assert_numpy_array_equal(c.get_values(), exp)
+        tm.assert_numpy_array_equal(c.to_dense(), exp)
 
         # all "pointers" to '4' must be changed from 3 to 0,...
         c = c.set_categories([4, 3, 2, 1])
@@ -262,21 +262,21 @@ def test_set_categories(self):
 
         # output is the same
         exp = np.array([1, 2, 3, 4, 1], dtype=np.int64)
-        tm.assert_numpy_array_equal(c.get_values(), exp)
+        tm.assert_numpy_array_equal(c.to_dense(), exp)
         assert c.min() == 4
         assert c.max() == 1
 
         # set_categories should set the ordering if specified
         c2 = c.set_categories([4, 3, 2, 1], ordered=False)
         assert not c2.ordered
 
-        tm.assert_numpy_array_equal(c.get_values(), c2.get_values())
+        tm.assert_numpy_array_equal(c.to_dense(), c2.to_dense())
 
         # set_categories should pass thru the ordering
         c2 = c.set_ordered(False).set_categories([4, 3, 2, 1])
         assert not c2.ordered
 
-        tm.assert_numpy_array_equal(c.get_values(), c2.get_values())
+        tm.assert_numpy_array_equal(c.to_dense(), c2.to_dense())
 
     @pytest.mark.parametrize('values, categories, new_categories', [
         # No NaNs, same cats, same order
@@ -383,15 +383,15 @@ def test_remove_unused_categories(self):
         tm.assert_index_equal(out.categories, Index(['B', 'D', 'F']))
         exp_codes = np.array([2, -1, 1, 0, 1, 2, -1], dtype=np.int8)
         tm.assert_numpy_array_equal(out.codes, exp_codes)
-        assert out.get_values().tolist() == val
+        assert out.to_dense().tolist() == val
 
         alpha = list('abcdefghijklmnopqrstuvwxyz')
         val = np.random.choice(alpha[::2], 10000).astype('object')
         val[np.random.choice(len(val), 100)] = np.nan
 
         cat = Categorical(values=val, categories=alpha)
         out = cat.remove_unused_categories()
-        assert out.get_values().tolist() == val.tolist()
+        assert out.to_dense().tolist() == val.tolist()
 
 
 class TestCategoricalAPIWithFactor(TestCategorical):

pandas/tests/arrays/sparse/test_array.py

@@ -616,7 +616,7 @@ def test_shape(self, data, shape, dtype):
         [1, np.nan, np.nan, 3, np.nan],
         [1, np.nan, 0, 3, 0],
     ])
-    @pytest.mark.parametrize("method", ["to_dense", "get_values"])
+    @pytest.mark.parametrize("method", ["to_dense"])  # , "get_values"])
     @pytest.mark.parametrize("fill_value", [None, 0])
     def test_dense_repr(self, vals, fill_value, method):
         vals = np.array(vals)

pandas/tests/frame/test_reshape.py

@@ -804,7 +804,7 @@ def _test_stack_with_multiindex(multiindex):
                     else:
                         assert_frame_equal(result, expected)
 
-                df.columns = MultiIndex.from_tuples(df.columns.get_values(),
+                df.columns = MultiIndex.from_tuples(df.columns.to_numpy(),
                                                     names=df.columns.names)
                 expected = df.stack(level=level, dropna=False)
                 if isinstance(expected, Series):

pandas/tests/indexes/multi/test_analytics.py

@@ -20,7 +20,7 @@ def test_shift(idx):
 
 def test_groupby(idx):
     groups = idx.groupby(np.array([1, 1, 1, 2, 2, 2]))
-    labels = idx.get_values().tolist()
+    labels = idx.to_numpy().tolist()
     exp = {1: labels[:3], 2: labels[3:]}
     tm.assert_dict_equal(groups, exp)
 

pandas/tests/indexes/period/test_period.py

@@ -162,15 +162,15 @@ def test_values(self):
 
         exp = np.array([], dtype=np.object)
         tm.assert_numpy_array_equal(idx.values, exp)
-        tm.assert_numpy_array_equal(idx.get_values(), exp)
+        #tm.assert_numpy_array_equal(idx.get_values(), exp)
         exp = np.array([], dtype=np.int64)
         tm.assert_numpy_array_equal(idx._ndarray_values, exp)
 
         idx = pd.PeriodIndex(['2011-01', pd.NaT], freq='M')
 
         exp = np.array([pd.Period('2011-01', freq='M'), pd.NaT], dtype=object)
         tm.assert_numpy_array_equal(idx.values, exp)
-        tm.assert_numpy_array_equal(idx.get_values(), exp)
+        #tm.assert_numpy_array_equal(idx.get_values(), exp)
         exp = np.array([492, -9223372036854775808], dtype=np.int64)
         tm.assert_numpy_array_equal(idx._ndarray_values, exp)
 
@@ -179,7 +179,7 @@ def test_values(self):
         exp = np.array([pd.Period('2011-01-01', freq='D'), pd.NaT],
                        dtype=object)
         tm.assert_numpy_array_equal(idx.values, exp)
-        tm.assert_numpy_array_equal(idx.get_values(), exp)
+        #tm.assert_numpy_array_equal(idx.get_values(), exp)
         exp = np.array([14975, -9223372036854775808], dtype=np.int64)
         tm.assert_numpy_array_equal(idx._ndarray_values, exp)